Why Battery Manufacturers Use the Citrine Platform
- Make data-driven decisions about material selection
- Use surrogate tests as predictors of lifetime cycle performance.
- Only move high-probability candidates forward for expensive, long tests.
- Uncover unintuitive combinations of materials uniquely suited to your battery chemistry.
Your Batteries Research Accelerator
Embark on a Data-Driven Path
Citrine’s platform utilizes chemistry-aware featurization to better harness your data and prior experiments. Harnessing data allows experiments to find the perfect electrolyte formulation for a new anode or cathode, or optimize a slurry formulation to hit specific power and energy density goals while staying inside of manufacturability windows, all with fewer experiments and less time.
Make Your Battery Testing More Efficient
Battery end-users require exceptional evidence of cycle life to accept emerging battery technologies in their products. Only testing batteries with a high probability of success, and stopping batteries with a low probability of success earlier in testing is an advantage of using battery lifetime prediction. Chemistry, formulation, configuration, and surrogate test inputs can all be used in an AI-guided approach to rank experiments by their probability of having excellent cycle life.
Support Team Research
Materials scientists will find the Citrine Platform is a cross-team enabler. The intuitive graphical interfaces show the exact history of materials information for final cells, eliminating the heritability problem when the development of individual aspects of the battery (cell fabrication, cathode, anode, and electrolyte) are happening on different teams at different times. Native visualization tools let you spot gaps in data, outliers, and trends, which can be immediately useful in AI-guided experiment design.
I feel like we’ve gone from the dark ages to the 21st century in one giant leap.”
Materials Scientist at a Battery company
Our customers in this sector include
Battery E-Book
Better batteries with with higher energy density and the ability to charge quickly are needed to enable the energy transition. This paper explores how AI can be used to reach ambitious battery property targets quickly, through material development, battery configuration optimization and improved battery testing.