'Discovery learning' AI tool predicts battery cycle life with just a few days' data

A 'learner,' 'interpreter' and 'oracle' work together with minimal experiments to draw parallels between historical data and new battery designs

University of Michigan

FacebookXLinkedInWeChatBlueskyMessageWhatsAppEmail

Illustrations of discovery learning process

An agentic AI tool for battery researchers harnesses data from previous battery designs to predict the cycle life of new battery concepts. With information from just 50 cycles, the tool—developed at University of Michigan Engineering—can predict how many charge-discharge cycles the battery can undergo before its capacity drops below 90 percent of its design capacity.

 

This could save months to years of testing, depending on the conditions of cycling experiments, as well as substantial electrical power during battery prototyping and testing. The team estimates that the cycle lives of new battery designs could be predicted with just 5% of the energy and 2% of the time required by conventional testing.

 

"When we learn from the historical battery designs, we leverage physics-based features to construct a generalizable mapping between early-stage tests and cycle life," said Ziyou Song, U-M assistant professor of electrical and computer engineering and corresponding author of the study in Nature. "We can minimize experimental efforts and achieve accurate prediction performance for new battery designs."

 

The study was funded by the battery company Farasis Energy USA in California, which also provided battery cells and data from its design and testing to assess how well the model—trained only on free, public data—performed.

 

The tool is inspired by a teaching approach known as discovery learning, or learning by doing. A student learning in this way has a problem to solve and resources to help discover the solution, while drawing on their own experiences and prior knowledge. Over the course of solving many problems, the student no longer needs the resources to solve similar ones—they have internalized the knowledge and skills. 

 

"Discovery learning is a general machine-learning approach that may be extended to other scientific and engineering domains," said Jiawei Zhang, U-M doctoral candidate in electrical and computer engineering and the first author of this study, who had the initial inspiration to design a team of AI agents that could simulate this mode of learning.

 

How the AI discovery learning tool works

 

The team designated an AI "learner" that would predict the cycle life for a given battery design and cycling conditions, such as temperature and current. The learner chooses a few battery candidates that would fill gaps in its knowledge, to be built and run for about 50 cycles. The results of those experiments flow to an "interpreter," which accesses historical data and runs calculations with a physics-based battery simulator. The "oracle" then makes cycle life predictions for the experimental batteries based on the historical data and calculations provided. 

 

Finally, the learner combines the new information with previous predictions to estimate the cycle life of the new battery design. Even with experiments, the discovery learning system provides huge time and energy savings, with the potential to improve further as the learner accumulates enough knowledge to make predictions without running the discovery loop.

 

Next-gen lithium-ion batteries are very different from previous iterations—in chemistry, structure and materials—but the team argues that there are parallels among them that may help predict how new designs will perform. Rather than using simple statistical features from current and voltage signals, the interpreter leverages underlying physical properties to establish commonalities among different batteries.

 

With this information in hand, the oracle considers the battery in two ways: its internal characteristics—information from the interpreter about the physics and chemistry of the cell—and its operating conditions. For instance, at higher temperatures, a particular chemical change may dominate how the battery is likely to degrade, but that mechanism is less important at lower temperatures.

 

The team tested out their model with data and pouch cells from Farasis Energy USA. After training on a data set that included only cylindrical cells, similar to the familiar AA battery, the model could predict the performance of these larger cells. While full tests run to 1,000 cycles and can take a few months to years, 50-cycle tests take only a few days to weeks, according to the team's estimates. Testing required fewer cells, as well as fewer cycles, resulting in energy savings of about 95%.

 

Within battery technology, the team intends to expand the approach to other areas of performance, such as safety and charging speed. However, as discovery learning is a new scientific machine-learning approach, the team believes that others could build similar predictive tools or develop new approaches to optimization. They hope it could speed development in many disciplines bottlenecked by the need for expensive experiments, most immediately in chemistry and material design.

 

Researchers from the National University of Singapore also contributed to the study.

 

Study: Discovery learning predicts battery cycle life from minimal experiments (DOI: 10.1038/s41586-025-09951-7)

---

Journal

Nature

DOI

10.1038/s41586-025-09951-7 

 

Study in US veterans identifies agent orange exposure as a risk factor for rare skin cancer

Mass General Brigham

FacebookXLinkedInWeChatBlueskyMessageWhatsAppEmail

A study of U.S. veterans led by investigators at Mass General Brigham, VA Boston Healthcare System, and the Melanoma Research Alliance has identified a possible link between exposure to the Agent Orange herbicide and a rare melanoma subtype less likely to be related to sun exposure. The authors of the study, published in JAMA Dermatology, say this link warrants further examination to inform diagnostic strategies for people who may be at a greater risk for acral melanoma.

