Comparison of earthquake-induced shallow landslide susceptibility assessment based on two-category LR and KDE-MLR

Fan, Xinyue; Liu, Bin; Luo, Jie; Pan, Ke; Han, Suyue; Zhou, Zhiping

doi:10.1038/s41598-023-28096-z

Cited by 13 publications

(11 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Depending on data availability, further research may provide insights into how factors such as soil moisture and geological structure can affect the model's generalizability. Lastly, the suggested ML-LaDeCORsat approach could be adapted to improve existing work on landslide susceptibility [11][12][13]. Accurate and rapid identification of landslides will likely become more important because extreme weather events are forecast to become more frequent, implying an increased likelihood of earthquakes following heavy precipitation events, which would increase the number of associated landslides.…”

Section: Discussionmentioning

confidence: 99%

“…In the event of an earthquake, coseismic ground deformation, and distance to the surface rupture zone are important influencing factors of landslide susceptibility [11]. In addition, landslide susceptibility models often take into account landslide conditioning factors such as the amount of rainfall that triggered the landslide event, indices derived from a Digital Elevation Model (DEM) including the topographic wetness index (TWI) and the sediment transport index (STI), as well as spectral vegetation indices such as the Normalized Difference Vegetation Index (NDVI) indicating vegetation density and health [12,13].…”

Section: Earthquakes and Coseismic Landslidesmentioning

confidence: 99%

See 1 more Smart Citation

Detecting Coseismic Landslides in GEE Using Machine Learning Algorithms on Combined Optical and Radar Imagery

Peters,

Liu,

Keppel

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Landslides, resulting from disturbances in slope equilibrium, pose a significant threat to landscapes, infrastructure, and human life. Triggered by factors such as intense precipitation, seismic activities, or volcanic eruptions, these events can cause extensive damage and endanger nearby communities. A comprehensive understanding of landslide characteristics, including spatio-temporal patterns, dimensions, and morphology, is vital for effective landslide disaster management. Existing remote sensing approaches mostly use either optical or synthetic aperture radar sensors. Integrating information from both these types of sensors promises greater accuracy for identifying and locating landslides. This study proposes a novel approach, the ML-LaDeCORsat (Machine Learning-based coseismic Landslide Detection using Combined Optical and Radar Satellite Imagery), that integrates freely available Sentinel-1, Palsar-2, and Sentinel-2 imagery data in Google Earth Engine (GEE). The approach also integrates relevant spectral indices and suitable bands used in a machine learning-based classification of coseismic landslides. The approach includes a robust and reproducible training and validation strategy and allows one to choose between five classifiers (CART, Random Forest, GTB, SVM, and Naive Bayes). Using landslides from four different earthquake case studies, we demonstrate the superiority of our approach over existing solutions in coseismic landslide identification and localization, providing a GTB-based detection accuracy of 87–92%. ML-LaDeCORsat can be adapted to other landslide events (GEE script is provided). Transfer learning experiments proved that our model can be applied to other coseismic landslide events without the need for additional training data. Our novel approach therefore facilitates quick and reliable identification of coseismic landslides, highlighting its potential to contribute towards more effective disaster management.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Earthquakes and Coseismic Landslidesmentioning

confidence: 99%

Detecting Coseismic Landslides in GEE Using Machine Learning Algorithms on Combined Optical and Radar Imagery

Peters,

Liu,

Keppel

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…When the number of geological disasters showing the geographical and temporal evolution law is combined with the impact of potential geological disasters, the inability to adequately explain geological disaster distribution features results. It gives more interpretable results than technologies like random forest and neural networks (Deng et al, 2020; Fan et al, 2023). As a result, this study employs a weighted ICM and AHP combination to examine the distribution characteristics of geological disaster susceptibility in the studied area.…”

Section: Research Methods and Data Sourcesmentioning

confidence: 99%

“…According to statistical studies, there is a negative correlation between the cutting degree and the accumulation fan's area of gullies in the study area (Figure 5a), whereas the watershed area of debris flow gullies has a positive correlation with the covered area of geological disasters in the basin (Figure 5b). Fan et al, 2023). As a result, this study employs a weighted ICM and AHP combination to examine the distribution characteristics of geological disaster susceptibility in the studied area.…”

Section: Overview the Study Areamentioning

confidence: 99%

Geological hazards susceptibility evaluation based on multi‐year spatial–temporal evolution of assessment factors in Luding area, Sichuan Province, China

