Landslide susceptibility mapping by attentional factorization machines considering feature interactions

Liu, Leilei; Yang, Can; Huang, Faming; Wang, Xiaomi

doi:10.1080/19475705.2021.1950217

Cited by 20 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researchers typically select factors with reference to the literature and expert knowledge. In this study, nine factors, i.e., elevation, slope, plan curvature, valley depth, topographic wetness index (TWI), land cover, rainfall, distance to rivers, and distance to roads (Figure 4), were selected based on a literature review to be used in landslide susceptibility mapping [78][79][80]. Elevation.…”

Section: Factors Influencing Landslide Susceptibilitymentioning

confidence: 99%

Mapping Post-Earthquake Landslide Susceptibility Using U-Net, VGG-16, VGG-19, and Metaheuristic Algorithms

Shafapourtehrany,

Rezaie,

Jun

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Landslides are among the most frequent secondary disasters caused by earthquakes in areas prone to seismic activity. Given the necessity of assessing the current seismic conditions for ensuring the safety of life and infrastructure, there is a rising demand worldwide to recognize the extent of landslides and map their susceptibility. This study involved two stages: First, the regions prone to earthquake-induced landslides were detected, and the data were used to train deep learning (DL) models and generate landslide susceptibility maps. The application of DL models was expected to improve the outcomes in both stages. Landslide inventory was extracted from Sentinel-2 data by using U-Net, VGG-16, and VGG-19 algorithms. Because VGG-16 produced the most accurate inventory locations, the corresponding results were used in the landslide susceptibility detection stage. In the second stage, landslide susceptibility maps were generated. From the total measured landslide locations (63,360 cells), 70% of the locations were used for training the DL models (i.e., convolutional neural network [CNN], CNN-imperialist competitive algorithm, and CNN-gray wolf optimizer [GWO]), and the remaining 30% were used for validation. The earthquake-induced landslide conditioning factors included the elevation, slope, plan curvature, valley depth, topographic wetness index, land cover, rainfall, distance to rivers, and distance to roads. The reliability of the generated susceptibility maps was evaluated using the area under the receiver operating characteristic curve (AUROC) and root mean square error (RMSE). The CNN-GWO model (AUROC = 0.84 and RMSE = 0.284) outperformed the other methods and can thus be used in similar applications. The results demonstrated the efficiency of applying DL in the natural hazard domain. The CNN-GWO predicted that approximately 38% of the total area consisted of high and very high susceptibility regions, mainly concentrated in areas with steep slopes and high levels of rainfall and soil wetness. These outcomes contribute to an enhanced understanding of DL application in the natural hazard domain. Moreover, using the knowledge of areas highly susceptible to landslides, officials can actively adopt steps to reduce the potential impact of landslides and ensure the sustainable management of natural resources.

show abstract

Section: Factors Influencing Landslide Susceptibilitymentioning

confidence: 99%

Mapping Post-Earthquake Landslide Susceptibility Using U-Net, VGG-16, VGG-19, and Metaheuristic Algorithms

Shafapourtehrany,

Rezaie,

Jun

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…3) The FR values of these environmental factors are taken as the input variables of the C5.0 DT/SVM models, the output variables are landslide and non-landslide (marked as 1 and 0, respectively). The mathematical relationship between input variables and output variables is established (Liu et al, 2021). 4) The input-output variables are randomly divided by 70 and 30% as training dataset and test dataset, respectively.…”

Section: Research Frameworkmentioning

confidence: 99%

Landslide Susceptibility Prediction Based on Frequency Ratio Method and C5.0 Decision Tree Model

et al. 2022

View full text Add to dashboard Cite

This paper aims to propose an efficient landslide susceptibility prediction (LSP) model based on the frequency ratio method and C5.0 Decision Tree (C5.0 DT) model. Taking Ruijin City as the study area, local landslide inventory and 12 environmental factors are collected. Then the nonlinear correlations between landslide inventory and environmental factors are established by frequency ratio (FR) method. Thirdly, the FR values of these environmental factors are taken as the input variables of the C5.0 DT/SVM models; landslide samples and non-landslide samples are set as the output variables with values of 1 and 0, respectively. The mathematical relationship between input variables and output variables is established by C5.0 DT/SVM models. Finally, the performance of LSP of both models is evaluated by the Area Under Receiver Operation Characteristic Curve (AUC). Results show that: 1) The landslide susceptibility mapping (LSM) of the C5.0 DT and the SVM models are similar on the whole, high and very high susceptibility levels are mainly distributed in the north and in the edge of the study area. 2) The AUC values of C5.0 DT and SVM are 0.886 and 0.819, respectively. Both models have good LSP accuracy, however, the overall LSP accuracy of the C5.0 DT model is better than that of SVM. 3) It is significant and reliable to carry out LSP based on frequency ratio method and C5.0 DT model.

show abstract

Landslide susceptibility mapping in Three Gorges Reservoir area based on GIS and boosting decision tree model

Miao

Zhao

et al. 2023

Stoch Environ Res Risk Assess

View full text Add to dashboard Cite

Recognized as one of the most destructive geological disasters, a myriad of landslides has revived and developed in the Three Gorges Reservoir area under the combined action of various detrimental factors, becoming a nightmare for the residents over vicinity. Therefore, the pertinently regional landslide susceptibility mapping (LSM) is of great significance for disaster prevention and mitigation. In this study, LSM was prepared by using a boosting-C5.0 decision tree model. Under the landslide verification of on-site investigations, the study area was divided into accumulation and rock areas, and a total of 12 impact factors including triggering factors and causing factors were skillfully selected as model inputs to felicitously explore spatial characteristics related to the landslide. TOL and VIF were employed to determine the multicollinearity among the impact factors. The independent training (80%) and validation (20%) datasets were constructed by random sampling for LSM. ANN, C5.0, and SVM were selected for comparative analysis. In addition, uncertainty analysis was appositely performed for boosting-C5.0 model. The results show that there is no rigorous multicollinearity among the impact factors proposed in this paper. The landslide susceptibility in the study area is divided into low, moderate, high, and very high. The highest susceptibility area distributes along the riverside and farmland where the landslide ratio is 37.05% in boosting-C5.0 model. Then the ROCs were expropriated to infer the accuracy of each model. The boosting-C5.0 performed the best with the largest area under the curve (AUC) in both accumulation and rock areas, reaching at 0.991 and 0.990 in the validation sets, respectively. Finally, the composite modification of the 5 validation sets shows that the uncertainty of boosting-C5.0 is concentrated in the intermediate probability areas of susceptibility. This research reveals that the machine learning model can be used to evaluate the susceptibility of regional landslides, which could provide a basis for the risk management and control of geological disasters.

show abstract

Landslide susceptibility mapping by attentional factorization machines considering feature interactions

Cited by 20 publications

References 38 publications

Mapping Post-Earthquake Landslide Susceptibility Using U-Net, VGG-16, VGG-19, and Metaheuristic Algorithms

Mapping Post-Earthquake Landslide Susceptibility Using U-Net, VGG-16, VGG-19, and Metaheuristic Algorithms

Landslide Susceptibility Prediction Based on Frequency Ratio Method and C5.0 Decision Tree Model

Landslide susceptibility mapping in Three Gorges Reservoir area based on GIS and boosting decision tree model

Contact Info

Product

Resources

About