Refined landslide susceptibility analysis based on InSAR technology and UAV multi-source data

Cao, Chen; Zhu, Kuanxing; Xu, Peng; Yang, Guang; Song, Shengyuan

doi:10.1016/j.jclepro.2022.133146

Cited by 31 publications

(15 citation statements)

References 83 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the evaluation of landslide susceptibility, the correct identification of landslide disaster-causing factors is the first step. According to the results of field surveys of landslide geological disasters in Muli County, combined with previous research results, we selected 10 factors, including elevation, slope, aspect, stratigraphic lithology, distance from the road, distance from the river, distance from the fault, land use cover type, normalized vegetation index, and average annual precipitation [27][28][29].…”

Section: Data Selection Basismentioning

confidence: 99%

See 1 more Smart Citation

Analysis of Geological Hazard Susceptibility of Landslides in Muli County Based on Random Forest Algorithm

Song

Chen

et al. 2023

Sustainability

View full text Add to dashboard Cite

Landslides seriously threaten human life and property. The rapid and accurate prediction of landslide geological hazard susceptibility is the key to disaster prevention and mitigation. Traditional landslide susceptibility evaluation methods have disadvantages in terms of factor classification and subjective weight determination. Based on this, this paper uses a random forest model built using Python language to predict the landslide susceptibility of Muli County in western Sichuan and outputs the factor weight and model accuracy. The results show that (1) the three most important factors are elevation, distance from the road, and average annual rainfall, and the sum of their weights is 67.54%; (2) the model’s performance is good, with ACC = 99.43%, precision = 99.3%, recall = 99.48%, and F1 = 99.39%; (3) the landslide development and susceptibility zoning factors are basically the same. Therefore, this model can effectively and accurately evaluate regional landslide susceptibility. However, there are some limitations: (1) the landslide information statistical table is incomplete; (2) there are demanding requirements in terms of training concentration relating to the definition of landslide and non-landslide point sets, and the landslide range should be accurately delineated according to field surveys.

show abstract

Section: Data Selection Basismentioning

confidence: 99%

“…There are two reasons for identifying distance from a fault as a key factor in analyzing landslide susceptibility [28]. One is that earthquakes usually develop on a fault, and when an earthquake occurs, its force will cause the slope to become less stable [45].…”

Section: (7) Distance From Faultmentioning

confidence: 99%

Analysis of Geological Hazard Susceptibility of Landslides in Muli County Based on Random Forest Algorithm

Song

Chen

et al. 2023

Sustainability

View full text Add to dashboard Cite

show abstract

“…Some scholars have integrated InSAR technology with landslide susceptibility evaluation results, all of which use InSAR deformation as a covariate or as a dynamic verification means to complete landslide susceptibility evaluations [22][23][24][25], and they have achieved good application results. However, the above methods rely on the availability of landslide remote sensing interpretation conditions after the earthquake as well as mastery of a complete landslide inventory, which obviously does not meet the requirements of the first-time landslide disaster emergency assessment after the earthquake.…”

Section: Insar Data-newmark Physical Fusion Driver Modelmentioning

confidence: 99%

“…The results of the InSAR deformation and the Newmark physical model have a direct influence on the final results of the IDNPM. Referring to the results of previous studies [22,23], and considering the limitations of the InSAR method and the importance of geological conditions on landslide development [26], an empirical weight value of 0.39 was taken in this study and combined with Equation (6) to form the final post-earthquake rapid emergency response assessment results of landslides. Figure 1 shows the flow chart of this model's construction.…”

Section: Insar Data-newmark Physical Fusion Driver Modelmentioning

confidence: 99%

Rapid Emergency Response Assessment of Earthquake-Induced Landslides Driven by Fusion of InSAR Deformation Data and Newmark Physical Models

