Risk Assessment and Prediction of Air Pollution Disasters in Four Chinese Regions

Evaluating the regional trends of air pollution disaster risk in areas heavy industry and economically developed cities is vital for sustainable development. Until now, previous studies have mainly adopted a traditional weighted comprehensive evaluation method to analyze risk. This research has integrated principal component analysis (PCA), genetic algorithm (GA) backpropagation (BP) neural network evaluate Hazard risk, hazard-laden environment sensitivity, hazard-bearing body vulnerability resilience were used measure degree The main findings were: (1) index Liaoning Province, Beijing, Shanghai Guangdong Province increased year by from 2010 2019; (2) mean absolute error (MAE), root square (RMSE) percentage (MAPE) each 2019, as predicted PCA-GA-BP network, 0.607, 0.317 20.3%, respectively; (3) results more accurate than those using PCA-BP GA-BP BP support vector regression (SVR) or extreme gradient boosting (XGBoost), which verified that machine learning could be assessment considerable extent.