Enhancing Estimation of Fine Particulate Matter Chemical Composition across North America by Including Geophysical A Priori Information in Deep Learning with Uncertainty Quantification

Overview

Estimating PM₂.₅ chemical composition across North America with deep learning that incorporates geophysical a priori information, with uncertainty quantification.

Figures

Reference and citation

Siyuan Shen, Aaron van Donkelaar, Nathan Jacobs, Chi Li, Randall V. Martin: Enhancing Estimation of Fine Particulate Matter Chemical Composition across North America by Including Geophysical A Priori Information in Deep Learning with Uncertainty Quantification. ACS ES&T Air, 3(2), 336–350 (2026). https://doi.org/10.1021/acsestair.5c00251

Related dataset: North America Satellite-derived PM₂.₅ and Composition (V6.NA.01)