An Integrated Geospatial Decision Framework for Micro‐Scale Air and Noise Pollution Hazard Mapping

ABSTRACT

Urban air and noise pollution represent critical challenges for sustainable city management, especially in rapidly industrializing regions. Traditional monitoring systems often fail to capture the fine‐scale spatial heterogeneity that determines actual exposure levels. This research develops an integrated geospatial decision framework that combines Geographically Weighted Regression (GWR) and Multi‐Criteria Decision‐Making (MCDM) methods to map and prioritize micro‐scale pollution hazards. Using Isfahan, Iran, as a case study, air pollutants (PM _2.5 , SO ₂ , CO) and environmental noise (Leq) were spatially modeled through GWR to identify local determinants, while four MCDM techniques (TOPSIS, VIKOR, WASPAS, COPRAS) were used to synthesize multiple indices into a unified hazard map. Results indicate that over 70% of urban neighborhoods fall within high or upper‐medium hazard zones, with the southern industrial and central districts exhibiting the greatest cumulative risk. None of the 15 municipal zones qualified as low‐risk areas. These findings underscore the need for micro‐scale management policies, targeted mitigation in high‐exposure clusters, and the integration of spatial analytics into urban decision‐making. The proposed GWR–MCDM framework advances current environmental modeling by merging spatial non‐stationarity analysis with multi‐criteria prioritization. It offers a scalable and transferable tool for urban planners seeking data‐driven, location‐specific strategies to reduce pollution exposure and enhance urban sustainability.