Literature DB >> 32980736

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

Lianfa Li1, Mariam Girguis2, Frederick Lurmann3, Nathan Pavlovic3, Crystal McClure3, Meredith Franklin2, Jun Wu4, Luke D Oman5, Carrie Breton2, Frank Gilliland2, Rima Habre6.   

Abstract

INTRODUCTION: Estimating PM2.5 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.
METHODS: Using ensemble-based deep learning with big data fused from multiple sources we developed a PM2.5 prediction model with uncertainty estimates at a high spatial (1 km × 1 km) and temporal (weekly) resolution for a 10-year time span (2008-2017). We leveraged autoencoder-based full residual deep networks to model complex nonlinear interrelationships among PM2.5 emission, transport and dispersion factors and other influential features. These included remote sensing data (MAIAC aerosol optical depth (AOD), normalized difference vegetation index, impervious surface), MERRA-2 GMI Replay Simulation (M2GMI) output, wildfire smoke plume dispersion, meteorology, land cover, traffic, elevation, and spatiotemporal trends (geo-coordinates, temporal basis functions, time index). As one of the primary predictors of interest with substantial missing data in California related to bright surfaces, cloud cover and other known interferences, missing MAIAC AOD observations were imputed and adjusted for relative humidity and vertical distribution. Wildfire smoke contribution to PM2.5 was also calculated through HYSPLIT dispersion modeling of smoke emissions derived from MODIS fire radiative power using the Fire Energetics and Emissions Research version 1.0 model.
RESULTS: Ensemble deep learning to predict PM2.5 achieved an overall mean training RMSE of 1.54 μg/m3 (R2: 0.94) and test RMSE of 2.29 μg/m3 (R2: 0.87). The top predictors included M2GMI carbon monoxide mixing ratio in the bottom layer, temporal basis functions, spatial location, air temperature, MAIAC AOD, and PM2.5 sea salt mass concentration. In an independent test using three long-term AQS sites and one short-term non-AQS site, our model achieved a high correlation (>0.8) and a low RMSE (<3 μg/m3). Statewide predictions indicated that our model can capture the spatial distribution and temporal peaks in wildfire-related PM2.5. The coefficient of variation indicated highest uncertainty over deciduous and mixed forests and open water land covers.
CONCLUSION: Our method can be generalized to other regions, including those having a mix of major urban areas, deserts, intensive smoke events, snow cover and complex terrains, where PM2.5 has previously been challenging to predict. Prediction uncertainty estimates can also inform further model development and measurement error evaluations in exposure and health studies.
Copyright © 2020 The Author(s). Published by Elsevier Ltd.. All rights reserved.

Entities:  

Keywords:  Air pollution exposure; California; High spatiotemporal resolution; Machine learning; PM(2.5); Remote sensing; Wildfires

Year:  2020        PMID: 32980736      PMCID: PMC7643812          DOI: 10.1016/j.envint.2020.106143

Source DB:  PubMed          Journal:  Environ Int        ISSN: 0160-4120            Impact factor:   9.621


  37 in total

1.  The association between PM2.5 exposure and neurological disorders: A systematic review and meta-analysis.

Authors:  Pengfei Fu; Xinbiao Guo; Felix Man Ho Cheung; Ken Kin Lam Yung
Journal:  Sci Total Environ       Date:  2018-11-15       Impact factor: 7.963

Review 2.  Uncertainty and risk in wildland fire management: a review.

Authors:  Matthew P Thompson; Dave E Calkin
Journal:  J Environ Manage       Date:  2011-04-13       Impact factor: 6.789

3.  Estimating regional spatial and temporal variability of PM(2.5) concentrations using satellite data, meteorology, and land use information.

Authors:  Yang Liu; Christopher J Paciorek; Petros Koutrakis
Journal:  Environ Health Perspect       Date:  2009-01-28       Impact factor: 9.031

4.  Maternal fine particulate matter (PM2.5) exposure and adverse birth outcomes: an updated systematic review based on cohort studies.

Authors:  Lei Yuan; Yan Zhang; Yu Gao; Ying Tian
Journal:  Environ Sci Pollut Res Int       Date:  2019-03-20       Impact factor: 4.223

5.  Estimating PM2.5 Concentrations in the Conterminous United States Using the Random Forest Approach.

Authors:  Xuefei Hu; Jessica H Belle; Xia Meng; Avani Wildani; Lance A Waller; Matthew J Strickland; Yang Liu
Journal:  Environ Sci Technol       Date:  2017-06-01       Impact factor: 9.028

6.  Fine and ultrafine particulate organic carbon in the Los Angeles basin: Trends in sources and composition.

Authors:  Farimah Shirmohammadi; Sina Hasheminassab; Arian Saffari; James J Schauer; Ralph J Delfino; Constantinos Sioutas
Journal:  Sci Total Environ       Date:  2015-11-11       Impact factor: 7.963

7.  Impacts of fire smoke plumes on regional air quality, 2006-2013.

Authors:  Alexandra E Larsen; Brian J Reich; Mark Ruminski; Ana G Rappold
Journal:  J Expo Sci Environ Epidemiol       Date:  2017-12-29       Impact factor: 5.563

8.  Spatial Variation in Particulate Matter Components over a Large Urban Area.

Authors:  Scott Fruin; Robert Urman; Fred Lurmann; Rob McConnell; James Gauderman; Ed Rappaport; Meredith Franklin; Frank D Gilliland; Martin Shafer; Patrick Gorski; Ed Avol
Journal:  Atmos Environ (1994)       Date:  2014-02-01       Impact factor: 4.798

9.  Modeling the residential infiltration of outdoor PM(2.5) in the Multi-Ethnic Study of Atherosclerosis and Air Pollution (MESA Air).

Authors:  Ryan W Allen; Sara D Adar; Ed Avol; Martin Cohen; Cynthia L Curl; Timothy Larson; L-J Sally Liu; Lianne Sheppard; Joel D Kaufman
Journal:  Environ Health Perspect       Date:  2012-02-22       Impact factor: 9.031

Review 10.  Critical Review of Health Impacts of Wildfire Smoke Exposure.

Authors:  Colleen E Reid; Michael Brauer; Fay H Johnston; Michael Jerrett; John R Balmes; Catherine T Elliott
Journal:  Environ Health Perspect       Date:  2016-04-15       Impact factor: 9.031

View more
  1 in total

1.  Wildfires in Pregnancy: Potential Threats to the Newborn.

Authors:  Amy M Padula; Tarik Benmarhnia
Journal:  Paediatr Perinat Epidemiol       Date:  2022-01       Impact factor: 3.980

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.