Landslide Susceptibility Prediction Considering Regional Soil Erosion Based on Machine-Learning Models

Huang, Faming; Chen, Jiawu; Du, Zhen; Yao, Chi; Huang, Jingsong; Jiang, Qinghui; Chang, Zhilu; Shu, Li

doi:10.3390/ijgi9060377

Cited by 48 publications

(16 citation statements)

References 75 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the past years, artificial intelligence, notably, machine learning techniques including deep learning have gained a momentum in geospatial big data processing. For example, data-driven algorithms such as support vector machines (SVMs), random forests (RFs), and artificial neural networks (ANNs) have been well applied in land cover mapping [ 7 ] and prediction of soil salinity [ 30 ] and ore mineralization [ 31 ] in geological fields, and shown superior performance to traditional approaches [ 32 , 33 , 34 , 35 , 36 ]. Comparing with other machine learning approaches, the RF algorithm has clear advantages, i.e., it does not require the data to be normalized and discretized, is less sensitive to outliers, and runs faster than SVMs [ 7 , 37 , 38 ].…”

Section: Introductionmentioning

confidence: 99%

Zonation of Landslide Susceptibility in Ruijin, Jiangxi, China

Zhou

Lin

et al. 2021

IJERPH

View full text Add to dashboard Cite

Landslides are one of the major geohazards threatening human society. The objective of this study was to conduct a landslide hazard susceptibility assessment for Ruijin, Jiangxi, China, and to provide technical support to the local government for implementing disaster reduction and prevention measures. Machine learning approaches, e.g., random forests (RFs) and support vector machines (SVMs) were employed and multiple geo-environmental factors such as land cover, NDVI, landform, rainfall, lithology, and proximity to faults, roads, and rivers, etc., were utilized to achieve our purposes. For categorical factors, three processing approaches were proposed: simple numerical labeling (SNL), weight assignment (WA)-based and frequency ratio (FR)-based. Then 19 geo-environmental factors were respectively converted into raster to constitute three 19-band datasets, i.e., DS1, DS2, and DS3 from three different processes. Then, 155 observed landslides that occurred in the past decades were vectorized, among which 70% were randomly selected to compose a training set (TS1) and the remaining 30% to form a validation set (VS1). A number of non-landslide (no-risk) samples distributed in the whole study area were identified in low slope (<1–3°) zones such as urban areas and croplands, and also added to the TS1 and VS1 in the same ratio. For comparison, we used the FR approach to identify the no-risk samples in both flat and non-flat areas, and merged them into the field-observed landslides to constitute another pair of training and validation sets (TS2 and VS2) using the same ratio of 7:3. The RF algorithm was applied to model the probability of the landslide occurrence using DS1, DS2, and DS3 as predictive variables and TS1 and TS2 for training to obtain the SNL-based, WA-based, and FR-based RF models, respectively. Verified against VS1 and VS2, the three models have similar overall accuracy (OA) and Kappa coefficient (KC), which are 89.61%, 91.47%, and 94.54%, and 0.7926, 0.8299, and 0.8908, respectively. All of them are much better than the three models obtained by SVM algorithm with OA of 81.79%, 82.86%, and 83%, and KC of 0.6337, 0.655, and 0.660. New case verification with the recent 26 landslide events of 2017–2020 revealed that the landslide susceptibility map from WA-based RF modeling was able to properly identify the high and very high susceptibility zones where 23 new landslides had occurred, and performed better than the SNL-based and FR-based RF modeling, though the latter has a slightly higher OA and KC. Hence, we concluded that all three RF models achieve reasonable risk prediction, but WA-based and FR-based RF modeling deserves a recommendation for application elsewhere. The results of this study may serve as reference for the local authorities in prevention and early warning of landslide hazards.

show abstract

Section: Introductionmentioning

confidence: 99%

Zonation of Landslide Susceptibility in Ruijin, Jiangxi, China

Zhou

Lin

et al. 2021

IJERPH

View full text Add to dashboard Cite

show abstract

“…3.3.3. C5.0 Decision Tree C5.0 uses the boosting method to improve the implementation efficiency and classification accuracy of the decision tree algorithm [71,72]. The C5.0 model can be constructed as four main steps [73]: (i) selecting the nodes of the optimal root segmentation tree using the training dataset and threshold with the highest gain ratio; (ii) finding the child nodes from two branch nodes produced by the tree structure; (iii) creating additional tree nodes that grow further with certain mathematical criteria, and in this process, children nodes that do not contribute to the model are eliminated; (iv) this process is continuous and repeated until all instances in the training dataset are assigned gain ratio values for leaf nodes or no remaining variables can be divided.…”

Section: Multiple Linear Regressionmentioning

confidence: 99%

Uncertainties Analysis of Collapse Susceptibility Prediction Based on Remote Sensing and GIS: Influences of Different Data-Based Models and Connections between Collapses and Environmental Factors

