A Hybrid MOO-MCDM-PSOM Approach for Mapping Urban Carbon Trade Policies

In response to the global prioritization of environmental protection, nations increasingly focus on transitioning to low-carbon economies as a central strategy for achieving sustainable socio-economic growth. This study introduces a novel framework designed to evaluate, cluster, and map urban carbon policies by employing an integrated methodology that hybrid Multi-Objective Optimization (MOO), Multi-Criteria Decision-Making (MCDM), and Particle Swarm Optimization - Self Organizing Map (PSOM) techniques. Furthermore, a machine learning model utilizing the Random Forest algorithm is developed to enhance predictive capabilities, incorporating adaptive weighting and dynamic clustering for expert-informed analysis of sustainability strategies. Applying this hybrid approach to testing the dataset reveals that the predictive results can effectively guide city-level carbon trading strategies, thereby supporting government initiatives based on technology-based policy-making. The findings demonstrate that the proposed framework can robustly analyze and visualize complex datasets, contributing to mapping carbon trading policies against cities. Future research directions include exploring the integration of Internet of Thinks (IoT) systems to refine carbon trading strategies further, thus advancing the development of smart cities and promoting a more adaptive and sustainable urban environment.