Unveiling An Efficient Framework for Predicting Flood Risk Areas, Using Earth Observatory Data, Google Earth Engine, and Multicriteria Decision Making-Analytical Hierarchy Process
Unveiling An Efficient Framework for Predicting Flood Risk Areas, Using Earth Observatory Data, Google Earth Engine, and Multicriteria Decision Making-Analytical Hierarchy Process

Summary/Abstract: The flood risk in the Niger-East region of Niger State is increasingly becoming an annual event. Climatic shifts, land-surface modifications, and human socioeconomic factors are among the conditions that trigger floods. This study explores geospatial technology and multicriteria decision analysis-analytical hierarchy process (MCDA-AHP) to develop a flood risk prediction system that leverages Google Earth Engine to process remote sensing data directly influencing flood risk. Elevation, slope, drainage density, rainfall, soil, proximity to drainage, proximity to road, population density, flow accumulation, and land use land cover (LULC). The weightage assignment was performed using the MCDA-AHP technique. Flood risk classes predicted as very low, 13.82 km2 (9.29%), low, 18.77 km2 (12.61%), low – moderate, 111.97 km2 (75.24%), high, 3.32 km2 (2.23%), and very high, 0.93 km2 (0.63%) of the study area, respectively. This research presents a flood emergency response system that highlights the impact of different prioritization criteria across multiple conditions. Therefore, integrating GEE to generate different flood-conditioning risk indicators, prioritized and ranked using MCDA-AHP, is crucial for developing an efficient methodological framework for flood risk prediction across a wide region, achieving 88% precision. Thus, effective for evidence-based decision-making by authorities, policy makers, and emergency response agencies.

• Details
• Contents