A Hybrid Approach to Estimate Spatially and Temporally Resolved PM2.5 Distribution from Multi-satellite AOD data

Keywords: Data fusion, Satellite-AOD, PM2.5 modeling
Session Type: Virtual Paper Abstract
Day: Friday
Session Start / End Time: 2/25/2022 12:40 PM (Eastern Time (US & Canada)) - 2/25/2022 02:00 PM (Eastern Time (US & Canada))
Room: Virtual 18

Abstract

Satellite-derived aerosol optical depth (AOD) has been widely used for ground-level PM2.5 modeling. Two critical limitations exist in the previous studies that estimated spatially and temporally resolved PM2.5 exposures using AODs: 1. Non-trivial missing data in AODs; 2. Disparate spatial and temporal resolutions of AODs obtained from different satellite platforms. In the present study, we developed a hybrid approach to estimate hourly PM2.5 variations at fine spatial resolution using multi-platformed AOD data by using both machine learning and geostatistical methods. We demonstrated that the application of the proposed approach improved data coverage, prediction accuracy, and spatiotemporal resolution for both AOD and ground PM2.5 using a case study conducted in East Asia.