scholarly journals Rainfall-induced landslide susceptibility assessment using random forest weight at basin scale

2017 ◽  
Vol 49 (5) ◽  
pp. 1363-1378 ◽  
Author(s):  
Chengguang Lai ◽  
Xiaohong Chen ◽  
Zhaoli Wang ◽  
Chong-Yu Xu ◽  
Bing Yang
Keyword(s):  
Random Forest ◽  
Landslide Susceptibility ◽  
Slope Angle ◽  
Fuzzy Comprehensive Evaluation ◽  
Assessment Model ◽  
Assessment Procedure ◽  
Susceptibility Assessment ◽  
Entropy Weight ◽  
Landslide Susceptibility Assessment ◽  
Basin Scale

Abstract Rainfall-induced landslide susceptibility assessment is currently considered an effective tool for landslide hazard assessment as well as for appropriate warning and forecasting. As part of the assessment procedure, a credible index weight matrix can strongly increase the rationality of the assessment result. This study proposed a novel weight-determining method by using random forests (RFs) to find a suitable weight. Random forest weights (RFWs) and eight indexes were used to construct an assessment model of the Dongjiang River basin based on fuzzy comprehensive evaluation. The results show that RF identified the elevation (EL) and slope angle (SL) as the two most important indexes, and soil erodibility factor (SEF) and shear resistance capacity (SRC) as the two least important indexes. The assessment accuracy of RFW can be as high as 79.71%, which is higher than the entropy weight (EW) of 63.77%. Two experiments were conducted by respectively removing the most dominant and the weakest indexes to examine the rationality and feasibility of RFW; both precision validation and contrastive analysis indicated the assessment results of RFW to be reasonable and satisfactory. The initial application of RF for weight determination shows significant potential and the use of RFW is therefore recommended.

scholarly journals GIS-Based Random Forest Weight for Rainfall-Induced Landslide Susceptibility Assessment at a Humid Region in Southern China

Water ◽  
2018 ◽  
Vol 10 (8) ◽  
pp. 1019 ◽  
Author(s):  
Peng Wang ◽  
Xiaoyan Bai ◽  
Xiaoqing Wu ◽  
Haijun Yu ◽  
Yanru Hao ◽  
...  
Keyword(s):  
Random Forest ◽  
Landslide Susceptibility ◽  
Vegetation Index ◽  
Southern China ◽  
Error Rates ◽  
Assessment Model ◽  
Average Error ◽  
Assessment Procedure ◽  
Susceptibility Assessment ◽  
Landslide Susceptibility Assessment

Landslide susceptibility assessment is presently considered an effective tool for landslide warning and forecasting. Under the assessment procedure, a credible index weight can greatly increase the rationality of the assessment result. Using the Beijiang River Basin, China, as a case study, this paper proposes a new weight-determining method based on random forest (RF) and used the weighted linear combination (WLC) to evaluate the landslide susceptibility. The RF weight and eight indices were used to construct the assessment model. As a comparison, the entropy weight (EW) and weight determined by analytic hierarchy process (AHP) were also used, respectively, to demonstrate the rationality of the proposed weight-determining method. The results show that: (1) the average error rates of training and testing based on RF are 18.12% and 15.83%, respectively, suggesting that the RF model can be considered rational and credible; (2) RF ranks the indices elevation (EL), slope (SL), maximum one-day precipitation (M1DP) and distance to fault (DF) as the Top 4 most important of the eight indices, occupying 73.24% of the total, while the indices runoff coefficient (RC), normalized difference vegetation index (NDVI), shear resistance capacity (SRC) and available water capacity (AWC) are less consequential, with an index importance degree of only 26.76% of the total; and (3) the verification of landslide susceptibility indicates that the accuracy rate based on the RF weight reaches 75.41% but are only 59.02% and 72.13% for the other two weights (EW and AHP), respectively. This paper shows the potential to provide a new weight-determining method for landslide susceptibility assessment. Evaluation results are expected to provide a reference for landslide management, prevention and reduction in the studied basin.

scholarly journals Seismic Landslide Susceptibility Assessment Using Principal Component Analysis And Support Vector Machine

