AI for Green Logistics and Decarbonized Transport Performance of Transport Organizations in Morocco

This study addresses the climate emergency by assessing the environmental performance of 270 Moroccan transport organizations (2019–2023) using four machine learning algorithms: Random Forest, XGBoost, SVM, and PLS. Among them, XGBoost achieved the best results with an R2 of 0.88 and F1-score of 0.83 in predicting fuel consumption and classifying environmental performance. The analysis identified route optimization and adoption of low-emission vehicles as key factors influencing environmental outcomes. The study also highlights differences in these factors' effectiveness across organization types (public vs. private) and sizes (SMEs vs. large firms). Ultimately, the research proposes a robust, data-driven framework to enhance environmental performance and guide public policies and managerial strategies towards greener logistics and decarbonized transport in Morocco.