Estimating PM2.5 concentration of the conterminous United States via interpretable convolutional neural networks. (January 2020)

• Record Type: Journal Article
• Authors: Park, Yongbee; Kwon, Byungjoon; Heo, Juyeon; Hu, Xuefei; Liu, Yang; Moon, Taesup
• Is Part Of: Environmental pollution. Volume 256(2020)
• Publication Date: 2020-01
• Subjects: Convolutional neural network (CNN) -- Layerwise relevance propagation (LRP) -- Predictor importance -- Deep learning -- National scale PM2.5 estimation; Pollution -- Periodicals; Pollution -- Environmental aspects -- Periodicals; Environmental Pollution -- Periodicals; Pollution -- Périodiques; Pollution -- Aspect de l'environnement -- Périodiques; Pollution -- Effets physiologiques -- Périodiques; Pollution; Pollution -- Environmental aspects; Periodicals; Electronic journals; 363.73
• DOI: 10.1016/j.envpol.2019.113395
• Languages: English
• ISSNs: 0269-7491

Abstract

Abstract: We apply convolutional neural network (CNN) model for estimating daily 24-h averaged ground-level P M 2.5 of the conterminous United States in 2011 by incorporating aerosol optical depth (AOD) data, meteorological fields, and land-use data. Unlike some of the recent supervised learning-based approaches, which only utilized the predictors from the location of which P M 2.5 value is estimated, we naturally aggregate predictors from nearby locations such that the spatial correlation among the predictors can be exploited. We carefully evaluate the performance of our method via overall, temporally-separated, and spatially-separated cross-validations (CV) and show that our CNN achieves competitive estimation accuracy compared to the recently developed baselines. Furthermore, we develop a novel predictor importance metric for our CNN based on the recent neural network interpretation method, Layerwise Relevance Propagation (LRP), and identify several informative predictors for P M 2.5 estimation. Graphical abstract: Image 1 Highlights: Convolutional neural network (CNN) accurately estimates daily averaged PM2.5. Layerwise relevance propagation (LRP) is used to obtain predictor impor-tance list. Exploiting spatial correlation of nearby predictors boosts the estimation accuracy. Weighted average feature of PM2.5 is useful even when CNN is used. CNN can generate smooth annual prediction map of PM2.5 for the con-terminous US. Abstract : Interpretable convolutional neural network, equipped with important predictors list, is utilized for the first time to accurately estimate ground-level P M 2.5 concentration based on spatially correlated predictors.