Qu,

Jin

2024

Geological Journal

View full text Add to dashboard Cite

More than 50 earthquakes occurred in the Luding region, including a 6.8‐magnitude earthquake on September 5, 2022, which induced huge amounts of geological disasters. As the main triggered factors for the geological disasters, the vegetation, precipitation and temperature show regular changes on the time axis. Thus, this paper based on the spatial–temporal evolution of the precipitation, temperature and normalized difference vegetation index (NDVI), focuses on the susceptibility of the Luding area using the weighted information content method (ICM) and analytic hierarchy process (AHP) for the post‐earthquake regional planning and reconstruction. In the Luding area, it was found that there were 18 debris flow gullies, and 470 geological disasters scattered in the debris flow gullies. The NDVI of the study area has been declining in recent years, with only about 12% of the NDVI increasing from 2015 to 2020. From 2011 to 2015, the annual cumulative precipitation has been dropping overall, while the July average temperature has increasing quadratic functions after decreasing trend. Furthermore, the studied area's geological hazards susceptibility was classified into five categories, with extremely low susceptibility accounting for 5.82%, low susceptibility accounting for 13.61%, moderate susceptibility accounting for 38.54%, high susceptibility accounting for 39.96% and extremely high susceptibility accounting for 2.08%. The geological disasters in moderate, high and extremely high susceptibility accounted for approximately 95.08%, and the covered area of geological disasters in moderate, high and extremely high susceptibility accounted for 88.06%. Through the receiver operating characteristic (ROC) curve of the model verification found the AUC = 0.743. The geological hazards susceptibility study results show that the approach is useful for the analysis and prevention of geological disasters.

show abstract

“…Landslides represent one of the most destructive and frequent natural hazard phenomena reported worldwide 1 . It creates a significant constraint in the pace of economic development due to the disruption of infrastructures and blockades of transportation facilities 2 .…”

Section: Introductionmentioning

confidence: 99%

Seismic landslide susceptibility assessment using principal component analysis and support vector machine

Xu,

Che,

Zhou

2024

Sci Rep

View full text Add to dashboard Cite

Seismic landslides are dangerous natural hazards that can cause immense damage to human lives and property. Susceptibility assessment of earthquake-triggered landslides provides the scientific basis and theoretical foundation for disaster emergency management in engineering projects. However, landslide susceptibility assessment requires a massive amount of historical landslide data. Evidence of past landslide activities may be lost due to changes in geographical conditions and human factors over time. The lack of landslide data poses difficulties in assessing landslide susceptibility. The aim of this study is to establish a generalized seismic landslide susceptibility assessment model for applying it to the Dayong highway in the Chenghai area, where earthquakes occur frequently but with a lack of landslide data. The landslide data used comes from the 2014 Ludian Ms (Surface wave magnitude) 6.5 earthquake in a region with geographical conditions similar to those in the Chenghai area. The influencing factors considered include elevation, slope, slope aspect, distance to streams, distance to faults, geology, terrain wetness index, normalized difference vegetation index, epicenter distance and peak ground acceleration. The frequency ratio method is used to eliminate influencing factors with poor statistical dispersion of landslides. Principal component analysis (PCA) is utilized to reduce the dimensionality of landslide conditioning factors and to improve the transferability of the assessment model to different regions. A support vector machine model is used to establish the susceptibility assessment model. The results show that the accuracy of the PCA–SVM model reaches 93.6%. The landslide susceptibility of the Chenghai area is classified into 5 classes, with the “Very high” landslide susceptibility class accounting for 0.63%. The 13-km section in the middle of the Dayong highway, which accounts for 8.9%, is identified as the high-risk area most obviously impacted by seismic landslides. This study provides a new approach for seismic landslide susceptibility assessment in areas lacking in landslide inventory data.

show abstract

Comparison of earthquake-induced shallow landslide susceptibility assessment based on two-category LR and KDE-MLR

Cited by 13 publications

References 46 publications

Detecting Coseismic Landslides in GEE Using Machine Learning Algorithms on Combined Optical and Radar Imagery

Detecting Coseismic Landslides in GEE Using Machine Learning Algorithms on Combined Optical and Radar Imagery

Geological hazards susceptibility evaluation based on multi‐year spatial–temporal evolution of assessment factors in Luding area, Sichuan Province, China

Seismic landslide susceptibility assessment using principal component analysis and support vector machine

Contact Info

Product

Resources

About