A graph deep learning method for landslide displacement prediction based on global navigation satellite system positioning DOI Creative Commons
Chuan Yang,

Yue Yin,

Jiantong Zhang

et al.

Geoscience Frontiers, Journal Year: 2023, Volume and Issue: 15(1), P. 101690 - 101690

Published: Aug. 22, 2023

The accurate prediction of displacement is crucial for landslide deformation monitoring and early warning. This study focuses on a in Wenzhou Belt Highway proposes novel multivariate method that relies graph deep learning Global Navigation Satellite System (GNSS) positioning. First model the structure system based engineering positions GNSS points build adjacent matrix nodes. Then construct historical predicted time series feature matrixes using processed temporal data including displacement, rainfall, groundwater table soil moisture content structure. Last introduce state-of-the-art GTS (Graph Time Series) to improve accuracy reliability which utilizes temporal-spatial dependency system. approach outperforms previous studies only learned features from single point maximally weighs performance priori proposed performs better than SVM, XGBoost, LSTM DCRNN models terms RMSE (1.35 mm), MAE (1.14 mm) MAPE (0.25) evaluation metrics, provided be effective future failure

Language: Английский

Physics-informed deep learning method for predicting tunnelling-induced ground deformations DOI
Zilong Zhang, Qiujing Pan, Zihan Yang

et al.

Acta Geotechnica, Journal Year: 2023, Volume and Issue: 18(9), P. 4957 - 4972

Published: April 14, 2023

Language: Английский

Citations

53
Data augmentation for CNN-based probabilistic slope stability analysis in spatially variable soils DOI
Shui‐Hua Jiang,

Guang-Yuan Zhu,

Ze Zhou Wang

et al.

Computers and Geotechnics, Journal Year: 2023, Volume and Issue: 160, P. 105501 - 105501

Published: May 9, 2023

Language: Английский

Citations

52
Efficient machine learning method for evaluating compressive strength of cement stabilized soft soil DOI
Chen Zhang, Zhiduo Zhu, Fa Liu

et al.

Construction and Building Materials, Journal Year: 2023, Volume and Issue: 392, P. 131887 - 131887

Published: May 24, 2023

Language: Английский

Citations

46
A systematic review and meta-analysis of artificial neural network, machine learning, deep learning, and ensemble learning approaches in field of geotechnical engineering DOI Creative Commons
Elaheh Yaghoubi, Elnaz Yaghoubi, Ahmed A. Khamees

et al.

Neural Computing and Applications, Journal Year: 2024, Volume and Issue: 36(21), P. 12655 - 12699

Published: May 13, 2024

Abstract Artificial neural networks (ANN), machine learning (ML), deep (DL), and ensemble (EL) are four outstanding approaches that enable algorithms to extract information from data make predictions or decisions autonomously without the need for direct instructions. ANN, ML, DL, EL models have found extensive application in predicting geotechnical geoenvironmental parameters. This research aims provide a comprehensive assessment of applications addressing forecasting within field related engineering, including soil mechanics, foundation rock environmental geotechnics, transportation geotechnics. Previous studies not collectively examined all algorithms—ANN, EL—and explored their advantages disadvantages engineering. categorize address this gap existing literature systematically. An dataset relevant was gathered Web Science subjected an analysis based on approach, primary focus objectives, year publication, geographical distribution, results. Additionally, study included co-occurrence keyword covered techniques, systematic reviews, review articles data, sourced Scopus database through Elsevier Journal, were then visualized using VOS Viewer further examination. The results demonstrated ANN is widely utilized despite proven potential methods engineering due real-world laboratory civil engineers often encounter. However, when it comes behavior scenarios, techniques outperform three other methods. discussed here assist understanding benefits geo area. enables practitioners select most suitable creating certainty resilient ecosystem.

Language: Английский

Citations

20
Trustworthy data-centric geotechnics DOI Creative Commons
Kok‐Kwang Phoon

Geodata and AI., Journal Year: 2025, Volume and Issue: unknown, P. 100008 - 100008

Published: Feb. 1, 2025

Language: Английский

Citations

2
Unpacking data-centric geotechnics DOI Creative Commons
Kok‐Kwang Phoon, Jianye Ching,

Zi-Jun Cao

et al.

