An Investigation of Landslide Susceptibility Using Logistic Regression and Statistical Index Methods in Dailekh District, Nepal

Kumar, Deepak; Xiong, Donghong; Wang, Zhao; Zhang, Baojun; Dahal, Nirmal Mani; Wu, Yanhong; Baig, Muhammad Aslam

doi:10.1007/s11769-022-1304-2

Cited by 19 publications

(7 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…NDVI is typically applied to distinguish between areas covered in vegetation and those that are not [ 72 ]. Numerous studies [ 83 , 84 , 85 ] demonstrate the connection between landslide occurrence and NDVI. It has a range of-1 to+1, and in the existing research region, it is between −0.11 and 0.48 ( Fig.…”

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

“…The questionnaires were tested, revised, and improved, before 514 questionnaires were completed in August and September 2019. Out of these, 468 (91.05%) valid, complete questionnaires were obtained [ 51 , 52 , 53 , 54 ].…”

Section: Methodsmentioning

confidence: 99%

Study on the Evolution Mechanism of Ecosystem Services in Karst Mountainous Areas from the Perspective of Humanities

Miao

Xin²,

Pu³

et al. 2022

IJERPH

View full text Add to dashboard Cite

Anthropogenic activities have altered ecosystem service functions in the karst mountainous areas. The implementation of ecological restoration projects by the government, the behavior, attitude, and willingness of farmers to participate in their implementation, the application of pesticides and fertilizers, in addition to other socio-economic activities, have had a significant impact on the ecosystem services (ESS) of the region. Taking Guangnan County, a typical karst mountainous area in Yunnan Province, as an example, this study analyzes the evolutionary characteristics of six types of ESS and the driving mechanism of the change in ESS from the anthropogenic macro and micro perspective using questionnaire surveys and the multivariate logistic model. The results showed that (1) ecological restoration projects in the past 20 years have promoted an overall ecological transformation in the typical karst mountainous areas of the Yunnan Province (2) from the macro perspective, and the implementation of such ecological projects is beneficial in increasing soil conservation, carbon sequestration, habitat support, and cultural services. The reduction in agricultural population is beneficial in improving habitat support services, and the increase in the annual average tourism income and the tertiary industry is beneficial in increasing cultural services. Among them, the impact of hydraulic engineering on water production and the tertiary industry on cultural services are the most significant, with the change in the human disturbance index having the most substantial impact on soil conservation, carbon sequestration, and habitat support (3) at the micro level. Increasing pesticide and fertilizer application, willingness and use by farmers has a positive impact on food supply and a negative impact on habitat quality. An increase in the number and willingness of farmers participating in restoring farmland to forests and water conservancy projects was observed. This has a positive impact on soil conservation, water production, and carbon sequestration. Among them, the application of chemical fertilizers and pesticides has the most significant impact on food supply and habitat support, and the willingness to implement the projects on restoring farmlands to forests has the most significant impact on carbon sequestration. The willingness to implement terracing has the greatest impact on water production and soil conservation, and aesthetic value has the greatest impact on cultural services.

show abstract

“…TP + TN TP + TN + FP + FN (11) AUC was the area under the receiver operating characteristic (ROC) curve, and the closer the value was to 1, the better the classification effect of the method was.…”

Section: Oa =mentioning

confidence: 99%

“…Since the uncertainty method considers the weight information of each indicator factor and has a high evaluation accuracy, it has found wide acclamation from scholars and researchers. Among the data-driven machine learning methods are those based on logistic regression (LR) [10,11], decision tree [12,13], random forest (RF) [14,15], and support vector machine (SVM) [16,17], all of which are well-suited to exploring the nonlinear relationship between landslide susceptibility and each evaluation factor. These methods are computationally efficient without much prior knowledge.…”

Section: Introductionmentioning

confidence: 99%

A Combination of Deep Autoencoder and Multi-Scale Residual Network for Landslide Susceptibility Evaluation

Wang

Liu

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Landslide susceptibility evaluation can accurately predict the spatial distribution of potential landslides, which offers great usefulness for disaster prevention, disaster reduction, and land resource management. Aiming at the problems of insufficient samples for landslide compilation, difficulty in expanding landslide samples, and insufficient expression of nonlinear relationships among evaluation factors, this paper proposes a new evaluation method of landslide susceptibility combining deep autoencoder and multi-scale residual network (DAE-MRCNN). In the first step, a deep autoencoder network was used to learn the feature expression of the original landslide data in order to acquire effective features in the data. Next, a multi-scale residual network was constructed; specifically, the model was improved into a deep residual network model by adding skip connections in the convolutional layer. In addition, the multi-scale idea was utilized to fully extract the scale characteristics of the evaluation factors. Finally, the model was used for feature training, and the results were input into the Softmax classifier to complete the prediction of landslide susceptibility. For this purpose, a machine learning method and two state-of-the-art deep learning methods, namely SVM, CPCNN-ML, and 2D-CNN, were utilized to model landslide susceptibility in Hanzhong City, Shaanxi Province. The proposed method produced the highest model performance of 0.891, followed by 0.842, 0.869, and 0.873. The experimental results show that the DAE-MRCNN method can fully express the complex nonlinear relationships among the evaluation factors, alleviate the problem of insufficient samples in convolutional neural networks (CNN) training, and significantly improve the accuracy of susceptibility prediction.

show abstract

An Investigation of Landslide Susceptibility Using Logistic Regression and Statistical Index Methods in Dailekh District, Nepal

Cited by 19 publications

References 64 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

Study on the Evolution Mechanism of Ecosystem Services in Karst Mountainous Areas from the Perspective of Humanities

A Combination of Deep Autoencoder and Multi-Scale Residual Network for Landslide Susceptibility Evaluation

Contact Info

Product

Resources

About