Zeng,

Zhang,

Liu

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Strong earthquakes induce a large number of secondary disasters, such as landslides, which bring serious challenges to post-disaster emergency rescue, and the rapid and accurate assessment of earthquake-induced landslide disasters is crucial for post-earthquake emergency rescue. This research aims to propose an emergency assessment model that is suitable for post-earthquake landslides, specifically targeting the first 72 h after an earthquake for emergency rescue guidance. The model combines remote sensing technology and the Newmark physical mechanics assessment model to form the InSAR Data–Newmark Physical Fusion Driver Model (IDNPM), which comprehensively considers the dynamic deformation of the ground surface and geological features. To validate the predictive performance of the IDNPM, the model is applied to the 5 September 2022 Luding earthquake event and the 8 August 2017 Jiuzhaigou earthquake event. The landslide qualitative evaluation, confusion matrix and Receiver Operating Characteristic (ROC) curve are utilized for quantitative assessment. The results show that the IDNPM can effectively reduce the false negative and false positive errors in landslide prediction by utilizing the SAR deformation information, and to a certain extent, it accounts for the dependence of the Newmark model on the accuracy of empirical formulas and geotechnical parameters. For the Luding earthquake event, the IDNPM shows an accuracy improvement of 10.296% compared to the traditional Newmark model. For the Jiuzhaigou earthquake event, there is also an improvement of 3.152%, with a promising generalization performance. The simplicity and ease of operation in constructing the model are accompanied by high reliability and accuracy. The research findings provide essential references for the development of post-earthquake landslide emergency prediction models and offer robust data support for emergency rescue and recovery efforts in earthquake-stricken areas in the future.

show abstract

“…In recent years, a few studies became to focus on the influence of surface deformation on landslide susceptibility and employed deformation features (derived by InSAR technique) to validate or refine the LSE results acquired from historical landslides (e.g., Xie et al, 2017;Zhao et al, 2019;Hussain et al, 2020;Hussain M.A. et al, 2021;Hussain S. et al, 2021;Lin et al, 2021;Meghanadh et al, 2021;Cao et al, 2022;Meghanadh et al, 2022). These studies actually concerned the known landslides.…”

Section: Introductionmentioning

confidence: 99%

Landslide susceptibility evaluation based on active deformation and graph convolutional network algorithm

Wang

et al. 2023

Front. Earth Sci.

View full text Add to dashboard Cite

Disastrous landslides have become a focus of the world’s attention. Landslide susceptibility evaluation (LSE) can predict where landslides may occur and has caught the attention of scientists all over the world. This work establishes integrated criteria of potential landslide recognition and combines the historical landslides and newly-identified potential landslides to improve the accuracy, rationality, and practicability of a LSE map. Moreover, slope units can well reflect the topographic constraint to landslide occurrence and development, and Graph Convolutional Network (GCN) can well portray the topological and feature relation among various slope units. The combination of slope units and GCN is for the first time employed in LSE. This work focuses on Wanzhou District, a famous landslide-serious region in the Three Gorges reservoir area, and employs multisource data to conduct potential landslide recognition and LSE and to reveal the distribution characteristics of high landslide susceptibility. Some new viewpoints are suggested as follows. 1) The established criteria of potential landslide recognition consist of the characteristics of active deformation, stratum and lithology, tectonics, topography, micro-geomorphology, environment, meteorology, earthquakes, and human engineering activity. These criteria can well eliminate 4 types of false alarm regions and is successfully validated by field survey. 2) 34 potential landslides are newly discovered, and the movement of these potential landslides were controlled or induced by the combined action of soft-hard interbedding rock mass, steep topography, frequent tectonic movement, strong fluvial erosion, abundant precipitation, and intensive road and building construction. 3) The GCN algorithm reaches a relatively high accuracy (AUC: 0.941) and outperforms the other representative machine learning algorithms of Convolutional Neural Network (AUC: 0.926), Support Vector Machine (AUC: 0.835), and CART Tree (AUC: 0.762). 4) High landslide susceptibility is caused by the coupled action of weathered rock cavities, soft rock and swelling soil, strong river erosion, abundant rainfall, and intensive human engineering activity.

show abstract

Refined landslide susceptibility analysis based on InSAR technology and UAV multi-source data

Cited by 31 publications

References 83 publications

Analysis of Geological Hazard Susceptibility of Landslides in Muli County Based on Random Forest Algorithm

Analysis of Geological Hazard Susceptibility of Landslides in Muli County Based on Random Forest Algorithm

Rapid Emergency Response Assessment of Earthquake-Induced Landslides Driven by Fusion of InSAR Deformation Data and Newmark Physical Models

Landslide susceptibility evaluation based on active deformation and graph convolutional network algorithm

Contact Info

Product

Resources

About