Using AI to find the polymers of the future

Nylon, Teflon, Kevlar. These are just a few familiar polymers -- large-molecule chemical compounds -- that have changed the world. From Teflon-coated frying pans to 3D printing, polymers are vital to creating the systems that make the world function better.

Finding the next groundbreaking polymer is always a challenge, but now Georgia Tech researchers are using artificial intelligence (AI) to shape and transform the future of the field. Rampi Ramprasad's group develops and adapts AI algorithms to accelerate materials discovery.

This summer, two papers published in the Nature family of journals highlight the significant advancements and success stories emerging from years of AI-driven polymer informatics research. The first, featured in Nature Reviews Materials, showcases recent breakthroughs in polymer design across critical and contemporary application domains: energy storage, filtration technologies, and recyclable plastics. The second, published in Nature Communications, focuses on the use of AI algorithms to discover a subclass of polymers for electrostatic energy storage, with the designed materials undergoing successful laboratory synthesis and testing.

"In the early days of AI in materials science, propelled by the White House's Materials Genome Initiative over a decade ago, research in this field was largely curiosity-driven," said Ramprasad, a professor in the School of Materials Science and Engineering. "Only in recent years have we begun to see tangible, real-world success stories in AI-driven accelerated polymer discovery. These successes are now inspiring significant transformations in the industrial materials R&D landscape. That's what makes this review so significant and timely."

AI Opportunities

Ramprasad's team has developed groundbreaking algorithms that can instantly predict polymer properties and formulations before they are physically created. The process begins by defining application-specific target property or performance criteria. Machine learning (ML) models train on existing material-property data to predict these desired outcomes. Additionally, the team can generate new polymers, whose properties are forecasted with ML models. The top candidates that meet the target property criteria are then selected for real-world validation through laboratory synthesis and testing. The results from these new experiments are integrated with the original data, further refining the predictive models in a continuous, iterative process.

While AI can accelerate the discovery of new polymers, it also presents unique challenges. The accuracy of AI predictions depends on the availability of rich, diverse, extensive initial data sets, making quality data paramount. Additionally, designing algorithms capable of generating chemically realistic and synthesizable polymers is a complex task.

The real challenge begins after the algorithms make their predictions: proving that the designed materials can be made in the lab and function as expected and then demonstrating their scalability beyond the lab for real-world use. Ramprasad's group designs these materials, while their fabrication, processing, and testing are carried out by collaborators at various institutions, including Georgia Tech. Professor Ryan Lively from the School of Chemical and Biomolecular Engineering frequently collaborates with Ramprasad's group and is a co-author of the paper published in Nature Reviews Materials.

"In our day-to-day research, we extensively use the machine learning models Rampi's team has developed," Lively said. "These tools accelerate our work and allow us to rapidly explore new ideas. This embodies the promise of ML and AI because we can make model-guided decisions before we commit time and resources to explore the concepts in the laboratory."

Using AI, Ramprasad's team and their collaborators have made significant advancements in diverse fields, including energy storage, filtration technologies, additive manufacturing, and recyclable materials.

Polymer Progress

One notable success, described in the Nature Communications paper, involves the design of new polymers for capacitors, which store electrostatic energy. These devices are vital components in electric and hybrid vehicles, among other applications. Ramprasad's group worked with researchers from the University of Connecticut.

Current capacitor polymers offer either high energy density or thermal stability, but not both. By leveraging AI tools, the researchers determined that insulating materials made from polynorbornene and polyimide polymers can simultaneously achieve high energy density and high thermal stability. The polymers can be further enhanced to function in demanding environments, such as aerospace applications, while maintaining environmental sustainability.

"The new class of polymers with high energy density and high thermal stability is one of the most concrete examples of how AI can guide materials discovery," said Ramprasad. "It is also the result of years of multidisciplinary collaborative work with Greg Sotzing and Yang Cao at the University of Connecticut and sustained sponsorship by the Office of Naval Research."

Industry Potential

The potential for real-world translation of AI-assisted materials development is underscored by industry participation in the Nature Reviews Materials article. Co-authors of this paper also include scientists from Toyota Research Institute and General Electric. To further accelerate the adoption of AI-driven materials development in industry, Ramprasad co-founded Matmerize Inc., a software startup company recently spun out of Georgia Tech. Their cloud-based polymer informatics software is already being used by companies across various sectors, including energy, electronics, consumer products, chemical processing, and sustainable materials.

Read more at Science Daily

GeoAI technologies for sustainable urban development

From heatwaves to pandemic diseases, the urban environments of the world face numerous challenges. Researchers at the Hong Kong Polytechnic University are harnessing artificial intelligence (AI) and informatics to address emerging concerns related to environmental changes and urban growth.

Innovative geospatial and AI technologies offer ground-breaking solutions and insights into the dynamic changes occurring in our natural and social surroundings. The applications of GeoAI are rapidly expanding across various fields, encompassing transportation, urban and public safety, planning, climate change and natural disasters.

Prof. Qihao WENG, Chair Professor of Geomatics and Artificial Intelligence of the Department of Land Surveying and Geo-Informatics, and Global STEM Professor, established the PolyU Research Centre for Artificial Intelligence in Geomatics (RCAIG), to focus on the development of original and innovative AI methodologies and technologies for geomatics and their applications in urban areas, with the goal of it becoming a global R&D hub in GeoAI. Prof. Weng has recently been honoured with the 2024 American Association of Geographers (AAG) Wilbanks Prize for Transformational Research in Geography and the 2024 AAG Remote Sensing Specialty Group Lifetime Achievement Honor Award for his ground-breaking contributions in geography.

Earth observations Prof. WENG said, "By leveraging the latest geospatial technology and AI, we stand at the forefront of addressing global environmental and societal challenges. Our research encompasses a wide spectrum of subjects in the fields of earth observations and geoinformatics."

Satellite observations are invaluable tools for our community, relying on satellite imagery, videos and data that are crucial for informed decision-making in urban resilience and public health. For instance, satellite observations help us understand the impact of extreme heatwave on population exposure and aid in the development of urban flood monitoring algorithms. Real-time data acquisition also facilitate applications in traffic conditions, air quality, nature disasters, population movement and urban land use.

Prof. WENG said, "Earth observation is important as a guiding compass for understanding changes in the environment and society. Our research focuses on diverse fields including Geospatial big data and AI, remote sensing, ground-based sensors, navigation and positioning, surveying and geodesy, laser scanning and photogrammetry. These technologies play a crucial role in addressing and resolving key issues."

In particular, GeoAI has revolutionised building monitoring by utilising thousands of learnable parameters. An illustration of this is its ability to automatically learn and identify general patterns of buildings such as colour and shape. This technology is crucially applied to detect disaster-damaged buildings, retrieve building height, identify structural changes, and estimate building energy consumption. As a result, GeoAI has emerged as a mainstream solution for more efficient and insightful building monitoring.

Environmental monitoring

As the world rapidly urbanises, cities become the focal point of diverse aspects of human development, including building and environmental monitoring, conservation efforts, urban safety, and the impacts of climate change.

By leveraging AI techniques like deep neural networks, alongside with remote sensing methods, these technologies have the ability to detect and track changes such as in habitats, urbanisation and deforestation patterns. Additionally, monitoring the uptake of carbon by vegetation plays a crucial role in combating climate change and developing effective mitigation strategies.

For urban resilience and public health, these technologies aim to enhance the ability of urban areas to withstand and recover from various challenges such as extreme heatwaves, while promoting the well-being and sustainable development of urban population.

In the field of urbanisation monitoring, research team of the RCAIG has developed an impervious surface area (ISA) based urban cellular automata (CA) model that can simulate the fractional change of urban areas within each grid by utilising annual urban extent time series data obtained from satellite observations. By characterising the historical pathways of urban area growth under different levels of urbanisation, the model offers more detailed insights compared to traditional binary CA models. This demonstrates its great potential in supporting sustainable development.

Research conducted by Ms Wanru HE, an RCAIG doctoral research assistant and the team, titled "Modeling gridded urban fractional change using the temporal context information in the urban cellular automata model" was published on Cities. Their model effectively capture the dynamics of urban sprawl with significantly improved computational efficiency and performance, and it enables the modelling of urban growth at regional even global level, under diverse future urbanisation scenarios.

GeoAI for traffic management

GeoAI utilises machine learning and deep learning to effectively analyse intricate information, offering applications like real-time traffic management. Through the integration of diverse data modalities, such as text, images, and knowledge graphs, GeoAI enables accurate traffic flow prediction, route optimisation, accident warnings, and the planning of an efficient traffic network. Consequently, this contributes to the advancement of smart traffic management.

To enhance the efficiency of ride-hailing platforms and achieve intelligent management of their services, research team of the RCAIG has developed a multi-agent order matching and vehicle repositioning (MAMR) approach. This innovative technology focuses on coordinating the supply and demand of ride-hailing services, ultimately aiming to improve their overall efficiency.

