Spatial clustering and modelling for landslide susceptibility mapping in the north of the Kathmandu Valley, Nepal

Pokharel, Badal; Althuwaynee, Omar F.; Aydda, Ali; Kim, Sang Wan; Lim, Samsung; Park, Hyuck‐Jin

doi:10.1007/s10346-020-01558-5

Cited by 38 publications

(16 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In unsupervised methods, landslide samples are grouped based on their similarity. In [14], the authors proposed an unsupervised method by utilizing six unsupervised well-known methods, including K-means, K-medoids, hierarchical cluster (HC) analysis, expectation-maximization using Gaussian mixture models (EM/GMM), affinity propagation, and mini-batch K-means, to find cluster pattern of landslides, which then acts as training data for the landslide detection problem.…”

Section: A Landslide Detectionmentioning

confidence: 99%

Integrative Few-Shot Classification and Segmentation for Landslide Detection

Tran-Anh

Bui-Quoc

et al. 2022

IEEE Access

View full text Add to dashboard Cite

There has been an ongoing demand for monitoring landslides due to the heavy economic losses and casualties caused by such natural disasters. In this paper, we introduce a swift landslide detection system that can detect and segment landslides occurring on roads. To tackle the challenges of data collection, we propose an automatic annotation procedure to create a new landslide dataset consisting of 2963 images, termed the LandslidePTIT dataset. Additionally, we construct a novel deep learning architecture that can perform both classification and segmentation tasks well from a few annotated images of landslides. Specifically, the model consists of four main modules that are delicately designed to solve the few-shot segmentation problem using landslide images, namely hypercorrelation construction, attentive squeeze block, a cross-feature layer, and broadcast and squeeze layer. Experimental results exhibit the superiority of the proposed methods in comparison with competitive baselines, in terms of both quantitative and qualitative manners.

show abstract

Section: A Landslide Detectionmentioning

confidence: 99%

Integrative Few-Shot Classification and Segmentation for Landslide Detection

Tran-Anh

Bui-Quoc

et al. 2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The SPI and TWI are two important hydrological parameters that are frequently used in the landsliderelated analysis (Nsengiyumva et al 2019, Saha andSaha 2021). The SPI denotes the erosive potential of the streams (Kumar and Anbalagan 2016) and TWI is an indicator of soil moisture contents that contribute to the occurrence of landslide (Pokharel et al 2021). Given β as the steepness of terrain and SCA as specific catchment area, Equations 1 and 2 express the formulation of these conditioning factors: For quantifying the relationship between the landslides and conditioning factors, the FR model is employed.…”

Section: Conditioning Factors and Correlation Assessmentmentioning

confidence: 99%

Landslide Susceptibility Zonation Using Statistical and Machine Learning Approaches in Northern Lecco, Italy

Mehrabi

2021

Preprint

View full text Add to dashboard Cite

This study deals with landslide susceptibility mapping in the northern part of Lecco Province, Lombardy Region, Italy. In so doing, a valid landslide inventory map and thirteen conditioning factors (including elevation, slope aspect, slope degree, plan curvature, profile curvature, distance to waterway, distance to road, distance to fault, soil type, land use, lithology, stream power index, and topographic wetness index) form the spatial database within geographic information system (GIS). The used evaluative models comprise a bivariate statistical approach called frequency ratio (FR) and two machine learning tools, namely multi-layer perceptron neural network (MLPNN) and adaptive neuro-fuzzy inference system (ANFIS). These models first use landslide and non-landslide records for comprehending the relationship between the landslide occurrence and conditioning factors. Then landslide susceptibility values are predicted for the whole area. The accuracy of the produced susceptibility maps is measured using area under the curve (AUC) index, according to which, the MLPNN (AUC = 0.916) presented the most accurate map, followed by the FR (AUC = 0. 898) and ANFIS (AUC = 0.889). Visual interpretation of the susceptibility maps, FR-based correlation analysis, as well as the importance assessment of conditioning factors, all indicated the significant contribution of the road networks to the crucial susceptibility of landslide. Lastly, an explicit predictive formula is extracted from the implemented MLPNN model for a convenient approximation of landslide susceptibility value.

show abstract

“…Diversos autores tem utilizado o método K-means para analisar dados morfométricos relacionados a deslizamentos, entre eles destacamos o trabalho de Wang et al (2017) em que utilizaram o algoritmo Kmeans para identificar combinações ideais de fatores causais de deslizamentos, e concluíram que os fatores área de captação e distância à cicatriz tiveram as menores consistências como coeficientes de informação, permitindo obter mapas de suscetibilidade a deslizamentos mais precisos usando os fatores causais. Pokharel et al (2020) testaram estratégias alternativas de amostragem com base em conceitos de distribuição de agrupamento para aumentar a eficiência dos resultados do modelo de suscetibilidade a deslizamentos, em vez do método de seleção aleatória comum para treinamento e teste de amostras. Utilizaram um inventário de deslizamento e seis algoritmos de agrupamento não supervisionados (K-médias, K-medoides, análise de agrupamento hierárquico (HC), expectativa-maximização usando modelos de mistura gaussiana (EM / GMM), propagação de afinidade e mini batch K-means) e geraram seis conjuntos de dados de treinamento diferentes.…”

Section: Discussõesunclassified

Relação entre ponto de ruptura e padrão morfométrico em deslizamentos, bacia hidrográfica do Rio Rolante - RS

et al. 2021

View full text Add to dashboard Cite

Grande parte dos deslizamentos no Brasil são relacionados a eventos pluviométricos extremos, ao tipo e espessura de solo e às características do relevo, e frequentemente causam perdas sociais e danos econômicos. O presente trabalho teve como objetivo analisar a relação entre pontos de ruptura (coroa) e parâmetros morfométricos de deslizamentos, relativos a um evento hidrometeorológico extremo, na bacia hidrográfica do Rio Rolante - RS. A partir de imagens SRTM 30m, foram obtidos dados de declividade, elevação, curvatura horizontal e vertical e aspecto. Com base no mapeamento foram obtidos 143 pontos de ruptura em cicatrizes de deslizamentos. Utilizando agrupamento K-means foram identificados padrões morfométricos relacionados aos pontos de ruptura, e gerados perfis de vertentes. Os resultados mostram 4 tipos de vertentes na bacia do rio Rolante, com ocorrência de processos de deslizamentos. Perfis côncavos e convergentes tiveram menor ocorrência, e perfis convexos e divergentes apresentaram maior ocorrência. Com base nas médias dos principais agrupamentos de clusters, a declividade e as curvaturas tiveram a maior importância em relação à localização das rupturas na vertente, e foram importantes condicionantes de suscetibilidade aos deslizamentos. As médias dos agrupamentos ocorreram acima de 30º de declividade no agrupamento com 4 clusters, que foi o mais representativo.

show abstract

Spatial clustering and modelling for landslide susceptibility mapping in the north of the Kathmandu Valley, Nepal

Cited by 38 publications

References 66 publications

Integrative Few-Shot Classification and Segmentation for Landslide Detection

Integrative Few-Shot Classification and Segmentation for Landslide Detection

Landslide Susceptibility Zonation Using Statistical and Machine Learning Approaches in Northern Lecco, Italy

Relação entre ponto de ruptura e padrão morfométrico em deslizamentos, bacia hidrográfica do Rio Rolante - RS

Contact Info

Product

Resources

About