Comparative analysis of multiple conventional neural networks for landslide susceptibility mapping

Aslam, Bilal; Zafar, Adeel; Khalil, Umer

doi:10.1007/s11069-022-05570-x

Cited by 27 publications

(8 citation statements)

References 93 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two of the most common indicators used to assess the multicollinearity among the parameters utilized as input in a mathematical model are Variance Inflation (VIF) and Tolerance (TL). The VIF and TL are found in various landslide susceptibility studies, viz., [ 98 , 99 , 100 ]. To detect collinearity throughout multiple regression, the VIF and TL constitute two highly connected statistical measures.…”

Section: Database and Methodologymentioning

confidence: 99%

GIS-based data-driven bivariate statistical models for landslide susceptibility prediction in Upper Tista Basin, India

Das¹,

Saha

Mitra

et al. 2023

Heliyon

View full text Add to dashboard Cite

Section: Database and Methodologymentioning

confidence: 99%

GIS-based data-driven bivariate statistical models for landslide susceptibility prediction in Upper Tista Basin, India

Das¹,

Saha

Mitra

et al. 2023

Heliyon

View full text Add to dashboard Cite

“…Appropriate terrain mapping is important in generating the LSM of the study area (Aslam et al, 2022b). We used WoE, FR, and IV techniques to compute LSM for the study area.…”

Section: Lsm Techniquesmentioning

confidence: 99%

Landslide susceptibility mapping (LSM) of Swat District, Hindu Kush Himalayan region of Pakistan, using GIS-based bivariate modeling

Islam¹,

Riaz

Ghaffar

et al. 2022

Front. Environ. Sci.

View full text Add to dashboard Cite

Landslides are a recurrent environmental hazard in hilly regions and affect the socioeconomic development in Pakistan. The current study area is the tourism and hydro energy hub of Pakistan and is affected by environmental hazard. A landslide susceptibility mapping (LSM) of the Hindu Kush Himalayan, Swat District, Pakistan, can be created to reduce demographic losses due to landslides. This current study is conducted to apply three bivariate models, including weights of evidence (WOE), frequency ratio (FR), and information value (IV) for an LSM that has not been explored or applied in the current study area. For this purpose, first, an inventory map of 495 landslides was constructed from both ground and satellite data and randomly divided into training (70%) and testing (30%) datasets. Furthermore, 10 conditioning factors (elevation, slope, aspect, curvature, fault, rainfall, land use land cover (LULC), lithology, road, and drainage) used for the mapping of landslides were prepared in ArcGIS 10.8. Finally, LSM is generated based on WOE, FR, and IV models and validated the performance of LSM models using the area under receiver operating characteristic curve (AUROC). The findings of success rate curve (SRC) of the WOE, FR, and IV models were 67%, 93%, and 64%, respectively, while the prediction rate curves (PRCs) of the three models were 87%, 95%, and 73%, respectively. The validation results for WOE, FR, and IV justified that the FR model is the most reliable technique of all three of these models to produce the highest accuracy LSM for the present study area. Policymakers can use the findings of current research work to mitigate the loss due to landslide hazard.

show abstract

“…The application of ML through its different algorithms is evidenced in the elaboration of several studies around the world. The most widely applied ML methods are the conventional ones such as Support Vector Machines (SVM) [8], Artificial Neural Networks (ANN) [9][10][11][12], Random Forests (RF) [13], Decision Trees, Logistic Regression (LR) [14], and Gradient Boosting, among others. The relatively current methods and applications of ML and its application for LSM can be reviewed in the study of Tehrani [15].…”

Section: Introductionmentioning

confidence: 99%

Analysis of Conditioning Factors in Cuenca, Ecuador, for Landslide Susceptibility Maps Generation Employing Machine Learning Methods

Bravo-López

Sellers

Fernández

2023

Land

View full text Add to dashboard Cite

Landslides are events that cause great impact in different parts of the world. Their destructive capacity generates loss of life and considerable economic damage. In this research, several Machine Learning (ML) methods were explored to select the most important conditioning factors, in order to evaluate the susceptibility to rotational landslides in a sector surrounding the city of Cuenca (Ecuador) and with them to elaborate landslide susceptibility maps (LSM) by means of ML. The methods implemented to analyze the importance of the conditioning factors checked for multicollinearity (correlation analysis and VIF), and, with an ML-based approach called feature selection, the most important factors were determined based on Classification and Regression Trees (CART), Feature Selection with Random Forests (FS RF), and Boruta and Recursive Feature Elimination (RFE) algorithms. LSMs were implemented with Random Forests (RF) and eXtreme Gradient Boosting (XGBoost) methods considering a landslide inventory updated to 2019 and 15 available conditioning factors (topographic (10), land cover (3), hydrological (1), and geological (1)), from which, based on the results of the aforementioned analyses, the six most important were chosen. The LSM were elaborated considering all available factors and the six most important ones, with the previously mentioned ML methods, and were compared with the result generated by an Artificial Neural Network with resilient backpropagation (ANN rprop-) with six conditioning factors. The results obtained were validated by means of AUC-ROC value and showed a good predictive capacity for all cases, highlighting those obtained with XGBoost, which, in addition to a high AUC value (>0.84), obtained a good degree of coincidence of landslides at high and very high susceptibility levels (>72%). Despite the findings of this research, it is necessary to study in depth the methods applied for the development of future research that will contribute to developing a preventive approach in the study area.

show abstract

Comparative analysis of multiple conventional neural networks for landslide susceptibility mapping

Cited by 27 publications

References 93 publications

GIS-based data-driven bivariate statistical models for landslide susceptibility prediction in Upper Tista Basin, India

GIS-based data-driven bivariate statistical models for landslide susceptibility prediction in Upper Tista Basin, India

Landslide susceptibility mapping (LSM) of Swat District, Hindu Kush Himalayan region of Pakistan, using GIS-based bivariate modeling

Analysis of Conditioning Factors in Cuenca, Ecuador, for Landslide Susceptibility Maps Generation Employing Machine Learning Methods

Contact Info

Product

Resources

About