Artificial Intelligence for sustainable logistics: Reducing carbon emissions and fuel consumption through route optimization

Sarioguz, Orcun (2025) Artificial Intelligence for sustainable logistics: Reducing carbon emissions and fuel consumption through route optimization. International Journal of Science and Research Archive, 15 (3). pp. 1527-1537. ISSN 2582-8185

The world logistics industry is coming under pressure to shift its operations to greener practices as environmental awareness and regulatory pressure on these environmental practices rise. Artificial Intelligence (AI) in the direction of an optimal route can help, in particular, find ways of transport logistics in which the savings in carbon emission and an increase in the actual fuel quality can be significantly reduced. The paper examines how AI-based optimization methods could be implemented in logistics networks and play a role in sustainability. With the help of the latest achievements in machine learning, ant colony optimization, and smart logistics with the support of IoT devices, the authors investigate AI technologies' role in minimizing fuel consumption and emissions following the principle of real-time adaptive routing. An extensive literature review provides an analysis of implementation frameworks, primary enablers, and difficulties in the adoption of AI technologies. Its findings suggest that AI-enabled route optimization can produce significant carbon and fuel savings via reductions of up to 15 and 30 percent in specific scenarios with an efficient digital infrastructure and data platforms. Moreover, sustainability benefits are optimized when AI is a part of wider policies in logistics, including green fleet management and reverse logistics. This paper adds to the expanding literature on sustainable logistics and AI and provides strategic suggestions to policymakers and logistics providers willing to decarbonize them via intelligent transportation systems.