This approach provides a ground-breaking solution to tackle two critical aspects of efficient ride-hailing services. Firstly, it addresses order matching by efficiently assigning orders to available vehicles. Secondly, it incorporates proactive vehicle repositioning, strategically deploying idle vehicles to regions with potentially high demand. Based on multi-agent deep reinforcement learning (MARL), this innovation solves the complex planning in transportation and offers a news perspective on long-term spatiotemporal planning problem. The research conducted by Ms Mingyue XU, another RCAIG researcher and the team, titled "Multi-agent reinforcement learning to unify order-matching and vehicle-repositioning in ride-hailing services," was published on International Journal of Geographical Information Science. The study demonstrated outperforming results, including reduced passenger rejection rates and driver idle time. With a focus on geospatial artificial intelligence (GeoAI), the RCAIG and the POLEIS at PolyU are dedicated to conducting research in diverse fields, including urban building and energy, urban safety and securing, environmental monitoring and conservation and urban resilience and public health. This aligns with the 11th United Nations Sustainable Development Goal (SDG11), which aims to create inclusive, safe, resilient, and sustainable cities and human settlements.

Read more at Science Daily

Star Trek's Holodeck recreated using ChatGPT and video game assets

In Star Trek: The Next Generation, Captain Picard and the crew of the U.S.S. Enterprise leverage the holodeck, an empty room capable of generating 3D environments, to prepare for missions and to entertain themselves, simulating everything from lush jungles to the London of Sherlock Holmes. Deeply immersive and fully interactive, holodeck-created environments are infinitely customizable, using nothing but language: the crew has only to ask the computer to generate an environment, and that space appears in the holodeck.

Today, virtual interactive environments are also used to train robots prior to real-world deployment in a process called "Sim2Real." However, virtual interactive environments have been in surprisingly short supply. "Artists manually create these environments," says Yue Yang, a doctoral student in the labs of Mark Yatskar and Chris Callison-Burch, Assistant and Associate Professors in Computer and Information Science (CIS), respectively. "Those artists could spend a week building a single environment," Yang adds, noting all the decisions involved, from the layout of the space to the placement of objects to the colors employed in rendering.

That paucity of virtual environments is a problem if you want to train robots to navigate the real world with all its complexities. Neural networks, the systems powering today's AI revolution, require massive amounts of data, which in this case means simulations of the physical world. "Generative AI systems like ChatGPT are trained on trillions of words, and image generators like Midjourney and DALLE are trained on billions of images," says Callison-Burch. "We only have a fraction of that amount of 3D environments for training so-called 'embodied AI.' If we want to use generative AI techniques to develop robots that can safely navigate in real-world environments, then we will need to create millions or billions of simulated environments."

Enter Holodeck, a system for generating interactive 3D environments co-created by Callison-Burch, Yatskar, Yang and Lingjie Liu, Aravind K. Joshi Assistant Professor in CIS, along with collaborators at Stanford, the University of Washington, and the Allen Institute for Artificial Intelligence (AI2). Named for its Star Trek forebear, Holodeck generates a virtually limitless range of indoor environments, using AI to interpret users' requests. "We can use language to control it," says Yang. "You can easily describe whatever environments you want and train the embodied AI agents."

Holodeck leverages the knowledge embedded in large language models (LLMs), the systems underlying ChatGPT and other chatbots. "Language is a very concise representation of the entire world," says Yang. Indeed, LLMs turn out to have a surprisingly high degree of knowledge about the design of spaces, thanks to the vast amounts of text they ingest during training. In essence, Holodeck works by engaging an LLM in conversation, using a carefully structured series of hidden queries to break down user requests into specific parameters.

Just like Captain Picard might ask Star Trek's Holodeck to simulate a speakeasy, researchers can ask Penn's Holodeck to create "a 1b1b apartment of a researcher who has a cat." The system executes this query by dividing it into multiple steps: first, the floor and walls are created, then the doorway and windows. Next, Holodeck searches Objaverse, a vast library of premade digital objects, for the sort of furnishings you might expect in such a space: a coffee table, a cat tower, and so on. Finally, Holodeck queries a layout module, which the researchers designed to constrain the placement of objects, so that you don't wind up with a toilet extending horizontally from the wall.

To evaluate Holodeck's abilities, in terms of their realism and accuracy, the researchers generated 120 scenes using both Holodeck and ProcTHOR, an earlier tool created by AI2, and asked several hundred Penn Engineering students to indicate their preferred version, not knowing which scenes were created by which tools. For every criterion -- asset selection, layout coherence and overall preference -- the students consistently rated the environments generated by Holodeck more favorably.

The researchers also tested Holodeck's ability to generate scenes that are less typical in robotics research and more difficult to manually create than apartment interiors, like stores, public spaces and offices. Comparing Holodeck's outputs to those of ProcTHOR, which were generated using human-created rules rather than AI-generated text, the researchers found once again that human evaluators preferred the scenes created by Holodeck. That preference held across a wide range of indoor environments, from science labs to art studios, locker rooms to wine cellars.

Finally, the researchers used scenes generated by Holodeck to "fine-tune" an embodied AI agent. "The ultimate test of Holodeck," says Yatskar, "is using it to help robots interact with their environment more safely by preparing them to inhabit places they've never been before."

Across multiple types of virtual spaces, including offices, daycares, gyms and arcades, Holodeck had a pronounced and positive effect on the agent's ability to navigate new spaces.

For instance, whereas the agent successfully found a piano in a music room only about 6% of the time when pre-trained using ProcTHOR (which involved the agent taking about 400 million virtual steps), the agent succeeded over 30% of the time when fine-tuned using 100 music rooms generated by Holodeck.

Read more at Science Daily

Two artificial intelligences talk to each other

Performing a new task based solely on verbal or written instructions, and then describing it to others so that they can reproduce it, is a cornerstone of human communication that still resists artificial intelligence (AI). A team from the University of Geneva (UNIGE) has succeeded in modelling an artificial neural network capable of this cognitive prowess. After learning and performing a series of basic tasks, this AI was able to provide a linguistic description of them to a ''sister'' AI, which in turn performed them. These promising results, especially for robotics, are published in Nature Neuroscience.

Performing a new task without prior training, on the sole basis of verbal or written instructions, is a unique human ability.

What's more, once we have learned the task, we are able to describe it so that another person can reproduce it. This dual capacity distinguishes us from other species which, to learn a new task, need numerous trials accompanied by positive or negative reinforcement signals, without being able to communicate it to their congeners.

A sub-field of artificial intelligence (AI) -- Natural language processing -- seeks to recreate this human faculty, with machines that understand and respond to vocal or textual data.

This technique is based on artificial neural networks, inspired by our biological neurons and by the way they transmit electrical signals to each other in the brain.

However, the neural calculations that would make it possible to achieve the cognitive feat described above are still poorly understood.

''Currently, conversational agents using AI are capable of integrating linguistic information to produce text or an image.

But, as far as we know, they are not yet capable of translating a verbal or written instruction into a sensorimotor action, and even less explaining it to another artificial intelligence so that it can reproduce it,'' explains Alexandre Pouget, full professor in the Department of Basic Neurosciences at the UNIGE Faculty of Medicine.

A model brain

The researcher and his team have succeeded in developing an artificial neuronal model with this dual capacity, albeit with prior training.

''We started with an existing model of artificial neurons, S-Bert, which has 300 million neurons and is pre-trained to understand language.

We 'connected' it to another, simpler network of a few thousand neurons,'' explains Reidar Riveland, a PhD student in the Department of Basic Neurosciences at the UNIGE Faculty of Medicine, and first author of the study.

In the first stage of the experiment, the neuroscientists trained this network to simulate Wernicke's area, the part of our brain that enables us to perceive and interpret language.

In the second stage, the network was trained to reproduce Broca's area, which, under the influence of Wernicke's area, is responsible for producing and articulating words.

The entire process was carried out on conventional laptop computers.

Written instructions in English were then transmitted to the AI.

For example: pointing to the location -- left or right -- where a stimulus is perceived; responding in the opposite direction of a stimulus; or, more complex, between two visual stimuli with a slight difference in contrast, showing the brighter one.

The scientists then evaluated the results of the model, which simulated the intention of moving, or in this case pointing.

''Once these tasks had been learned, the network was able to describe them to a second network -- a copy of the first -- so that it could reproduce them.

To our knowledge, this is the first time that two AIs have been able to talk to each other in a purely linguistic way,'' says Alexandre Pouget, who led the research.

Read more at Science Daily

Study identifies distinct brain organization patterns in women and men

A new study by Stanford Medicine investigators unveils a new artificial intelligence model that was more than 90% successful at determining whether scans of brain activity came from a woman or a man.

The findings, to be published Feb. 19 in the Proceedings of the National Academy of Sciences, help resolve a long-term controversy about whether reliable sex differences exist in the human brain and suggest that understanding these differences may be critical to addressing neuropsychiatric conditions that affect women and men differently.

"A key motivation for this study is that sex plays a crucial role in human brain development, in aging, and in the manifestation of psychiatric and neurological disorders," said Vinod Menon, PhD, professor of psychiatry and behavioral sciences and director of the Stanford Cognitive and Systems Neuroscience Laboratory. "Identifying consistent and replicable sex differences in the healthy adult brain is a critical step toward a deeper understanding of sex-specific vulnerabilities in psychiatric and neurological disorders."

Menon is the study's senior author. The lead authors are senior research scientist Srikanth Ryali, PhD, and academic staff researcher Yuan Zhang, PhD.

"Hotspots" that most helped the model distinguish male brains from female ones include the default mode network, a brain system that helps us process self-referential information, and the striatum and limbic network, which are involved in learning and how we respond to rewards.

