Uncertainties of landslide susceptibility prediction due to different spatial resolutions and different proportions of training and testing datasets

被引：0

作者：

Huang F. ^{[1
,2
]}

Chen J. ^{[1
]}

Tang Z. ^{[1
]}

Fan X. ^{[2
]}

Huang J. ^{[3
]}

Zhou C. ^{[1
]}

Chang Z. ^{[1
]}

机构：

[1] School of Civil Engineering and Architecture, Nanchang University, Nanchang

[2] State Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu

[3] ARC Centre of Excellence for Geotechnical Science and Engineering, University of Newcastle, 2287, NSW

来源：

Yanshilixue Yu Gongcheng Xuebao/Chinese Journal of Rock Mechanics and Engineering | 2021年 / 40卷 / 06期

基金：

中国国家自然科学基金;

关键词：

Environmental factors; Landslide susceptibility prediction; Machine learning; Proportions of training and testing datasets; Slope engineering; Spatial resolution; Uncertainty analysis;

D O I：

10.13722/j.cnki.jrme.2020.1119

中图分类号：

学科分类号：

摘要：

It is of great significance to explore the influences of the spatial resolution and the proportion of model training and testing dataset on the uncertainties of landslide susceptibility prediction(LSP). Taking the landslides in Ningdu County of Jiangxi Province as examples, the frequency ratios of various environmental factors under different spatial resolutions(15, 30, 60, 90 and 120 m) are firstly calculated. Then, the landslide and non-landslide samples are divided into different model training and testing datasets with the proportions of 9/1, 8/2, 7/3, 6/4 and 5/5, and the model input and output variables under 25 combined conditions are obtained. Furthermore, these input and output variables are imported into the Support Vector Machine(SVM) and Random Forest(RF) models to carry out LSP. Finally, the uncertainties of LSP modeling under the 25 combined conditions are discussed using the accuracy assessment as well as the distribution characteristics of landslide susceptibility indexes. The results show that the landslide susceptibility accuracy predicted by the RF model under the spatial resolution of 15 m and training and testing dataset proportion of 9: 1 is the highest, and that the more important environmental factors under each condition are elevation, slope and topographic relief, etc. With decreasing the spatial resolution and/or the proportion of training and testing dataset, the LSP accuracies of both SVM and RF models decrease gradually, and the mean values of landslide susceptibility indexes increase with a decrease of the corresponding standard deviation value. For all combined conditions, as the spatial resolutions and the proportions of training and testing dataset decrease, the LSP accuracies decrease gradually while the corresponding uncertainties increase. It is also indicated that the LSP accuracy of the RF model is better than that of the SVM model under various combined conditions, and that the influence of the spatial resolution on the RF model is significantly greater than that of the proportion of training and testing dataset while there is little difference between the effects of the two factors on the SVM model. © 2021, Science Press. All right reserved.

引用

页码：1155 / 1169

页数：14

共 39 条

[11]

GAROSI Y, SHEKLABADI M, POURGHASEMI H R, Et al., Comparison of differences in resolution and sources of controlling factors for gully erosion susceptibility mapping, Geoderma, 330, pp. 65-78, (2018)

[12]

CAMA M, CONOSCENTI C, LOMBARDO L, Et al., Exploring relationships between grid cell size and accuracy for debris-flow susceptibility models: a test in the Giampilieri catchment(Sicily, Italy), Environmental Earth Sciences, 75, 3, pp. 1-21, (2016)

[13]

LUCA F, CONFORTI M, ROBUSTELLI G., Comparison of GIS-based gullying susceptibility mapping using bivariate and multivariate statistics: Northern Calabria, South Italy, Geomorphology, 134, 3-4, pp. 297-308, (2011)

[14]

LI Jun, ZHOU Chenghu, Appropriate grid size for terrain based landslide risk assessment in Lantau Island, Hong Kon, Journal of Remote Sensing, 7, 2, pp. 86-92, (2003)

[15]

FAN Linfeng, HU Ruilin, ZHOU Shunjiang, Et al., Sensitivity and error analysis of controlling factors due to variation of grid sizes in geohazard assessment, Journal of Engineering Geology, 20, 2, pp. 152-159, (2012)

[16]

ZHANG Qikai, LING Sixiang, LI Xiaoning, Et al., Comparison of landslide susceptibility mapping rapid assessment models in Jiuzhaigou County, Sichuan province, China, Chinese Journal of Rock Mechanics and Engineering, 39, 8, pp. 1595-1610, (2020)

[17]

HUANG F, CAO Z, GUO J, Et al., Comparisons of heuristic, general statistical and machine learning models for landslide susceptibility prediction and mapping, CATENA, 191, (2020)

[18]

REICHENBACH P, ROSSI M, MALAMUD B D, Et al., A review of statistically-based landslide susceptibility models, Earth-Science Reviews, 180, pp. 60-91, (2018)

[19]

HUANG Faming, YIN Kunlong, ZHANG Guirong, Et al., Landslide groundwater level time series prediction bases on phase space reconstruction and wavelet analysis-support vector machine optimized by pso algorithm, Earth Science-Journal of China University of Geosciences, 40, 7, pp. 1254-1265, (2015)

[20]

HUANG Faming, YIN Kunlong, JIANG Shuihua, Et al., Landslide susceptibility assessment based on clustering analysis and supportvector machine, Chinese Journal of Rock Mechanics and Engineering, 37, 1, pp. 156-167, (2018)

← 1 2 3 4 →