A multi-criteria landslide susceptibility mapping using deep multi-layer perceptron network: A case study of Srinagar-Rudraprayag region (India)

Meghanadh, Devara; Maurya, Vipin Kumar; Tiwari, Ashutosh; Dwivedi, Ramji

doi:10.1016/j.asr.2021.10.021

Cited by 26 publications

(11 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hybrid ML models, in particular, do not rely on statistical assumptions and may quantify the relevance and effect of landslide-related factors (Achour & Pourghasemi, 2020). Previously, single models, such as the MLP model, were often applied to build landslide susceptibility maps (Adnan et al, 2020;Meghanadh et al, 2022;Zare et al, 2013). The results in Table 3 and Fig.…”

Section: Discussionmentioning

confidence: 99%

“…The factors are referred to in previous studies and are based on the available data in the research area (Kavzoglu et al, 2019). Precipitation, topography, hydrology, geology, geomorphology, and geoenvironment are factors that signi cantly impact landslide formation in mountain areas (Bui et al, 2019;Meghanadh et al, 2022). In this study, 16 landslide causative factors were taken for the modeling in the following subsections (Fig.…”

Section: Landslide Causative Factorsmentioning

confidence: 99%

See 1 more Smart Citation

Landslide susceptibility prediction mapping with advanced ensemble models: Son La province, Vietnam

Bui

Khuc

et al. 2022

Nat Hazards

View full text Add to dashboard Cite

Landslides are a serious geohazard in many mountainous areas of Vietnam during the rainy season.They directly threaten human lives and properties every year. Landslide susceptibility maps are useful tools for risk mitigation, land-use planning, and early warning systems for local areas. It is necessary to update these maps continuously because of the complexity of landslide events. This fact requires further extending the approach techniques with practical implications. Therefore, this study aimed to develop landslide susceptibility prediction maps based on advanced Machine Learning (ML) techniques. Five state-of-art hybrid ML models were developed: Bagging -MLP, Dagging -MLP, Decorate -MLP, Rotation Forest -MLP, Random SubSpace -MLP with Multi-Layer Perceptron (MLP) as a base classi er. Sixteen causative factors were collected to build landslide susceptibility maps based on the relationship between historical landslide locations and speci c local geo-environmental conditions. The model performance was veri ed using various statistical indexes. Based on the Area Under ROC curve (AUC) analysis results of the testing dataset, the Rotation Forest -MLP model has the greatest predictive accuracy of AUC = 0.818. It is followed by the Decorate -MLP and Bagging -MLP (AUC=0.804), the Random SubSpace -MLP model (AUC=0.796), the Dagging -MLP (AUC=0.789), and the single MLP (AUC=0.698). The results of this study can be applied effectively to other mountainous regions to mitigate the risk of landslides.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Landslide Causative Factorsmentioning

confidence: 99%

Landslide susceptibility prediction mapping with advanced ensemble models: Son La province, Vietnam

Bui

Khuc

et al. 2022

Nat Hazards

View full text Add to dashboard Cite

show abstract

“…Furthermore, different methods such as AHP (Panchal & Shrivastava, 2021), Heuristic, Probabilistic, simple statistical bivariate, regression, and deterministic models have been used by the researchers. In a variety of case studies, meaningful ndings were obtained using AHP (Meghanadh et al, 2022;Moragues et al, 2021;Roccati et al, 2021) and Weights-of-evidence models with high accuracy and reliability .…”

Section: Introductionmentioning

confidence: 99%

Landslide hazard, susceptibility and risk assessment (HSRA) based on remote sensing and GIS data models: a case study of Muzaffarabad Pakistan

