AI-based identification of low-frequency debris flow catchments in the Bailong River basin, China

Abstract

Debris flow is a major geohazard in mountainous regions and poses a significant threat to life and property. The damage caused by debris flows have increased with the expansion of human settlements and activity into the mountainous regions of China. In regards to risks from debris flows, previously unrecognized low-frequency debris flow catchments constitute an especially significant threat. According to our investigation, only about 500 catchments have debris flow records in >2000 catchments of Bailong River basin. The main purpose of this paper is to introduce a new methodology using Artificial Intelligence (AI) that can simultaneously input parameters related to geomorphological conditions and material conditions to better distinguish low-frequency debris flow catchments (LFDs) from medium-high frequency debris flow catchments (MHFDs). A total of 449 prototypical debris flow catchments, 15 parameters, and 9 commonly used learning machines were used to build identification models. Debris flow catchments are divided into 4 cases (LO1-LO4) based on different sample ratios of LFDs and MHFDs, which are input into each classifier one by one. Based on model evaluation, the CHAID model in the case LO2 performs best, which only uses five parameters (formation lithology index, land use index, vegetation coverage index, drainage density and landslide density index) to predict LFDs. The results indicate that LFDs are mainly distributed in areas with less landslide distribution and better vegetation coverage compared with MHFDs. However, the distribution of LFDs is concentrated on FLI (formation lithology index) =4, which is the weak lithology area. The tree classifier seems to be better at classifying fluvial processes. The model developed in this paper can help us quickly find LFDs in similar areas, and help to assess the risk of debris flows.