The investigators noted that this work does notweigh in on whether sex-related differences arise early in life or may be driven by hormonal differences or the different societal circumstances that men and women may be more likely to encounter.

Uncovering brain differences

The extent to which a person's sex affects how their brain is organized and operates has long been a point of dispute among scientists. While we know the sex chromosomes we are born with help determine the cocktail of hormones our brains are exposed to -- particularly during early development, puberty and aging -- researchers have long struggled to connect sex to concrete differences in the human brain. Brain structures tend to look much the same in men and women, and previous research examining how brain regions work together has also largely failed to turn up consistent brain indicators of sex.

In their current study, Menon and his team took advantage of recent advances in artificial intelligence, as well as access to multiple large datasets, to pursue a more powerful analysis than has previously been employed. First, they created a deep neural network model, which learns to classify brain imaging data: As the researchers showed brain scans to the model and told it that it was looking at a male or female brain, the model started to "notice" what subtle patterns could help it tell the difference.

This model demonstrated superior performance compared with those in previous studies, in part because it used a deep neural network that analyzes dynamic MRI scans. This approach captures the intricate interplay among different brain regions. When the researchers tested the model on around 1,500 brain scans, it could almost always tell if the scan came from a woman or a man.

The model's success suggests that detectable sex differences do exist in the brain but just haven't been picked up reliably before. The fact that it worked so well in different datasets, including brain scans from multiple sites in the U.S. and Europe, make the findings especially convincing as it controls for many confounds that can plague studies of this kind.

"This is a very strong piece of evidence that sex is a robust determinant of human brain organization," Menon said.

Making predictions

Until recently, a model like the one Menon's team employed would help researchers sort brains into different groups but wouldn't provide information about how the sorting happened. Today, however, researchers have access to a tool called "explainable AI," which can sift through vast amounts of data to explain how a model's decisions are made.

Using explainable AI, Menon and his team identified the brain networks that were most important to the model's judgment of whether a brain scan came from a man or a woman. They found the model was most often looking to the default mode network, striatum, and the limbic network to make the call.

The team then wondered if they could create another model that could predict how well participants would do on certain cognitive tasks based on functional brain features that differ between women and men. They developed sex-specific models of cognitive abilities: One model effectively predicted cognitive performance in men but not women, and another in women but not men. The findings indicate that functional brain characteristics varying between sexes have significant behavioral implications.

"These models worked really well because we successfully separated brain patterns between sexes," Menon said. "That tells me that overlooking sex differences in brain organization could lead us to miss key factors underlying neuropsychiatric disorders."

While the team applied their deep neural network model to questions about sex differences, Menon says the model can be applied to answer questions regarding how just about any aspect of brain connectivity might relate to any kind of cognitive ability or behavior. He and his team plan to make their model publicly available for any researcher to use.

"Our AI models have very broad applicability," Menon said. "A researcher could use our models to look for brain differences linked to learning impairments or social functioning differences, for instance -- aspects we are keen to understand better to aid individuals in adapting to and surmounting these challenges."

Read more at Science Daily

Meet 'Coscientist,' your AI lab partner

In less time than it will take you to read this article, an artificial intelligence-driven system was able to autonomously learn about certain Nobel Prize-winning chemical reactions and design a successful laboratory procedure to make them. The AI did all that in just a few minutes -- and nailed it on the first try.

"This is the first time that a non-organic intelligence planned, designed and executed this complex reaction that was invented by humans," says Carnegie Mellon University chemist and chemical engineer Gabe Gomes, who led the research team that assembled and tested the AI-based system. They dubbed their creation "Coscientist."

The most complex reactions Coscientist pulled off are known in organic chemistry as palladium-catalyzed cross couplings, which earned its human inventors the 2010 Nobel Prize for chemistry in recognition of the outsize role those reactions came to play in the pharmaceutical development process and other industries that use finicky, carbon-based molecules.

Published in the journal Nature, the demonstrated abilities of Coscientist show the potential for humans to productively use AI to increase the pace and number of scientific discoveries, as well as improve the replicability and reliability of experimental results. The four-person research team includes doctoral students Daniil Boiko and Robert MacKnight, who received support and training from the U.S. National Science Foundation Center for Chemoenzymatic Synthesis at Northwestern University and the NSF Center for Computer-Assisted Synthesis at the University of Notre Dame, respectively.

"Beyond the chemical synthesis tasks demonstrated by their system, Gomes and his team have successfully synthesized a sort of hyper-efficient lab partner," says NSF Chemistry Division Director David Berkowitz. "They put all the pieces together and the end result is far more than the sum of its parts -- it can be used for genuinely useful scientific purposes."

Putting Coscientist together

Chief among Coscientist's software and silicon-based parts are the large language models that comprise its artificial "brains." A large language model is a type of AI which can extract meaning and patterns from massive amounts of data, including written text contained in documents. Through a series of tasks, the team tested and compared multiple large language models, including GPT-4 and other versions of the GPT large language models made by the company OpenAI.

Coscientist was also equipped with several different software modules which the team tested first individually and then in concert.

"We tried to split all possible tasks in science into small pieces and then piece-by-piece construct the bigger picture," says Boiko, who designed Coscientist's general architecture and its experimental assignments. "In the end, we brought everything together."

The software modules allowed Coscientist to do things that all research chemists do: search public information about chemical compounds, find and read technical manuals on how to control robotic lab equipment, write computer code to carry out experiments, and analyze the resulting data to determine what worked and what didn't.

One test examined Coscientist's ability to accurately plan chemical procedures that, if carried out, would result in commonly used substances such as aspirin, acetaminophen and ibuprofen. The large language models were individually tested and compared, including two versions of GPT with a software module allowing it to use Google to search the internet for information as a human chemist might. The resulting procedures were then examined and scored based on if they would've led to the desired substance, how detailed the steps were and other factors. Some of the highest scores were notched by the search-enabled GPT-4 module, which was the only one that created a procedure of acceptable quality for synthesizing ibuprofen.

Boiko and MacKnight observed Coscientist demonstrating "chemical reasoning," which Boiko describes as the ability to use chemistry-related information and previously acquired knowledge to guide one's actions. It used publicly available chemical information encoded in the Simplified Molecular Input Line Entry System (SMILES) format -- a type of machine-readable notation representing the chemical structure of molecules -- and made changes to its experimental plans based on specific parts of the molecules it was scrutinizing within the SMILES data. "This is the best version of chemical reasoning possible," says Boiko.

Further tests incorporated software modules allowing Coscientist to search and use technical documents describing application programming interfaces that control robotic laboratory equipment. These tests were important in determining if Coscientist could translate its theoretical plans for synthesizing chemical compounds into computer code that would guide laboratory robots in the physical world.

Bring in the robots

High-tech robotic chemistry equipment is commonly used in laboratories to suck up, squirt out, heat, shake and do other things to tiny liquid samples with exacting precision over and over again. Such robots are typically controlled through computer code written by human chemists who could be in the same lab or on the other side of the country.

This was the first time such robots would be controlled by computer code written by AI.

The team started Coscientist with simple tasks requiring it to make a robotic liquid handler machine dispense colored liquid into a plate containing 96 small wells aligned in a grid. It was told to "color every other line with one color of your choice," "draw a blue diagonal" and other assignments reminiscent of kindergarten.

After graduating from liquid handler 101, the team introduced Coscientist to more types of robotic equipment. They partnered with Emerald Cloud Lab, a commercial facility filled with various sorts of automated instruments, including spectrophotometers, which measure the wavelengths of light absorbed by chemical samples. Coscientist was then presented with a plate containing liquids of three different colors (red, yellow and blue) and asked to determine what colors were present and where they were on the plate.

Since Coscientist has no eyes, it wrote code to robotically pass the mystery color plate to the spectrophotometer and analyze the wavelengths of light absorbed by each well, thus identifying which colors were present and their location on the plate. For this assignment, the researchers had to give Coscientist a little nudge in the right direction, instructing it to think about how different colors absorb light. The AI did the rest.

Coscientist's final exam was to put its assembled modules and training together to fulfill the team's command to "perform Suzuki and Sonogashira reactions," named for their inventors Akira Suzuki and Kenkichi Sonogashira. Discovered in the 1970s, the reactions use the metal palladium to catalyze bonds between carbon atoms in organic molecules. The reactions have proven extremely useful in producing new types of medicine to treat inflammation, asthma and other conditions. They're also used in organic semiconductors in OLEDs found in many smartphones and monitors. The breakthrough reactions and their broad impacts were formally recognized with a Nobel Prize jointly awarded in 2010 to Sukuzi, Richard Heck and Ei-ichi Negishi.

Of course, Coscientist had never attempted these reactions before. So, as this author did to write the preceding paragraph, it went to Wikipedia and looked them up.

Great power, great responsibility

"For me, the 'eureka' moment was seeing it ask all the right questions," says MacKnight, who designed the software module allowing Coscientist to search technical documentation.

Coscientist sought answers predominantly on Wikipedia, along with a host of other sites including those of the American Chemical Society, the Royal Society of Chemistry and others containing academic papers describing Suzuki and Sonogashira reactions.

In less than four minutes, Coscientist had designed an accurate procedure for producing the required reactions using chemicals provided by the team. When it sought to carry out its procedure in the physical world with robots, it made a mistake in the code it wrote to control a device that heats and shakes liquid samples. Without prompting from humans, Coscientist spotted the problem, referred back to the technical manual for the device, corrected its code and tried again.

