File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1007/s00603-023-03235-0
- Scopus: eid_2-s2.0-85147761044
- WOS: WOS:000932677000002
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Novel Rock Image Classification: The Proposal and Implementation of HKUDES_Net
Title | Novel Rock Image Classification: The Proposal and Implementation of HKUDES_Net |
---|---|
Authors | |
Keywords | Alerting level Automatic rock classification Convolutional neural networks (CNNs) HKUDES_Net |
Issue Date | 10-Feb-2023 |
Publisher | Springer |
Citation | Rock Mechanics and Rock Engineering, 2023, v. 56, n. 5, p. 3825-3841 How to Cite? |
Abstract | 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. |
Persistent Identifier | http://hdl.handle.net/10722/337489 |
ISSN | 2023 Impact Factor: 5.5 2023 SCImago Journal Rankings: 1.902 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Zhou, Yimeng | - |
dc.contributor.author | Wong, Louis Ngai Yuen | - |
dc.contributor.author | Tse, Keith Ki Chun | - |
dc.date.accessioned | 2024-03-11T10:21:17Z | - |
dc.date.available | 2024-03-11T10:21:17Z | - |
dc.date.issued | 2023-02-10 | - |
dc.identifier.citation | Rock Mechanics and Rock Engineering, 2023, v. 56, n. 5, p. 3825-3841 | - |
dc.identifier.issn | 0723-2632 | - |
dc.identifier.uri | http://hdl.handle.net/10722/337489 | - |
dc.description.abstract | <p>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.<br></p> | - |
dc.language | eng | - |
dc.publisher | Springer | - |
dc.relation.ispartof | Rock Mechanics and Rock Engineering | - |
dc.subject | Alerting level | - |
dc.subject | Automatic rock classification | - |
dc.subject | Convolutional neural networks (CNNs) | - |
dc.subject | HKUDES_Net | - |
dc.title | Novel Rock Image Classification: The Proposal and Implementation of HKUDES_Net | - |
dc.type | Article | - |
dc.identifier.doi | 10.1007/s00603-023-03235-0 | - |
dc.identifier.scopus | eid_2-s2.0-85147761044 | - |
dc.identifier.volume | 56 | - |
dc.identifier.issue | 5 | - |
dc.identifier.spage | 3825 | - |
dc.identifier.epage | 3841 | - |
dc.identifier.eissn | 1434-453X | - |
dc.identifier.isi | WOS:000932677000002 | - |
dc.identifier.issnl | 0723-2632 | - |