2000 character limit reached
Bayesian Optimisation for Active Monitoring of Air Pollution (2202.07595v2)
Published 15 Feb 2022 in cs.LG and physics.ao-ph
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.
- Application of an entropy-based Bayesian optimization technique to the redesign of an existing monitoring network for single air pollutants. Journal of Environmental Management, 90(8): 2715–2729.
- Active Localization of Gas Leaks Using Fluid Simulation. IEEE Robotics and Automation Letters, 4(2): 1776–1783.
- Exploration Enhanced Expected Improvement for Bayesian Optimization. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Lecture Notes in Computer Science, 621–637. Springer International Publishing. ISBN 978-3-030-10928-8.
- Emerging miniaturized technologies for airborne particulate matter pervasive monitoring. Measurement, 101: 250–256.
- Prediction of air pollution frequency distribution—Part I. The lognormal model. Atmospheric Environment (1967), 14(2): 255–258.
- Understanding the Metropolis - Hastings Algorithm. The American Statistician, 49(4): 327–335.
- Hierarchical space-time modelling of PM10 pollution. Atmospheric Environment, 41(3): 532–542.
- Estimates and 25-year trends of the global burden of disease attributable to ambient air pollution: an analysis of data from the Global Burden of Diseases Study 2015. The Lancet, 389(10082): 1907–1918.
- Copernicus. 2018. Sentinel-5P TROPOMI Level 2 Nitrogen Dioxide total column products. Version 01. Processed by ESA. DOI: 10.5270/S5P-s4ljg54.
- Where Is the Clean Air? A Bayesian Decision Framework for Personalised Cyclist Route Selection Using R-INLA. Bayesian Analysis, 16(1): 61–91.
- How Bayesian Should Bayesian Optimisation Be? arXiv:2105.00894.
- Optimising Placement of Pollution Sensors in Windy Environments. Presented at the NeurIPS 2020 Workshop on AI for Earth Sciences, arXiv:2012.10770.
- The No-U-Turn Sampler: Adaptively Setting Path Lengths in Hamiltonian Monte Carlo. Journal of Machine Learning Research, 15(1): 1593–1623.
- Imperial College London, E. R. G. 1993. London Air Quality Network. https://www.londonair.org.uk/LondonAir/Default.aspx. Accessed: 2021-08-31.
- Efficient Global Optimization of Expensive Black-Box Functions. Journal of Global Optimization, 13(4): 455–492.
- Katsouyanni, K. 2003. Ambient air pollution and health. British Medical Bulletin, 68(1): 143–156.
- Ambient and laboratory evaluation of a low-cost particulate matter sensor. Environmental Pollution, 221: 491–500.
- Approximate Inference for Fully Bayesian Gaussian Process Regression. Symposium on Advances in Approximate Bayesian Inference, 1–12. PMLR.
- The contribution of outdoor air pollution sources to premature mortality on a global scale. Nature, 525(7569): 367–371. Number: 7569 Publisher: Nature Publishing Group.
- Low-cost sensors as an alternative for long-term air quality monitoring. Environmental Research, 185: 109438.
- Bayesian optimisation for Intelligent Environmental Monitoring. In 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2242–2249. IEEE.
- Sequential Bayesian optimization as a POMDP for environment monitoring with UAVs. In 2017 IEEE International Conference on Robotics and Automation (ICRA), 6381–6388. IEEE.
- Slice sampling covariance hyperparameters of latent Gaussian models. In Advances in Neural Information Processing Systems, volume 23.
- Gaussian Processes for Machine Learning. MIT Press.
- Using local wind information for gas distribution mapping in outdoor environments with a mobile robot. In 2009 IEEE SENSORS, 1715–1720.
- Sahu, S. K. 2012. Hierarchical Bayesian Models for Space–Time Air Pollution Data. In Subba Rao, T.; Subba Rao, S.; and Rao, C. R., eds., Handbook of Statistics, volume 30 of Time Series Analysis: Methods and Applications, 477–495. Elsevier.
- Taking the Human Out of the Loop: A Review of Bayesian Optimization. Proceedings of the IEEE, 104(1): 148–175.
- A Survey of Model Evaluation Approaches With a Tutorial on Hierarchical Bayesian Methods. Cognitive Science, 32(8): 1248–1284.
- Modeling and decision making in spatio-temporal processes for environmental surveillance. In 2010 IEEE International Conference on Robotics and Automation, 5490–5497.
- Machine Learning for a Low-cost Air Pollution Network. Presented at the NeurIPS 2019 Workshop on Machine Learning for the Developing World, arXiv:1911.12868.
- Practical Bayesian Optimization of Machine Learning Algorithms. Advances in Neural Information Processing Systems, 25: 2951–2959.
- Gaussian processes for regression. Advances in neural information processing systems, 8.
- World Health Organization. 2006. Air quality guidelines: global update 2005: particulate matter, ozone, nitrogen dioxide, and sulfur dioxide. Copenhagen, Denmark: World Health Organization. ISBN 978-92-890-2192-0. OCLC: ocn162119780.