2021 ◽  
Author(s):  
Ziyao Xu ◽  
Ailan Che ◽  
Yanbo Cao ◽  
Fanghao Zhang
Keyword(s):  
Landslide Susceptibility ◽  
Principal Component ◽  
Assessment Model ◽  
Support Vector ◽  
Susceptibility Assessment ◽  
Risk Class ◽  
Conditioning Factors ◽  
Landslide Susceptibility Assessment ◽  
Susceptibility Model ◽  
Seismic Landslide

Abstract Seismic landslides are dangerous natural hazards, causing immense damage in terms of human lives and property. Susceptibility assessment of earthquake triggered landslide is the scientific premise and theoretical basis of disaster emergency management of engineering. The aim of this study is to applied the seismic landslide susceptibility model to Dayong Expressway in Chenghai area prone to frequent earthquakes. Support vector machine is used to establish the assessment model based on the data of 716 landslides caused by Ludian Ms6.5 earthquake in 2014. To improve the universality of the assessment model in different regions. Principal component analysis (PCA) is used for reducing the dimension of landslide conditioning factors and weaking difference of the regional characteristics between historical earthquake regions with Dayong expressway area. To applied the SVM model for seismic landslide susceptibility in Dayong Expressway region where the conditioning factors information is similar to Ludian area. Gutenberg-Richter model and Dieterich model are used to assume an earthquake in Chenghai area for landslide susceptibility assessment. Inverse distance weight (IDW) method is used for assessing the landslide risk class of Dayong Expressway. The results show that the “Very high” landslide susceptibility class account for 0.63% of Chenghai area. The seismic landslide has the most obvious impact on the middle 13 km section of Dayong expressway and this section account for 8.9% is defined as high-risk class. The study verifies the practicability of the seismic landslide susceptibility model based on machine learning and provides constructive reference for the susceptibility assessment of engineering facilities under earthquake.

Application of Fuzzy Weights of Evidence Method in Landslide Susceptibility Assessment Based on GIS

2013 ◽  
Vol 864-867 ◽  
pp. 2756-2759
Author(s):  
Zhi Wang Wang ◽  
Jian Hua Zhang ◽  
Duan You Li
Keyword(s):  
Landslide Susceptibility ◽  
Research Result ◽  
Slope Angle ◽  
Weights Of Evidence ◽  
Slope Aspect ◽  
Susceptibility Assessment ◽  
Gis Technology ◽  
Landslide Susceptibility Assessment ◽  
Rs And Gis ◽  
Fuzzy Weights

This paper deals with landslide hazards susceptibility assessment in the study area from Zigui to Badong counties in TGP reservoir region using RS and GIS technology. The causative factors including lithology, distance to faults, elevation, slope aspect, slope angle, drainage network, distance to river and distribution of plant are derived from geological map, Digital Elevation Model (DEM) and Spot imagery data using RS and GIS technology. The paper analyzes landslide susceptibility assessment using fuzzy weights of evidence method, which could combine knowledge-based fuzzy membership values with data-based conditional probabilities to improve the accuracy of landslide susceptibility assessment. The research result is very coincident with the occurrence of the known landslides in the study area.

scholarly journals Scale and spatial distribution assessment of rainfall-induced landslides in a catchment with mountain roads

2018 ◽  
Vol 18 (2) ◽  
pp. 687-708 ◽  
Author(s):  
Chih-Ming Tseng ◽  
Yie-Ruey Chen ◽  
Szu-Mi Wu
Keyword(s):  
Landslide Susceptibility ◽  
Satellite Images ◽  
Evaluation Method ◽  
Image Interpretation ◽  
Assessment Model ◽  
Hazard Evaluation ◽  
Susceptibility Assessment ◽  
Landslide Susceptibility Assessment ◽  
Before And After ◽  
Surface Changes

Abstract. This study focused on landslides in a catchment with mountain roads that were caused by Nanmadol (2011) and Kong-rey (2013) typhoons. Image interpretation techniques were employed to for satellite images captured before and after the typhoons to derive the surface changes. A multivariate hazard evaluation method was adopted to establish a landslide susceptibility assessment model. The evaluation of landslide locations and relationship between landslide and predisposing factors is preparatory for assessing and mapping landslide susceptibility. The results can serve as a reference for preventing and mitigating slope disasters on mountain roads.

scholarly journals Evaluating the Effects of Digital Elevation Models in Landslide Susceptibility Mapping in Rangamati District, Bangladesh

