<p>Efficient fuel management in mining operations is critical for reducing operational costs and environmental impact. This research conducts a comparison of multiple Artificial Intelligence (AI) methods to forecast the SFC of rear dump trucks used in a major coal mining project in India. The dataset comprises extensive operational parameters collected from different classes of rear dumpers, varying in payload capacity, across multiple shifts and haul cycles. Key input variables include payload, lead distance, haul road condition and machine age. The study employs different AI tools to develop predictive models for SFC. Performance metrics such as R² score and RMSE were used to evaluate and compare model accuracy. It has been observed that all the study models possessed good predicting capabilities. However, the ANN model has demonstrated superior predictive performance, capturing the nonlinear relationships between operational variables and fuel consumption with higher accuracy. The results indicate that AI-driven approaches can serve as effective tools for real-time monitoring and optimization of fuel efficiency in mining logistics, offering significant potential for cost savings and sustainability in coal mining operations.</p>