Development and Assessment of GIS-Based Landslide Susceptibility Mapping Models Using ANN, Fuzzy-AHP, and MCDA in Darjeeling Himalayas, West Bengal, India DOI Creative Commons
Abhik Saha, Vasanta Govind Kumar Villuri, Ashutosh Bhardwaj

et al.

Land, Journal Year: 2022, Volume and Issue: 11(10), P. 1711 - 1711

Published: Oct. 2, 2022

Landslides, a natural hazard, can endanger human lives and gravely affect the environment. A landslide susceptibility map is required for managing, planning, mitigating landslides to reduce damage. Various approaches are used susceptibility, with varying degrees of efficacy depending on methodology utilized in research. An analytical hierarchy process (AHP), fuzzy-AHP, an artificial neural network (ANN) current study construct maps part Darjeeling Kurseong West Bengal, India. On inventory map, 114 sites were randomly split into training testing 70:30 ratio. Slope, aspect, profile curvature, drainage density, lineament geomorphology, soil texture, land use cover, lithology, rainfall as model inputs. The area under curve (AUC) was examine models. When tested validation, ANN prediction performed best, AUC 88.1%. values fuzzy-AHP AHP 86.1% 85.4%, respectively. According statistics, northeast eastern portions most vulnerable. This might help development by preventing economic losses.

Language: Английский

Space–time landslide hazard modeling via Ensemble Neural Networks DOI Creative Commons
Ashok Dahal, Hakan Tanyaş, C.J. van Westen

et al.

Natural hazards and earth system sciences, Journal Year: 2024, Volume and Issue: 24(3), P. 823 - 845

Published: March 8, 2024

Abstract. Until now, a full numerical description of the spatio-temporal dynamics landslide could be achieved only via physically based models. The part geoscientific community in developing data-driven models has instead focused on predicting where landslides may occur susceptibility Moreover, they have estimate when that belong to early-warning system or rainfall-threshold classes. In this context, few published research works explored joint model structure. Furthermore, third element completing hazard definition, i.e., size (i.e., areas volumes), hardly ever been modeled over space and time. However, technological advancements reached level maturity allows all three components (Location, Frequency, Size). This work takes direction proposes for first time solution assessment given area by jointly modeling occurrences their associated areal density per mapping unit, To achieve this, we used database generated Nepalese region affected Gorkha earthquake. relies deep-learning architecture trained using an Ensemble Neural Network, densities are aggregated squared unit 1 km × classified regressed against nested 30 m lattice. At level, expressed predisposing triggering factors. As temporal units, approximately 6 month resolution. results promising as our performs satisfactorily both (AUC = 0.93) prediction (Pearson r tasks entire domain. significant distance from common literature, proposing integrated framework context.

Language: Английский

Citations

16
Exploring machine learning and statistical approach techniques for landslide susceptibility mapping in Siwalik Himalayan Region using geospatial technology DOI
Abhik Saha,

Lakshya Tripathi,

Vasanta Govind Kumar Villuri

et al.

Environmental Science and Pollution Research, Journal Year: 2024, Volume and Issue: 31(7), P. 10443 - 10459

Published: Jan. 10, 2024

Language: Английский

Citations

13
A critical review of rock failure Criteria: A scope of Machine learning approach DOI
Mohatsim Mahetaji, Jwngsar Brahma

Engineering Failure Analysis, Journal Year: 2024, Volume and Issue: 159, P. 107998 - 107998

Published: Feb. 9, 2024

Language: Английский

Citations

10
Structural characterization and attempted displacement interpretation of the Baishuihe landslide using integrated geophysical methods DOI
Kai Lu, Fan Li, Jianwei Pan

et al.

Engineering Geology, Journal Year: 2024, Volume and Issue: 336, P. 107568 - 107568

Published: May 27, 2024

Language: Английский

Citations

10
Occurrence mechanism and prevention technology of rockburst, coal bump and mine earthquake in deep mining DOI Creative Commons
Kun Du,

Ruiyang Bi,

Manoj Khandelwal

et al.

Geomechanics and Geophysics for Geo-Energy and Geo-Resources, Journal Year: 2024, Volume and Issue: 10(1)

Published: May 29, 2024

Abstract Rockburst, coal bump, and mine earthquake are the most important dynamic disaster phenomena in deep mining. This paper summarizes differences connections between rockburst, bumps earthquakes terms of definition, mechanism, phenomenon, evaluation index, etc. The definition evolution progress three categories summarized, as well monitoring, early warning, prevention measures also presented. Firstly, by combining theoretical research with specific technologies engineering field cases, main failure mechanisms introduced. Then, indexes bump a new index rockburst is given. Finally, characteristics warning methods bumps, discussed technology application. At last, future directions put forward.

