Close
Seminar
series event

Satellite-based machine learning models to estimate high-resolution environmental exposures across the UK

Air pollution is a public health concern, especially fine particulate matter (PM2.5). Both long- and short-term PM2.5 exposures are associated with adverse health outcomes (such as increased mortality and morbidity). Epidemiological assessment often rely on measurements from monitoring networks, which however are geographically sparse and mostly located in major cities. Novel big data data resources, such as aerosol optical depth (AOD) measurement from satellite instruments, offer a wide spatio-temporal coverage and can address limitations of traditional exposure methods. 

In this talk, we present satellite-based machine learning models to reconstruct levels of PM2.5 at high spatial and temporal resolution in Great Britain within the period 2003-2018. The model combines earth observation satellite measurements with multiple resources, including station data, climate and atmospheric models, traffic data, land-cover, and other geospatial features. The model then rely on a multi-stage random forest algorithm to predict PM2.5 concentrations at various temporal (daily to yearly) and spatial (1km to 100m) resolution. Such exposure data can be liked to small-area or individual-level health databases to perform country-wide epidemiological analyses on the health risks associated to air pollution.  

 

About the speakers

Rochelle Schneider is an advocate of building opportunities to introduce the benefits of satellite technologies into public health research, helping to ensure this relationship will generate impact at a worldwide scale. Her research interest encompasses in understanding the association between health and the environment, more specifically the impact on human health of short- and long-term exposures to different climate and air pollution stressors. Rochelle’s current project focuses on the development of a multi-stage satellite-based machine learning approach to reconstruct spatio-temporal missing Particulate Matter 10 and 2.5 concentrations across the UK, combining open and free data from NASA satellites, Copernicus climate and atmospheric models, chemical transport models, and public sector sources of geospatial features. 

Antonio Gasparrini’s interests encompass various research areas in epidemiology and public health evaluation, from methodology, applied research, and software implementation. His current research focuses on development of novel study designs for individual and small-area analyses, use of novel remote sensing and mobile technologies in epidemiology, spatio-temporal modelling of environmental exposures and risks, and health impact projections for climate change.

 

The session will be lives-streamed and recorded - accessible to internal audience only 

Watch the session

 

 

LSHTM CSM

Admission

Admission
No registration required. Seats available on first come, first served basis.

Contact