An in-depth analysis of factors and forecasting techniques for emerging solid waste streams

Area of Science:

• Environmental Science
• Waste Management Engineering
• Data Science

Background:

• Technological advancements generate novel emerging solid waste streams (ESWSs).
• Inadequate management policies for ESWSs present significant environmental and economic challenges.
• Accurate forecasting of ESWS quantities is crucial for effective policy formulation and resource allocation.

Purpose of the Study:

• To systematically review and analyze forecasting models for major ESWSs: PV waste, e-waste, battery waste, and biomedical waste.
• To categorize identified models based on methodology, variables, scale, and data type.
• To provide guidance on data source selection and highlight future research gaps in ESWS forecasting.

Main Methods:

• Systematic literature review of forecasting models for four key ESWSs.
• Classification of 40 identified modelling methodologies into distinct categories.
• Analysis of over 100 independent variables and data sources used in forecasting.

Main Results:

• Identification and categorization of 40 distinct forecasting methodologies for ESWSs.
• Analysis of crucial independent variables and data types influencing forecast accuracy.
• Evaluation of data uncertainty and recommendations for suitable data source selection.

Conclusions:

• A structured categorization of ESWS forecasting models aids in selecting appropriate methods.
• Understanding data uncertainty and source selection is vital for accurate waste quantity predictions.
• This research provides a foundational guide for developing robust waste management policies for emerging solid wastes.