Ahmad

Shao

Aslam

et al. 2022

Stoch Environ Res Risk Assess

View full text Add to dashboard Cite

The notion of this research is based on the two devastating earthquake events that happened on October 8, 2005, and September 24, 2019, in the regions of Azad Kashmir. This study aims at (i) identi cation of the susceptible zones where landslides will occur in the future; (ii) preparation of landslide inventory maps using vector data, satellite imagery, Shuttle Radar Topographic Mission (STRM) and Advanced Space-borne Thermal Emission and Re ection Radiometer (ASTER) DEM; (iii) implementation of Analytical Hierarchy Process (AHP) model using weighted overlay analysis (WOA). For this purpose, key factors such as land-use, faults, slope, contours, soil and seismology are used to develop a landslide hazard zonation map. The output landslide susceptibility map has four susceptibility levels such as low, medium, high, and very high vulnerable zones. The results indicated that a highly susceptible landslide zone is found in the northwestern part of Muzaffarabad, which is a metropolitan region. Moreover, there are 127 active landslides are identi ed and collectively about 9% of the study area is very highly susceptible to future landslides. Moreover, research ndings are helpful in tactful thinking for future infrastructure development, ecological protection in high-susceptible landslide regions in Muzaffarabad.It also allows the Government to make strategies for that speci c zones on a priority basis to reduce the casualties and destruction in future landslide events.

show abstract

“…(2) LSEs were conducted by combining InSAR-detected surface deformation and other influencing factors. The factors of surface deformation, lithology, topography, land use and so on were used together as the input parameters to evaluate landslide susceptibility [ 50 , 51 , 52 ]. (3) The surface deformation features detected by InSAR technique were adopted to improve the LSE results obtained from optical images and known landslides [ 53 , 54 , 55 ] or to refine the LSE map acquired from a physical model [ 56 ].…”

Section: Introductionmentioning

confidence: 99%

Landslide Susceptibility Evaluation Based on Potential Disaster Identification and Ensemble Learning

Wang

Zhang

Jia

et al. 2022

IJERPH

View full text Add to dashboard Cite

Catastrophic landslides have much more frequently occurred worldwide due to increasing extreme rainfall events and intensified human engineering activity. Landslide susceptibility evaluation (LSE) is a vital and effective technique for the prevention and control of disastrous landslides. Moreover, about 80% of disastrous landslides had not been discovered ahead and significantly impeded social and economic sustainability development. However, the present studies on LSE mainly focus on the known landslides, neglect the great threat posed by the potential landslides, and thus to some degree constrain the precision and rationality of LSE maps. Moreover, at present, potential landslides are generally identified by the characteristics of surface deformation, terrain, and/or geomorphology. The essential disaster-inducing mechanism is neglected, which has caused relatively low accuracies and relatively high false alarms. Therefore, this work suggests new synthetic criteria of potential landslide identification. The criteria involve surface deformation, disaster-controlling features, and disaster-triggering characteristics and improve the recognition accuracy and lower the false alarm. Furthermore, this work combines the known landslides and discovered potential landslides to improve the precision and rationality of LSE. This work selects Chaya County, a representative region significantly threatened by landslides, as the study area and employs multisource data (geological, topographical, geographical, hydrological, meteorological, seismic, and remote sensing data) to identify potential landslides and realize LSE based on the time-series InSAR technique and XGBoost algorithm. The LSE precision indices of AUC, Accuracy, TPR, F1-score, and Kappa coefficient reach 0.996, 97.98%, 98.77%, 0.98, and 0.96, respectively, and 16 potential landslides are newly discovered. Moreover, the development characteristics of potential landslides and the cause of high landslide susceptibility are illuminated. The proposed synthetic criteria of potential landslide identification and the LSE idea of combining known and potential landslides can be utilized to other disaster-serious regions in the world.

show abstract

A multi-criteria landslide susceptibility mapping using deep multi-layer perceptron network: A case study of Srinagar-Rudraprayag region (India)

Cited by 26 publications

References 36 publications

Landslide susceptibility prediction mapping with advanced ensemble models: Son La province, Vietnam

Landslide susceptibility prediction mapping with advanced ensemble models: Son La province, Vietnam

Landslide hazard, susceptibility and risk assessment (HSRA) based on remote sensing and GIS data models: a case study of Muzaffarabad Pakistan

Landslide Susceptibility Evaluation Based on Potential Disaster Identification and Ensemble Learning

Contact Info

Product

Resources

About