Establishing Mechanism of Warning for River Dust Event Based on an Artificial Neural Network

Abstract

PM10 is one of contributors to air pollution. One cause of increases in PM10 concentration in ambient air is the dust of bare land from rivers in drought season. The Taan and Tachia river are this study area, and data on PM10 concentration, PM2.5 concentration and meteorological condition at air monitoring site are used to establish a model for predicting next PM10 concentration (PM10(T + 1)) based on an artificial neural network (ANN) and to establish a mechanism for warning about PM10(T + 1) concentration exceed 150 μg/m3 from rivers in drought season. The optimal architecture of an ANN for predicting PM10(T + 1) concentration has six input factors include PM10, PM2.5 and meteorological condition. The train and test R was 0.8392 and 0.7900. PM10(T) was the most important factor in predicting PM10(T + 1) by sensitivity analysis. Finally, mechanism constraints were established for warning of high PM10(T + 1) concentrations in river basins.