This paper presents a novel approach for modeling temperature evolution in Lithium Iron Phosphate (LiFePO4) electric vehicle batteries using Neural Operators. The method overcomes limitations of traditional heat transfer models by learning a data-driven surrogate that accurately predicts battery temperature as a function of driving diagnostics and environmental conditions. The study explores regularization techniques and a time stability loss function to enhance the model’s robustness and accuracy. Results demonstrate the efficacy of the proposed Neural Operator framework for estimating battery temperature dynamics.