Researchers and manufacturers of electric vehicles often receive many questions, such as, “What are factors affecting battery life?” or “Does the performance of an electric vehicle vary depending on the weather?”. Though they might be able to answer these questions using data they have individually collected, it would be a lot easier if they shared their data for all to understand.
The Battery Data Genome project is a new initiative led by Argonne National Laboratory in Illinois and Idaho National Laboratory, among others. The name references the Human Genome Project, a data-sharing project initiated in 1990 that enabled a new medical science innovation era. Like the Human Genome Project, the Battery Data Genome aims to encourage data generation, collection, and storage with flexible sharing. This would help develop energy storage further to meet decarbonization goals. This project will collect information on every part of the battery life cycle, how batteries respond to certain types of charging, and the effects of temperature, among other things.
“It’s going to take a lot of data, data from a lot of sources,” said George Crabtree, an American physicist and director of the Department of Energy’s Joint Center for Energy Storage Research. “We’re trying to energize and organize the battery community to contribute their data, whenever possible to as many researchers as possible, to enable powerful data science methods to catalyze breakthroughs,”
The participants of this project will include national labs, like Argonne and Idaho, and any other institution that wants to join. This may include universities, automakers, and other businesses. These preceding participants will be able to choose how much they want to contribute.
With increased access to valuable battery data, researchers hope to continue improving physics models and AI methodologies to optimize battery development. Information from the Battery Data Genome can support research into transport properties, reaction rates, and thermodynamic capacity for new cell designs. These models will provide a rough prediction of how a battery might perform.
Consumers, businesses, and the research and
development community would benefit because of research that should make batteries more durable and inexpensive. This would apply to EVs, stationary battery storage, and others. Moreover, Crabtree thinks that the insurance industry can use some of the data collected to better understand how to insure EVs.
“Having standardized and easily accessible, extensive data set may spur new questions for the battery community,” Crabtree said. “With access to data that all conform to a universal set of standards, guided by machine learning and artificial intelligence, we may find new pathways for innovation that to date we have not yet considered.”