Mapping Landslide Hazard Risk Using Random Forest Algorithm in Guixi, Jiangxi, China

Bibliographic Data

ID22031380
AuthorsYang Zhang (0000-0001-6777-3487, East China University of Technology), Weicheng Wu (0000-0001-6362-9840, East China University of Technology, corresponding author), Yaozu Qin (0000-0003-1998-2916, East China University of Technology), Ziyu Lin (0000-0003-0886-7285, East China University of Technology), Guiliang Zhang (0000-0003-0501-7533, 264 Geological Team of Jiangxi Nuclear Industry, Ganzhou 341000, China), Renxiang Chen (0000-0001-7890-5342, 264 Geological Team of Jiangxi Nuclear Industry, Ganzhou 341000, China), Yong Song (0000-0002-1067-7598, 264 Geological Team of Jiangxi Nuclear Industry, Ganzhou 341000, China), Tao Lang (0009-0001-7811-2905, 264 Geological Team of Jiangxi Nuclear Industry, Ganzhou 341000, China), Xiaoting Zhou (0000-0001-9698-4005, East China University of Technology), Wenchao Huangfu (East China University of Technology), Penghui Ou (East China University of Technology), Lifeng Xie (East China University of Technology), Xiaolan Huang (0000-0002-3330-4858, East China University of Technology), Shanling Peng (East China University of Technology), Chongjian Shao (0000-0002-2228-1515, East China University of Technology)
Year2020
Volume9
Issue11
Pages695
Publication date2020-11-23
Open AccessYes
TypeARTICLE
VenueISPRS International Journal of Geo-Information (JOURNAL)
Journal identifiersISSN: 2220-9964 • E-ISSN: 2220-9964
PublisherMDPI AG (PUBLISHER • IT)
DOI10.3390/ijgi9110695
OpenAlexW3107040622
LanguageEN
Citations received3
References cited23

Landslide hazards affect the security of human life and property. Mapping the spatial distribution of landslide hazard risk is critical for decision-makers to implement disaster prevention measures. This study aimed to predict and zone landslide hazard risk, using Guixi County in eastern Jiangxi, China, as an example. An integrated dataset composed of 21 geo-information layers, including lithology, rainfall, altitude, slope, distances to faults, roads and rivers, and thickness of the weathering crust, was used to achieve the aim. Non-digital layers were digitized and assigned weights based on their landslide propensity. Landslide locations and non-risk zones (flat areas) were both vectorized as polygons and randomly divided into two groups to create a training set (70%) and a validation set (30%). Using this training set, the Random Forests (RF) algorithm, which is known for its accurate prediction, was applied to the integrated dataset for risk modeling. The results were assessed against the validation set. Overall accuracy of 91.23% and Kappa Coefficient of 0.82 were obtained. The calculated probability for each pixel was consequently graded into different zones for risk mapping. Hence, we conclude that landslide risk zoning using the RF algorithm can serve as a pertinent reference for local government in their disaster prevention and early warning measures

Algorithm · Cartography · Civil engineering · Data mining · Geography · Hazard · Landslide · Lithology · Random forest · Remote sensing · Seismology · Zoning · Computer Science · Engineering · Fire effects on ecosystems · Flood Risk Assessment and Management · Landslides and related hazards · Artificial Intelligence · Geology

Tools

Open DOIOpen Access