Results 111 to 120 of about 6,140 (264)

Probabilistic prediction of rate‐dependent rock strength using natural gradient boosting and Gaussian process regression

Deep Underground Science and Engineering, EarlyView.
Probabilistic natural gradient boosting and Gaussian process regression models accurately predict rate‐dependent rock strength across lithologies. Static strength and strain rate dominate, while geometric factors have minimal influence, enabling interpretable and uncertainty‐aware predictions for dynamic geomechanical applications. Abstract The dynamic
Hadi Fathipour‐Azar
wiley   +1 more source

Rock mechanical properties under reconstructed deep in situ thermo–hydro–mechanical conditions: Implications for CO₂‐related injection scenarios

Deep Underground Science and Engineering, EarlyView.
The graphical abstract illustrates a reconstructed in situ thermo‐hydro‐mechanical (THM) framework in which porosity serves as the central variable linking stress, pore pressure, and temperature to evolving mechanical properties of rocks. Under burial conditions, in situ stress, pore pressure, and temperature jointly govern volumetric strain and ...
Mingyuan Lu, Jun Wang, Zixiong Qi, Ruixuan Chen, Hongtao Wang, Hongwei Zhou   +5 more
wiley   +1 more source

Explainable hybrid stacking ensemble method for hard rock pillar stability prediction and engineering applications

Deep Underground Science and Engineering, EarlyView.
This research proposes an interpretable hybrid stacking ensemble framework, optimized by the Sparrow Search Algorithm, to enhance hard rock pillar stability prediction. By integrating six machine learning models—k‐nearest neighbors, support vector machines, random forests, Gradient Boosting Decision Tree, eXtreme Gradient Boosting, and Light Gradient ...
Ning Wang, Guoyan Zhao, Meng Wang, Taraka Pattela   +3 more
wiley   +1 more source

TAMNet: Temporal and adaptive‐frequency network with MixStyle for cross‐region oil and fluid production forecasting

Deep Underground Science and Engineering, EarlyView.
This paper presents temporal and adaptive‐frequency network with MixStyle (TAMNet), a deep time‐series modeling framework for accurate and robust multi‐well oil productivity forecasting. TAMNet integrates transformer and long short‐term memory architectures to capture both short‐ and long‐term temporal dependencies, enhanced by a temporal gate unit ...
Chunxi Yang, Leifeng Meng, Qinghu Fan, Ziang Guo, Ting Bao, Pingdong Zhong, Fulin Luo   +6 more
wiley   +1 more source

Investigation on the failure evolution characteristics of surrounding rock in deep cross‐fault roadway: Based on physical model test and numerical simulation

Deep Underground Science and Engineering, EarlyView.
This study reveals the failure evolution characteristics of deep cross‐fault roadway surrounding rock under excavation support and periodic weighting. Periodic weighting readily induces fault activation, with the spatial distribution of failed rock masses being controlled by the fault strike and dip.
Tiezhu Li, Suping Peng, Jing Zheng, Zhanhua Yang, Qijun Tian   +4 more
wiley   +1 more source

Experimental and smoothed particle hydrodynamics‐finite element method simulation investigation of synergistic erosion mechanism of gangue‐based abrasive water jets

Deep Underground Science and Engineering, EarlyView.
This study proposes an eco‐friendly coal permeability enhancement technique by utilizing mine waste gangue as an abrasive in high‐pressure water jets. Integrating erosion experiments with smoothed particle hydrodynamics‐finite element method coupled simulations, the research study elucidates the flow field dynamics and a nonlinear solid–liquid ...
Qingxiang Wang, Jiaxu Tang, Qiheng Ren, Ding Wang, Tong Wang   +4 more
wiley   +1 more source

Role of tectonic stress and topography on repeated lateral dikes: application to the 1975-1984 Krafla and 2023-2025 Svartsengi rifting episodes in Iceland. [PDF]

Bull Volcanol
Yang Y, Sigmundsson F, Geirsson H, Gottsmann J.   +3 more
europepmc   +1 more source

Combination of CO 2 ${\text{CO}}_{2}$ storage and geothermal energy production in porous and fractured superhot geothermal systems

Deep Underground Science and Engineering, EarlyView.
The graphical abstract depicts the workflow for porous‐ and fractured‐media simulations, where stochastically generated discrete natural fractures are required for the fracture‐media simulation. Abstract CO 2 ${\text{CO}}_{2}$ leakage is one of the main risks and barriers to geologic carbon storage. However, under the high‐temperature and high‐pressure
Christoph Scherounigg, Rotman Criollo, Victor Vilarrasa, Keita Yoshioka   +3 more
wiley   +1 more source

Multi‐factor coupling effects in hydraulic fracturing of laminated shale: Experimental insights and physics‐informed neural network‐driven optimization

Deep Underground Science and Engineering, EarlyView.
This study establishes a multi‐factor coupling framework for predicting breakdown pressure in laminated shale by integrating experimental hydraulic fracturing tests, physics‐informed neural networks (PINNs), and Sobol sensitivity analysis. It reveals how differential stress, the bedding dip angle, and the injection rate interact to influence fracture ...
Tao Wang, Guoyao Xu, Liyuan Liu, Yao Zhang, Sitao Zhu, Hongyang Chu, Kaikai Zhao   +6 more
wiley   +1 more source

Study on failure mechanism and energy dissipation law of single fissured coal in different tectonic stress areas. [PDF]

Sci Rep
Lan T, Liu Y, Wang F, Wu G, Li Z, Ling X, Zhang C, Liu G, Feng W.   +8 more
europepmc   +1 more source