“Acral melanoma appears on the palms, soles of feet, or under fingernails or toenails and has a poorer prognosis than the more common cutaneous melanoma, because it is often diagnosed at later stages and doesn’t respond as well to current therapies,” said senior author Rebecca I. Hartman, MD, MPH, Director of Melanoma Epidemiology at Brigham and Women’s Hospital in the Mass General Brigham Department of Dermatology. “We need more information on risk factors to help us identify high-risk patients, which may lead to earlier detection, when treatments are most effective.”

"Acral melanoma is often diagnosed later and can be harder to treat, which makes research like this especially urgent," said MRA's chief executive officer, Marc Hurlbert, PhD, and team principal investigator. "For veterans who may have been exposed decades ago, this study provides important insight and reinforces the need to keep investing in research that can translate into earlier diagnosis and better outcomes."

For their study, researchers analyzed 2000–2024 data from the Veterans Health Administration, which contains a wealth of medical information on U.S. veterans, who have unique environmental and occupational exposures and higher melanoma rates than the general population.

The investigators compared 1,292 veterans with acral melanoma with 5,168 veterans without melanoma. Veterans with acral melanoma were also compared to veterans with cutaneous melanoma.

Exposure to the herbicide Agent Orange, which was used extensively during the Vietnam War and was banned in the 1970s, was linked with an approximately 30% higher odds of having acral melanoma. This finding is especially noteworthy, according to the authors, because officials have stated that several cancers are related to Agent Orange exposure, but that current evidence is insufficient to determine a link with melanoma.

Other potential risk factors for acral melanoma—including female sex, certain races/ethnicities, and prior skin lesions—were also identified in this study, but without as strong of an association.

“Our results support the need for continued studies of acral melanoma as a distinct entity from cutaneous melanoma,” said Hartman. “We should also consider additional investigations of Agent Orange as a risk factor for acral melanoma and evaluate whether a similar link might exist with other herbicides.”

 

Authorship: In addition to Hartman, Mass General Brigham authors include Jonathan C. Hwang, Kelly Cho, and John M. Gaziano. Additional authors include Linden B. Huhmann, Sergey D. Goryachev, Nicholas Starink, Martin A. Weinstock, Maryam M. Asgari, Christy Zheng, Charles Lu, Theodore C. Feldman, Nhan V. Do, Yevgeniy R. Semenov, Marc S. Hurlbert, and Nathanael R. Fillmore.

Paper cited: Hwang JC et al. “Identification of Risk Factors for Acral Melanoma in US Veterans” JAMA Dermatology DOI: 10.1001/jamadermatol.2025.5827

###

About Mass General Brigham

Mass General Brigham is an integrated academic health care system, uniting great minds to solve the hardest problems in medicine for our communities and the world. Mass General Brigham connects a full continuum of care across a system of academic medical centers, community and specialty hospitals, a health insurance plan, physician networks, community health centers, home care, and long-term care services. Mass General Brigham is a nonprofit organization committed to patient care, research, teaching, and service to the community. In addition, Mass General Brigham is one of the nation’s leading biomedical research organizations with several Harvard Medical School teaching hospitals. For more information, please visit massgeneralbrigham.org.

---

Journal

JAMA Dermatology

DOI

10.1001/jamadermatol.2025.5827 

Method of Research

Observational study

Subject of Research

People

Article Title

Identification of Risk Factors for Acral Melanoma in US Veterans

Article Publication Date

4-Feb-2026

COI Statement

Hartman reported grants from DOD and grants from VA CSRD during the conduct of the study. Additional author disclosures can be found in the paper.

 

Sounding out animal reactions to the 2024 eclipse

Calling behavior subtly altered by temporary darkening, study finds

Ohio State University

FacebookXLinkedInWeChatBlueskyMessageWhatsAppEmail

COLUMBUS, Ohio – No natural phenomenon provides a rarer chance to study the secrets of the animal world than a total solar eclipse. 

This was recently demonstrated by researchers investigating how a total solar eclipse might affect the soundscape of Midwestern United States prairie communities. Their objective was to discover how soundscapes — combinations of natural and artificial sounds that shape an environment — are influenced by ambient light, as light level helps cue annual biological events such as sexual reproduction and migration. 

