Comprehensive analysis of air quality in northern cities based on TOPSIS-BP neural network model
基于TOPSIS—BP神经网络模型的北方城市空气质量综合分析

摘要

为贯彻落实“双碳”政策，推动绿色发展，针对改善空气质量这一问题，以北京、天津、石家庄等北方城市为研究区，基于华顿研究院中国百强城市排行榜指标体系，结合中国空气质量指数和封闭式问卷调查数据，将2023年各城市资金要素投入、人力要素投入、管理要素投入作为输入，空气质量指标作为输出，建立BP神经网络模型，分析投入要素与空气质量之间的关系，采用熵权法确定指标权重，基于TOPSIS法建立综合评价模型，根据评价结果，进而对政府提出改进空气质量的建议。

Abstract

In order to implement the "dual carbon" policy and promote green development, in order to improve air quality, taking Beijing, Tianjin, Shijiazhuang and other northern cities as the study area, based on the index system of Wharton Research Institute's ranking of China's top 100 cities, combined with China's air quality index and closed-end questionnaire survey data, the investment of capital elements, human factors and management factors in 2023 was taken as input, and air quality indicators were used as outputs to establish a BP neural network model. The relationship between input factors and air quality was analyzed, the entropy weight method was used to determine the index weight, and a comprehensive evaluation model was established based on the TOPSIS method, and then suggestions for improving air quality were put forward to the government according to the evaluation results.