AIGIS-based methodology for natural terrain landslide susceptibility mapping in Hong Kong

Abstract

This paper presents a novel application of Artificial Intelligence (AI) and Geographic Information System (GIS) to the mapping of natural terrain landslide susceptibility in Hong Kong. The method is applied to the central part of Lantau Island as a pilot study. First, we discuss the key technical concepts of AI and GIS, the advantages of their integrated application, and the growing importance of remote sensing data. We then describe the working procedure including the construction of the GIS database, pre-treatment of input data, and training of the network classifier. High prediction rates and positive outcomes from reliability tests demonstrate the success of the methodology and show its great potential for use in landslide disaster mitigation planning in Hong Kong.