Prediction and health impact assessment of municipal solid waste generation in Tianjin: Based on GRA-BiLSTM model

Abstract

With the large amount of municipal solid waste (MSW) generated, incineration has become the primary technology used for MSW treatment in development nowadays, but the gas pollution produced by this process can adversely affect public health. Despite the clear link between air pollution and health, the relationship between gases generated from MSW and health has been less studied. Therefore, to further investigate the relationship between PM_2.5 generated from MSW incineration and human health, this study proposes a multi-factor prediction model integrating grey correlation analysis (GRA) and bidirectional long short-term memory (BiLSTM) neural network for premature mortality due to MSW incineration in Tianjin in 2035. The impact of future policies and development trends in Tianjin is fully considered, and the impact of incineration technology on human health in Tianjin is quantitatively discussed by analysing the results of three scenarios and suggesting corresponding policy recommendations. Further experimental results showed that (1) the mean absolute error, mean absolute percentage error and root mean square error values based on the GRA-BiLSTM model were 12.14, 15.78 and 4.75, respectively, showing good applicability for the prediction of MSW generation in Tianjin. (2) By 2035, the MSW generation in Tianjin is projected to reach 6.42 million tonnes, with premature mortality rates ranging from 1.7 to 2.7% under different incineration scenarios. (3) Based on the trends of MSW generation and disposal methods in Tianjin, the government needs to actively promote domestic waste separation policies, further strengthen the functions of sanitation administrative departments and promote domestic waste separation and recycling.