Developing comprehensive geocomputation tools for landslide susceptibility mapping: LSM tool pack

Şahin, Emrehan Kutluğ; Çölkesen, İsmail; Acmali, Suheda Semih; Akgün, Aykut; Aydınoğlu, Arif Çağdaş

doi:10.1016/j.cageo.2020.104592

Cited by 55 publications

(11 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Beside these stages, a slope information system is needed to create public awareness concerning potential hazards related to wet mass movements, and to cultivate a responsibility towards maintaining slope safety within own property boundaries. A future approach should include landslide susceptibility mapping by using the Landslide Susceptibility Mapping Tool Pack (LSM Tool Pack, Department of Civil Engineering, Bolu Abant Izzet Baysal University, Bolu, Turkey) as proposed by Sahin et al [ 91 ]. Public education regarding slope maintenance and landslide reporting is needed as well.…”

Section: Management Implications and Mitigation Measuresmentioning

confidence: 99%

Shaping Sustainable Urban Environments by Addressing the Hydro-Meteorological Factors in Landslide Occurrence: Ciuperca Hill (Oradea, Romania)

Morar

Lukić

Basarin

et al. 2021

IJERPH

View full text Add to dashboard Cite

Romania is one of the countries severely affected by numerous natural hazards, where landslides constitute a very common geomorphic hazard with strong economic and social impacts. The analyzed area, known as the “Ciuperca Hill”, is located in Oradea (NW part of Romania) and it has experienced a number of landsliding events in previous years, which have endangered anthropogenic systems. Our investigation, focused on the main causal factors, determined that landslide events have rather complex components, reflected in the joint climatological characteristics, properties of the geological substrate, and human activity that further contributed to the intensive change of landscape and acceleration of slope instability. Analysis of daily precipitation displays the occurrence and intensive distribution between May and September. Higher values of rainfall erosivity (observed for the 2014–2017 period), are occurring between April and August. Erosivity density follows this pattern and indicates high intensity events from April until October. SPI index reveals the greater presence of various wet classes during the investigated period. Geological substrate has been found to be highly susceptible to erosion and landsliding when climatological conditions are suitable. Accelerated urbanization and reduced vegetation cover intensified slope instability. The authors implemented adequate remote-sensing techniques in order to monitor and assess the temporal changes in landslide events at local level. Potential solutions for preventative actions are given in order to introduce and conduct qualitative mitigation strategies for shaping sustainable urban environments. Results from this study could have implications for mitigation strategies at national, regional, county, and municipality levels, providing knowledge for the enhancement of geohazard prevention and appropriate response plans.

show abstract

Section: Management Implications and Mitigation Measuresmentioning

confidence: 99%

Shaping Sustainable Urban Environments by Addressing the Hydro-Meteorological Factors in Landslide Occurrence: Ciuperca Hill (Oradea, Romania)

Morar

Lukić

Basarin

et al. 2021

IJERPH

View full text Add to dashboard Cite

show abstract

“…The RF model is a widely used model for regression and classification problems. It provides a high prediction accuracy, low errors, and can reduce the risk of overfitting [42,54]. To achieve good model performance and minimize the errors in the RF model, three hyperparameters are defined, namely: (i) the number of trees to be grown/combined (ntree), (iii) the maximum number of features to be considered at each split (mtree), and (iv) the size of the terminal nodes (nodesize).…”

Section: Random Forest (Rf) Modelmentioning

confidence: 99%

“…Machine learning (ML) techniques can minimize human interference and have the advantage of quantitatively analyzing factor dependence and continuous updating and reproducing datasets [40,41]. Some commonly applied ML techniques includes logistic regression (LR) [42][43][44], support vector machine (SVM) [45,46], decision trees (DT) [47,48], artificial neural network (ANN) [49][50][51], naïve Bayes (NB) [52,53], and random forest (RF) [54,55]. However, ML techniques also have limitations, including overfitting data and difficulty relating the results with existing scientific landslide theories.…”

Section: Introductionmentioning

confidence: 99%

Entropy-Based Hybrid Integration of Random Forest and Support Vector Machine for Landslide Susceptibility Analysis

2021

View full text Add to dashboard Cite

Landslide susceptibility mapping is a crucial step in comprehensive landslide risk management. The purpose of the present study is to analyze the landslide susceptibility of Mandi district, Himachal Pradesh, India, based on optimum feature selection and hybrid integration of the Shannon entropy (SE) model with random forest (RF) and support vector machine (SVM) models. An inventory of 1723 rainfall-induced landslides was generated and randomly selected for training (1199; 70%) and validation (524; 30%) purposes. A set of 14 relevant factors was selected and checked for multicollinearity. These factors were first ranked using Information Gain and Chi-square feature ranking algorithms. Furthermore, Wilcoxon Signed Rank Test and One-Sample T-Test were applied to check their statistical significance. An optimum subset of 11 landslide causative factors was then used for generating landslide susceptibility maps (LSM) using hybrid SE-RF and SE-SVM models. These LSM’s were validated and compared using receiver operating characteristic (ROC) curves and performance matrices. The SE-RF performed better with training and validation accuracies of 96.93% and 88.94%, respectively, compared with the SE-SVM model with training and validation accuracies of 94.05% and 82.4%, respectively. The prediction matrices also confirmed that the SE-RF model is better and is recommended for the landslide susceptibility analysis of similar mountainous regions worldwide.

show abstract

“…In recent years, with the rapid development of Artificial Intelligence (AI) field, machine learning has been used by more and more researchers in the field of landslide disaster prediction. (Roy et al, 2019) (Chang et al, 2019) (Sahin et al, 2020). Tran Van Phonga et al (Phong et al, 2019) selected Support Vector Machine (SVM), Artificial Neural Network (ANN), Logistic Regression (LR) and Reduced Error Pruning Tree (REPT), and nine landslide condition factors were used to generate data sets for training and validation of the model.…”

Section: Introductionmentioning

confidence: 99%

Landslide susceptibility evaluation based on optimized support vector machine

Liu

Lin

et al. 2021

Proc. Int. Cartogr. Assoc.

View full text Add to dashboard Cite

Abstract. Landslide is a natural disaster that has caused great property losses and human casualties in the world. To strengthen the target prevention and management level, ZhaShui county, Shaanxi province, is selected as the research area to evaluate the landslide susceptibility. First of all, under the premise of considering the correlation, 10 evaluation factors closely related to landslide disaster (i.e., elevation, rainfall, rock group, slope, slope aspect, vegetation index, landform, distance to residential area, distance to road, distance to river system) are taken together with non-landslide points, which are selected under multi-constraint conditions to form a sample data-set. Secondly, the sample dataset is substituted into the Support Vector Machine (SVM) model optimized by firefly algorithm for training and prediction. Finally, the result map was partitioned according to the natural discontinuous point method, and the landslide susceptibility map was obtained. The results show that the model optimized by the firefly algorithm has higher accuracy, and the landslide susceptibility results are more consistent with the actual distribution of disaster points.

show abstract

Developing comprehensive geocomputation tools for landslide susceptibility mapping: LSM tool pack

Cited by 55 publications

References 33 publications

Shaping Sustainable Urban Environments by Addressing the Hydro-Meteorological Factors in Landslide Occurrence: Ciuperca Hill (Oradea, Romania)

Shaping Sustainable Urban Environments by Addressing the Hydro-Meteorological Factors in Landslide Occurrence: Ciuperca Hill (Oradea, Romania)

Entropy-Based Hybrid Integration of Random Forest and Support Vector Machine for Landslide Susceptibility Analysis

Landslide susceptibility evaluation based on optimized support vector machine

Contact Info

Product

Resources

About