460. AI-Driven GIS for Dynamic Flood Risk Assessment: Integrating MCDA, Remote Sensing, and Real-Time Climate Analytics
Invited abstract in session WD-39: Sustainable & Resilient Cities, stream Sustainable & Resilient Systems and Infrastructures.
Wednesday, 14:30-16:00Room: Newlyn LG.01
Authors (first author is the speaker)
| 1. | Amirbahador Kouchakkapourchali
|
| DIST, Polytechnic University of Turin |
Abstract
As climate change intensifies extreme weather events, traditional flood risk models struggle to provide dynamic and data-driven assessments. This study introduces a novel AI-powered GIS framework that combines Multi-Criteria Decision Analysis (MCDA) with real-time climate data and machine learning for adaptive flood risk prediction. Using the Analytic Hierarchy Process (AHP), risk factors—including precipitation anomalies, elevation, land use dynamics, soil permeability, and hydrological networks—are weighted and processed through Python-based geospatial analysis. Satellite-derived climate data and remote sensing imagery enable real-time hazard detection, while AI-driven pattern recognition enhances predictive accuracy. The framework generates an interactive flood risk map, dynamically updating based on changing environmental conditions. By bridging GIS, artificial intelligence, and climate analytics, this approach offers an automated, scalable tool for real-time disaster resilience, empowering policymakers with precise, data-driven insights for climate adaptation and urban planning.
Keywords
- Decision Analysis
- Machine Learning
- Water Management
Status: accepted
Back to the list of papers