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...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:PloS one Jg. 20; H. 7; S. e0327738
Hauptverfasser: Abdlmutalib, Ammar J., Ayranci, Korhan, Waheed, Umair Bin, Alhajri, Hamad D., MacEachern, James A., Al-Khabbaz, Mohammed N.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States Public Library of Science 18.07.2025
Public Library of Science (PLoS)
Schlagworte:
Accuracy
Algorithms
Artificial neural networks
Automation
Boxes
Datasets
Deep learning
Geology
Identification
Identification and classification
Image processing
Lithology
Machine learning
Methods
Neural networks
Object recognition
Sedimentary structures
Saudi Arabia
ISSN:1932-6203, 1932-6203
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1932-6203
1932-6203
DOI:10.1371/journal.pone.0327738