AI-Driven Digital Twins for Sustainable Urban Mobility: Integrating Generative Models for Traffic Optimization

Abstract

Due to the rapid expansion of the cities nowadays it is difficult to cope with the traffic congestions, air and noise contamination and the quality of the transportation. A framework is presented supporting AI and integrated digital twins and generative models to optimize how cities manage their public services and transportation system. Urban transportation using digital twins implies that you can test and assess policies by looking at the future and applying data to a dynamic model. Generative AI models that predict the flow of traffic, assist with the design of optimal routes, and enable machines to make decisions on their own make traffic management systems much more flexible. The system is depicted by the research of a metropolitan city and it results in an improved traffic, a decrease of resources consumption and emissions. The research proposes that digit twins enhanced with AI could significantly enhance the planning of smart cities and the sustainable (environmentally friendly) development of cities.