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

Journal: Environment international
Published Date: Dec 1, 2020

Abstract

INTRODUCTION: Estimating PM concentrations and their prediction uncertainties at a high spatiotemporal resolution is important for air pollution health effect studies. This is particularly challenging for California, which has high variability in natural (e.g, wildfires, dust) and anthropogenic emissions, meteorology, topography (e.g. desert surfaces, mountains, snow cover) and land use.

Authors

  • Lianfa Li
    Department of Preventive Medicine, University of Southern California, Los Angeles, CA, USA; State Key Laboratory of Resources and Environmental Information System, Institute of Geographical Sciences and Natural Resources, Chinese Academy of Sciences, Beijing, China. Electronic address: lianfali@usc.edu.
  • Mariam Girguis
    Department of Preventive Medicine, University of Southern California, Los Angeles, CA, USA.
  • Frederick Lurmann
    Sonoma Technology, Inc., Petaluma, CA, USA.
  • Nathan Pavlovic
    Sonoma Technology, Inc., Petaluma, CA, USA.
  • Crystal McClure
    Sonoma Technology, Inc., Petaluma, CA, USA.
  • Meredith Franklin
    Department of Preventive Medicine, University of Southern California, Los Angeles, CA, USA.
  • Jun Wu
    Department of Emergency, Zhuhai Integrated Traditional Chinese and Western Medicine Hospital, Zhuhai, 519020, Guangdong Province, China. quanshabai43@163.com.
  • Luke D Oman
    Goddard Space Flight Center, National Aeronautics and Space Administration, Greenbelt, MD, USA.
  • Carrie Breton
    Department of Preventive Medicine, University of Southern California, Los Angeles, CA, USA.
  • Frank Gilliland
    Department of Preventive Medicine, University of Southern California, Los Angeles, CA, USA.
  • Rima Habre
    Department of Preventive Medicine, University of Southern California, Los Angeles, CA, USA.

Keywords

External Resources

Popular Topics
Recent Journals