Machine learning driven optimization of biofuel powered urban mobility for cleaner and smarter cities

Abstract

Urban transportation is a major contributor to greenhouse gas emissions and air pollution, particularly in rapidly urbanizing regions. Although alternative fuels and smart mobility solutions have been widely investigated, existing approaches often address emission prediction, air quality monitoring, and fuel optimization separately, limiting their effectiveness for integrated urban sustainability planning. This study presents Biofuel Powered Urban Mobility Platform, an integrated machine learning driven framework designed to support sustainable urban transportation. The framework combines CO 2 emission prediction, biofuel scenario analysis, air quality monitoring, and interactive web based visualization within a unified decision support platform. A dataset containing more than 7,000 vehicle configurations was used to develop and evaluate multiple machine learning models. Vehicle, fuel consumption, and engine related parameters were utilized to predict CO 2 emissions, while alternative fuel scenarios including E10 ethanol, E20 ethanol, B20 biodiesel, and Bio CNG were assessed to estimate their environmental impact. Among the evaluated machine learning algorithms, Random Forest Regression achieved the best predictive performance with an R 2 score of 0.970, a Mean Absolute Error (MAE) of 4.07 g/km, and a Mean Squared Error (MSE) of 52.83. Simulation results further demonstrated that E20 ethanol, B20 biodiesel, and Bio-CNG produced lower estimated CO 2 emissions than conventional fuels. The developed web-based platform enables real-time visualization of emission trends and environmental indicators for sustainable urban mobility planning. The proposed Biofuel Powered Urban Mobility Platform framework demonstrates the potential of integrating machine learning, biofuel optimization, environmental monitoring, and interactive visualization within a single smart city platform. The study highlights how data driven decision support systems can assist policymakers, urban planners, and transportation stakeholders in evaluating cleaner fuel alternatives and promoting more sustainable urban mobility strategies.