Fan

Huang

et al. 2020

Remote Sensing

Self Cite

View full text Add to dashboard Cite

To study the uncertainties of a collapse susceptibility prediction (CSP) under the coupled conditions of different data-based models and different connection methods between collapses and environmental factors, An’yuan County in China with 108 collapses is used as the study case, and 11 environmental factors are acquired by data analysis of Landsat TM 8 and high-resolution aerial images, using a hydrological and topographical spatial analysis of Digital Elevation Modeling in ArcGIS 10.2 software. Accordingly, 20 coupled conditions are proposed for CSP with five different connection methods (Probability Statistics (PSs), Frequency Ratio (FR), Information Value (IV), Index of Entropy (IOE) and Weight of Evidence (WOE)) and four data-based models (Analytic Hierarchy Process (AHP), Multiple Linear Regression (MLR), C5.0 Decision Tree (C5.0 DT) and Random Forest (RF)). Finally, the CSP uncertainties are assessed using the area under receiver operation curve (AUC), mean value, standard deviation and significance test, respectively. Results show that: (1) the WOE-based models have the highest AUC accuracy, lowest mean values and average rank, and a relatively large standard deviation; the mean values and average rank of all the FR-, IV- and IOE-based models are relatively large with low standard deviations; meanwhile, the AUC accuracies of FR-, IV- and IOE-based models are consistent but higher than those of the PS-based model. Hence, the WOE exhibits a greater spatial correlation performance than the other four methods. (2) Among all the data-based models, the RF model has the highest AUC accuracy, lowest mean value and mean rank, and a relatively large standard deviation. The CSP performance of the RF model is followed by the C5.0 DT, MLR and AHP models, respectively. (3) Under the coupled conditions, the WOE-RF model has the highest AUC accuracy, a relatively low mean value and average rank, and a high standard deviation. The PS-AHP model is opposite to the WOE-RF model. (4) In addition, the coupled models show slightly better CSP performances than those of the single data-based models not considering connect methods. The CSP performance of the other models falls somewhere in between. It is concluded that the WOE-RF is the most appropriate coupled condition for CSP than the other models.

show abstract

“…All the ten terrain factors are respectively divided into five classes using the natural breakpoint method [31][32][33]. This is because the natural breakpoint method can effectively identify the frequency distribution characteristics of terrain factors to obtain the best class division scheme, and it has been successfully used in the research of the class divisions by many other scholars [34][35][36][37]. The purpose of class division is to better represent the distribution rules of these terrain factors (Figure 2).…”

Section: Description Of Terrain Factorsmentioning

confidence: 99%

“…The elevation [36,38] of the study area ranges from 2 to 2147 m. The mountains with high elevation mainly distribute around the Jiangxi province, while the central area of Jiangxi province has relatively low elevation. Generally speaking, the higher the elevation in the southern hilly area, the greater the terrain complexity (Figure 2a).…”

Section: ) Elevationmentioning

confidence: 99%

Regional Terrain Complexity Assessment Based on Principal Component Analysis and Geographic Information System: A Case of Jiangxi Province, China

Huang

Yang

Zhang

et al. 2020

IJGI

Self Cite

View full text Add to dashboard Cite

Regional terrain complexity assessment (TCA) is an important theoretical foundation for geological feature identification, hydrological information extraction and land resources utilization. However, the previous TCA models have many disadvantages; for example, comprehensive consideration and redundancy information analysis of terrain factors is lacking, and the terrain complexity index is difficult to quantify. To overcome these drawbacks, a TCA model based on principal component analysis (PCA) and a geographic information system (GIS) is proposed. Taking Jiangxi province of China as an example, firstly, ten terrain factors are extracted using a digital elevation model (DEM) in GIS software. Secondly, PCA is used to analyze the information redundancy of these terrain factors and deal with data compression. Then, the comprehensive evaluation of the compressed terrain factors is conducted to obtain quantitative terrain complexity indexes and a terrain complexity map (TCM). Finally, the TCM produced by the PCA method is compared with those produced by the slope-only, the variation coefficient and K-means clustering models based on the topographic map drawn by the Bureau of Land and Resources of Jiangxi province. Meanwhile, the TCM is also verified by the actual three-dimensional aerial images. Results show that the correlation coefficients between the TCMs produced by the PCA, slope-only, variable coefficient and K-means clustering models and the local topographic map are 0.894, 0.763, 0.816 and 0.788, respectively. It is concluded that the TCM of the PCA method matches well with the actual field terrain features, and the PCA method can reflect the regional terrain complexity characteristics more comprehensively and accurately when compared to the other three methods.

show abstract

Landslide Susceptibility Prediction Considering Regional Soil Erosion Based on Machine-Learning Models

Cited by 48 publications

References 75 publications

Zonation of Landslide Susceptibility in Ruijin, Jiangxi, China

Zonation of Landslide Susceptibility in Ruijin, Jiangxi, China

Uncertainties Analysis of Collapse Susceptibility Prediction Based on Remote Sensing and GIS: Influences of Different Data-Based Models and Connections between Collapses and Environmental Factors

Regional Terrain Complexity Assessment Based on Principal Component Analysis and Geographic Information System: A Case of Jiangxi Province, China

Contact Info

Product

Resources

About