Optimising Placement of Pollution Sensors in Windy Environments
This work aims to improve the efficiency of air pollution monitoring for environmental scientists and public health officials, which is an incremental improvement to existing sensor placement methods.
This paper addresses the challenge of efficiently placing air pollution sensors by introducing two novel wind-informed kernels for Bayesian optimization. The goal is to identify locations of maximum pollution more effectively by accounting for the statistical structure of air pollution propagation in windy environments.
Air pollution is one of the most important causes of mortality in the world. Monitoring air pollution is useful to learn more about the link between health and pollutants, and to identify areas for intervention. Such monitoring is expensive, so it is important to place sensors as efficiently as possible. Bayesian optimisation has proven useful in choosing sensor locations, but typically relies on kernel functions that neglect the statistical structure of air pollution, such as the tendency of pollution to propagate in the prevailing wind direction. We describe two new wind-informed kernels and investigate their advantage for the task of actively learning locations of maximum pollution using Bayesian optimisation.