Abstract
Currently, the computer vision area, which represents one of the subfields of artificial intelligence and machine learning, has been widely used to process data in the oil and gas industry. In this context, the detection of specific properties inside carbonate rocks in different datasets from petroleum reservoirs represents a considerable challenge, that consumes enormous resources and time. Therefore, the automatic separation of the lithologies within rocks of reservoirs has attracted the increasing attention of many research groups. The consistent classification of these lithologies is the main factor for the construction of reliable depositional, diagenetic, and reservoir models. This work deals with this last issue by presenting the development of a technique for the automatic classification of carbonate thin sections obtained from plane-polarized and cross-polarized microscopy images corresponding to natural rocks belonging to the Brazilian pre-salt reservoir. Our proposed model transforms the analyzed images into structured data by defining texture parameters (Haralick parameters), and Wavelets transforms. Later, a stacked autoencoder neural network is used to eliminate images with anomalies and/or distortions in order to define relevant characteristics of the data. This stage is followed by supervised classifier called multilayer feed-forward neural network. The definition of the model’s hyperparameters is tuned by Bayesian optimization and the Gaussian process. For training and testing of the network, images of 570 thin sections were used (each image obtained with plane-polarized and cross-polarized light) totaling 1140 images. Our model reported an accuracy of 83% for the test samples, confirming the validity of the proposed model in the automatic classification of carbonate rocks.
Similar content being viewed by others
Data Availability
The dataset used in this research belongs to Petrobras.
References
Abolhasanzadeh, B.: Nonlinear dimensionality reduction for intrusion detection using auto-encoder bottleneck features. In: 2015 7th conference on information and knowledge technology (IKT), IEEE, pp 1–5 (2015)
Akhiyarov, D., Gherbi, A., Araya-Polo, M., Graham, G.: Scaling deep learning applications in geosciences. In: SEG international exposition and annual meeting, OnePetro (2020)
Alzubaidi, F., Mostaghimi, P., Swietojanski, P., Clark, Stuart, R., Armstrong, R.T.: Automated lithology classification from drill core images using convolutional neural networks. J. Pet. Sci. Eng 197, 107933 (2021)
Arivazhagan, S., Ganesan, L.: Texture classification using wavelet transform. Pattern Recog. Lett 24(9–10), 1513–1521 (2003)
Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H., et al.: Greedy layer-wise training of deep networks. Adv. Neural. Inf. Process. Syst 19, 153 (2007)
Budennyy, S., Pachezhertsev, A., Bukharev, A., Erofeev, A., Mitrushkin, D., Belozerov, B.: Image processing and machine learning approaches for petrographic thin section analysis. In: SPE russian petroleum technology conference, OnePetro (2017)
Burchette, T.P.: Carbonate rocks and petroleum reservoirs: a geological perspective from the industry. Geol. Soc. London Spec. Publ 370(1), 17–37 (2012)
Caja, M.Á., Peña, A.C., Campos, J.R., Diego, L.G., Tritlla, J., Bover-Arnal, T., Martín-Martín, J.D.: Image processing and machine learning applied to lithology identification, classification and quantification of thin section cutting samples. In: SPE Annual Technical Conference and Exhibition, OnePetro (2019)
Cheng, G., Guo, W.: Rock images classification by using deep convolution neural network. In: Journal of Physics: Conference Series, vol 887, IOP Publishing, p 012089 (2017)
De Lima, R.P., Bonar, A., Coronado, D.D., Marfurt, K., Nicholson, C.: Deep convolutional neural networks as a geological image classification tool. Sediment. Rec 17, 4–9 (2019)
Demirel, H., Anbarjafari, G.: Image resolution enhancement by using discrete and stationary wavelet decomposition. IEEE Trans. Image Process 20(5), 1458–1460 (2010)
Dozat, T.: Incorporating nesterov momentum into adam (2016)
Duan, Y., Xie, J., Li, B., Wang, M., Zhang, T., Zhou, Y.: Lithology identification and reservoir characteristics of the mixed siliciclastic-carbonate rocks of the lower third member of the shahejie formation in the south of the laizhouwan sag, bohai bay basin, china. Carbonates Evaporites 35(2), 1–19 (2020)
Farahbakhsh, E., Chandra, R., Olierook, H.K.H., Scalzo, R., Clark, C., Reddy, S.M., Müller, R D.: Computer vision-based framework for extracting tectonic lineaments from optical remote sensing data. Int. J. Remote Sens 41(5), 1760–1787 (2020)
Ferreira, L., Pilastri, A., Martins, C.M., Pires, P.M., Cortez, P.: A comparison of automl tools for machine learning, deep learning and xgboost. In: 2021 international joint conference on neural networks (IJCNN), IEEE, pp 1–8 (2021)
Ge, P.: Analysis on approaches and structures of automated machine learning frameworks. In: 2020 international conference on communications, information system and computer engineering (CISCE), IEEE, pp 474–477 (2020)
