BatteryML is an early-stage research initiative in the Rolston Lab at Arizona State University focused on applying machine learning to battery data to understand degradation and predict battery health.
Using machine learning to analyze electrochemical impedance spectroscopy (EIS) data for battery degradation diagnostics and health prediction.
- Explore machine learning methods for battery diagnostics
- Analyze battery cycling and electrochemical data
- Develop models for battery degradation and health prediction
- Build reproducible pipelines for battery data analysis
BatteryML is building tools and workflows for:
- Battery dataset processing
- Feature extraction from cycling and impedance data
- Machine learning model experimentation
- Visualization and benchmarking of battery health metrics
Rolston Lab studies reliability and materials science challenges in energy technologies, including photovoltaics and batteries.
- Website: https://rolston.lab.asu.edu/
- GitHub: https://github.com/rolston-lab-asu
This work is in active early development. Code, datasets, and documentation continue to expand as projects progress.
