Envisioning the Battery Data Genome, a Central Data Hub for Battery Innovation

Back in the 1990s, researchers embarked on the Human Genome Project, a 13-year journey that would enable a new era of innovation in medicine. By collecting and sharing vast amounts of data to unravel the mysteries behind the genetic determinants of disease, this project transformed the medical industry and led to countless breakthroughs. Now researchers are extending this innovation model to battery science with an eye on implications on a global scale.

Scientists from an international consortium led by researchers from the US Department of Energy’s Argonne and Idaho National Laboratories have recently proposed a comprehensive new data science paradigm called the Battery Data Genome. Developing unified data collection and data sharing practices across the wide-ranging battery community is an ambitious endeavor. These innovative practices will create an extensive database network to enable breakthroughs in energy storage using artificial intelligence (AI).

This is a call to action. We’re trying to motivate and organize the battery community to make their data available to as many researchers as possible to catalyze breakthroughs with powerful data science methods.” — Noah Paulson, Argonne Battery Scientist

The electrochemical science that is sorely needed for a zero-carbon economy requires cutting-edge data science,” said Argonne battery scientist Sue Babinec.​Tackling the extremely complex technical issues faced by battery scientists requires the generation of vast amounts of data AI and machine learning algorithms.”

Although there are some specialized battery data science projects, such as the Electrolyte Genome Project, the undertaking to create a battery data genome dedicated to all aspects of the battery and unifying work across institutions and scales is unprecedented,” said Argonne Distinguished Fellow and George Crabtree, director of the Joint Center for Energy Storage Research.

According to Crabtree, the Battery Data Genome will collect and store data from every step of the battery lifecycle, from discovery through development to manufacturing and all types of deployments. Universal data management standards for every segment of the battery community are required for data creation to unleash performance AI Algorithms designed to identify everything from new electrode material candidates to improved battery pack designs and cell lifetimes.

Also Read :  EFG Expands C-Suite Spearheading Technology Innovation to Support Industry Evolution | News

This is a call to action,” said Argonne battery scientist Noah Paulson.​We are trying to motivate and organize the battery community to make their data available to as many researchers as possible to catalyze breakthroughs with powerful data science methods.”

According to Paulson, when measuring a battery’s performance, scientists are interested in many different properties and qualities. Because of this, the datasets collected from different groups are not identical even when looking at the same battery in the same configuration.​We need to find the basic information that should be associated with each data set so we don’t have to spend time cleaning up the data to fit our models,” he said.

There are many common types of data for batteries, but there is no one-size-fits-all approach to them,” added Logan Ward, computer scientist at Argonne.​When data comes in many different formats, doesn’t include how it’s collected, and isn’t shared frequently between different groups, it becomes very difficult to create this type of large-scale data AI Analysis and predictions needed to accelerate the development and deployment of new batteries.”

Having data consistent and accessible means that it is formatted a certain way with consistent standards for metadata – which indicate how the data is collected.​The metadata can include, for example, the ambient temperature or even the resistance of the contacts to your electrodes,” said Babinec.

Paulson says increased collaboration is needed across the spectrum of battery researchers, from those studying individual molecules to those designing and testing battery packs, to create the new standards.

The transition of diverse groups of researchers studying different stages of a battery’s development to create a universal data set that can be universally accessed, understood and used presents a significant challenge, Babinec said.​It’s as if part of the community data were written in Spanish and part in German; They need a common scientific language.”

Also Read :  Biopharmaceutical Leader, Entrepreneur, Medical Educator and Visterra CEO Dr. Brian Pereira to be Honored with the Lifetime Achievement Award 2022

In order to attract as many participants as possible, the Battery Data Genome offers many options for data exchange.​It’s important to realize that not all data needs to be shared openly to be successful; There are many different sharing scenarios that could offer individual benefits to the many groups in the complex ecosystem,” said Babinec.

This would potentially make participation in the Battery Data Genome more attractive to industrial partners, who could leverage the data produced by academic or government partners without necessarily having to contribute their own.​It’s not dissimilar to blood types,” Babinec saidSome groups would be universal data donors, other groups would be universal data recipients, and overall the community would benefit.”

Once scientists fill the battery data genome with data, they need to test it. For this they useChallenge Problems” to validate the best AI Algorithms using the data in the battery data genome to solve real-world questions.​We might want to find out what happens to a specific type of battery running for a specific number of cycles at a specific temperature, but to do so proactively AIsaid Babinec.​A strong repository of standardized data is the first step.”

“A standardized and easily accessible large dataset can raise new questions for the battery community,” Crabtree said. “There are many unknown unknowns in batteries,” he said.​With access to data, all conforming to a universal set of standards and guided by machine learning and artificial intelligence, we may find new avenues for innovation that we haven’t considered before,” he said.

Argonne already offers open software to clean existing data files with the ​Battery-Data-Toolkit”, available at https://​github​.com/​m​a​t​e​r​i​a​l​s​-​d​a​t​a​- ​f​a​c​i​l​i​t​y​/​b​a​t​t​e​r​y​-​d​a​t​a​-​t​o​olkit . A release of full cycle life files for 300 lithium-ion batteries with six different cathode chemistries will follow later in October.

Also Read :  AMA Ed Hub member benefits

A paper announcing the Battery Data Genome will appear in the October 19 issue joules.

The Joint Center for Energy Storage Research (JCESR)a DOE Energy Innovation Hub is an important partnership that brings together researchers from many disciplines to break critical scientific and engineering barriers and develop new breakthrough energy storage technologies. Led by the US Department of Energy’s Argonne National Laboratory, partners include national leaders in science and technology from academia, the private sector and national laboratories. Their combined expertise spans the full spectrum of the technology development pipeline from basic research and prototyping to product development and market launch.

Argonne National Laboratory seeks solutions to pressing national problems in science and technology. Argonne, the nation’s premier national laboratory, conducts pioneering basic and applied scientific research in virtually every scientific discipline. Argonne researchers work closely with researchers from hundreds of corporations, universities, and federal, state, and local governments to help solve their specific problems, advance America’s scientific leadership, and prepare the nation for a brighter future. With employees from more than 60 nations, Argonne is managed by UChicago Argonne, GMBH for the Office of Science of the US Department of Energy.

Courtesy of Argonne National Laboratory. By Jared Sagoff

Related story: Mapping the battery data genome for better batteries


 

Do you appreciate CleanTechnica’s originality and coverage of CleanTechnica? Consider becoming a CleanTechnica Member, Supporter, Technician, or Ambassador—or a Patron on Patreon.


Don’t want to miss a cleantech story? Sign up for daily CleanTechnica news updates via email. Or follow us on Google News!


Do you have a tip for CleanTechnica, would you like to advertise or suggest a guest for our CleanTech Talk Podcast? Contact us here.


advertisement




Leave a Reply

Your email address will not be published.