Estimating ground-level PM2.5 by fusing satellite and station observations: A geo-intelligent deep learning approach

TL;DR

This paper introduces a geo-intelligent deep learning model that fuses satellite and station data to accurately estimate ground-level PM2.5 pollution, significantly outperforming traditional neural networks in Chinese data from 2015.

Contribution

It develops Geoi-DBN, a deep belief network that incorporates geographical correlations, providing a novel method for air pollution estimation over large regions.

Findings

Geoi-DBN achieves a cross-validation R of 0.94, up from 0.63.

RMSE decreases from 29.56 to 13.68 μg/m3.

Over 80% of the Chinese population lives in areas with PM2.5 > 35 μg/m3.

Abstract

Fusing satellite observations and station measurements to estimate ground-level PM2.5 is promising for monitoring PM2.5 pollution. A geo-intelligent approach, which incorporates geographical correlation into an intelligent deep learning architecture, is developed to estimate PM2.5. Specifically, it considers geographical distance and spatiotemporally correlated PM2.5 in a deep belief network (denoted as Geoi-DBN). Geoi-DBN can capture the essential features associated with PM2.5 from latent factors. It was trained and tested with data from China in 2015. The results show that Geoi-DBN performs significantly better than the traditional neural network. The cross-validation R increases from 0.63 to 0.94, and RMSE decreases from 29.56 to 13.68${\mu}$g/m3. On the basis of the derived PM2.5 distribution, it is predicted that over 80% of the Chinese population live in areas with an annual mean PM2.5 of greater than 35${\mu}$g/m3. This study provides a new perspective for air pollution monitoring in large geographic regions.