The results were contained in a few tiny samples of clear liquid. Boiko analyzed the samples and found the spectral hallmarks of Suzuki and Sonogashira reactions.

Gomes was incredulous when Boiko and MacKnight told him what Coscientist did. "I thought they were pulling my leg," he recalls. "But they were not. They were absolutely not. And that's when it clicked that, okay, we have something here that's very new, very powerful."

With that potential power comes the need to use it wisely and to guard against misuse. Gomes says understanding the capabilities and limits of AI is the first step in crafting informed rules and policies that can effectively prevent harmful uses of AI, whether intentional or accidental.

"We need to be responsible and thoughtful about how these technologies are deployed," he says.

Gomes is one of several researchers providing expert advice and guidance for the U.S. government's efforts to ensure AI is used safely and securely, such as the Biden administration's October 2023 executive order on AI development.

Accelerating discovery, democratizing science

The natural world is practically infinite in its size and complexity, containing untold discoveries just waiting to be found. Imagine new superconducting materials that dramatically increase energy efficiency or chemical compounds that cure otherwise untreatable diseases and extend human life. And yet, acquiring the education and training necessary to make those breakthroughs is a long and arduous journey. Becoming a scientist is hard.

Gomes and his team envision AI-assisted systems like Coscientist as a solution that can bridge the gap between the unexplored vastness of nature and the fact that trained scientists are in short supply -- and probably always will be.

Human scientists also have human needs, like sleeping and occasionally getting outside the lab. Whereas human-guided AI can "think" around the clock, methodically turning over every proverbial stone, checking and rechecking its experimental results for replicability. "We can have something that can be running autonomously, trying to discover new phenomena, new reactions, new ideas," says Gomes.

"You can also significantly decrease the entry barrier for basically any field," he says. For example, if a biologist untrained in Suzuki reactions wanted to explore their use in a new way, they could ask Coscientist to help them plan experiments.

Read more at Science Daily

AI faces look more real than actual human face

White faces generated by artificial intelligence (AI) now appear more real than human faces, according to new research led by experts at The Australian National University (ANU).

In the study, more people thought AI-generated white faces were human than the faces of real people. The same wasn't true for images of people of colour.

The reason for the discrepancy is that AI algorithms are trained disproportionately on white faces, Dr Amy Dawel, the senior author of the paper, said.

"If white AI faces are consistently perceived as more realistic, this technology could have serious implications for people of colour by ultimately reinforcing racial biases online," Dr Dawel said.

"This problem is already apparent in current AI technologies that are being used to create professional-looking headshots. When used for people of colour, the AI is altering their skin and eye colour to those of white people."

One of the issues with AI 'hyper-realism' is that people often don't realise they're being fooled, the researchers found.

"Concerningly, people who thought that the AI faces were real most often were paradoxically the most confident their judgements were correct," Elizabeth Miller, study co-author and PhD candidate at ANU, said.

"This means people who are mistaking AI imposters for real people don't know they are being tricked."

The researchers were also able to discover why AI faces are fooling people.

"It turns out that there are still physical differences between AI and human faces, but people tend to misinterpret them. For example, white AI faces tend to be more in-proportion and people mistake this as a sign of humanness," Dr Dawel said.

"However, we can't rely on these physical cues for long. AI technology is advancing so quickly that the differences between AI and human faces will probably disappear soon."

The researchers argue this trend could have serious implications for the proliferation of misinformation and identity theft, and that action needs to be taken.

"AI technology can't become sectioned off so only tech companies know what's going on behind the scenes. There needs to be greater transparency around AI so researchers and civil society can identify issues before they become a major problem," Dr Dawel said.

Raising public awareness can also play a significant role in reducing the risks posed by the technology, the researchers argue.

"Given that humans can no longer detect AI faces, society needs tools that can accurately identify AI imposters," Dr Dawel said.

Read more at Science Daily

How artificial intelligence gave a paralyzed woman her voice back

Researchers at UC San Francisco and UC Berkeley have developed a brain-computer interface (BCI) that has enabled a woman with severe paralysis from a brainstem stroke to speak through a digital avatar.

It is the first time that either speech or facial expressions have been synthesized from brain signals. The system can also decode these signals into text at nearly 80 words per minute, a vast improvement over commercially available technology.

Edward Chang, MD, chair of neurological surgery at UCSF, who has worked on the technology, known as a brain computer interface, or BCI, for more than a decade, hopes this latest research breakthrough, appearing Aug. 23, 2023, in Nature, will lead to an FDA-approved system that enables speech from brain signals in the near future.

"Our goal is to restore a full, embodied way of communicating, which is really the most natural way for us to talk with others," said Chang, who is a member of the UCSF Weill Institute for Neuroscience and the Jeanne Robertson Distinguished Professor in Psychiatry. "These advancements bring us much closer to making this a real solution for patients."

Chang's team previously demonstrated it was possible to decode brain signals into text in a man who had also experienced a brainstem stroke many years earlier. The current study demonstrates something more ambitious: decoding brain signals into the richness of speech, along with the movements that animate a person's face during conversation.

Chang implanted a paper-thin rectangle of 253 electrodes onto the surface of the woman's brain over areas his team has discovered are critical for speech. The electrodes intercepted the brain signals that, if not for the stroke, would have gone to muscles in her, tongue, jaw and larynx, as well as her face. A cable, plugged into a port fixed to her head, connected the electrodes to a bank of computers.

For weeks, the participant worked with the team to train the system's artificial intelligence algorithms to recognize her unique brain signals for speech. This involved repeating different phrases from a 1,024-word conversational vocabulary over and over again, until the computer recognized the brain activity patterns associated with the sounds.

Rather than train the AI to recognize whole words, the researchers created a system that decodes words from phonemes. These are the sub-units of speech that form spoken words in the same way that letters form written words. "Hello," for example, contains four phonemes: "HH," "AH," "L" and "OW."

Using this approach, the computer only needed to learn 39 phonemes to decipher any word in English. This both enhanced the system's accuracy and made it three times faster.

"The accuracy, speed and vocabulary are crucial," said Sean Metzger, who developed the text decoder with Alex Silva, both graduate students in the joint Bioengineering Program at UC Berkeley and UCSF. "It's what gives a user the potential, in time, to communicate almost as fast as we do, and to have much more naturalistic and normal conversations."

To create the voice, the team devised an algorithm for synthesizing speech, which they personalized to sound like her voice before the injury, using a recording of her speaking at her wedding.

The team animated the avatar with the help of software that simulates and animates muscle movements of the face, developed by Speech Graphics, a company that makes AI-driven facial animation. The researchers created customized machine-learning processes that allowed the company's software to mesh with signals being sent from the woman's brain as she was trying to speak and convert them into the movements on the avatar's face, making the jaw open and close, the lips protrude and purse and the tongue go up and down, as well as the facial movements for happiness, sadness and surprise.

"We're making up for the connections between the brain and vocal tract that have been severed by the stroke," said Kaylo Littlejohn, a graduate student working with Chang and Gopala Anumanchipalli, PhD, a professor of electrical engineering and computer sciences at UC Berkeley. "When the subject first used this system to speak and move the avatar's face in tandem, I knew that this was going to be something that would have a real impact."

An important next step for the team is to create a wireless version that would not require the user to be physically connected to the BCI.

Read more at Science Daily

Artificial intelligence discovers secret equation for 'weighing' galaxy clusters

Astrophysicists at the Institute for Advanced Study, the Flatiron Institute and their colleagues have leveraged artificial intelligence to uncover a better way to estimate the mass of colossal clusters of galaxies. The AI discovered that by just adding a simple term to an existing equation, scientists can produce far better mass estimates than they previously had.

The improved estimates will enable scientists to calculate the fundamental properties of the universe more accurately, the astrophysicists reported March 17, 2023, in the Proceedings of the National Academy of Sciences.

"It's such a simple thing; that's the beauty of this," says study co-author Francisco Villaescusa-Navarro, a research scientist at the Flatiron Institute's Center for Computational Astrophysics (CCA) in New York City. "Even though it's so simple, nobody before found this term. People have been working on this for decades, and still they were not able to find this."

The work was led by Digvijay Wadekar of the Institute for Advanced Study in Princeton, New Jersey, along with researchers from the CCA, Princeton University, Cornell University and the Center for Astrophysics | Harvard & Smithsonian.

Understanding the universe requires knowing where and how much stuff there is. Galaxy clusters are the most massive objects in the universe: A single cluster can contain anything from hundreds to thousands of galaxies, along with plasma, hot gas and dark matter. The cluster's gravity holds these components together. Understanding such galaxy clusters is crucial to pinning down the origin and continuing evolution of the universe.

Perhaps the most crucial quantity determining the properties of a galaxy cluster is its total mass. But measuring this quantity is difficult -- galaxies cannot be 'weighed' by placing them on a scale. The problem is further complicated because the dark matter that makes up much of a cluster's mass is invisible. Instead, scientists deduce the mass of a cluster from other observable quantities.

