Multivariate Analysis and Index Forecast of Influencing Factors of Shanghai Municipal Domestic Waste Generation

Traditional methods of municipal domestic waste analysis and prediction lack precision, while most data’s sample size is not suitable for many neural networks. In this paper, combining the advantage of deep learning methods with the results of association analysis, a waste production prediction method TLSTM is proposed based on long short-term memory(LSTM). It is found that the most influencing factors are population, public cost, household and GDP. Meanwhile, the garbage production in Shanghai will continue to decline in the future, indicating the policy of refuse classification is effective. The R-square index and MSE index of the model were 0.55 and 76571.73 respectively, surpassing other state-of-the-art models. In cooperation with School of Environmental Science and Engineering at Shanghai Jiao Tong University, the dataset comes from the average data of the Shanghai Household Waste Management Regulation from 1980 to 2020. This research method has a certain guiding significance to both the related fields of municipal solid waste management and environmental planning and the application of neural network models in other fields.