2021-09-08, 15:00–15:20, HUGOTech
Exposure to fine particulate matter (PM2.5) is linked to adverse health outcomes. Usually, epidemiological studies rely on PM2.5 measurements collected from ground monitors. However, in many places such as Great Britain the existing monitoring network provides limited spatio-temporal coverage of PM2.5. Data from satellites, climate/atmospheric reanalysis models, and chemical transport models offer additional information that can be used to reconstruct PM2.5 concentrations, filling the gaps in the ground monitoring network. This study developed a multi-stage satellite-based machine learning (ML) model to estimate daily PM2.5 levels across Great Britain during 2008-2018. Stage-1 estimated PM2.5 concentrations in monitors with only PM10 records. Stage-2 imputed missing satellite aerosol-optical-depth due to cloudiness and bad retrievals. Stage-3 applied the Random Forest algorithm to estimate PM2.5 concentrations using a combined dataset from Stage-1, Stage-2, and a list of spatiotemporally synchronised predictors. Stage-4 estimated daily PM2.5 using Stage-3 model. The model performed well with an overall mean R2 of 0.77. The high spatio-temporal resolution and the relatively high precision allowed these estimates (approximately 950 million points) to be used in epidemiological analyses to assess health risks associated with both short- and long-term exposure to PM2.5.
I've used several open and free Copernicus products to reconstruct historical PM2.5 levels across Great Britain.
paper: https://www.mdpi.com/2072-4292/12/22/3803/htm
Rochelle Schneider1,2,3,4, Ana M. Vicedo-Cabrera5,6, Francesco Sera2,7, Pierre Masselot2, Massimo Stafoggia8, Kees de Hoogh9,10, Itai Kloog11, Stefan Reis12,13, Massimo Vieno12 and Antonio Gasparrini2,3,14
1 European Space Agency, Φ-Lab, Frascati, 00044, Italy
2 Department of Public Health, Environments and Society, London School of Hygiene & Tropical Medicine, London WC1H 9SH, UK
3 The Centre on Climate Change and Planetary Health, London School of Hygiene & Tropical Medicine, London WC1H 9SH, UK
4 European Centre for Medium-Range Weather Forecast (ECMWF), Reading, UK
5 Institute of Social and Preventive Medicine, University of Bern, 3012 Bern , Switzerland
6 Oeschger Center for Climate Change Research, University of Bern, 3012 Bern, Switzerland
7 University of Florence, Department of Statistics, Computer Science and Applications "G. Parenti", Florence, 60550, Italy
8 Department of Epidemiology, Lazio Regional Health Service, Rome 00147, Italy
9 Swiss Tropical and Public Health Institute, Basel, Switzerland
10 University of Basel, Basel, Switzerland
11 Department of Geography and Environmental Development, Ben-Gurion University of the Negev, P.O.B. 653 Beer Sheva
12 UK Centre for Ecology & Hydrology, Bush Estate, Penicuik, Edinburgh, Midlothian, EH26 0QB, UK
13 University of Exeter Medical School, Knowledge Spa, Truro, TR1 3HD, United Kingdom
14 Centre for Statistical Methodology, London School of Hygiene & Tropical Medicine, London WC1E 7HT, UK
Rochelle Schneider is a Research Fellow in AI4EO at the European Space Agency Φ-Lab. She is also visiting scientist at ECMWF and honorary Assistant Professor at London School of Hygiene & Tropical Medicine (LSHTM). Dr Schneider holds a PhD in Geospatial Analytics, MSc GIS & Science, and MRes in Remote Sensing. Rochelle is passionate about EO missions and an advocate of building opportunities to introduce the benefits of satellite technologies into public health research, unlocking and ensuring the generation of global impact.