APPLICATION OF SWARM INTELLIGENCE FOR LANDSLIDE SUSCEPTIBILITY MODELING FROM GEOSPATIAL DATA FUSION

摘要

This study utilizes and explores the feasibility and application of swarm intelligence for landslide susceptibility modeling based on collected inventory of rainfall-induced shallow landslide events. Eleven geospatial factors are considered, including topographic, vegetative, environmental, geological and man-made information. Landslide inventory and factors are overlapped to obtain the training data for modeling (classification) and verification. Experimental results indicate that swarm intelligence algorithms can provide plausible results for landslide susceptibility modeling, comparing with conventional landslide detection and prediction methods.