Performance Evaluation of Five GIS-Based Models for Landslide Susceptibility Prediction and Mapping: A Case Study of Kaiyang County, China

Qin, Yigen; Yang, Guosheng; Lu, Kunpeng; Sun, Qianzheng; Jin, Xu; Wu, Yunwu

doi:10.3390/su13116441

Cited by 22 publications

(9 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As above mentioned, the reasonable processing, e.g., discrete processing of the continuous geo-environmental factors, together with WoE can improve the performance of ML models 10 , 21 , 38 . In this research, the OA and KC of all the coupled models are better than those of single models, which reflects the usefulness of such preprocessing prior to ML modeling.…”

Section: Discussionmentioning

confidence: 99%

“…Statistical analysis and machine learning (ML) modeling are two major data-driven approaches. The calculation process of the statistical models such as frequency ratio (FR), certainty coefficient (CF), information value (IV) and weight of evidence (WoE) is simple; and qualitative or categorical factors can be converted into quantitative weights by these approaches, and thence, they are widely employed for landslide risk assessment 15 , 21 – 23 . However, the statistical models are sensitive to the nonlinear phenomena which require specific algorithms to sort them out 23 , 24 .…”

Section: Introductionmentioning

confidence: 99%

“…It has been decades since hybrid models were proposed for landslide risk assessment. Hybrid models are in fact constructed by integrating two or more models in aspect of sample selection 28 , 37 , feature selection 21 , 38 , information extraction and finally landslide hazard prediction with reasonable accuracy 10 , 22 , 25 , 39 – 41 . Hence, hybrid modeling has gained recently a momentum in improving the accuracy and reliability of landslide risk mapping 26 , 36 , 40 , 42 , 43 .…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Geoinformation-based landslide susceptibility mapping in subtropical area

Zhou

Qin

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Mapping susceptibility of landslide disaster is essential in subtropical area, where abundant rainfall may trigger landslide and mudflow, causing damages to human society. The purpose of this paper is to propose an integrated methodology to achieve such a mapping work with improved prediction results using hybrid modeling taking Chongren, Jiangxi as an example. The methodology is composed of the optimal discretization of the continuous geo-environmental factors based on entropy, weight of evidence (WoE) calculation and application of the known machine learning (ML) models, e.g., Random Forest (RF), Support Vector Machine (SVM) and Logistic Regression (LR). The results show the effectiveness of the proposed hybrid modeling for landslide hazard mapping in which the prediction accuracy vs the validation set reach 82.35–91.02% with an AUC [area under the receiver operating characteristic (ROC) curve] of 0.912–0.970. The RF algorithm performs best among the observed three ML algorithms and WoE-based RF modeling will be recommended for the similar landslide risk prediction elsewhere. We believe that our research can provide an operational reference for predicting the landslide hazard in the subtropical area and serve for disaster reduction and prevention action of the local governments.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Geoinformation-based landslide susceptibility mapping in subtropical area

Zhou

Qin

et al. 2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Shen Huaifei et al, meanwhile, selected Gansu Province as the study zone, an area where landslide disasters occur frequently in China, and used the IV and AHP to comprehensively assess landslides that had occurred in the study region, adding experience for the prevention and control of landslide disasters locally [12]. Elsewhere, Qin Yigen et al used five evaluation models-CF, AHP, LR, CF-AHP and CF-LR-to produce a landslide susceptibility map for Kaiyang County, China, with the results indicating that the CF-LR model was better than the others [13]. There are many kinds of landslide disasters, and while a lot of the research has focused on earthquake landslides, so far, there is very little research on highway landslide disasters.…”

Section: Introductionmentioning

confidence: 99%

A Landslide Susceptibility Evaluation of Highway Disasters Based on the Frequency Ratio Coupling Model

Fan

Hu³

et al. 2022

Sustainability

View full text Add to dashboard Cite

A landslide disaster, especially a highway landslide, may greatly impact the transport capacity of nearby roads. Keeping highways open, in particular, is crucial for supporting the functioning of the economy, society and people. Therefore, evaluating the highway landslide susceptibility is particularly important. In this paper, the city of Laibin, in the Guangxi Zhuang Autonomous Region of China, was taken as the study zone. According to data on 641 highway landslide disaster points measured in the field and a basic evaluation of the study area, nine evaluation factors—the elevation, slope, aspect, height difference, plan curve, profile curve, precipitation, Topographic Wetness Index (TWI) and vegetation coverage—were selected. We coupled a Frequency Ratio (FR) model, Analytic Hierarchy Process (AHP), Logistic Regression (LR), Back Propagation Neural Network (BPNN) and Support Vector Machine (SVM) to evaluate the susceptibility to highway landslides, with a Receiver Operating Characteristic (ROC) curve used to analyze the precision of these models. The ROC curve showed that the accuracy of the five models was greater than 0.700 and thus had a certain reliability. Among them, the FR-LR model had the highest accuracy, at 0.804. The study protocol presented here can therefore provide a reference for evaluation studies on landslide susceptibility in other areas.

show abstract

“…The solution speed of the model is relatively fast, and the application is convenient. The model may take any value and has a high application value in practice(Qin et al 2021;Pradhan and Lee 2010). The logistic regression function is expressed as:…”

mentioning

confidence: 99%

Susceptibility evaluation of highway landslide disaster s based on SBAS-InSAR: A case study of S211 Highway in Lanping County

Liu

et al. 2022

Preprint

View full text Add to dashboard Cite

Evaluation of landslide susceptibility along highways is critical for risk management in engineering development, construction, and operation and maintenance. The research target is the S211 Highway in Lanping County, Nujiang Prefecture, Yunnan Province, with its buffer zone extending 10 km as the research area. Eight evaluation factors are selected for the study, including slope, slope aspect, vegetation coverage, distance from the water system, rock group, rainfall, distance from the fault, and elevation. The findings of the susceptibility evaluation were classified into five categories, and the susceptibility grades of landslide disasters in the study area were evaluated using the information value and logistic regression coupling model. The accuracy of the coupling model was evaluated by the ROC curve and AUC value. The deformation rate in the study area was estimated by processing 28 Sentinel-1A satellite images captured from January to December 2019 using the SBAS-InSAR technology and was used to optimize the landslide susceptibility grade. The results show that the extremely high and high-risk areas of the information value-logistic regression coupling model account for 28.33% of the total area of the study area, which constitutes nearly 83.82% of the historical landslide disaster sites, mainly occupying areas along highways with low vegetation coverage and within 2000 m from rivers. The AUC values in the accuracy verification reach 0.843, indicating that the evaluation model can accurately predict the landslide susceptibility. The vulnerability grade of landslide geological disaster in the entire evaluation unit is significantly increased by optimizing the result of the surface deformation obtained by SBAS-InSAR technology. A total of 79587 grid units were added to the area, resulting in an extremely high vulnerability grade. This technique may optimize the evaluation results of landslide hazard susceptibility and provide decision support for disaster prevention and maintenance along highways.

show abstract

Performance Evaluation of Five GIS-Based Models for Landslide Susceptibility Prediction and Mapping: A Case Study of Kaiyang County, China

Cited by 22 publications

References 78 publications

Geoinformation-based landslide susceptibility mapping in subtropical area

Geoinformation-based landslide susceptibility mapping in subtropical area

A Landslide Susceptibility Evaluation of Highway Disasters Based on the Frequency Ratio Coupling Model

Susceptibility evaluation of highway landslide disaster s based on SBAS-InSAR: A case study of S211 Highway in Lanping County

Contact Info

Product

Resources

About