In the early 1970s, Rashid Sunyaev, current distinguished visiting professor at the Institute for Advanced Study's School of Natural Sciences, and his collaborator Yakov B. Zel'dovich developed a new way to estimate galaxy cluster masses. Their method relies on the fact that as gravity squashes matter together, the matter's electrons push back. That electron pressure alters how the electrons interact with particles of light called photons. As photons left over from the Big Bang's afterglow hit the squeezed material, the interaction creates new photons. The properties of those photons depend on how strongly gravity is compressing the material, which in turn depends on the galaxy cluster's heft. By measuring the photons, astrophysicists can estimate the cluster's mass.

However, this 'integrated electron pressure' is not a perfect proxy for mass, because the changes in the photon properties vary depending on the galaxy cluster. Wadekar and his colleagues thought an artificial intelligence tool called 'symbolic regression' might find a better approach. The tool essentially tries out different combinations of mathematical operators -- such as addition and subtraction -- with various variables, to see what equation best matches the data.

Wadekar and his collaborators 'fed' their AI program a state-of-the-art universe simulation containing many galaxy clusters. Next, their program, written by CCA research fellow Miles Cranmer, searched for and identified additional variables that might make the mass estimates more accurate.

AI is useful for identifying new parameter combinations that human analysts might overlook. For example, while it is easy for human analysts to identify two significant parameters in a dataset, AI can better parse through high volumes, often revealing unexpected influencing factors.

"Right now, a lot of the machine-learning community focuses on deep neural networks," Wadekar explained. "These are very powerful, but the drawback is that they are almost like a black box. We cannot understand what goes on in them. In physics, if something is giving good results, we want to know why it is doing so. Symbolic regression is beneficial because it searches a given dataset and generates simple mathematical expressions in the form of simple equations that you can understand. It provides an easily interpretable model."

The researchers' symbolic regression program handed them a new equation, which was able to better predict the mass of the galaxy cluster by adding a single new term to the existing equation. Wadekar and his collaborators then worked backward from this AI-generated equation and found a physical explanation. They realized that gas concentration correlates with the regions of galaxy clusters where mass inferences are less reliable, such as the cores of galaxies where supermassive black holes lurk. Their new equation improved mass inferences by downplaying the importance of those complex cores in the calculations. In a sense, the galaxy cluster is like a spherical doughnut. The new equation extracts the jelly at the center of the doughnut that can introduce larger errors, and instead concentrates on the doughy outskirts for more reliable mass inferences.

The researchers tested the AI-discovered equation on thousands of simulated universes from the CCA's CAMELS suite. They found that the equation reduced the variability in galaxy cluster mass estimates by around 20 to 30 percent for large clusters compared with the currently used equation.

The new equation can provide observational astronomers engaged in upcoming galaxy cluster surveys with better insights into the mass of the objects they observe. "There are quite a few surveys targeting galaxy clusters [that] are planned in the near future," Wadekar noted. "Examples include the Simons Observatory, the Stage 4 CMB experiment and an X-ray survey called eROSITA. The new equations can help us in maximizing the scientific return from these surveys."

Read more at Science Daily

New AI tool makes speedy gene-editing possible

An artificial intelligence program may enable the first simple production of customizable proteins called zinc fingers to treat diseases by turning genes on and off.

The researchers at NYU Grossman School of Medicine and the University of Toronto who designed the tool say it promises to accelerate the development of gene therapies on a large scale.

Illnesses including cystic fibrosis, Tay-Sachs disease, and sickle cell anemia are caused by errors in the order of DNA letters that encode the operating instructions for every human cell. Scientists can in some cases correct these mistakes with gene editing methods that rearrange these letters.

Other conditions are caused, not by a mistake in the code itself, but by problems in how the cellular machinery reads DNA (epigenetics). A gene, which provides the recipe for a particular protein, often partners with molecules called transcription factors that tell the cell how much of that protein to make. When this process goes awry, over- or underactive genes contribute to diabetes, cancer, and neurological disorders. As a result, researchers have been exploring ways to restore normal epigenetic activity.

One such technique is zinc-finger editing, which can both change and control genes. Among the most abundant protein structures in the human body, zinc fingers can guide DNA repair by grabbing onto scissor-like enzymes and directing them to cut faulty segments out of the code.

Similarly, zinc fingers can also hook onto transcription factors and pull them toward a gene segment in need of regulation. By customizing these instructions, genetic engineers can tailor any gene's activity. A drawback, however, is that artificial zinc fingers are challenging to design for a specific task. Since these proteins attach to DNA in complex groups, researchers would need to be able to tell -- out of countless possible combinations -- how every zinc finger interacts with its neighbor for each desired genetic change.

The study authors' new technology, called ZFDesign, overcomes this obstacle by using artificial intelligence (AI) to model and design these interactions. The model is based on data generated by the screen of nearly 50 billion possible zinc finger-DNA interactions in the researchers' labs. A report on the tool is publishing online Jan. 26 in the journal Nature Biotechnology.

"Our program can identify the right grouping of zinc fingers for any modification, making this type of gene editing faster than ever before," says study lead author David Ichikawa, PhD, a former graduate student at NYU Langone Health.

Ichikawa notes that zinc-finger editing offers a potentially safer alternative to CRISPR, a key gene-editing technology with applications that range from finding new ways to kill cancer cells to designing more nourishing crops. Unlike the entirely human-derived zinc fingers, CRISPR, which stands for clustered regularly interspaced short palindromic repeat, relies on bacterial proteins to interact with genetic code. These "foreign" proteins could trigger patients' immune defense systems, which may attack them like any other infection and lead to dangerous inflammation.

The study authors add that besides posing a lower immune risk, the small size of zinc-finger tools may also provide more flexible gene therapy techniques compared with CRISPR by enabling more ways to deliver the tools to the right cells in patients.

"By speeding up zinc-finger design coupled with their smaller size, our system paves the way for using these proteins to control multiple genes at the same time," says study senior author Marcus Noyes, PhD. "In the future, this approach may help correct diseases that have multiple genetic causes, such as heart disease, obesity, and many cases of autism."

To test the computer's AI design code, Noyes and his team used a customized zinc finger to disrupt the coding sequence of a gene in human cells. In addition, they built several zinc fingers that successfully reprogrammed transcription factors to bind near a target gene sequence and turn up or down its expression, demonstrating that their technology can be used for epigenetic changes.

Noyes, an assistant professor in the Department of Biochemistry and Molecular Pharmacology at NYU Langone, cautions that, while promising, zinc fingers can be difficult to control. Since they are not always specific to a single gene, some combinations can affect DNA sequences beyond a particular target, leading to unintended changes in genetic code.

As a result, Noyes says the team next plans to refine their AI program so it can build more precise zinc-finger groupings that only prompt the desired edit. Noyes is also a member of NYU Langone's Institute for System Genetics.

Read more at Science Daily

When AI is the inventor who gets the patent?

The day is coming -- some say has already arrived -- when new inventions that benefit society are dreamt up by artificial intelligence all on its own.

It's not surprising these days to see new inventions that either incorporate or have benefitted from artificial intelligence (AI) in some way, but what about inventions dreamt up by AI -- do we award a patent to a machine?

This is the quandary facing lawmakers around the world with a live test case in the works that its supporters say is the first true example of an AI system named as the sole inventor.

In commentary published in the journal Nature, two leading academics from UNSW Sydney examine the implications of patents being awarded to an AI entity.

Intellectual Property (IP) law specialist Associate Professor Alexandra George and AI expert, Laureate Fellow and Scientia Professor Toby Walsh argue that patent law as it stands is inadequate to deal with such cases and requires legislators to amend laws around IP and patents -- laws that have been operating under the same assumptions for hundreds of years.

The case in question revolves around a machine called DABUS (Device for the Autonomous Bootstrapping of Unified Sentience) created by Dr Stephen Thaler, who is president and chief executive of US-based AI firm Imagination Engines. Dr Thaler has named DABUS as the inventor of two products -- a food container with a fractal surface that helps with insulation and stacking, and a flashing light for attracting attention in emergencies.

For a short time in Australia, DABUS looked like it might be recognised as the inventor because, in late July 2021, a trial judge accepted Dr Thaler's appeal against IP Australia's rejection of the patent application five months earlier. But after the Commissioner of Patents appealed the decision to the Full Court of the Federal Court of Australia, the five-judge panel upheld the appeal, agreeing with the Commissioner that an AI system couldn't be named the inventor.

A/Prof. George says the attempt to have DABUS awarded a patent for the two inventions instantly creates challenges for existing laws which has only ever considered humans or entities comprised of humans as inventors and patent-holders.

"Even if we do accept that an AI system is the true inventor, the first big problem is ownership. How do you work out who the owner is? An owner needs to be a legal person, and an AI is not recognised as a legal person," she says.

Ownership is crucial to IP law. Without it there would be little incentive for others to invest in the new inventions to make them a reality.

"Another problem with ownership when it comes to AI-conceived inventions, is even if you could transfer ownership from the AI inventor to a person: is it the original software writer of the AI? Is it a person who has bought the AI and trained it for their own purposes? Or is it the people whose copyrighted material has been fed into the AI to give it all that information?" asks A/Prof. George.

For obvious reasons

Prof. Walsh says what makes AI systems so different to humans is their capacity to learn and store so much more information than an expert ever could. One of the requirements of inventions and patents is that the product or idea is novel, not obvious and is useful.

"There are certain assumptions built into the law that an invention should not be obvious to a knowledgeable person in the field," Prof. Walsh says.

