In recent years, we have witnessed the world becoming more concerned with air pollution and its links to climate change. Particularly in the global north, countries are implementing systems to monitor air pollution on a large scale to aid decision making especially in urban settings. Such efforts are important but costly and cannot be implemented expediently. Furthermore, air pollution is a global problem and expensive solutions are challenging to implement in the global south, which consists of predominantly developing and unfortunately, poorer, nations. In this paper, we demonstrate that we can estimate air pollution using open-source information about the structure of roads. Our approach makes it possible to implement an inexpensive and accurate estimation of air pollution worldwide. We show that that despite the challenges, the estimation is accurate enough to be considered useful. Impact Statement: We show that a linear regression model underpinned by just a single structural property -- length of the track and unclassified road network within 0.5\% of districts within England and Wales -- is enough data to identify an ordering for which districts are the most polluted. The model discussed presents a low-cost method of achieving similar results to more expensive models such as the one currently used by DEFRA in the UK. The model has clear practical uses for policymakers who want to pursue clean air initiatives but lack the capital to invest in comprehensive dedicated monitoring networks, opening the door for the implementation of systems to estimate air pollution levels in low-income countries.