Using novel acoustic capture devices to record animal vocalizations in the days before, during and after the April 2024 eclipse, researchers measured changes in soundscape diversity, complexity, and intensity at three different sites in Ohio: Larry R. Yoder Prairie Learning Laboratory, the Tecumseh Nature Preserve and Highbanks Metro Park. Their findings showed that while the eclipse was associated with both changes in sound activity and diversity, it was not associated with major changes in acoustic complexity.

“Solar eclipses are wonderful events that let us experiment in natural settings what sudden losses of light could be doing to animals,” said Madison Von Deylen, lead author of the study and a PhD student in evolution, ecology and organismal biology at The Ohio State University. 

“Both overexposure and underexposure to light can have negative consequences on animal physiology, and only a handful of studies have experimentally assessed how eclipses influence animal behavior.”

The study was recently published in the journal Ethology Ecology & Evolution. 

While similar soundscape research has been used to detect cryptic species and even identify members of those once thought extinct, Von Deylen said this study is one of the few to have used passive acoustic monitoring to quantify the effects of a solar eclipse on the animal soundscape. 

“We used a fairly novel technique to accomplish this,” she said. “Acoustic monitoring and soundscape analysis has a lot of promise for being able to track changes in ecosystem composition over time.”

Analyzing these subtle ecosystem changes allowed the team to dig deeper into the circumstances behind their results. For example, the time of year was important in this work. Any number of environmental differences would have altered the natural soundscape, but since  the eclipse coincided with the breeding season for many prairie birds, many unique calling patterns were able to be detected. 

Initially, researchers expected that a sudden decrease in ambient light would cause the prairie soundscape to mimic that of dusk. Their results suggest that overall sound activity was highest on the day of the eclipse, suggesting that even temporary environmental changes, such as lowered temperatures and moon phases, can inspire unexpected behavioral responses.

These new insights will not only aid scientists in understanding animal adaptability in the wild, but could spark new ideas on how to quantitatively measure environmental change, said Von Deylen, 

“The conclusions that we were able to draw from this study were extremely context-specific,” said Von Deylen. “But it lays the groundwork for more complex, larger-scale studies.” 

Future work will likely aim to sharpen the novel quantitative methods used in this paper so that soundscape analysis can become a vital research tool for other areas of study as well. 

“I’m really excited to see where soundscape work goes in the next couple of decades,” said Von Deylen. ““It will be of great help in answering new conservation questions.”

The study was supported by Ohio State’s Summer Research Opportunities Program. Other Ohio State co-authors include Sabeel Haddad and Susan Gershman. 

#

Contact: Madison Von Deylen, Vondeylen.12@osu.edu

Written by: Tatyana Woodall, Woodall.52@osu.edu 

---

Journal

Ethology Ecology & Evolution

DOI

10.1080/03949370.2025.2564807 

Article Title

Evaluating the impacts of a total solar eclipse on Midwest prairie soundscape

 

Researchers find brain mechanism behind ‘flashes of intuition’

Humanlike ability of related AI model to impact industry

NYU Langone Health / NYU Grossman School of Medicine

FacebookXLinkedInWeChatBlueskyMessageWhatsAppEmail

Despite decades of research, the mechanisms behind fast flashes of insight that change how a person perceives their world, termed “one-shot learning,” have remained unknown. A mysterious type of one-shot learning is perceptual learning, in which seeing something once dramatically alters our ability to recognize it again. 

Now a new study, led by researchers at NYU Langone Health, addresses the moments when we first recognize a blurry object, a primal ability that enabled our ancestors to avoid threats. 

Published online February 4 in Nature Communications, the new work pinpoints for the first time the brain region called the high-level visual cortex (HLVC) as the place where “priors” — images seen in the past and stored — are accessed to enable one-shot perceptual learning.

“Our work revealed, not just where priors are stored, but also the brain computations involved,” said co-senior study author Biyu He, Ph.D., associate professor in the departments of Neurology, Neuroscience, and Radiology at NYU Grossman School of Medicine.

Importantly, past studies had shown that patients with schizophrenia and Parkinson’s disease have abnormal one-shot learning, such that previously stored priors overwhelm what a person is presently looking at to generate hallucinations.

“This study yielded a directly testable theory on how priors act up during hallucinations, and we are now investigating the related brain mechanisms in patients with neurological disorders to reveal what goes wrong,” added Dr. He. 

The research team is also looking into likely connections between the brain mechanisms behind visual perception and the better-known type of “aha moment” when we comprehend a new idea.

Sharper Image

For the study, Dr. He’s team explored changes in brain activity triggered when people are shown Mooney images — faded pictures of animals and objects. Specifically, study participants are shown blurred images of the same object and then a clear version. In Dr. He’s 2018 study of this process, after seeing the clear version (and experiencing one-shot learning), subjects became twice as good at recognizing images because the experiment forced them to use their stored priors.