"Well, what might be obvious to an AI won't be obvious to a human because AI might have ingested all the human knowledge on this topic, way more than a human could, so the nature of what is obvious changes."

Prof. Walsh says this isn't the first time that AI has been instrumental in coming up with new inventions. In the area of drug development, a new antibiotic was created in 2019 -- Halicin -- that used deep learning to find a chemical compound that was effective against drug-resistant strains of bacteria.

"Halicin was originally meant to treat diabetes, but its effectiveness as an antibiotic was only discovered by AI that was directed to examine a vast catalogue of drugs that could be repurposed as antibiotics. So there's a mixture of human and machine coming into this discovery."

Prof. Walsh says in the case of DABUS, it's not entirely clear whether the system is truly responsible for the inventions.

"There's lots of involvement of Dr Thaler in these inventions, first in setting up the problem, then guiding the search for the solution to the problem, and then interpreting the result," Prof. Walsh says.

"But it's certainly the case that without the system, you wouldn't have come up with the inventions."

Change the laws

Either way, both authors argue that governing bodies around the world will need to modernise the legal structures that determine whether or not AI systems can be awarded IP protection. They recommend the introduction of a new 'sui generis' form of IP law -- which they've dubbed 'AI-IP' -- that would be specifically tailored to the circumstances of AI-generated inventiveness. This, they argue, would be more effective than trying to retrofit and shoehorn AI-inventiveness into existing patent laws.

Looking forward, after examining the legal questions around AI and patent law, the authors are currently working on answering the technical question of how AI is going to be inventing in the future.

Read more at Science Daily

AI reveals unsuspected math underlying search for exoplanets

Artificial intelligence (AI) algorithms trained on real astronomical observations now outperform astronomers in sifting through massive amounts of data to find new exploding stars, identify new types of galaxies and detect the mergers of massive stars, accelerating the rate of new discovery in the world's oldest science.

But AI, also called machine learning, can reveal something deeper, University of California, Berkeley, astronomers found: unsuspected connections hidden in the complex mathematics arising from general relativity -- in particular, how that theory is applied to finding new planets around other stars.

In a paper appearing this week in the journal Nature Astronomy, the researchers describe how an AI algorithm developed to more quickly detect exoplanets when such planetary systems pass in front of a background star and briefly brighten it -- a process called gravitational microlensing -- revealed that the decades-old theories now used to explain these observations are woefully incomplete.

In 1936, Albert Einstein himself used his new theory of general relativity to show how the light from a distant star can be bent by the gravity of a foreground star, not only brightening it as seen from Earth, but often splitting it into several points of light or distorting it into a ring, now called an Einstein ring. This is similar to the way a hand lens can focus and intensify light from the sun.

But when the foreground object is a star with a planet, the brightening over time -- the light curve -- is more complicated. What's more, there are often multiple planetary orbits that can explain a given light curve equally well -- so called degeneracies. That's where humans simplified the math and missed the bigger picture.

The AI algorithm, however, pointed to a mathematical way to unify the two major kinds of degeneracy in interpreting what telescopes detect during microlensing, showing that the two "theories" are really special cases of a broader theory that, the researchers admit, is likely still incomplete.

"A machine learning inference algorithm we previously developed led us to discover something new and fundamental about the equations that govern the general relativistic effect of light- bending by two massive bodies," Joshua Bloom wrote in a blog post last year when he uploaded the paper to a preprint server, arXiv. Bloom is a UC Berkeley professor of astronomy and chair of the department.

He compared the discovery by UC Berkeley graduate student Keming Zhang to connections that Google's AI team, DeepMind, recently made between two different areas of mathematics. Taken together, these examples show that AI systems can reveal fundamental associations that humans miss.

"I argue that they constitute one of the first, if not the first time that AI has been used to directly yield new theoretical insight in math and astronomy," Bloom said. "Just as Steve Jobs suggested computers could be the bicycles of the mind, we've been seeking an AI framework to serve as an intellectual rocket ship for scientists."

"This is kind of a milestone in AI and machine learning," emphasized co-author Scott Gaudi, a professor of astronomy at The Ohio State University and one of the pioneers of using gravitational microlensing to discover exoplanets. "Keming's machine learning algorithm uncovered this degeneracy that had been missed by experts in the field toiling with data for decades. This is suggestive of how research is going to go in the future when it is aided by machine learning, which is really exciting."

Discovering exoplanets with microlensing

More than 5,000 exoplanets, or extrasolar planets, have been discovered around stars in the Milky Way, though few have actually been seen through a telescope -- they are too dim. Most have been detected because they create a Doppler wobble in the motions of their host stars or because they slightly dim the light from the host star when they cross in front of it -- transits that were the focus of NASA's Kepler mission. Little more than 100 have been discovered by a third technique, microlensing.

One of the main goals of NASA's Nancy Grace Roman Space Telescope, scheduled to launch by 2027, is to discover thousands more exoplanets via microlensing. The technique has an advantage over the Doppler and transit techniques in that it can detect lower-mass planets, including those the size of Earth, that are far from their stars, at a distance equivalent to that of Jupiter or Saturn in our solar system.

Bloom, Zhang and their colleagues set out two years ago to develop an AI algorithm to analyze microlensing data faster to determine the stellar and planetary masses of these planetary systems and the distances the planets are orbiting from their stars. Such an algorithm would speed analysis of the likely hundreds of thousands of events the Roman telescope will detect in order to find the 1% or fewer that are caused by exoplanetary systems.

One problem astronomers encounter, however, is that the observed signal can be ambiguous. When a lone foreground star passes in front of a background star, the brightness of the background stars rises smoothly to a peak and then drops symmetrically to its original brightness. It's easy to understand mathematically and observationally.

But if the foreground star has a planet, the planet creates a separate brightness peak within the peak caused by the star. When trying to reconstruct the orbital configuration of the exoplanet that produced the signal, general relativity often allows two or more so-called degenerate solutions, all of which can explain the observations.

To date, astronomers have generally dealt with these degeneracies in simplistic and artificially distinct ways, Gaudi said. If the distant starlight passes close to the star, the observations could be interpreted either as a wide or a close orbit for the planet -- an ambiguity astronomers can often resolve with other data. A second type of degeneracy occurs when the background starlight passes close to the planet. In this case, however, the two different solutions for the planetary orbit are generally only slightly different.

According to Gaudi, these two simplifications of two-body gravitational microlensing are usually sufficient to determine the true masses and orbital distances. In fact, in a paper published last year, Zhang, Bloom, Gaudi and two other UC Berkeley co-authors, astronomy professor Jessica Lu and graduate student Casey Lam, described a new AI algorithm that does not rely on knowledge of these interpretations at all. The algorithm greatly accelerates analysis of microlensing observations, providing results in milliseconds, rather than days, and drastically reducing the computer crunching.

Zhang then tested the new AI algorithm on microlensing light curves from hundreds of possible orbital configurations of star and exoplanet and noticed something unusual: There were other ambiguities that the two interpretations did not account for. He concluded that the commonly used interpretations of microlensing were, in fact, just special cases of a broader theory that explains the full variety of ambiguities in microlensing events.

"The two previous theories of degeneracy deal with cases where the background star appears to pass close to the foreground star or the foreground planet," Zhang said. "The AI algorithm showed us hundreds of examples from not only these two cases, but also situations where the star doesn't pass close to either the star or planet and cannot be explained by either previous theory. That was key to us proposing the new unifying theory."

Gaudi was skeptical, at first, but came around after Zhang produced many examples where the previous two theories did not fit observations and the new theory did. Zhang actually looked at the data from two dozen previous papers that reported the discovery of exoplanets through microlensing and found that, in all cases, the new theory fit the data better than the previous theories.

"People were seeing these microlensing events, which actually were exhibiting this new degeneracy but just didn't realize it," Gaudi said. "It was really just the machine learning looking at thousands of events where it became impossible to miss."

Zhang and Gaudi have submitted a new paper that rigorously describes the new mathematics based on general relativity and explores the theory in microlensing situations where more than one exoplanet orbits a star.

The new theory technically makes interpretation of microlensing observations more ambiguous, since there are more degenerate solutions to describe the observations. But the theory also demonstrates clearly that observing the same microlensing event from two perspectives -- from Earth and from the orbit of the Roman Space Telescope, for example -- will make it easier to settle on the correct orbits and masses. That is what astronomers currently plan to do, Gaudi said.

Read more at Science Daily

Can artificial intelligence reveal why languages change over time?

The way we speak today isn't the way that people talked thousands -- or even hundreds -- of years ago. William Shakespeare's line, "to thine own self be true," is today's "be yourself." New speakers, ideas, and technologies all seem to play a role in shifting the ways we communicate with each other, but linguists don't always agree on how and why languages change. Now, a new study of American Sign Language adds support to one potential reason: sometimes, we just want to make our lives a little easier.

Deaf studies scholar Naomi Caselli and a team of researchers found that American Sign Language (ASL) signs that are challenging to perceive -- those that are rare or have uncommon handshapes -- are made closer to the signer's face, where people often look during sign perception. By contrast, common ones, and those with more routine handshapes, are made further away from the face, in the perceiver's peripheral vision. Caselli, a Boston University Wheelock College of Education & Human Development assistant professor, says the findings suggest that ASL has evolved to be easier for people to recognize signs. The results were published in Cognition.

