Interpretable and Actionable Vehicular Greenhouse Gas Emission Prediction at Link-level

As a means to help systematically lower anthropogenic Greenhouse gas (GHG) emissions, accurate and precise GHG emission prediction models have became a key focus of many researchers. The appeal is that the predictive models will inform policymakers, and hopefully, in turn, they will bring about systematic changes. Since the transportation sector is constantly among the top GHG emission contributors, substantial effort in the field has been going into building more accurate and informative GHG prediction models. In this work, we seek to establish a predictive framework of GHG emissions at the road segment or link level of road networks. The key theme of the framework centers around model interpretability and actionability for high-level decision-makers. The main model adopted in this framework is a Discrete Choice Model (DCM). We show that, for the first time, DCM is capable of predicting link-level GHG emission levels on road networks in a parsimonious and effective manner. We also argue that since the goal of most GHG emission prediction models focuses on involving high-level decision-makers to make changes and curb emissions, the DCM-based GHG emission prediction framework is the most suitable framework to high-level decision-makers. The nature of the model framework can provide the decision-makers with ease and clarity to address the high GHG emission level with immediate and impactful strategies.