A Machine Learning-Based Multi-Criteria Decision-Making Approach Utilizing D-Numbers for Water-Energy-Food Nexus Assessment

The interdependency between the water and energy infrastructure represents the core challenge of resource management. Effective decision-making for water-energy-food (WEN) scenarios requires robust tools. Traditional Multi-Criteria Decision-Making (MCDM) approaches are undermined by uncertainty because they assume perfect and complete information, which rarely occurs in Water-Energy Nexus (WEN) issues. Classical models oversimplify the complex interconnections between water and energy systems and therefore result in suboptimal decision-making approaches. Although fuzzy and intuitionistic models are efforts towards uncertainty modelling, they also fall short of fully capturing the dynamics of real-world scenarios. They are inefficient in addressing conflicting and uncertain information, which hinders the practical implementation of these techniques. In addition, the lack of a platform that unites MCDM with integrated uncertainty management increases decisionmaking complications. To bridge these gaps, the current study proposes a new framework that integrates D-number-based multi-criteria analysis with Dempster-Shafer theory (DST) for WEN decision-making. The integration of DST rigorously enhances the ability of DST to process complete, uncertain, and conflicting information for WEN decision-making. The study also compared the performance of the Random Forest and Optimized Artificial Neural Network models.