Data-Driven Selection of Nature-Based Solutions for Urban Resilience in Cities

This study presents a preliminary decision-support tool based on a Bayesian network (BN) model to evaluate nature-based solutions (NbS) for enhancing urban resilience. Focusing on Istanbul, a city highly vulnerable to extreme heat, flooding, humidity, and air pollution, the research designs a BN model by integrating land use data, meteorological data, and urban heat island mapping. The proposed method guides to develop a model with high accuracy and resolution, allowing for more precise identification of NbS that effectively achieve the goals of mitigating climate risks—temperature reduction, runoff reduction, humidity control, and air quality improvement. A key novelty is the incorporation of district-level data, ensuring that the proposed NbS are tailored specifically to Istanbul’s unique environmental and urban conditions. This hybrid methodology provides both city-specific insights for urban resilience planning worldwide. The findings contribute to sustainable urban development and inform policy recommendations for incorporating NbS into urban planning and climate adaptation strategies.