Evaluation of waste management and energy saving for sustainable green building through analytic hierarchy process and artificial neural network model

• Published in: Chemosphere (Oxford) 2023-03, Vol.318, p.137708-137708, Article 137708
• Main Authors: Lu, Yanjie, Ge, Yisu, Zhang, Guodao, Abdulwahab, Abdulkareem, Salameh, Anas A., Ali, H. Elhosiny, Nguyen Le, Binh
• Format: Article
• Language: English
• Subjects: Analytic Hierarchy Process; Analytic Hierarchy Process (AHP); Artificial Neural Network (ANN); Energy saving; Incineration; Refuse Disposal; Solid waste; Solid Waste - analysis; Sustainable green building; Waste Disposal Facilities; Waste Management
• ISSN: 0045-6535; 1879-1298
• DOI: 10.1016/j.chemosphere.2022.137708

A significant portion of the solid waste filling landfills worldwide is debris from construction and demolition projects. Across the world, a significant portion of the solid waste filling landfills is made up of construction and demolition waste. Recycling construction waste may help cut down on the quantity of waste sent to landfills and the requirement for energy and other natural resources. To help with construction waste reduction, a management hierarchy that begins with rethink, reduce, redesign, refurbish, reuse, incineration, composting, recycle, and eventually disposal is likely to be effective. The objective of this research is to investigate the viability of the Analytic Hierarchy Process (AHP) as a data gathering instrument for the development of a solid waste management assessment tool, followed by an examination of an artificial neural network (ANN). Using a standardized questionnaire, all data was gathered from waste management practitioners in three industry sectors. The survey data was subsequently analyzed using ANN and later AHP. The suggested framework consisted of four components: (1) the development of different level structures for fluffy AHP, (2) the calculation of weights, (3) the collection of data, and (4) the making of decisions. An ANN feedforward with error back propagation (EBP) learning computation is coupled to identify the association between the items and the store execution. It was found that the combination of AHP and ANN has emerged as a key decision support tool for landfilling, incineration, and composting waste management strategies, taking into account the environmental profile and economic and social characteristics of each choice. Composting has the highest sustainable performance when a balanced weight distribution of criteria is assumed, especially if the environmental component is considered in comparison to the other criteria. However, if social and economic features are addressed, incineration or landfilling have more favorable characteristics, respectively. [Display omitted] •Viability of AHP as a data gathering instrument Freeze thaw cycles aspect is investigated.•Development of solid waste management assessment tool is aimed.•ANN feedforward with error back propagation (EBP) learning computation is used.•Association between the items and the store execution is conducted.•If social and economic features are addressed, incineration or landfilling have more favorable characteristics.