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...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Environment international Jg. 145; S. 106143
Hauptverfasser:	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
Sprache:	Englisch
Veröffentlicht:	Goddard Space Flight Center Elsevier Ltd 01.12.2020 Elsevier
Schlagworte:	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-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!