Bayesian Aerosol Retrieval-Based PM2.5 Estimation through Hierarchical Gaussian Process Models

Satellite-based aerosol optical depth (AOD) data are widely used to estimate land surface PM2.5 concentrations in areas not covered by ground PM2.5 monitoring stations. However, AOD data obtained from satellites are typically at coarse spatial resolutions, limiting their applications on small or medium scales. In this paper, we propose a new two-step approach to estimate 1-km-resolution PM2.5 concentrations in Shanghai using high spatial resolution AOD retrievals from MODIS. In the first step, AOD data are refined to a 1 x 1 km(2) resolution via a Bayesian AOD retrieval method. In the second step, a hierarchical Gaussian process model is used to estimate PM2.5 concentrations. We evaluate our approach by model fitting and out-of-sample cross-validation. Our results show that the proposed approach enjoys accurate predictive performance in estimating PM2.5 concentrations.

Automated summary

This paper proposes a new two-step approach to estimate 1-km-resolution PM2.5 concentrations in Shanghai using satellite data. The approach refines AOD data to a higher resolution using a Bayesian retrieval method and then uses a hierarchical Gaussian process model to estimate PM2.5 concentrations. The results show accurate predictive performance of the proposed approach.