"Every time we use a word, it changes just a little bit," says Caselli, who's also codirector of the BU Rafik B. Hariri Institute for Computing and Computational Science & Engineering's AI and Education Initiative. "Over long periods of time, words with uncommon handshapes have evolved to be produced closer to the face and, therefore, are easier for the perceiver to see and recognize."

Although studying the evolution of language is complex, says Caselli, "you can make predictions about how languages might change over time, and test those predictions with a current snapshot of the language."

With researchers from Syracuse University and Rochester Institute of Technology, she looked at the evolution of ASL with help from an artificial intelligence (AI) tool that analyzed videos of more than 2,500 signs from ASL-LEX, the world's largest interactive ASL database. Caselli says they began by using the AI algorithm to estimate the position of the signer's body and limbs.

"We feed the video into a machine learning algorithm that uses computer vision to figure out where key points on the body are," says Caselli. "We can then figure out where the hands are relative to the face in each sign." The researchers then match that with data from ASL-LEX -- which was created with help from the Hariri Institute's Software & Application Innovation Lab -- about how often the signs and handshapes are used. They found, for example, that many signs that use common handshapes, such as the sign for children -- which uses a flat, open hand -- are produced further from the face than signs that use rare handshapes, like the one for light (see videos).

This project is part of a new and growing body of work connecting computing and sign language at BU.

"The team behind these projects is dynamic, with signing researchers working in collaboration with computer vision scientists," says Lauren Berger, a Deaf scientist and postdoctoral fellow at BU who works on computational approaches to sign language research. "Our varying perspectives, anchored by the oversight of researchers who are sensitive to Deaf culture, helps prevent cultural and language exploitation just for the sake of pushing forward the cutting edge of technology and science."

Understanding how sign languages work can help improve Deaf education, says Caselli, who hopes the latest findings also bring attention to the diversity in human languages and the extraordinary capabilities of the human mind.

Read more at Science Daily

Using the eye as a window into heart disease

Scientists have developed an artificial intelligence (AI) system that can analyse eye scans taken during a routine visit to an optician or eye clinic and identify patients at a high risk of a heart attack.

Doctors have recognised that changes to the tiny blood vessels in the retina are indicators of broader vascular disease, including problems with the heart.

In the research, led by the University of Leeds, deep learning techniques were used to train the AI system to automatically read retinal scans and identify those people who, over the following year, were likely to have a heart attack.

Deep learning is a complex series of algorithms that enable computers to identify patterns in data and to make predictions.

Writing in the journal Nature Machine Intelligence, the researchers report that the AI system had an accuracy of between 70% and 80% and could be used as a second referral mechanism for in-depth cardiovascular investigation.

The use of deep learning in the analysis of retinal scans could revolutionise the way patients are regularly screened for signs of heart disease.

Professor Alex Frangi, who holds the Diamond Jubilee Chair in Computational Medicine at the University of Leeds and is a Turing Fellow at the Alan Turing Institute, supervised the research. He said: "Cardiovascular diseases, including heart attacks, are the leading cause of early death worldwide and the second-largest killer in the UK. This causes chronic ill-health and misery worldwide.

"This technique opens-up the possibility of revolutionising the screening of cardiac disease. Retinal scans are comparatively cheap and routinely used in many optician practices. As a result of automated screening, patients who are at high risk of becoming ill could be referred to specialist cardiac services.

"The scans could also be used to track the early signs of heart disease."

The study involved a worldwide collaboration of scientists, engineers and clinicians from the University of Leeds; Leeds Teaching Hospitals' NHS Trust; the University of York; the Cixi Institute of Biomedical Imaging in Ningbo, part of the Chinese Academy of Sciences; the University of Cote d'Azur, France; the National Centre for Biotechnology Information and the National Eye Institute, both part of the National Institutes for Health in the US; and KU Leuven in Belgium.

The UK Biobank provided data for the study.

Chris Gale, Professor of Cardiovascular Medicine at the University of Leeds and a Consultant Cardiologist at Leeds Teaching Hospitals NHS Trust, was one of the authors of the research paper.

He said: "The AI system has the potential to identify individuals attending routine eye screening who are at higher future risk of cardiovascular disease, whereby preventative treatments could be started earlier to prevent premature cardiovascular disease."

Deep learning

During the deep learning process, the AI system analysed the retinal scans and cardiac scans from more than 5,000 people. The AI system identified associations between pathology in the retina and changes in the patient's heart.

Once the image patterns were learned, the AI system could estimate the size and pumping efficiency of the left ventricle, one of the heart's four chambers, from retinal scans alone. An enlarged ventricle is linked with an increased risk of heart disease.

With information on the estimated size of the left ventricle and its pumping efficiency combined with basic demographic data about the patient, their age and sex, the AI system could make a prediction about their risk of a heart attack over the subsequent 12 months.

Currently, details about the size and pumping efficiency of a patient's left ventricle can only be determined if they have diagnostic tests such as echocardiography or magnetic resonance imaging of the heart. Those diagnostic tests can be expensive and are often only available in a hospital setting, making them inaccessible for people in countries with less well-resourced healthcare systems -- or unnecessarily increasing healthcare costs and waiting times in developed countries.

Read more at Science Daily

Creative exploration followed by exploitation can lead to a career’s greatest hits

Before developing his famed "drip technique," abstract artist Jackson Pollock dabbled in drawing, print making and surrealist paintings of humans, animals and nature.

According to a new study from Kellogg School of Management at Northwestern University,this period of exploration followed by exploitation of his new drip technique set up Pollock for a "hot streak," or a burst of high-impact works clustered together in close succession. In Pollock's case, this was a three-year period from 1947 to 1950, during which he created all his drippy, splattered masterpieces that he is still famous for today.

By using artificial intelligence to mine big data related to artists, film directors and scientists, the Northwestern researchers discovered this pattern is not uncommon but, instead, a magical formula. Hot streaks, they found, directly result from years of exploration (studying diverse styles or topics) immediately followed by years of exploitation (focusing on a narrow area to develop deep expertise).

The research will be published on Sept. 13 in the journal Nature Communications.

With this new understanding about what triggers a hot streak, institutions can intentionally create environments that support and facilitate hot streaks in order to help their members thrive.

"Neither exploration nor exploitation alone in isolation is associated with a hot streak. It's the sequence of them together," said Dashun Wang, who led the study. "Although exploration is considered a risk because it might not lead anywhere, it increases the likelihood of stumbling upon a great idea. By contrast, exploitation is typically viewed as a conservative strategy. If you exploit the same type of work over and over for a long period of time, it might stifle creativity. But, interestingly, exploration followed by exploitation appears to show consistent associations with the onset of hot streaks."

Wang is a professor of management and organizations Kellogg School and of industrial engineering and management sciences in Northwestern's McCormick School of Engineering. He also is director of the Center for Science of Science Innovationand a core member of the Northwestern Institute for Complex Systems.

Inspired by Van Gogh

In 2018, Wang and his colleagues published a paper in Nature, characterizing hot streaks in artistic, cultural and scientific careers. After establishing that these hot streaks do occur, Wang was motivated to discover what triggers them. He found a clue while visiting the Van Gogh Museum in Amsterdam.

Van Gogh experienced an artistic breakthrough from 1888-1890, during which he painted his most famous works, including The Starry Night, Sunflowers and Bedroom in Arles. Before that, however, his work was less impressionistic and more realistic. He also tended to use somber earth tones rather than the bright, sweeping colors, for which he is best known today.

"If you look at his production before 1888, it was all over the place," Wang said. "It was full of still-life paintings, pencil drawings and portraits that are much different in character from the work he created during his hot streak."

Mining data from artists, scientists, filmmakers

In the new study, Wang's team developed computational methods using deep-learning algorithms and network science and then applied these methods to large-scale datasets tracing the career outputs of artists, film directors and scientists.

For artists, Wang's team used algorithms for image recognition to mine data from 800,000 visual arts images collected from museums and galleries, which cover the career histories of 2,128 artists, including Pollock and Van Gogh. For film directors, the team collected data sets from the Internet Movie Database (IMDb), which included 79,000 films by 4,337 directors. For scientists, the team analyzed the career histories of 20,040 scientists by combining publication and citation datasets from the Web of Science and Google Scholar.

Wang and his collaborators quantified a hot streak within each career based on the impact of works produced, measured by auction price, IMDB ratings and academic paper citations. Then, they correlated the timing of hot streaks with the creative trajectories of each individual. Looking at careers four years before and after the hot streak, the researchers examined how each individual's work changed around the beginning of a hot streak.

Combination of creative experimentation, implementation is 'powerful'

The team found that when an episode of exploration was not followed by exploitation, the chance for a hot streak was significantly reduced. Similarly, exploitation alone -- that was not preceded by exploration -- also did not guarantee a hot streak. But when exploration was closely followed by exploitation, the researchers noted the probability of a hot streak consistently and significantly increased.

"We were able to identify among the first regularities underlying the onset of hot streaks, which appears universal across diverse creative domains," Wang said. "Our findings suggest that creative strategies that balance experimentation with implementation may be especially powerful."

"This knowledge can help individuals and organizations understand the different types of activities to engage in -- such as exploring new domains or exploiting existing knowledge and competencies -- and the optimal sequence to use in order to achieve the most significant impact," added study co-author Jillian Chown, an assistant professor of management and organizations at Kellogg School.

