Forecasting and Identifying the Meteorological and Hydrological Conditions Favoring the Occurrence of Severe Hazes in Beijing and Shanghai using Deep Learning

Abstract

Abstract. Severe haze or low visibility event caused by abundant atmospheric aerosols has become a serious environmental issue in many countries. A framework based on deep convolutional neural networks has been developed to forecast the occurrence of such events in two Asian megacities: Beijing and Shanghai. Trained using time sequential regional maps of meteorological and hydrological variables alongside surface visibility data over the past 41 years, the machine has achieved a good overall accuracy in associating the haze events with favorite meteorological and hydrological conditions. Furthermore, an unsupervised cluster analysis using features with a greatly reduced dimensionality produced by the trained machine has, arguably for the first time, successfully categorized typical regional meteorological-hydrological regimes alongside local quantities associated with haze and non-haze events in the two targeted cities, providing substantial insights to advance our understandings of this environmental extreme.\n