Abstract
This article addresses one of the most serious environmental challenges in the world — greenhouse gas emissions. The logistics sector is among the main sources of these emissions and, given its critical importance to the operation of any enterprise, the environmental issue remains extremely urgent. Technological progress brings new opportunities, one of which is analyzed in this article: the use of artificial intelligence to optimize transportation processes and reduce harmful emissions into the atmosphere. The purpose of this study is to explore and assess the potential of machine learning algorithms and neural networks for the development and adaptation of freight transport chains, taking into account the increasing traffic intensity and the growing number of vehicles, especially in large urban areas, as well as factors such as weather conditions, delivery deadlines, and unexpected restrictions on heavy transport. The research objectives include developing a method for evaluating the sustainability of logistics processes using indicators such as fuel consumption, CO₂ emissions, and idle mileage, as well as conducting a comparative analysis of traditional and intelligent route planning. A practical test was carried out through urban transport simulation. Route optimization using AI resulted in a 15% reduction in kilometers traveled and a 10–12% decrease in CO₂ emissions. The results confirm that intelligent algorithms can serve as an effective tool for implementing green logistics principles and integrating environmental criteria into transportation sector strategies.