Automated identification of sedimentary structures in core images using object detection algorithms.
Manual interpretation of sedimentary structures in core-based analyses is critical for understanding subsurface geology but remains time-intensive, expert-dependent, and susceptible to bias. This study investigates the use of convolutional neural networks (CNNs) to automate structure identification...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0327738 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839619607738974208 |
|---|---|
| author | Ammar J Abdlmutalib Korhan Ayranci Umair Bin Waheed Hamad D Alhajri James A MacEachern Mohammed N Al-Khabbaz |
| author_facet | Ammar J Abdlmutalib Korhan Ayranci Umair Bin Waheed Hamad D Alhajri James A MacEachern Mohammed N Al-Khabbaz |
| author_sort | Ammar J Abdlmutalib |
| collection | DOAJ |
| description | Manual interpretation of sedimentary structures in core-based analyses is critical for understanding subsurface geology but remains time-intensive, expert-dependent, and susceptible to bias. This study investigates the use of convolutional neural networks (CNNs) to automate structure identification in core images, focusing on siliciclastic deposits from deltaic, shoreface, fluvial, and lacustrine environments. Two object detection models-YOLOv4 and Faster R-CNN-were trained on annotated datasets comprising 15 sedimentary structure types. YOLOv4 achieved high precision (up to 95%) with faster training and shorter inference times (3.2 s/image) compared to Faster R-CNN (2.5 s/image) under consistent batch size and hardware conditions. Although Faster R-CNN reached a higher mean average precision (94.44%), it exhibited lower recall, particularly for frequently occurring structures. Both models faced challenges in distinguishing morphologically similar features, such as mud drapes and bioturbated media. Performance declined slightly in tests involving previously unseen datasets (Split III), indicating limitations in generalization across varied core imagery. Despite these challenges, the results demonstrate the promise of deep learning for streamlining core interpretation, reducing manual effort, and enhancing reproducibility. This study establishes a robust framework for advancing automated facies analysis in sedimentological research and geoscientific applications. |
| format | Article |
| id | doaj-art-6a4f94e65b8e47c894a9acbb06e6a1bb |
| institution | Matheson Library |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-6a4f94e65b8e47c894a9acbb06e6a1bb2025-07-23T05:31:08ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01207e032773810.1371/journal.pone.0327738Automated identification of sedimentary structures in core images using object detection algorithms.Ammar J AbdlmutalibKorhan AyranciUmair Bin WaheedHamad D AlhajriJames A MacEachernMohammed N Al-KhabbazManual interpretation of sedimentary structures in core-based analyses is critical for understanding subsurface geology but remains time-intensive, expert-dependent, and susceptible to bias. This study investigates the use of convolutional neural networks (CNNs) to automate structure identification in core images, focusing on siliciclastic deposits from deltaic, shoreface, fluvial, and lacustrine environments. Two object detection models-YOLOv4 and Faster R-CNN-were trained on annotated datasets comprising 15 sedimentary structure types. YOLOv4 achieved high precision (up to 95%) with faster training and shorter inference times (3.2 s/image) compared to Faster R-CNN (2.5 s/image) under consistent batch size and hardware conditions. Although Faster R-CNN reached a higher mean average precision (94.44%), it exhibited lower recall, particularly for frequently occurring structures. Both models faced challenges in distinguishing morphologically similar features, such as mud drapes and bioturbated media. Performance declined slightly in tests involving previously unseen datasets (Split III), indicating limitations in generalization across varied core imagery. Despite these challenges, the results demonstrate the promise of deep learning for streamlining core interpretation, reducing manual effort, and enhancing reproducibility. This study establishes a robust framework for advancing automated facies analysis in sedimentological research and geoscientific applications.https://doi.org/10.1371/journal.pone.0327738 |
| spellingShingle | Ammar J Abdlmutalib Korhan Ayranci Umair Bin Waheed Hamad D Alhajri James A MacEachern Mohammed N Al-Khabbaz Automated identification of sedimentary structures in core images using object detection algorithms. PLoS ONE |
| title | Automated identification of sedimentary structures in core images using object detection algorithms. |
| title_full | Automated identification of sedimentary structures in core images using object detection algorithms. |
| title_fullStr | Automated identification of sedimentary structures in core images using object detection algorithms. |
| title_full_unstemmed | Automated identification of sedimentary structures in core images using object detection algorithms. |
| title_short | Automated identification of sedimentary structures in core images using object detection algorithms. |
| title_sort | automated identification of sedimentary structures in core images using object detection algorithms |
| url | https://doi.org/10.1371/journal.pone.0327738 |
| work_keys_str_mv | AT ammarjabdlmutalib automatedidentificationofsedimentarystructuresincoreimagesusingobjectdetectionalgorithms AT korhanayranci automatedidentificationofsedimentarystructuresincoreimagesusingobjectdetectionalgorithms AT umairbinwaheed automatedidentificationofsedimentarystructuresincoreimagesusingobjectdetectionalgorithms AT hamaddalhajri automatedidentificationofsedimentarystructuresincoreimagesusingobjectdetectionalgorithms AT jamesamaceachern automatedidentificationofsedimentarystructuresincoreimagesusingobjectdetectionalgorithms AT mohammednalkhabbaz automatedidentificationofsedimentarystructuresincoreimagesusingobjectdetectionalgorithms |