Bayesian Optimisation for Active Monitoring of Air Pollution
Abstract
Air pollution is one of the leading causes of mortality globally, resulting in millions of deaths each year. Efficient monitoring is important to measure exposure and enforce legal limits. New low-cost sensors can be deployed in greater numbers and in more varied locations, motivating the problem of efficient automated placement. Previous work suggests Bayesian optimisation is an appropriate method, but only considered a satellite data set, with data aggregated over all altitudes. It is ground-level pollution, that humans breathe, which matters most. We improve on those results using hierarchical models and evaluate our models on urban pollution data in London to show that Bayesian optimisation can be successfully applied to the problem.
Keywords
Cite
@article{arxiv.2202.07595,
title = {Bayesian Optimisation for Active Monitoring of Air Pollution},
author = {Sigrid Passano Hellan and Christopher G. Lucas and Nigel H. Goddard},
journal= {arXiv preprint arXiv:2202.07595},
year = {2024}
}
Comments
Presented at AAAI 2022 in the Special Track on AI for Social Impact. Updates: - Small corrections to references - Correction that baselines use gradient-based optimisation, not gradient descent - Correction to data preprocessing for LAQN data - Correction that the kernel signal variances were modelled internally, not their square roots - Correction to iteration for Table 3 (31, not 30)