Regarding the construction of a mathematical model between air quality index (AQI) and different pollutant concentrations, firstly, a genetic algorithm was used to optimize the BP neural network model with PM2.5, PM10, , CO, and as the main air pollutants, and then the air pollution in Beijing from 2015 to 2021 was used as the validation object, and it was found that the fitted R-squared on the basis of 20% test set is greater than 0.95 or above, and finally the Spearman correlation model is used to analyze the main pollutants associated with AQI index to provide solutions for the subsequent treatment of air pollution. Regarding the construction of a comprehensive water quality evaluation model, firstly, the weight integration method based on the moment estimation theory was used to assign subjective and objective weights to the indicators, and dissolved oxygen, temperature, turbidity, ammonia nitrogen, permanganate index and hydrogen ion concentration index were used as indicators for evaluating water quality, and then the optimal weights of each indicator were derived as 7.766%, 9.509%, 37.962%, 19.666%, 17.726% and 7.7371%, and finally the comprehensive evaluation of water quality in each city was carried out by TOPSIS method. Regarding the construction of urban noise pollution monitoring network, firstly, a genetic algorithm based on Gaussian kernel support vector machine was used to optimize the model, and Guangzhou was used as the validation object to solve the Gaussian response surface with the building density as the noise index, and the optimal number of monitoring points of 10 was obtained by using genetic algorithm for optimization. **************** ACKNOWLEDGEMENTS**************** Thanks for the data support provided by the NAIS database and the China-PCS, as well as the project funding of Vehicle Measurement Control and Safety Key Laboratory of Sichuan Province (QCCK2021-011) and the State Administration of Market Administration Project (202248).
Read full abstract