Large Quantitative Models (LQMs): An End-to-End AI Platform for Battery Materials Discovery and Capacity Fade Prediction

Predicting the end-of-life (EOL) of lithium-ion batteries across different manufacturerspresents significant challenges due to variations in electrode materials, manufacturingprocesses, cell formats, and a lack of generally available data. Methods that constructfeatures solely on voltage-capacity profile data typically fail to generalize across cellchemistries. This study introduces a methodology that combines traditional voltagecapacity features with Direct Current Internal Resistance (DCIR) measurements, enabling more accurate and generalizable EOL predictions. The use of early-cycle DCIRdata captures critical degradation mechanisms related to internal resistance growth, enhancing model robustness. Models are shown to successfully predict the number of cyclesto EOL for unseen manufacturers of varied electrode composition with a mean absoluteerror (MAE) of 150 cycles. This cross-manufacturer generalizability reduces the need forextensive new data collection and retraining, enabling manufacturers to optimize newbattery designs using existing datasets. Additionally, a novel DCIR-compatible datasetis released as part of ongoing efforts to enrich the growing ecosystem of cycling data andaccelerate battery materials development.