Strategy of oversampling geotechnical parameters through geostatistical, SMOTE, and CTGAN methods for assessing susceptibility of landslide

Min, Dae-Hong; Kim, YoungSeok; Kim, Sewon; Yoon, Hyung-Koo

doi:10.1007/s10346-023-02166-9

Cited by 2 publications

(1 citation statement)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Indeed, a proper rainfall infiltration analysis requires knowledge of the saturated and unsaturated soil properties of all the materials involved in the seepage process [44]. In addition, the geotechnical characteristics of the soil are of paramount importance for any kind of slope stability analysis, landslide susceptibility mapping, and/or the establishment of rainfall intensity-duration thresholds [5,[45][46][47][48]. In the literature, a great deal of effort has been devoted to the investigation of the geotechnical and hydrological properties of rather homogeneous soils, both for fine-grained soils [49] and coarse-grained soils [50][51][52][53].…”

Section: Introductionmentioning

confidence: 99%

Geotechnical Characterisation of Flysch-Derived Colluvial Soils from a Pre-Alpine Slope Affected by Recurrent Landslides

Del Fabbro,

Paronuzzi,

Bolla

2024

Geosciences

View full text Add to dashboard Cite

Heterogeneous rock masses that include rhythmic alternations of marl, shale, marly limestone, sandstone, siltstone, and argillite, such as Flysch, are particularly prone to generating colluvial deposits on gentle slopes, which are often subject to failures triggered by heavy rainfall. Flysch-derived colluvial soils are made up of highly heterogeneous sediments ranging from clayey loam to rock fragments, and they have been studied more rarely than homogeneous soils. In this work, we present a geotechnical and hydraulic characterisation performed both in situ and in the laboratory on flysch-derived colluvial soils that were involved in a channelised landslide in the pre-alpine area of the Friuli Venezia Giulia region (NE Italy). The investigated soils were characterised by the average values of the grain size composition of about 25% gravel, 20% sand, 30% silt, and 25% clay. The loamy matrix presented low-to-medium values of the liquid and plastic limits, as well as of the plasticity index (LL = 40%, PL = 23%, and PI = 17%, respectively). The values of the peak friction angle for natural intact samples were 33° < ϕ’p < 38°, whereas the residual friction angle fell to 23–24° at great depths and high vertical stresses, for a prevailing silty–clayey matrix. Variable head permeability tests were performed both in situ and in the laboratory, showing that the values of the vertical and horizontal permeability were very close and in the range 1 × 10−4–1 × 10−6 m/s. The soil permeability measured in the field was generally higher than the hydraulic conductivity calculated on laboratory samples. The proposed geotechnical and hydrological characterisation of flysch-derived colluvial soils can be of fundamental importance before the use of more thorough analyses/models aimed at forecasting the possible occurrence of slope failures and evaluating the related landslide hazard. The reported geotechnical and hydraulic parameters of flysch-derived colluvial materials can represent a useful reference for rainfall infiltration modelling and slope stability analyses of colluvial covers that are subject to intense and/or prolonged precipitation. However, when facing engineering problems involving colluvial soils, particularly those coming from flysch rock masses, the intrinsic variability in their grain size composition, consistency, and plasticity characteristics is a key feature and attention should be paid to the proper assumption of the corresponding geotechnical and hydraulic parameters.

show abstract

Section: Introductionmentioning

confidence: 99%

Geotechnical Characterisation of Flysch-Derived Colluvial Soils from a Pre-Alpine Slope Affected by Recurrent Landslides

Del Fabbro,

Paronuzzi,

Bolla

2024

Geosciences

View full text Add to dashboard Cite

show abstract

Generative deep learning for data generation in natural hazard analysis: motivations, advances, challenges, and opportunities

Ma,

Mei,

2024

Artif Intell Rev

View full text Add to dashboard Cite

Data mining and analysis are critical for preventing or mitigating natural hazards. However, data availability in natural hazard analysis is experiencing unprecedented challenges due to economic, technical, and environmental constraints. Recently, generative deep learning has become an increasingly attractive solution to these challenges, which can augment, impute, or synthesize data based on these learned complex, high-dimensional probability distributions of data. Over the last several years, much research has demonstrated the remarkable capabilities of generative deep learning for addressing data-related problems in natural hazards analysis. Data processed by deep generative models can be utilized to describe the evolution or occurrence of natural hazards and contribute to subsequent natural hazard modeling. Here we present a comprehensive review concerning generative deep learning for data generation in natural hazard analysis. (1) We summarized the limitations associated with data availability in natural hazards analysis and identified the fundamental motivations for employing generative deep learning as a critical response to these challenges. (2) We discuss several deep generative models that have been applied to overcome the problems caused by limited data availability in natural hazards analysis. (3) We analyze advances in utilizing generative deep learning for data generation in natural hazard analysis. (4) We discuss challenges associated with leveraging generative deep learning in natural hazard analysis. (5) We explore further opportunities for leveraging generative deep learning in natural hazard analysis. This comprehensive review provides a detailed roadmap for scholars interested in applying generative models for data generation in natural hazard analysis.

show abstract

Strategy of oversampling geotechnical parameters through geostatistical, SMOTE, and CTGAN methods for assessing susceptibility of landslide

Cited by 2 publications

References 44 publications

Geotechnical Characterisation of Flysch-Derived Colluvial Soils from a Pre-Alpine Slope Affected by Recurrent Landslides

Geotechnical Characterisation of Flysch-Derived Colluvial Soils from a Pre-Alpine Slope Affected by Recurrent Landslides

Generative deep learning for data generation in natural hazard analysis: motivations, advances, challenges, and opportunities

Contact Info

Product

Resources

About