Estimating annual ambient air pollution using structural properties of road networks

Abstract

In recent years, the world has become increasingly concerned about air pollution. Particularly, High-Income Countries (HIC) and Upper Middle-Income Countries (UMIC) are implementing systems to monitor air pollution on a large scale to aid decision-making. Such efforts are essential, but they have at least three shortcomings: (1) they are costly; (2) they are slow to deploy; and (3) they focus on urban areas, which leads to urban-rural inequalities. Here, we show that we can estimate annual air pollution using open-source information about the structural properties of roads; we focus on England and Wales in the United Kingdom (UK) in this paper, although we argue that our methods are independent of specific country features. Our approach is an inexpensive method of estimating annual air pollution concentrations to an accuracy level that can underpin policymakers’ decisions while providing an estimate in all districts, not just urban areas. Furthermore, we contend that our process is interpretable and explainable.