Evaluating the capability of municipal solid waste separation in China based on AHP-EWM and BP neural network

Hao Xi; Zhiheng Li; Jingyi Han; Dongsheng Shen; Na Li; Yuyang Long; Zhenlong Chen; Linglin Xu; Xianghong Zhang; Dongjie Niu; Huijun Liu

doi:10.1016/j.wasman.2021.12.015

Evaluating the capability of municipal solid waste separation in China based on AHP-EWM and BP neural network

Waste Manag. 2022 Feb 15:139:208-216. doi: 10.1016/j.wasman.2021.12.015. Epub 2021 Dec 31.

Authors

Hao Xi¹, Zhiheng Li¹, Jingyi Han¹, Dongsheng Shen¹, Na Li¹, Yuyang Long¹, Zhenlong Chen², Linglin Xu¹, Xianghong Zhang¹, Dongjie Niu³, Huijun Liu⁴

Affiliations

¹ School of Environmental Science and Engineering, Zhejiang Gongshang University, Hangzhou, Zhejiang 310018, China.
² School of Statistics and Mathematics, Zhejiang Gongshang University, Hangzhou, Zhejiang 310018, China.
³ College of Environmental Science and Engineering, Tongji University, Shanghai 200086, China.
⁴ School of Environmental Science and Engineering, Zhejiang Gongshang University, Hangzhou, Zhejiang 310018, China. Electronic address: lhj@zjgsu.edu.cn.

PMID: 34974315
DOI: 10.1016/j.wasman.2021.12.015

Abstract

With the increase in municipal solid waste (MSW), most cities face solid waste management issues. In this study, the analytic hierarchy process (AHP) and artificial neural network (ANN) models were improved to assess the MSW separation capability based on 18 selected indicators of solid waste separation in 15 cities in China. The entropy weight method (EWM) was used in AHP to optimize and determine the indicators and then evaluate their weights, which showed that the general public budget expenditure had the highest weight (0.5239). This implied that the MSW separation capability could be mainly influenced by government financial support. ANN based on scan optimization and machine learning methods were established (R² = 0.9992) to predict the missing indicators. The mapping relationship between MSW separation indicators and capabilities was also significantly improved from R² = 0.5317 to R² = 0.9993, thereby increasing the prediction accuracy of MSW separation capabilities to 95.15%. Thus, this research provides a new avenue for MSW separation and establishes a combined model to predict the separation capability in practical applications.

Keywords: Analytic Hierarchy Process; Artificial Neural Network; Entropy Weight Method; Municipal Solid Waste; Waste Management; Waste Separation.

MeSH terms

Analytic Hierarchy Process
China
Cities
Entropy
Neural Networks, Computer
Refuse Disposal*
Solid Waste / analysis
Waste Management*

Substances

Solid Waste