Data-Driven Machine Learning Models for Predicting CO2 Emission Rates Combustion from Grey Hydrogen and Classification of Traffic Congestion Level for Enhanced Smart Mobility
Zeina Alabido · Transportation research procedia · 2026
Smart mobility is a term that refers to how adopting cleaner, safer, and efficient behaviour towards shifting to clean transportation matters to enhance smart mobility. The term refers to using different modes of transportation, or instead of owning a gas-fuelled vehicle, such as ride sharing, public transportation, car-sharing, biking, or even walking. Finding a reasonable solution to monitor the traffic congestion and the emission of carbon resulted from the grey hydrogen, which is nature gas, is the future of eco-friendly technology towards saving the environment. Following this approach, we will get closer to zero emissions, zero accidents, and zero pollution. There are key principles to achieve smart mobility, flexibility of transportation options, efficiency of the travel with minimum disruption, safety, and clean technology. However, many cities are facing problems in roads and streets, which leads to complex traffic congestion, has a negative impact on the environment. Also, high congestion leads to other problems, such as the disruption of road infrastructure, a high rate of potential accidents, and leads to high CO 2 emission resulting from the combustion of grey hydrogen. To mitigate and support this environmental problem, an artificial optimized machine learning approach will be built to predict the levels of CO 2 emissions, and predicting traffic conditions, thereby enabling data-driven strategies for cleaner, smarter, and more efficient mobility systems. In this research, regression models will be employed to detect the CO 2 emission rate. In addition, classification techniques to predict the traffic conditions Geotab (2024).