Search

Fracture Index (FI), which represents the count of fractures over an arbitrary length of core with similar intensity of fracturing, provides insight into the fracture state of rock masses. Manual interpretation of core is not only time-consuming but also prone to human error. To address these challenges, this study develops a computational algorithm that automatically calculates the FI of core runs based on fracture spacing data. The variance of fracture spacing values is selected as the key evaluating indicator. The algorithm automatically groups fractures appearing in core imagery based on uniformity of fracture spacing. Upon counting the number of fractures in each group over a certain length of core run obtained from the optimal grouping scheme, the algorithm outputs the FIs automatically. The algorithm's performance has been effectively demonstrated on synthetic data and three real-life core datasets. Algorithm results show good agreement with those produced by logging geologists and listed in standard human-generated reports. The occasional discrepancies are attributed to the inherent subjective nature associated with the manual logging. Highlights: The definition of fracture index in various standards and guidelines is reviewed. An algorithm for calculating the fracture index of core runs is proposed. The algorithm's application is demonstrated through three examples, yielding satisfactory results. Subjective judgement in manual logging accounts for the differences between algorithmic and traditional manual methods. [ABSTRACT FROM AUTHOR]

Rock classification provides vital information to geosciences and geological engineering practices. Reaping the benefits of the advances of computer vision-based deep learning artificial intelligence (AI) technology, this study aims to develop a next-generation convolutional neural network (CNN) to perform automatic rock classification. Two major challenging issues have been particularly addressed. First, most of the previous rock classifications are simply transfer learning of CNNs that are trained by life-like scenarios. Second, classifying rock types with similar textures leads to severe overfitting of CNNs. In this study, a novel CNN called HKUDES_Net is proposed and implemented to classify seven common Hong Kong rock types, namely fine-grained granite, medium-grained granite, coarse-grained granite, coarse ash tuff, fine ash tuff, feldsparphyric rhyolite, and granodiorite. With the aid of dynamic expansion, squeeze and excitation, and other strategies, HKUDES_Net can classify rock types with similar texture patterns/colors but different grain sizes. As compared with the other ten landmark CNNs and seven feature-based algorithms, HKUDES_Net has the best performance in precision (90.9%), recall (90.4%), and f1-score (90.5%). By implementing the alerting level, which restricts the training loss hovering above a small constant and prevents the validation loss from rising, the overfitting has been efficiently eliminated. The proposal and implementation of HKUDES_Net highlight the value of interdisciplinary research and will continuously pave the way for better coupling AI and geosciences. Highlights: A next-generation convolutional neural network (CNN) called HKUDES_Net is developed to perform automatic rock classification. HKUDES_Net can classify rock types with similar texture patterns/colors but different grain sizes. By implementing the alerting level in HKUDES_Net, the overfitting has been efficiently eliminated. Plain Language Summary: Rock classification provides vital information to geosciences and geological engineering practices. However, the traditional way of rock classification is to a certain degree experience-based. Computer vision-based artificial intelligence (AI), especially convolutional neural network (CNN), a sub-branch of AI, may help people automatically classify rock types with the hope to train AI models (CNNs), which can instantly and precisely perceive rock images similar to how human beings observe rocks. In other words, by putting a rock image into a CNN, the CNN will read the information from the image and tell people what rock type in the image is. This study develops and implements a next-generation CNN called HKUDES_Net to classify seven different rock types. Adopting different computational strategies, HKUDES_Net can classify rock types of different grain sizes with similar texture patterns/colors, which is challenging for other CNNs. As compared with the other landmark CNNs and machine learning algorithms, HKUDES_Net has much a better prediction accuracy performance. The proposal and implementation of HKUDES_Net exemplify an interdisciplinary research study, and we are confident that this paper will be instrumental to pave the way for further coupling AI and geosciences. [ABSTRACT FROM AUTHOR]

Rock classification provides vital information to geosciences and geological engineering practices. Reaping the benefits of the advances of computer vision-based deep learning artificial intelligence (AI) technology, this study aims to develop a next-generation convolutional neural network (CNN) to perform automatic rock classification. Two major challenging issues have been particularly addressed. First, most of the previous rock classifications are simply transfer learning of CNNs that are trained by life-like scenarios. Second, classifying rock types with similar textures leads to severe overfitting of CNNs. In this study, a novel CNN called RockNet is proposed and implemented to classify seven common Hong Kong rock types, namely fine-grained granite, medium-grained granite, coarse-grained granite, coarse ash tuff, fine ash tuff, feldspar phyric rhyolite, and granodiorite. With the aid of dynamic expansion, squeeze and excitation, and other strategies, RockNet can classify rock types with similar texture patterns/colors but different grain sizes. As compared with the other ten landmark CNNs and seven feature-based algorithms, RockNet has the best performance in precision (90.9%), recall (90.4%), and f1-score (90.5%). By implementing the alerting level, which restricts the training loss hovering above a small constant, and prevents the validation loss from rising, the overfitting has been efficiently eliminated. The proposal and implementation of RockNet highlight the value of interdisciplinary research and will continuously pave the way for better coupling AI and geosciences. Highlights: A next-generation convolutional neural network (CNN) called RockNet is developed to perform automatic rock classification. RockNet can classify rock types with similar texture patterns/colors but different grain sizes. By implementing the alerting level in RockNet, the overfitting has been efficiently eliminated. Plain Language Summary: Rock classification provides vital information to geosciences and geological engineering practices. However, the traditional way of rock classification is to a certain degree experience-based. Computer vision-based artificial intelligence (AI), especially convolutional neural network (CNN), a sub-branch of AI, may help people automatically classify rock types with the hope to train AI models (CNNs), which can instantly and precisely perceive rock images similar to how human beings observe rocks. In other words, by putting a rock image into a CNN, the CNN will read the information from the image and tell people what rock type in the image is. This study develops and implements a next-generation CNN called RockNet to classify seven different rock types. Adopting different computational strategies, RockNet can classify rock types of different grain sizes with similar texture patterns/colors, which is challenging for other CNNs. As compared with the other landmark CNNs and machine learning algorithms, RockNet has much a better prediction accuracy performance. The proposal and implementation of RockNet exemplify an interdisciplinary research study, and we are confident that this paper will be instrumental to pave the way for further coupling AI and geosciences. [ABSTRACT FROM AUTHOR]

B Retraction Note: Rock Mechanics and Rock Engineering (2022) 55:6521-6539 b https://doi.org/10.1007/s00603-022-03003-6 For legal reasons, the authors have retracted this article and the content has been removed. All authors agree to this retraction. [Extracted from the article]