2020 ◽  
Vol 12 (17) ◽  
pp. 2718 ◽  
Author(s):  
Yasin Wahid Rabby ◽  
Asif Ishtiaque ◽  
Md. Shahinoor Rahman
Keyword(s):  
Random Forest ◽  
Landslide Susceptibility ◽  
Digital Elevation Models ◽  
Susceptibility Mapping ◽  
Landslide Susceptibility Mapping ◽  
Susceptibility Assessment ◽  
Alos Palsar ◽  
Bivariate Model ◽  
Landslide Susceptibility Assessment ◽  
Digital Elevation

Digital elevation models (DEMs) are the most obvious data sources in landslide susceptibility assessment. Many landslide casual factors are often generated from DEMs. Most studies on landslide susceptibility assessments rely on freely available DEMs. However, very little is known about the performance of different DEMs with varying spatial resolutions on the accurate assessment of landslide susceptibility. This study compared the performance of four different DEMs including 30 m Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) Global Digital Elevation Model (GDEM), 30–90 m Shuttle Radar Topographic Mission (SRTM), 12.5 m Advanced Land Observation Satellite (ALOS) Phased Array Type L band Synthetic Aperture Radar (PALSAR), and 25 m Survey of Bangladesh (SOB) DEM in landslide susceptibility assessment in the Rangamati district in Bangladesh. This study used three different landslide susceptibility assessment techniques: modified frequency ratio (bivariate model), logistic regression (multivariate model), and random forest (machine-learning model). This study explored two scenarios of landslide susceptibility assessment: using only DEM-derived causal factors and using both DEM-derived factors as well as other common factors. The success and prediction rate curves indicate that the SRTM DEM provides the highest accuracies for the bivariate model in both scenarios. Results also reveal that the ALOS PALSAR DEM shows the best performance in landslide susceptibility mapping using the logistics regression and the random forest models. A relatively finer resolution DEM, the SOB DEM, shows the lowest accuracies compared to other DEMs for all models and scenarios. It can also be noted that the performance of all DEMs except the SOB DEM is close (72%–84%) considering the success and prediction accuracies. Therefore, anyone of the three global DEMs: ASTER, SRTM, and ALOS PALSAR can be used for landslide susceptibility mapping in the study area.

scholarly journals LANDSLIDE SUSCEPTIBILITY ASSESSMENT OF KOKAP AREA USING MULTIPLE LOGISTIC REGRESSION

2015 ◽  
Vol 6 (2) ◽  
Author(s):  
Somyot Makealoun ◽  
Doni Prakasa Eka Putra ◽  
Wahyu Wilopo
Keyword(s):  
Logistic Regression ◽  
Landslide Susceptibility ◽  
Slope Angle ◽  
Research Area ◽  
Multiple Logistic Regression ◽  
Susceptibility Assessment ◽  
Geologic Structure ◽  
Landslide Susceptibility Assessment ◽  
Total Study Area ◽  
Very High

A number of landslides have occured in Kokap SubDistrict, Kulon Progo Regency, Yogyakarta Special Province, Indonesia, which have influenced the communities. The natural disaster is commonly associated with a few days of heavy rainfall events. To mitigate the impact of landslides in this area, a landslide susceptibility assessment needs to be carried out. The main objective of this research is to develop a landslide susceptibility zonation in the research area by applying a logistic regression (LR) method. Field observation was conducted at 68 locations in the research area, in which 46 landslides occured. Data of slope angle, lithology, geologic structure and groundwater conditions were collected. The relationship between landslide occurrence and the slope angle, lithology, geologic structure and groundwater conditions was analysed using the LR method. The analysis results showed a 0.984 standard error, implying a good-fit model. The study area was classified into very low, low, moderate, high and very high landslide susceptibility zones with 0–20%, 20–40%, 40–60%, 60–80%, and 80–100%, respectively, probabilities of occurrence. A 60% area of the total study area was classified as a moderate to very high susceptibility to landslide. From 47 landslides, 80% landslides occured in high and very high landslide susceptibility zones, 17% landslides occured in the moderate susceptibility zone and 2% landslides occured in the low susceptible zone. None of landslides occured in the very low landslide susceptibility zone. The analysis results show that LR method is a very useful method for landslide prediction. Keywords: landslide susceptibility, multiple logistic regression, Kokap Kulon Progo-Indonesia

Sign in / Sign up

Export Citation Format

Share Document