A Spatial-Temporal Interpretable Deep Learning Model for improving interpretability and predictive accuracy of satellite-based PM2.5

Xing Yan; Zhou Zang; Yize Jiang; Wenzhong Shi; Yushan Guo; Dan Li; Chuanfeng Zhao; Letu Husi

doi:10.1016/j.envpol.2021.116459

A Spatial-Temporal Interpretable Deep Learning Model for improving interpretability and predictive accuracy of satellite-based PM_2.5

Environ Pollut. 2021 Jan 11:273:116459. doi: 10.1016/j.envpol.2021.116459. Online ahead of print.

Authors

Xing Yan¹, Zhou Zang², Yize Jiang², Wenzhong Shi³, Yushan Guo², Dan Li², Chuanfeng Zhao², Letu Husi⁴

Affiliations

¹ State Key Laboratory of Remote Sensing Science, College of Global Change and Earth System Science, Beijing Normal University, Beijing, 100875, China. Electronic address: yanxing@bnu.edu.cn.
² State Key Laboratory of Remote Sensing Science, College of Global Change and Earth System Science, Beijing Normal University, Beijing, 100875, China.
³ Department of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University, Hong Kong, China.
⁴ Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences (CAS), DaTun Road No. 20 (North), Beijing, 100101, China.

PMID: 33465651
DOI: 10.1016/j.envpol.2021.116459

Abstract

Being able to monitor PM_2.5 across a range of scales is incredibly important for our ability to understand and counteract air pollution. Remote monitoring PM_2.5 using satellite-based data would be incredibly advantageous to this effort, but current machine learning methods lack necessary interpretability and predictive accuracy. This study details the development of a new Spatial-Temporal Interpretable Deep Learning Model (SIDLM) to improve the interpretability and predictive accuracy of satellite-based PM_2.5 measurements. In contrast to traditional deep learning models, the SIDLM is both "wide" and "deep." We comprehensively evaluated the proposed model in China using different input data (top-of-atmosphere (TOA) measurements-based and aerosol optical depth (AOD)-based, with or without meteorological data) and different spatial resolutions (10 km, 3 km, and 250 m). TOA-based SIDLM PM_2.5 achieved the best predictive accuracy in China, with root-mean-square errors (RMSE) of 15.30 and 15.96 μg/m³, and R² values of 0.70 and 0.66 for PM_2.5 predictions at 10 km and 3 km spatial resolutions, respectively. Additionally, we tested the SIDLM in PM_2.5 retrievals at a 250 m spatial resolution over Beijing, China (RMSE = 16.01 μg/m³, R² = 0.62). Furthermore, SIDLM demonstrated higher accuracy than five machine learning inversion methods, and also outperformed them regarding feature extraction and the interpretability of its inversion results. In particular, modeling results indicated the strong influence of the Tongzhou district on the principle PM_2.5 in the Beijing urban area. SIDLM-extracted temporal characteristics revealed that summer months (June-August) might have contributed less to PM_2.5 concentrations, indicating the limited accumulation of PM_2.5 in these months. Our study shows that SIDLM could become an important tool for other earth observation data in deep learning-based predictions and spatiotemporal analysis.

Keywords: Deep learning; Interpretability; MODIS; PM(2.5).