Language: Английский

Citations

9
Generative deep learning for data generation in natural hazard analysis: motivations, advances, challenges, and opportunities DOI Creative Commons

Zhengjing Ma,

Gang Mei, Nengxiong Xu

et al.

Artificial Intelligence Review, Journal Year: 2024, Volume and Issue: 57(6)

Published: May 30, 2024

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

Language: Английский

Citations

9
Early warning system for landslide of gentle Piedmont slope based on displacement velocity, factor of safety, and effective rainfall threshold DOI
Liangchen Yu,

Houxu Huang,

Changhong Yan

et al.

International Journal of Disaster Risk Reduction, Journal Year: 2025, Volume and Issue: unknown, P. 105232 - 105232

Published: Jan. 1, 2025

Language: Английский

Citations

1
Analysis of seepage and hysteresis effect mechanism of unsaturated loess based on resistivity test DOI
Bo Cui,

Tianfeng Gu,

J. Wang

et al.

Journal of Hydrology, Journal Year: 2025, Volume and Issue: unknown, P. 132749 - 132749

Published: Jan. 1, 2025

Language: Английский

Citations

1
Detecting Ground Deformation in the Built Environment Using Sparse Satellite InSAR Data With a Convolutional Neural Network DOI
Nantheera Anantrasirichai, Juliet Biggs, Krisztina Kelevitz

et al.

IEEE Transactions on Geoscience and Remote Sensing, Journal Year: 2020, Volume and Issue: 59(4), P. 2940 - 2950

Published: Aug. 31, 2020

The large volumes of Sentinel-1 data produced over Europe are being used to develop pan-national ground motion services. However, simple analysis techniques like thresholding cannot detect and classify complex deformation signals reliably making providing usable information a broad range nonexpert stakeholders challenge. Here, we explore the applicability deep learning approaches by adapting pretrained convolutional neural network (CNN) in national-scale velocity field. For our proof-of-concept, focus on U.K. where previously identified is associated with coal-mining, water withdrawal, landslides, tunneling. sparsity measurement points presence spike noise make this challenging application for networks, which involve calculations spatial convolution between images. Moreover, insufficient truth exist construct balanced training set, slower more localized than previous applications. We propose three enhancement methods tackle these problems: 1) interpolation modified matrix completion; 2) synthetic set based characteristics real map; 3) enhanced overwrapping techniques. Using maps spanning 2015-2019, framework detects several areas coal mining subsidence, uplift due dewatering, slate quarries, tunnel engineering works. results demonstrate potential proposed development automated systems.

Language: Английский

Citations

65
Four‐dimensional electrical resistivity tomography for continuous, near‐real‐time monitoring of a landslide affecting transport infrastructure in British Columbia, Canada DOI Creative Commons
Jessica Holmes, Jonathan Chambers,

Philip Meldrum

et al.

Near Surface Geophysics, Journal Year: 2020, Volume and Issue: 18(4), P. 337 - 351

Published: April 14, 2020

ABSTRACT The Ripley Landslide is a small (0.04 km 2 ), slow‐moving landslide in the Thompson River Valley, British Columbia, that threatening serviceability of two national railway lines. Slope failures this area are having negative impacts on infrastructure, terrestrial and aquatic ecosystems, public safety, communities, local heritage economy. This driving need for monitoring at site, recent years there has been shift from traditional geotechnical surveys visual inspections infrastructure assets toward less invasive, lower cost, time‐intensive methods, including geophysics. We describe application novel electrical resistivity tomography system landslide. provides near‐real time geoelectrical imaging, with results delivered remotely via modem, avoiding costly repeat field visits, enabling interpretation four‐dimensional data. Here, we present alongside sensor‐derived relationships between suction, resistivity, moisture content continuous single‐frequency Global Navigation Satellite System stations. Four‐dimensional data allows us to monitor spatial temporal changes by extension, soil suction. models reveal complex hydrogeological pathways, as well considerable seasonal variation response subsurface changing weather conditions, which cannot be predicted through interrogation sensor alone, providing new insight into processes active site Landslide.

Language: Английский

Citations

55