The researchers “took pictures” of brain activity during prior access using functional magnetic resonance imaging (fMRI), which measures brain cell activity by tracking blood flow to active cells. Signaling strength along nerve pathways (plasticity), however, is fine-tuned in the structural spaces (synapses) between brain cells, and fMRI can only measure activity within cells.

For that reason, the researchers combined fMRI with behavioral tests using Mooney images, electroencephalography (EEG) brain recordings, and a model based on machine learning — a form of AI — to locate priors in the HLVC.

To find the seat of one-shot perceptual learning, the research team first determined what kind of information is encoded in signaling changes as prior access improves image recognition. To do so, the team changed the size of images, their position on the page, and their orientation (by rotating them), and recorded the effect of each change on image recognition rates. This behavioral study revealed that changes in the image size did not change one-shot learning, while rotating an image or changing its position partially decreased learning. The results suggested that perceptual priors encode previously seen patterns but not more abstract concepts (e.g., the breed of a dog in an image).

The team then created statistical models that captured brain cell activity patterns via fMRI during prior access, and found that only the known neural coding patterns in the high-level visual cortex matched the properties of the priors that the behavioral study revealed. The authors also probed the timing properties of activity changes using intracranial electroencephalography (EEG) by asking patients already undergoing iEEG monitoring during neurosurgical treatment to perform a short perceptual task. iEEG collects readouts from electrodes on brain tissue to measure fast changing signaling patterns that fMRI cannot measure. The HLVC showed the earliest neural signaling strength changes just as prior-guided object recognition occurred.

As a final step, the research team built a vision transformer — an artificial intelligence model that finds patterns in image parts and fills in what is missing based on probabilities. Just as the HLVC was found to add prior weight to information coming in from the eyes, the AI model stored accumulated image information (priors) in one module, and then used the stored data to better recognize incoming imaging data in another module. Once trained on enough images, the neural network model achieved one-shot learning capability like that seen in humans, and better than other leading AI models without a comparable prior module.

“Although AI has made great progress in object recognition over the past decade, no tool has yet been capable of one-shot learning like humans,” added co-senior author Eric Oermann, M.D., assistant professor in the Departments of Neurosurgery and Radiology at NYU Langone. “We now anticipate the development of AI models with human-like perceptual mechanisms that classify new objects or learn new tasks with few or no training examples. This is more evidence of a growing convergence between computational neuroscience and advances in AI.”

Along with Drs. He and Oermann, authors included first authors Ayaka Hachisuka and Jonathan Shor, in NYU Langone Institute for Translational Neuroscience and first author Xujin Chris Liu of NYU Tandon School of Engineering. Other authors from NYU Langone Health are Daniel Friedman, Patricia Dugan, and Orrin Devinsky in the Department of Neurology and Werner Doyle in the Department of Neurosurgery. Author Yao Wang is in the Department of Electrical and Computer Engineering at the NYU Tandon School of Engineering. Authors from the Icahn School of Medicine at Mount Sinai are Ignacio Saez in the Department of Neuroscience and Fedor Panov in the Department of Neurosurgery.

This work was supported by a W.M. Keck Foundation medical research grant, National Science Foundation grant BCS-1926780, and the NYU Grossman School of Medicine. Oermann holds equity in Artisight Inc., Delvi Inc., and Eikon Therapeutics, and has consulting arrangements with Google Inc., and Sofinnova Partners. These relationships are managed in accordance with New York University policies.

About NYU Langone Health

NYU Langone Health is a fully integrated health system that consistently achieves the best patient outcomes through a rigorous focus on quality that has resulted in some of the lowest mortality rates in the nation. Vizient, Inc., has ranked NYU Langone No. 1 out of 118 comprehensive academic medical centers across the nation for four years in a row, and U.S. News & World Report recently ranked four of its clinical specialties No. 1 in the nation. NYU Langone offers a comprehensive range of medical services with one high standard of care across seven inpatient locations, its Perlmutter Cancer Center, and more than 320 outpatient locations in the New York area and Florida. The system also includes two tuition-free medical schools, in Manhattan and on Long Island, and a vast research enterprise.

---

Journal

Nature Communications

DOI

10.1038/s41467-026-68711-x 

Method of Research

Experimental study

Subject of Research

People

Article Title

Neural and computational mechanisms underlying one-shot perceptual learning in humans

Article Publication Date

4-Feb-2026