Explainable AI for Battery Degradation Prediction in EVs: Toward Transparent Energy Forecasting

The rapid growth of electric vehicles (EVs) has intensified the demand for accurate and interpretable battery health prediction systems. While machine learning models have demonstrated high accuracy in forecasting battery degradation, their “black-box” nature poses challenges for real-world deployment in safety-critical applications. This paper proposes an explainable artificial intelligence (XAI) framework for battery degradation prediction, aiming to provide transparent and reliable insights into energy storage dynamics in EVs. The study integrates data-driven models such as Gradient Boosting Machines (GBMs) and Long Short-Term Memory (LSTM) networks with post hoc explainability tools, including SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME). Experimental evaluations on real-world EV battery datasets show that the proposed framework achieves strong predictive performance while offering interpretable outputs regarding feature influence and degradation dynamics. These findings suggest that XAI-enabled models can bridge the gap between predictive power and trust, contributing to smarter battery management systems and sustainable transportation.