Comparison of general kernel, multiple kernel, infinite ensemble and semi-supervised support vector machines for landslide susceptibility prediction

Fang, Zhice; Wang, Yi; Duan, Hexiang; Niu, Ruiqing; Peng, Ling

doi:10.1007/s00477-022-02208-z

Cited by 21 publications

(5 citation statements)

References 80 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Model applicability. (1) The RF and RBFSVM models are well suited to DFS assessments which require high-dimensional data; in addition, related literature shows that they have higher accuracy in landslide, flood, and other disaster susceptibility assessments than other models ( Fang et al, 2022 ; Prasad et al, 2022 ). The linear SVM model cannot capture complex nonlinear relationships well and is prone to overfitting, thus not applicable to DFS assessment.…”

Section: Discussionmentioning

confidence: 99%

Machine learning approaches to debris flow susceptibility analyses in the Yunnan section of the Nujiang River Basin

Zhou,

Huang,

Sun

et al. 2024

PeerJ

View full text Add to dashboard Cite

Background The Yunnan section of the Nujiang River (YNR) Basin in the alpine-valley area is one of the most critical areas of debris flow in China. Methods We analyzed the applicability of three machine learning algorithms to model of susceptibility to debris flow—Random Forest (RF), the linear kernel support vector machine (Linear SVM), and the radial basis function support vector machine (RBFSVM)—and compared 20 factors to determine the dominant controlling in debris flow occurrence in the region. Results We found that (1) RF outperformed RBFSVM and Linear SVM in terms of accuracy, (2) topographic conditions were prerequisites, and geology, precipitation, vegetation, and anthropogenic influence were critical to forming debris flows. Also, the relative elevation difference was the most prominent evaluation factor of debris flow susceptibility, and (3) susceptibility maps based on RF’s debris flow susceptibility (DFS) showed that zones with very high susceptibility were distributed along the mainstream of the Nujiang River. These findings provide methodological guidance and reference for improvement of DFS assessment. It enriches the content of DFS studies in the alpine-valley areas.

show abstract

Section: Discussionmentioning

confidence: 99%

Machine learning approaches to debris flow susceptibility analyses in the Yunnan section of the Nujiang River Basin

Zhou,

Huang,

Sun

et al. 2024

PeerJ

View full text Add to dashboard Cite

show abstract

“…Defining sensitivity, or the true positive rate, as TPR = TP P ; and specificity, or the true negative rate, as TNR = TN N , the ROC curve then displays a quantitative relationship of sensitivity against the FN rate (FNR = 1 − TNR) at each threshold. Ideally, curves at the top have a lower FP rate ( FPR = 1 − TPR) [44]. When curves intersect, the area under curve (AUC) is calculated for evaluation:…”

Section: Evaluation Of Model Accuracymentioning

confidence: 99%

The Prediction of Cross-Regional Landslide Susceptibility Based on Pixel Transfer Learning

Wang,

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Considering the great time and labor consumption involved in conventional hazard assessment methods in compiling landslide inventory, the construction of a transferable landslide susceptibility prediction model is crucial. This study employs UAV images as data sources to interpret the typical alpine valley area of Beichuan County. Eight environmental factors including a digital elevation model (DEM) are extracted to establish a pixel-wise dataset, along with interpreted landslide data. Two landslide susceptibility models were built, each with a deep neural network (DNN) and a support vector machine (SVM) as the learner, and the DNN model was determined to have the best pre-training performance (accuracy = 88.6%, precision = 91.3%, recall = 94.8%, specificity = 87.8%, F1-score = 93.0%, and area under curve = 0.943), with higher parameters in comparison to the SVM model (accuracy = 77.1%, precision = 80.9%, recall = 87.8%, specificity = 73.9%, F1-score = 84.2%, and area under curve = 0.878). The susceptibility model of Beichuan County is then transferred to Mao County (which has no available dataset) to realize cross-regional landslide susceptibility prediction. The results suggest that the model predictions accomplish susceptibility zoning principles and that the DNN model can more precisely distinguish between high and very-high susceptibility areas in relation to the SVM model.

show abstract

“…SVM is able to transform the initial input space into a higher-dimension feature space and select the ideal separating hyperplane from the feature space during the modeling phase, thus separating landslide data from nonlandslide data [53,54]. SVM has shown good performance in many tasks, including landslide identification and detection, and is a representative machine learning model that is applicable when the dataset is small and the statistical distribution is unknown [6,55]. In addition to the innovative use of CNN models based on adaptive windows to identify potential landslide hazards, we also tested the effectiveness of CNN models using only 48 × 48, 32 × 32, 16 × 16, and 8 × 8 px fixed windows and SVM.…”

Section: Network Structure Of the Cnn Usedmentioning

confidence: 99%

Section: Network Structure Of the Cnn Usedmentioning

confidence: 99%

An Adaptive Identification Method for Potential Landslide Hazards Based on Multisource Data

Yin

Niu

Bai³

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

The effectiveness of landslide disaster prevention depends largely on the quality of early identification of potential hazards, and how to comprehensively, deeply, and accurately identify such hazards has become a major difficulty in landslide disaster management. Existing deep learning methods for potential landslide hazard identification often use fixed-size window modeling and ignore the different window sizes required by landslides of different scales. To address this problem, we propose an adaptive identification method for potential landslide hazards based on multisource data. Taking Yongping County, China, as the study area, we create a multisource factor dataset based on the landslide disaster background in terms of topography, geology, human activities, hydrology, and vegetation as the sample for the identification model after processing. Moreover, we combine differential interferometric synthetic aperture radar (D-InSAR) and multitemporal InSAR (MT-InSAR) to process the surface deformation of the study area, and we measure the deformation richness based on the average of the pixel deformation difference within the current window of a pixel point in the image. Therefore, convolutional neural networks (CNNs) with different window sizes are adaptively selected. The results show that the precision of adaptive identification of potential landslide hazards in the study area is 85.30%, the recall is 83.03%, and the F1 score is 84.15%. The recognition rate for potential hazards reaches 80%, which is better than the fixed-window modeling result and proves the effectiveness of the proposed method. This method can help to improve intelligent identification systems for potential landslide hazards, and also contribute to the identification of other potential geological hazards, such as mudslides and collapses.

show abstract

Comparison of general kernel, multiple kernel, infinite ensemble and semi-supervised support vector machines for landslide susceptibility prediction

Cited by 21 publications

References 80 publications

Machine learning approaches to debris flow susceptibility analyses in the Yunnan section of the Nujiang River Basin

Machine learning approaches to debris flow susceptibility analyses in the Yunnan section of the Nujiang River Basin

The Prediction of Cross-Regional Landslide Susceptibility Based on Pixel Transfer Learning

An Adaptive Identification Method for Potential Landslide Hazards Based on Multisource Data

Contact Info

Product

Resources

About