Transportation emissions monitoring and policy research: Integrating machine learning and satellite imaging

Abstract

Determining and monitoring greenhouse gas (GHG) emissions remains complex as the global community endeavours to achieve emissions reduction goals. The road transportation sector poses a notable challenge in accurately calculating and monitoring global emissions due to its significant contribution to emissions worldwide. This research proposes integration of machine learning, satellite imaging, and localized emissions data to establish a precise and universally applicable system for monitoring GHG emissions in road transportation. This approach is known for its high level of accuracy, global scalability, and adaptability to diverse needs. The results indicate that integrating machine learning algorithms with satellite imagery is very effective method for monitoring GHG emissions in the transportation industry. The study’s conclusions are important for policymakers, transport authorities, and worldwide organizations working to reduce GHG emissions.