EcoSta 2019: Start Registration
View Submission - EcoSta2019
Title: Modeling and Regionalization of China's PM2.5 Using Spatial-Functional Mixture Model Authors:  Decai Liang - Peking University (China) [presenting]
Hui Huang - Peking University (China)
Abstract: Severe air pollution affects billions of people around the world, particularly in developing countries such as China. Effective emission control policies rely primarily on proper assessment of air pollutants and accurate spatial clustering outcomes. Unfortunately, emission patterns are difficult to observe as they are highly confounded by many meteorological and geographical factors. The standard clustering techniques generally fail to exploit the spatiotemporal features of data. We propose a novel approach for modeling and clustering daily PM2.5 concentrations all over China. Observed concentrations from monitoring stations are modeled as spatially dependent functional data. We assume the latent emission processes originate from a functional mixture model with each component as a spatiotemporal process. Cluster memberships of stations follow a Markov random field model and geographical factors are also considered. The superior performance of our approach compared to others is demonstrated using extensive simulation studies. Our method is effective in dividing China into several regions based on PM2.5 concentrations, suggesting separate local emission control policies are needed.