Clustering of lithotypes based on visual features of cores using convolutional neural networks and K-Means
- Authors: Abdimanap G.S.1,2, Bostanbekov K.A.1, Alimova A.N.1, Saliev N.B.2, Nurseitov D.B.1,2
-
Affiliations:
- KMG Engineering
- Satbayev University
- Issue: Vol 6, No 2 (2024)
- Pages: 25-38
- Section: Geology
- URL: https://journals.rcsi.science/2707-4226/article/view/260112
- DOI: https://doi.org/10.54859/kjogi108720
- ID: 260112
Cite item
Full Text
Abstract
Background: Lithology is a vital field of study in both geology and the oil and gas sector that focuses on the properties of geological rocks. The primary objectives of lithology to classify rocks, determine their origin, and investigate the conditions of their formation and changes over time. Lithological core examination employ various methods, encompassing both conventional techniques (e.g., visual inspection of the rock samples or microscopic analysis of slides) and modern technologies. Conventional methods of examination require high qualifications and experience, and can be labour-intensive, especially in visual analysis (description of core material). The application of machine learning methods and automated technologies can enhance the efficiency and accuracy of analysis, save time, and provide quick access to information.
Aim: To develop lithotypes clustering model on core images using machine learning methods.
Materials and methods: The paper discusses an algorithm for clustering lithotypes using K-Means method combined with VGG16, VGG19 and ResNet50 convolutional neural networks to identify key features (similarities and distinctions as determined from photos).
Results: The algorithm for clustering lithotypes using K-Means method and convolutional neural networks is developed. The advantages and limitations of the algorithm when working with core images are determined. Results from experiments conducted using an actual dataset are presented.
Conclusion: The findings of the study offer important practical insights that can be applied to deep learning methods for core analysis as well as geological research. The application of this approach in geology can be broadened and the analysis of alternative machine learning models and techniques can be strengthened with more investigation.
Full Text
##article.viewOnOriginalSite##About the authors
Galymzhan S. Abdimanap
KMG Engineering; Satbayev University
Email: g.abdimanap@kmge.kz
ORCID iD: 0000-0003-1676-4075
Kazakhstan, Astana; Almaty
Kairat A. Bostanbekov
KMG Engineering
Email: k.bostanbekov@kmge.kz
ORCID iD: 0000-0003-2869-772X
PhD
Kazakhstan, AstanaAnel N. Alimova
KMG Engineering
Author for correspondence.
Email: a.alimova@kmge.kz
ORCID iD: 0000-0002-5155-2417
PhD
Kazakhstan, AstanaNurlan B. Saliev
Satbayev University
Email: saliyevnurlan@gmail.com
ORCID iD: 0009-0001-6537-6960
Kazakhstan, Almaty
Daniyar B. Nurseitov
KMG Engineering; Satbayev University
Email: d.nurseitov@kmge.kz
ORCID iD: 0000-0003-1073-4254
Cand. Sc. (Physics and Mathematics), professor (associate)
Kazakhstan, Astana; AlmatyReferences
- Gandhi SM, Sarkar BC. Essentials of mineral exploration and evaluation. Elsevier; 2016. 410 p.
- Corina AN, Hovda S. Automatic lithology prediction from well logging using kernel density estimation. Journal of Petroleum Science and Engineering. 2018;170:664–674. doi: 10.1016/j.petrol.2018.06.012.
- He J, La Croix AD, Wang J, et al. Using neural networks and the Markov Chain approach for facies analysis and prediction from well logs in the Precipice Sandstone and Evergreen Formation, Surat Basin, Australia. Marine and Petroleum Geology. 2019;101:410–427. doi: 10.1016/j.marpetgeo.2018.12.022.
- Zhang P, Sun J, Jiang Y, Gao JS. Deep learning method for lithology identification from borehole images. 79th EAGE conference and exhibition; 2017 Jun; Paris, France. Available from: https://www.earthdoc.org/content/papers/10.3997/2214-4609.201700945.
- Caja MA, Pena AC, Campos JR, et al. Image processing and machine learning applied to lithology identification, classification and quantification of thin section cutting samples. SPE Annual technical conference and exhibition; 2019 Sept 30 – Oct 2; Calgary, Alberta, Canada. Available from: https://onepetro.org/SPEATCE/proceedings-abstract/19ATCE/2-19ATCE/D022S083R001/217751.
- Wang J, Yang Y, Mao J, et al. CNN-RNN: A unified framework for multi-label image classification. 2016 IEEE conference on computer vision and pattern recognition (CVPR); 2016 Dec 12; Las Vegas, USA. Available from: https://ieeexplore.ieee.org/document/7780620.
- Abdallah A, Berendeyev A, Nuradin I, Nurseitov D. TNCR: Table net detection and classification dataset. Neurocomputing. 2022;473:79–97. doi: 10.1016/j.neucom.2021.11.101.
- Nurseitov D, Bostanbekov K, Kurmankhojayev D, et al. Handwritten Kazakh and Russian (HKR) database for text recognition. Multimedia tools and applications. 2021;80(21): 33075–33097. doi: 10.1007/s11042-021-11399-6.
- Nurseitov D., Bostanbekov K., Kanatov M., et al. Classification of handwritten names of cities and handwritten text recognition using various Deep learning models. Advances in science, technology and engineering systems journal. 2020;5(5):934–943. doi: 10.25046/aj0505114.
- Goodfellow I, Bengio Y, Courville A. Deep learning. Cambridge : MIT Press; 2016. 801 p.
- LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521:436–444. doi: 10.1038/nature14539.
- Steinhaus H. Sur la division des corps materiels en parties. Bulletin Lacademie Polonaise des Science. 1957;4:801-804.
- scikit-learn.ru/clustering [Internet]. Scikit-learn developers (BSD License) [cited 20.12.2023]. Available from: https://scikit-learn.ru/clustering/.
- Dutta A, Zisserman A. The Via Annotation software for images, audio and video. 27th ACM international conference on multimedia; 2019 Oct 21–25; Nice, France. Available from: https://dl.acm.org/doi/10.1145/3343031.3350535.
- Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. International Conference on Learning Representations. 2015. doi: 10.48550/arXiv.1409.1556.
- Krizhevsky A, Sutskever I, Hinton G. ImageNet classification with deep convolutional neural networks. Communications of the ACM. 2017;60(6):84–90. doi: 10.1145/3065386.
Supplementary files