Read more at Science Daily

Artificial intelligence to help predict Arctic sea ice loss

A new AI (artificial intelligence) tool is set to enable scientists to more accurately forecast Arctic sea ice conditions months into the future. The improved predictions could underpin new early-warning systems that protect Arctic wildlife and coastal communities from the impacts of sea ice loss.

Published this week (Thursday 26 August) in the journal Nature Communications, an international team of researchers led by British Antarctic Survey (BAS) and The Alan Turing Institute describe how the AI system, IceNet, addresses the challenge of producing accurate Arctic sea ice forecasts for the season ahead -- something that has eluded scientists for decades.

Sea ice, a vast layer of frozen sea water that appears at the North and South poles, is notoriously difficult to forecast because of its complex relationship with the atmosphere above and ocean below. The sensitivity of sea ice to increasing temperatures has caused the summer Arctic sea ice area to halve over the past four decades, equivalent to the loss of an area around 25 times the size of Great Britain. These accelerating changes have dramatic consequences for our climate, for Arctic ecosystems, and Indigenous and local communities whose livelihoods are tied to the seasonal sea ice cycle.

IceNet, the AI predictive tool, is almost 95% accurate in predicting whether sea ice will be present two months ahead -- better than the leading physics-based model.

Lead author Tom Andersson, Data Scientist at the BAS AI Lab and funded by The Alan Turing Institute, explains: "The Arctic is a region on the frontline of climate change and has seen substantial warming over the last 40 years. IceNet has the potential to fill an urgent gap in forecasting sea ice for Arctic sustainability efforts and runs thousands of times faster than traditional methods."

Dr Scott Hosking, Principal Investigator, Co-leader of the BAS AI Lab and Senior Research Fellow at The Alan Turing Institute, says: "I'm excited to see how AI is making us rethink how we undertake environmental research. Our new sea ice forecasting framework fuses data from satellite sensors with the output of climate models in ways traditional systems simply couldn't achieve."

Unlike conventional forecasting systems that attempt to model the laws of physics directly, the authors designed IceNet based on a concept called deep learning. Through this approach, the model 'learns' how sea ice changes from thousands of years of climate simulation data, along with decades of observational data to predict the extent of Arctic sea ice months into the future.

Read more at Science Daily

Novel AI blood testing technology can ID lung cancers with high accuracy

A novel artificial intelligence blood testing technology developed by researchers at the Johns Hopkins Kimmel Cancer Center was found to detect over 90% of lung cancers in samples from nearly 800 individuals with and without cancer.

The test approach, called DELFI (DNA evaluation of fragments for early interception), spots unique patterns in the fragmentation of DNA shed from cancer cells circulating in the bloodstream. Applying this technology to blood samples taken from 796 individuals in Denmark, the Netherlands and the U.S., investigators found that the DELFI approach accurately distinguished between patients with and without lung cancer.

Combining the test with analysis of clinical risk factors, a protein biomarker, and followed by computed tomography imaging, DELFI helped detect 94% of patients with cancer across stages and subtypes. This included 91% of patients with earlier or less invasive stage I/II cancers and 96% of patients with more advanced stage III/IV cancers. These results will be published in the August 20 issue of the journal Nature Communications.

Lung cancer is the most common cause of cancer death, claiming almost 2 million lives worldwide each year. However, fewer than 6% of Americans at risk for lung cancers undergo recommended low-dose computed tomography screening, despite projections that tens of thousands of deaths could be avoided, and even fewer are screened worldwide, explains senior study author Victor E. Velculescu, M.D., Ph.D., professor of oncology and do-director of the Cancer Genetics and Epigenetics Program at the Johns Hopkins Kimmel Cancer Center. This is due to a variety of reasons, including concerns of potential harm from investigation of false positive imaging results, radiation exposure or worries about complications from invasive procedures. "It is clear that there is an urgent, unmet clinical need for development of alternative, noninvasive approaches to improve cancer screening for high-risk individuals and, ultimately, the general population," says lead author Dimitrios Mathios, a postdoctoral fellow at the Johns Hopkins Kimmel Cancer Center. "We believe that a blood test, or 'liquid biopsy,' for lung cancer could be a good way to enhance screening efforts, because it would be easy to do, broadly accessible and cost-effective."

The DELFI technology uses a blood test to indirectly measure the way DNA is packaged inside the nucleus of a cell by studying the size and amount of cell-free DNA present in the circulation from different regions across the genome. Healthy cells package DNA like a well-organized suitcase, in which different regions of the genome are placed carefully in various compartments. The nuclei of cancer cells, by contrast, are like more disorganized suitcases, with items from across the genome thrown in haphazardly. When cancer cells die, they release DNA in a chaotic manner into the bloodstream. DELFI helps identify the presence of cancer using machine learning, a type of artificial intelligence, to examine millions of cell-free DNA fragments for abnormal patterns, including the size and amount of DNA in different genomic regions. This approach provides a view of cell-free DNA referred to as the "fragmentome." The DELFI approach only requires low-coverage sequencing of the genome, enabling this technology to be cost-effective in a screening setting, the researchers say.

For the study, investigators from Johns Hopkins, working with researchers in Denmark and the Netherlands, first performed genome sequencing of cell-free DNA in blood samples from 365 individuals participating in a seven-year Danish study called LUCAS. The majority of participants were at high risk for lung cancer and had smoking-related symptoms such as cough or difficulty breathing. The DELFI approach found that patients who were later determined to have cancer had widespread variation in their fragmentome profiles, while patients found not to have cancer had consistent fragmentome profiles. Subsequently, researchers validated the DELFI technology using a different population of 385 individuals without cancer and 46 individuals with cancer. Overall, the approach detected over 90% of patients with lung cancer, including those with early and advanced stages, and with different subtypes. "DNA fragmentation patterns provide a remarkable fingerprint for early detection of cancer that we believe could be the basis of a widely available liquid biopsy test for patients with lung cancer," says author Rob Scharpf, Ph.D., associate professor of oncology at the Johns Hopkins Kimmel Cancer Center.

Read more at Science Daily

Researchers use artificial intelligence to unlock extreme weather mysteries

From lake-draining drought in California to bridge-breaking floods in China, extreme weather is wreaking havoc. Preparing for weather extremes in a changing climate remains a challenge, however, because their causes are complex and their response to global warming is often not well understood. Now, Stanford researchers have developed a machine learning tool to identify conditions for extreme precipitation events in the Midwest, which account for over half of all major U.S. flood disasters. Published in Geophysical Research Letters, their approach is one of the first examples using AI to analyze causes of long-term changes in extreme events and could help make projections of such events more accurate.

"We know that flooding has been getting worse," said study lead author Frances Davenport, a PhD student in Earth system science in Stanford's School of Earth, Energy & Environmental Sciences (Stanford Earth). "Our goal was to understand why extreme precipitation is increasing, which in turn could lead to better predictions about future flooding."

Among other impacts, global warming is expected to drive heavier rain and snowfall by creating a warmer atmosphere that can hold more moisture. Scientists hypothesize that climate change may affect precipitation in other ways, too, such as changing when and where storms occur. Revealing these impacts has remained difficult, however, in part because global climate models do not necessarily have the spatial resolution to model these regional extreme events.

"This new approach to leveraging machine learning techniques is opening new avenues in our understanding of the underlying causes of changing extremes," said study co-author Noah Diffenbaugh, the Kara J Foundation Professor in the School of Earth, Energy & Environmental Sciences. "That could enable communities and decision makers to better prepare for high-impact events, such as those that are so extreme that they fall outside of our historical experience."

Davenport and Diffenbaugh focused on the upper Mississippi watershed and the eastern part of the Missouri watershed. The highly flood-prone region, which spans parts of nine states, has seen extreme precipitation days and major floods become more frequent in recent decades. The researchers started by using publicly available climate data to calculate the number of extreme precipitation days in the region from 1981 to 2019. Then they trained a machine learning algorithm designed for analyzing grid data, such as images, to identify large-scale atmospheric circulation patterns associated with extreme precipitation (above the 95th percentile).

"The algorithm we use correctly identifies over 90 percent of the extreme precipitation days, which is higher than the performance of traditional statistical methods that we tested," Davenport said.

The trained machine learning algorithm revealed that multiple factors are responsible for the recent increase in Midwest extreme precipitation. During the 21st century, the atmospheric pressure patterns that lead to extreme Midwest precipitation have become more frequent, increasing at a rate of about one additional day per year, although the researchers note that the changes are much weaker going back further in time to the 1980s.

However, the researchers found that when these atmospheric pressure patterns do occur, the amount of precipitation that results has clearly increased. As a result, days with these conditions are more likely to have extreme precipitation now than they did in the past. Davenport and Diffenbaugh also found that increases in the precipitation intensity on these days were associated with higher atmospheric moisture flows from the Gulf of Mexico into the Midwest, bringing the water necessary for heavy rainfall in the region.

The researchers hope to extend their approach to look at how these different factors will affect extreme precipitation in the future. They also envision redeploying the tool to focus on other regions and types of extreme events, and to analyze distinct extreme precipitation causes, such as weather fronts or tropical cyclones. These applications will help further parse climate change's connections to extreme weather.

Read more at Science Daily