What question did this study set out to answer?

This research aims to evaluate the effectiveness of various machine learning models for predicting lithium-ion battery state of charge (SOC).

August 3, 2026Scientific ReportsOpen Access

Battery performance prediction using supervised learning: a comparative study

View Full Paper

Ask AI

Bookmark

Authors

Comparative analysis demonstrates impact of machine learning models on predicting battery state of charge.

This research aims to evaluate the effectiveness of various machine learning models for predicting lithium-ion battery state of charge (SOC).
Five regression models (GLM, GBM, XGBoost, DRF, and XRT) are compared using the SiCWell dataset.
Model performance assessed using multiple regression metrics, including MAE, MSE, and R².
A consistent train-test evaluation protocol is applied for all models.
GLM shows low prediction errors, indicating a strong linear relationship with SOC (R² high).
Ensemble models display higher variance, leading to reduced generalization performance.
Dataset characteristics and feature linearity significantly affect model accuracy.

Reddy et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark