Landslide susceptibility prediction using slope unit-based machine learning models considering the heterogeneity of conditioning factors

Journal of Rock Mechanics and Geotechnical Engineering, Journal Year: 2022, Volume and Issue: 15(5), P. 1127 - 1143

Published: Aug. 11, 2022

To perform landslide susceptibility prediction (LSP), it is important to select appropriate mapping unit and landslide-related conditioning factors. The efficient automatic multi-scale segmentation (MSS) method proposed by the authors promotes application of slope units. However, LSP modeling based on these units has not been performed. Moreover, heterogeneity factors in neglected, leading incomplete input variables modeling. In this study, extracted MSS are used construct modeling, represented internal variations within using descriptive statistics features mean, standard deviation range. Thus, units-based machine learning models considering (variant slope-machine learning) proposed. Chongyi County selected as case study divided into 53,055 Fifteen original unit-based expanded 38 through their variations. Random forest (RF) multi-layer perceptron (MLP) variant Slope-RF Slope-MLP models. Meanwhile, without factors, conventional grid (Grid-RF MLP) built for comparisons performance assessments. Results show that Slope-machine have higher performances than models; results stronger directivity practical Grid-machine It concluded can be more comprehensively reflect relationships between landslides. research reference significance land use prevention.

Language: Английский

---

Fiber optic monitoring of an anti-slide pile in a retrogressive landslide

Journal of Rock Mechanics and Geotechnical Engineering, Journal Year: 2023, Volume and Issue: 16(1), P. 333 - 343

Published: March 17, 2023

Anti-slide piles are one of the most important reinforcement structures against landslides, and evaluating working conditions is great significance for landslide mitigation. The widely adopted analytical methods pile internal forces include cantilever beam method elastic foundation method. However, due to many assumptions involved in calculation, models cannot be fully applicable complex site situations, e.g. landslides with multi-sliding surfaces pile-soil interface separation as discussed herein. In view this, combination distributed fiber optic sensing (DFOS) strain-internal force conversion was proposed evaluate an anti-sliding a typical retrogressive Three Gorges reservoir area, China. Brillouin optical time domain reflectometry (BOTDR) utilized monitor strain distribution along pile. Next, by analyzing relative deformation between its adjacent inclinometer, profiled. Finally, anti-slide were derived based on According ratio calculated design values, could evaluated. results demonstrated that reveal pattern system, can quantitatively conditions.

Language: Английский

---

Characterization of sliding surface deformation and stability evaluation of landslides with fiber–optic strain sensing nerves

Engineering Geology, Journal Year: 2023, Volume and Issue: 314, P. 107011 - 107011

Published: Jan. 14, 2023

Language: Английский

---

Shear deformation calculation of landslide using distributed strain sensing technology considering the coupling effect

Landslides, Journal Year: 2023, Volume and Issue: 20(8), P. 1583 - 1597

Published: April 14, 2023

Language: Английский

---

Detecting pipeline leakage using active distributed temperature Sensing: Theoretical modeling and experimental verification

Tunnelling and Underground Space Technology, Journal Year: 2023, Volume and Issue: 135, P. 105065 - 105065

Published: March 2, 2023

Language: Английский

---

State-of-the-art review on the use of AI-enhanced computational mechanics in geotechnical engineering

Artificial Intelligence Review, Journal Year: 2024, Volume and Issue: 57(8)

Published: July 5, 2024

Abstract Significant uncertainties can be found in the modelling of geotechnical materials. This attributed to complex behaviour soils and rocks amidst construction processes. Over past decades, field has increasingly embraced application artificial intelligence methodologies, thus recognising their suitability forecasting non-linear relationships intrinsic review offers a critical evaluation AI methodologies incorporated computational mechanics for engineering. The analysis categorises four pivotal areas: physical properties, mechanical constitutive models, other characteristics relevant Among various analysed, ANNs stand out as most commonly used strategy, while methods such SVMs, LSTMs, CNNs also see significant level application. widely algorithms are Artificial Neural Networks (ANN), Random Forest (RF), Support Vector Machines (SVM), representing 35%, 19%, 17% respectively. extensive is domain accounting 59%, followed by applications at 16%. efficacy intrinsically linked type datasets employed, selected model input. study outlines future research directions emphasising need integrate physically guided adaptive learning mechanisms enhance reliability adaptability addressing multi-scale multi-physics coupled problems geotechnics.

Language: Английский

---

A review of previous studies on the applications of fiber optic sensing technologies in geotechnical monitoring

Rock Mechanics Bulletin, Journal Year: 2022, Volume and Issue: 2(1), P. 100021 - 100021

Published: Nov. 25, 2022

Geotechnical engineering is characterized by many uncertainties, including soil material properties, environmental effects, and design construction, which bring a significant challenge to geotechnical monitoring. However, conventional sensors with several inherent limitations, such as electromagnetic interference, signal loss in long-distance transmission, low durability harsh environments cannot fully meet current monitoring needs. Recently, fiber optic sensing technologies have been successfully applied due the advantages of anti-electromagnetic stable high durability, sensitivity, lightweight, can be considered an ideal replacement for sensors. In this paper, working principle different technologies, development optic-based sensors, recent application status these were comprehensively reviewed discussed detail. Finally, challenges countermeasures also presented discussed.

Language: Английский

---

A Review of Hydromechanical Coupling Tests, Theoretical and Numerical Analyses in Rock Materials

Water, Journal Year: 2023, Volume and Issue: 15(13), P. 2309 - 2309

Published: June 21, 2023

The hydromechanical coupling behavior of rocks is widely present in the fields rock mechanics and engineering studies. Analyzing summarizing relevant literature, current status experimental theory research on systematically described, commonly used numerical simulation methods their applications are briefly introduced, problems mining engineering, water conservancy, hydropower slope tunneling other analyzed. Regarding studies rocks, test aspect needs to further enhance triaxial shear permeability material, adopt a combination macroscopic, fine, microscopic study hydraulic materials from different scales. To couple theory, traditional concepts broken through, new theories mathematical models explain solve practical problems. Meanwhile, application interdisciplinary approaches solving future emphasized. In terms applications, large data algorithms developed improve efficiency calculations. addition, consideration should be given effects, coupled rheological dynamic properties masses under high-ground stress high pressure.

Language: Английский

---

Fiber optic sensing and performance evaluation of a water conveyance tunnel with composite linings under super-high internal pressures

Journal of Rock Mechanics and Geotechnical Engineering, Journal Year: 2023, Volume and Issue: 15(8), P. 1997 - 2012

Published: April 15, 2023

For long-distance water conveyance shield tunnels in operation, the high internal pressure may cause excessive deformation of composite linings, affecting their structural integrity and serviceability. However, failure characteristics lining structures under are not well investigated literature, particularly for three-layer linings. This study presents an situ experimental investigation on response two types linings (i.e. separated combined structures) subjected to pressures, which a fiber optic nerve system (FONS) equipped with distributed strain displacement sensing nerves was employed monitor performance during testing. The results clearly show that damage tunnel different pressures mainly located self-compaction concrete layer. structure responded more aggressively variations than one. Moreover, evaluation indices, i.e. radial effective stiffness coefficient, proposed describing changes bearing performance. coefficients were reduced by 39.4% 29.5%, respectively. Considering convenience field monitoring, it is suggested average strains at layers can be used as characteristic parameters estimating health conditions service. analysis provide practical reference design

Language: Английский

---

Experimental study on the deformation and failure mechanism of overburden rock during coal mining using a comprehensive intelligent sensing method

Journal of Rock Mechanics and Geotechnical Engineering, Journal Year: 2022, Volume and Issue: 14(5), P. 1626 - 1641

Published: Sept. 5, 2022

Understanding the spatiotemporal evolution of overburden deformation during coal mining is still a challenge in engineering practice due to limitation monitoring techniques. Taking Yangliu Coal Mine as an example, similarity model test was designed and conducted investigate failure mechanism overlying rocks this study. Distributed fiber optic sensing (DFOS), high-density electrical resistivity tomography (HD-ERT) close-range photogrammetry (CRP) technologies were used for comprehensive analyses. The combined use three methods facilitates investigation characteristics deformation, showing that mining-induced strata dynamic process. This process accompanied by formation, propagation, closure redevelopment separation cracks. Moreover, key rock stratum with high strength high-quality lithology played crucial role whole deformation. There generally modes layers, including bending tension, overall shearing, shearing sliding. Shear often leads falling off blocks, which poses serious threat safety. Therefore, real-time accurate great significance safe underground seams.

Language: Английский

---