Deep Transfer Learning on Satellite Imagery Improves Air Quality Estimates in Developing Nations
This addresses the lack of air quality monitoring infrastructure in LMICs, enabling improved emergency preparedness and risk mitigation, though it is incremental as it applies an existing method to new data.
The paper tackled the problem of accurately estimating air quality in low- and middle-income countries (LMICs) by adapting deep transfer learning from satellite imagery trained on high-income country data, achieving meaningful estimates for Accra, Ghana, based on patterns from Los Angeles and New York.
Urban air pollution is a public health challenge in low- and middle-income countries (LMICs). However, LMICs lack adequate air quality (AQ) monitoring infrastructure. A persistent challenge has been our inability to estimate AQ accurately in LMIC cities, which hinders emergency preparedness and risk mitigation. Deep learning-based models that map satellite imagery to AQ can be built for high-income countries (HICs) with adequate ground data. Here we demonstrate that a scalable approach that adapts deep transfer learning on satellite imagery for AQ can extract meaningful estimates and insights in LMIC cities based on spatiotemporal patterns learned in HIC cities. The approach is demonstrated for Accra in Ghana, Africa, with AQ patterns learned from two US cities, specifically Los Angeles and New York.