Evaluation of landslide susceptibility in a hill city of Sikkim Himalaya with the perspective of hybrid modelling techniques

Kaur, Harjeet; Gupta, Srimanta; Parkash, Surya; Thapa, Raju; Gupta, Arindam; Khanal, Ganesh

doi:10.1080/19475683.2019.1575906

Cited by 48 publications

(5 citation statements)

References 86 publications

(110 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The rest of the slope directions are less susceptible to the landslides. Kaur et al [29] studied landslide at Sikkim which is one of the states of India and neighbour to Bhutan and it is also a part of the Himalayan region. Kaur et al [29] observed that the south, southeast, and southwest with a higher value of (Pij).…”

Section: Results and Discussion 1) The Spatial Relationship Between Tmentioning

confidence: 99%

“…Kaur et al [29] studied landslide at Sikkim which is one of the states of India and neighbour to Bhutan and it is also a part of the Himalayan region. Kaur et al [29] observed that the south, southeast, and southwest with a higher value of (Pij). This may be due blockage of wind that comes from the south (Indian Ocean) by the giant Himalayan mountain.…”

Section: Results and Discussion 1) The Spatial Relationship Between Tmentioning

confidence: 99%

See 1 more Smart Citation

Landslide Identification and Zonation Using the Index of Entropy Technique at Ossey Watershed Area in Bhutan

Thongley

Vansarochana

2020

App. Envi. Res.

View full text Add to dashboard Cite

The landslide is one of the natural disasters which claim human lives and incur huge economic losses, especially in the mountainous area. The main aim of this study is to develop different zones of landslide-prone area using the index of entropy (IOE) at the Ossey watershed area in Bhutan. During the landslide inventory, 164 landslides were identified of which 115 locations were used for the training dataset while the remaining 49 locations were used for the validation dataset. A total of ten causal factors were used for this study including elevation, slope, aspect, slope curvature, stream power index, normalized difference vegetation index (NDVI), distance from the road, distance from the river, lithology, and rainfall. The IOE was used to obtain the relationship between the landslide events and the causal factors. The most influential causal factors were NDVI, slope, and rainfall with the weightage of 0.377, 0.347, and 0.175 respectively as per the IOE. The final landslide susceptibility map was classified into five classes using the geometrical interval classification. The validation was done using the receiver operating characteristic (ROC) curves and the kappa index. The area under the curve (AUC) for the success rate and prediction rate was 0.7821 and 0.8377, respectively. The kappa index using the training dataset and validation dataset were 0.4111 and 0.4898, respectively. The final landslide susceptibility map is accurate enough for the future references by the decision-makers and the engineers.

show abstract

Section: Results and Discussion 1) The Spatial Relationship Between Tmentioning

confidence: 99%

Section: Results and Discussion 1) The Spatial Relationship Between Tmentioning

confidence: 99%

Landslide Identification and Zonation Using the Index of Entropy Technique at Ossey Watershed Area in Bhutan

Thongley

Vansarochana

2020

App. Envi. Res.

View full text Add to dashboard Cite

show abstract

“…Elevation, slope, aspect, profile curvature, Topographical Roughness Index (TRI), Topographical Wetness Index (TWI), and Stream Power Index (SPI) extracted from the Digital Surface Model (DSM) are provided by the ALOS Global Surface Model. Lineaments [23] include faults, ridgelines, fissures, or boundaries between strata on the Earth's surface, with different lengths and orientations. To extract the lineaments in the study area, the DSM is used to obtain 0 • , 45 The raster data for lithology and landform are obtained from A New Map of Global Ecological Land Units [24] and The New Global Lithological Map Database [25].…”

Section: Data Preparationmentioning

confidence: 99%

A Novel Heterogeneous Ensemble Framework Based on Machine Learning Models for Shallow Landslide Susceptibility Mapping

Tang,

Wang,

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Landslides are devastating natural disasters that seriously threaten human life and property. Landslide susceptibility mapping (LSM) plays a key role in landslide hazard management. Machine learning (ML) models are widely used in LSM but suffer from limitations such as overfitting and unreliable accuracy. To improve the classification performance of a single machine learning (ML) model, this study selects logistic regression (LR), support vector machine (SVM), random forest (RF), and gradient boosting decision tree (GBDT), and proposes a novel heterogeneous ensemble framework based on Bayesian optimization (BO), namely, stratified weighted averaging (SWA), to test its applicability in a typical landslide area in Yanbian Prefecture, China. Firstly, a dataset consisting of 1531 historical landslides was collected from field investigations and historical records, and a spatial database containing 16 predisposing factors was established. The dataset was divided into a training set and a test set in a ratio of 7:3. The results showed that SWA effectively improved the Accuracy, AUC, and robustness of the model compared to a single ML model. The SWA achieved the best classification results (Accuracy = 91.39% and AUC = 0.967). To verify the generalization ability of SWA, we selected published landslide datasets from Yanshan country and Yongxin country in China for testing. SWA also performed well, with an AUC of 0.871 and 0.860, respectively. As indicated by shapely values (SVs), Normalized Difference Vegetation Index (NDVI) is the factor that has the greatest impact on landslide occurrence. The landslide susceptibility maps obtained from this study will provide an effective reference program for land use planning and disaster prevention and mitigation projects in Yanbian Prefecture, China.

show abstract

“…Approximately CHF 15 million are spent each year on landslide protective measures in Switzerland (Dorren et al, 2009). To mitigate this risk, regional landslide hazard mapping and modelling provide an important basis for indicating potential hazard areas (Dahl et al, 2010;Kaur et al, 2019;Shano et al, 2020;Di Napoli et al, 2021). In Switzerland, nationalscale shallow landslide modelling was carried out at within the SilvaProtect-CH project (Dorren and Schwarz, 2016).…”

Evaluation of landslide susceptibility in a hill city of Sikkim Himalaya with the perspective of hybrid modelling techniques

Cited by 48 publications

References 86 publications

Landslide Identification and Zonation Using the Index of Entropy Technique at Ossey Watershed Area in Bhutan

Landslide Identification and Zonation Using the Index of Entropy Technique at Ossey Watershed Area in Bhutan

A Novel Heterogeneous Ensemble Framework Based on Machine Learning Models for Shallow Landslide Susceptibility Mapping

Comment on nhess-2024-76

Contact Info

Product

Resources

About