Ghiasi-Freez, J., Honarmand-Fard, S., Ziaii, M.: The automated dunham classification of carbonate rocks through image processing and an intelligent model. Pet. Sci. Technol 32(1), 100–107 (2014)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016). http://www.deeplearningbook.org. Accessed 10 Jan 2022
Goodfellow, I., Bengio, Y., Courville, A., Bengio, Y.: Deep learning, vol. 1. MIT press, Cambridge (2016)
Gu, Y., Bao, Z., Rui, Z.: Prediction of shell content from thin sections using hybrid image process techniques. J. Pet. Sci. Eng 163, 45–57 (2018)
Haralick, R.M., Shanmugam, K., Dinstein, Its’ H: Textural features for image classification. IEEE Trans. Syst. Man Cybernet SMC-3(6), 610–621 (1973)
Hinton, G., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)
Huszar, F., Theis, L., Shi, W., Cunningham, A.: Lossy image compression with compressive autoencoders (2020)
Jin, H., Song, Q., Hu, X.: Auto-keras: an efficient neural architecture search system. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, pp 1946–1956 (2019)
Karpatne, A., Ebert-Uphoff, I., Ravela, S., Babaie, H.A., Kumar, V.: Machine learning for the geosciences: challenges and opportunities. IEEE Trans. Knowl. Data Eng 31(8), 1544–1554 (2018)
Lai, Z., Deng, H.: Medical image classification based on deep features extracted by deep model and statistic feature fusion with multilayer perceptron. Comput. Intell. Neurosci 2018, 2061516 (2018)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
Liu, Y., Cheng, G., Ma, W., Guo, C.: Rock classification based on features form color space and morphological gradient of rock thin section image. Zhongnan Daxue Xuebao (Ziran Kexue ban)/J Central South University (Science and Technology) 47, 2375–2382 (2016)
Löfstedt, T, Brynolfsson, P., Asklund, T., Nyholm, T., Garpebring, A.: Gray-level invariant haralick texture features. PloS ONE 14(2), e0212110 (2019)
Młynarczuk, M, Górszczyk, A, Ślipek, B: The application of pattern recognition in the automatic classification of microscopic rock images. Comput. Geosci 60, 126–133 (2013)
Nanjo, T., Tanaka, S.: Carbonate lithology identification with machine learning. In: Abu Dhabi international petroleum exhibition & conference, OnePetro (2019)
O’Mahony, N., Campbell, S., Carvalho, A., Harapanahalli, S., Hernandez, G.V., Krpalkova, L., Riordan, D., Walsh, J.: Deep learning vs. traditional computer vision. In: Science and information conference, Springer, pp 128–144 (2019)
Pang, G., Shen, C., Cao, L., Van Den Hengel, A.: Deep learning for anomaly detection: a review. ACM Comput. Surv. (CSUR) 54(2), 1–38 (2021)
Rabbani, A., Assadi, A., Kharrat, R., Dashti, N., Ayatollahi, S.: Estimation of carbonates permeability using pore network parameters extracted from thin section images and comparison with experimental data. J. Natural Gas Sci. Eng 42, 85–98 (2017)
Rosenblatt, F.: The perceptron: a probabilistic model for information storage and organization in the brain. Psychol. Rev 65(6), 386–0 (1958)
Rumelhart, D.E., Hinton, G., Williams, R.: Learning representations by back-propagating errors. Nature 323(6088), 533–536 (1986)
Sagayam, K.M., Bruntha, P.M., Sridevi, M., Sam, M.R., Kose, U., Deperlioglu, O.: A cognitive perception on content-based image retrieval using an advanced soft computing paradigm. In: Advanced machine vision paradigms for medical image analysis, pp 189–211 (2021)
Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6(1), 1–48 (2019)
Su, C., Xu, S-j, Zhu, K-y, Zhang, X-c: Rock classification in petrographic thin section images based on concatenated convolutional neural networks. Earth Sci. Inform 13(4), 1477–1484 (2020)
Tan, L., Jiang, J.: Digital signal processing: fundamentals and applications. Academic Press, Cambridge (2018)
Tasdemir, S.B.Y., Tasdemir, K., Aydin, Z.: Roi detection in mammogram images using wavelet-based haralick and hog features. In: 2018 17th IEEE international conference on machine learning and applications (ICMLA), IEEE, pp 105–109 (2018)
Visa, S., Ramsay, B., Ralescu, A.L., Van Der, K.E.: Confusion matrix-based feature selection. MAICS 710, 120–127 (2011)
Voulodimos, A., Doulamis, N., Doulamis, A., Protopapadakis, E.: Deep learning for computer vision: a brief review. Comput. Intell. Neurosci 2018, 7068349 (2018)
Worden, R.H., Armitage, P.J., Butcher, A.R., Churchill, J.M., Csoma, A.E., Hollis, C., Lander, R.H., Omma, J.E.: Petroleum reservoir quality prediction: overview and contrasting approaches from sandstone and carbonate communities. Geol. Soc. Lond. Spec. Publ 435(1), 1–31 (2018)
Acknowledgements
This work was possible due to the R&D cooperation agreement between Petrobras and CBPF.
Funding
Petrobras financed all research developed in this work.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interests
The authors declare that they have no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Faria, E.L., Coelho, J.M., Matos, T.F. et al. Lithology identification in carbonate thin section images of the Brazilian pre-salt reservoirs by the computational vision and deep learning. Comput Geosci 26, 1537–1547 (2022). https://doi.org/10.1007/s10596-022-10168-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10596-022-10168-0