Identification of rock discontinuities by coda wave analysis while borehole drilling in deep buried tunnels

L Liu, S Li, M Zheng, Y Wang, J Shen, Z Shi… - … and Underground Space …, 2024‏ - Elsevier
Rock discontinuities are widely and randomly developed in deep buried tunnels and have a
profound impact on construction safety, support design, and geological hazard prevention …

Automatic fracture detection from the images of electrical image logs using Mask R-CNN

L Du, X Lu, H Li - Fuel, 2023‏ - Elsevier
This paper presents a novel approach for automatically detecting fractures from electrical
image logs using a state-of-the-art object detection and segmentation method, ie, the Mask …

Svalbox digital model database: a geoscientific window into the high Arctic

P Betlem, N Rodés, T Birchall, A Dahlin… - …, 2023‏ - pubs.geoscienceworld.org
Digital outcrop models (DOMs) have revolutionized the way twenty-first century geoscientists
work. DOMs are georeferenced three-dimensional (3-D) digital representations of outcrops …

A deep learning object detection method for fracture identification using conventional well logs

S Dong, J Hao, L Zeng, X Yang, L Wang… - … on Geoscience and …, 2024‏ - ieeexplore.ieee.org
Reservoir characterization struggles with identifying fractures, a typical imbalance
classification problem. To handle this issue, a novel approach called fracture identification …

Geocrack: A high-resolution dataset for segmentation of fracture edges in geological outcrops

M Yaqoob, M Ishaq, MY Ansari, VRS Konagandla… - Scientific Data, 2024‏ - nature.com
GeoCrack is the first large-scale open source annotated dataset of fracture traces from
geological outcrops, enabling deep learning-based fracture segmentation, setting a new …

Sediment grain segmentation in thin-section images using dual-modal Vision Transformer

D Zheng, L Hou, X Hu, M Hou, K Dong, S Hu… - Computers & …, 2024‏ - Elsevier
Accurately identifying grain types in thin sections of sandy sediments or sandstones is
crucial for understanding their provenance, depositional environments, and potential as …

Intelligent identification and segmentation of fractures in images of ultrasonic image logging based on transfer learning

C Li, C Zou, C Peng, X Lan, YY Zhang - Fuel, 2024‏ - Elsevier
Ultrasonic imaging well logging is an oil and gas exploration technique that provides visual
identification of reservoir fractures. It holds significant importance in accurately predicting …

Fracture analyser: a Python toolbox for the 2D analysis of fracture patterns

L Borghini, G Striglio, G Bacchiani… - Italian Journal of …, 2024‏ - pubs.geoscienceworld.org
Fractures are the most common result of rock brittle failure in the Earth's crust. Their
presence, distribution, orientation, and interconnection are some of the main parameters that …

Intelligent recognition and identification of fracture types and parameters for borehole images based on developed convolutional neural networks and post-processing

C Liu, J Kim, JJ Song, X Zheng, NM Shahani… - Engineering Fracture …, 2023‏ - Elsevier
Borehole imaging is one of the main methods for fracture observation in the rock formations,
but there is still a lack of identification systems for deriving fracture parameters from borehole …

Automatic borehole fracture detection and characterization with tailored Faster R-CNN and simplified Hough transform

S Han, X **ao, B Song, T Guan, Y Zhang… - Engineering Applications of …, 2023‏ - Elsevier
Understanding the geological information of fractures from borehole images is essential for
conducting a thorough geological analysis in engineering. Recently, the convolutional …