Ensemble-based deep learning for estimating PM2.5 over California with multisource big data including wildfire smoke

•California has high variability in PM2.5 sources, meteorology and topography.•We used ensemble deep learning with multisource big data to improve PM2.5 estimates.•We reliably imputed missing satellite AOD and fused wildfire dispersion estimates.•Our model achieved high PM2.5 prediction performance...

Full description

Saved in:

Bibliographic Details
Published in:	Environment international Vol. 145; p. 106143
Main Authors:	Li, Lianfa, Girguis, Mariam, Lurmann, Frederick, Pavlovic, Nathan, McClure, Crystal, Franklin, Meredith, Wu, Jun, Oman, Luke D., Breton, Carrie, Gilliland, Frank, Habre, Rima
Format:	Journal Article
Language:	English
Published:	Goddard Space Flight Center Elsevier Ltd 01.12.2020 Elsevier
Subjects:	aerosols air pollution Air pollution exposure air temperature California carbon monoxide cloud cover Computer Programming And Software dust Earth Resources And Remote Sensing environment Environment Pollution Geosciences (General) High spatiotemporal resolution land cover Machine learning meteorology PM2.5 prediction relative humidity Remote sensing smoke snowpack spatial distribution topography traffic uncertainty Wildfires California Wildfires High spatiotemporal resolution Air pollution exposure PM2.5 Machine learning California Remote sensing Air Quality Air Pollution Exposure Wildfire Pm2.5 Remote Sensing High Spatiotemporal Resolution Machine Learning
ISSN:	0160-4120, 1873-6750, 1873-6750
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!