From pixels to policy: Multi-scale flood susceptibility mapping using interpretable machine learning for urban resilience

Key Points

• Flood susceptibility mapping demonstrates how urban areas can be made more resilient.
• An interpretable machine learning model shows a 30% improvement in accuracy compared to traditional methods.
• Analysis utilizes multi-scale mapping techniques to evaluate flood risks across varied urban landscapes.
• Calls for integrating these predictive tools into urban planning to better anticipate and manage flood hazards.