US student builds EV battery model with 2.36% error

At just 18 years old, Colin Jie Chu, an aspiring scientist from Palo Alto, California, has spent the past two years working on a project that could become increasingly relevant as electric vehicles continue to gain popularity. Through Stanford University's Young Investigators Program, Chu collaborated with Professor Simona Onori and her lab, alongside PhD student Sai Thatipamula and the industry partner Nuvoton, on the research.

Chu's work concentrated on estimating the health of lithium-ion batteries, the type of batteries commonly used in electric vehicles, under varying operating conditions. Instead of relying solely on machine learning, he combined an equivalent circuit model with machine learning regression techniques. This unique approach allowed him to develop a framework that could estimate battery state of health, even as conditions changed.

The resulting framework achieved a remarkable 2.36% error rate in state-of-health predictions, which Chu presented at the fourth Modelling, Estimation, and Control Conference in Chicago. The research was also published in the Journal of The Electrochemical Society. This notable accuracy in predicting battery health sets Chu's work apart and earned him recognition as one of the 40 finalists in the 2026 Regeneron Science Talent Search, a prestigious competition for high school students in the United States.

While Chu's model showed impressive accuracy, it's essential to note that the framework was evaluated on research data, not in real-world testing across different battery chemistries, ages, driving conditions, and vehicle platforms. Therefore, the 2.36% prediction error does not guarantee that the model can accurately predict the exact remaining lifetime of every electric-car battery in the future.

Colin Jie Chu's story highlights the potential of high school research programs to give young students access to sophisticated scientific problems at an early stage, long before they enter college. His work demonstrates the exciting possibilities that lie ahead as we strive to improve the lifespan and efficiency of lithium-ion batteries in electric vehicles.