“The Aionics platform enables us to seamlessly implement machine learning models on our in-house data in real time, which brings another layer of rigorous analysis to help identify the chemical features driving performance that we care about most. The automated machine learning model-building and screening workflow also lets us screen hundreds of thousands of candidate materials for our devices in the blink of an eye.”

“Aionics is dramatically accelerating materials discovery, one of the slowest and most frustrating parts of battery R&D. Engineering and science teams can radically reduce the size of their designs of experiment and quickly hone in on material candidates that are most likely to produce optimal results. We see Aionics driving step-change improvements that will move us faster to the promise of ultra-high energy densities and custom-designed energy storage solutions.”

“Our in-house team of battery materials informatics experts at Showa Denko benefits greatly from our partnership with Aionics. What Aionics brings to our materials development program is far from a commodity: it is unique, cannot be found anywhere else, and is built on rigorous research from Stanford University. Since beginning our partnership with Aionics in 2019, our team regularly calls the Aionics API to predict the properties of novel materials, which accelerates our rate of materials discovery significantly.”

“Before we started this project, I said, 'there's no way we can use machine learning - we don't have data!' But ... we were able to double our cycle life under accelerated aging in eight weeks of electrolyte optimization. Sepion has been around for five years - we've never effected change that quickly before.”

“The project with Aionics started before I joined, and I was immediately impressed by the thoroughness and flexibility of the platform. Everything they do is, as far as I can tell, a data science best practice, especially for small datasets where extra care is needed. After meeting with them a few times, it became clear that their team is made of not just data scientists and developers, but also battery experts. Together, we were able to identify the “true” inputs to our system and independently validate conclusions reached by our own battery team (unknown to me at the time) – in less time and with less data.”