Underground Space, Journal Year: 2022, Volume and Issue: 7(6), P. 967 - 989

Published: July 1, 2022

The purpose of this paper (presented online as a keynote lecture at the 25th Annual Indonesian Geotechnical Conference on 10 Nov 2021) is to broadly conceptualize agenda for data-centric geotechnics, an emerging field that attempts prepare geotechnical engineering digital transformation. must include (1) development methods make sense all real-world data (not selective input physical model), (2) offering insights significant value critical decisions current or future practice ideal world minor concern engineers), and (3) sensitivity context geotechnics abstract data-driven analysis connected in peripheral way, i.e., engagement with knowledge experience base should be substantial). These three elements are termed “data centricity”, “fit (and transform) practice”, “geotechnical context” agenda. Given site central any project, characterization (DDSC) constitute one key application domain although other infrastructure lifecycle phases such project conceptualization, design, construction, operation, decommission/reuse would benefit from data-informed decision support well. One part DDSC addresses numerical soil investigation report property databases pursued under Project DeepGeo. In principle, source can also go beyond investigation, type numbers, categorical data, text, audios, images, videos, expert opinion. DeepGeo produce 3D stratigraphic map subsurface volume below full-scale estimate relevant properties each spatial point based actual Big Indirect Data (BID). Uncertainty quantification necessary, insufficient, incomplete, and/or not directly construct deterministic map. debatable. computational cost do true scale reasonable. Ultimately, structures need completely smart fits circular economy focus delivering service end-users community conceptualization full integration city society. Although has been very successful taking “calculated risk” informed by limited imperfect theories, prototype testing, observations, among others exercising judicious caution judgment, there no clear pathway forward leverage big technologies machine learning, BIM, twin meet more challenging needs sustainability resilience engineering.

Language: Английский

Citations

64
A new index for cutter life evaluation and ensemble model for prediction of cutter wear DOI Open Access
Nan Zhang, Shui‐Long Shen, Annan Zhou

et al.

Tunnelling and Underground Space Technology, Journal Year: 2022, Volume and Issue: 131, P. 104830 - 104830

Published: Nov. 14, 2022

Language: Английский

Citations

52
Novel hybrid MFO-XGBoost model for predicting the racking ratio of the rectangular tunnels subjected to seismic loading DOI
Van‐Quang Nguyen, Viet‐Linh Tran, Duy‐Duan Nguyen

et al.

Transportation Geotechnics, Journal Year: 2022, Volume and Issue: 37, P. 100878 - 100878

Published: Oct. 8, 2022

Language: Английский

Citations

40
Smart prediction of liquefaction-induced lateral spreading DOI Creative Commons
Muhammad Nouman Amjad Raja,

Tarek Abdoun,

Waleed El-Sekelly

et al.

Journal of Rock Mechanics and Geotechnical Engineering, Journal Year: 2023, Volume and Issue: 16(6), P. 2310 - 2325

Published: Sept. 5, 2023

The prediction of liquefaction-induced lateral spreading/displacement (Dh) is a challenging task for civil/geotechnical engineers. In this study, new approach proposed to predict Dh using gene expression programming (GEP). Based on statistical reasoning, individual models were developed two topographies: free-face and gently sloping ground. Along with comparison conventional approaches predicting the Dh, four additional regression-based soft computing models, i.e. Gaussian process regression (GPR), relevance vector machine (RVM), sequential minimal optimization (SMOR), M5-tree, compared GEP model. results indicate that less bias, as evidenced by root mean square error (RMSE) absolute (MAE) training (i.e. 1.092 0.815; 0.643 0.526) testing 0.89 0.705; 0.773 0.573) in ground topographies, respectively. overall performance topology was ranked follows: > RVM M5-tree GPR SMOR, total score 40, 32, 24, 15, 10, For condition, SMOR 21, 19, 8, Finally, sensitivity analysis showed both ground, liquefiable layer thickness (T15) major parameter percentage deterioration (%D) value 99.15 90.72,

Language: Английский

Citations

33
Data-driven and physics-informed Bayesian learning of spatiotemporally varying consolidation settlement from sparse site investigation and settlement monitoring data DOI

Hua-Ming Tian,

Yu Wang

Computers and Geotechnics, Journal Year: 2023, Volume and Issue: 157, P. 105328 - 105328

Published: Feb. 25, 2023

Language: Английский

Citations

30