Abstract
Lithology identification of rock is one of the main bases for stratigraphic division in geology and plays a very important role in oil and gas exploration. In recent years, with the increasing amount of data obtained by MWD and other methods, it is possible to use artificial intelligence method to dynamically identify lithology based on these data. This paper establishes a formation lithology prediction model based on CNN-LSTM-Attention, predicts formation lithology through drilling parameters and logging data, and verifies the drilling data of a block in Huizhou, South China Sea. Three artificial intelligence methods, convolutional neural network - Long short-term memory neural network -Attention mechanism (CNN-LSTM-Attention), convolutional neural network - long short-term memory neural network (CNN-LSTM) and long short-term memory neural network (LSTM), are compared and analyzed. The results show that the lithology prediction model proposed in this paper has good accuracy and low error, and has certain reliability and practicability.
Funding: Supported by the Postgraduate Innovation and Practice Ability Development Fund of Xi’an Shiyou University (YCS22215305).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Xu, Z., et al.: Lithology identification: method, current situation and intelligent development trend. Geolog. Rev. 68(06), 2290–2304 (2022)
Cai, H., et al.: Classification of metallogenic prospect areas based on convolutional neural network model: a case study of gold polymetallic ore field in Daqiao Area, Gansu Province. Geolog. Bull. China 38(12), 1999–2009 (2019)
Duan, Y., Wang, Y., Sun, Q.: Application of selective ensemble learning model in lithology-porosity prediction. Sci. Technol. Eng. 20(03), 1001–1008 (2020)
Xu, T., et al.: Evaluation of active learning algorithms for formation lithology identification. J. Petrol. Sci. Eng. 206, 108999 (2021)
Arnø, M., Morten, J., Morten Aamo, O.: Real-time classification of drilled lithology from drilling data using deep learning with online calibration. In: SPE/IADC International Drilling Conference and Exhibition (2021)
Lei, M., et al.: Research on intelligent recognition method and application of Rock lithology Mask R-CNN. J. Railway Sci. Eng. 19(11), 3372–3382 (2022)
Yue, Z., et al.: Research progress of machine learning algorithms for lithology identification based on LWD data. Sci. Technol. Eng. 23(10), 4044–4057 (2023)
Wei, Y., Gong, J.: Rolling bearing fault diagnosis based on CNN-LSTM-attention. J. Shenyang Univ. Technol. (08) (2022)
Liu, W., Liu, W., Gu, J.: Prediction of daily oil production of oil Wells based on machine learning method. Oil Drill. Prod. Technol. 421, 70–75 (2020)
Ma, Z., Ma, L., Li, K., Yao, W., Wang, P., Wang, X.: Multi-scale lithology recognition based on deep learning of rock images. Geolog. Sci. Technol. Bull. 41(06), 316–322 (2022)
Yang, J., Zhang, H.: Research on neural network method of formation lithology identification while drilling. Nat. Gas. Ind. 26(12), 109–111 (2006)
Hochreiters, S.J.: Longshort-termmemory. Neural Comput. 8, 1735–1780 (1997)
Yin, Q.S., Yang, J., Hou, X.X., et al.: Drilling performance improvement in offshore batch Wells based on rig state classification using machine learning. J. Petrol. Sci. Eng. 192, 107306 (2020)
Zhu, H., Ning, Q., Lei, Y.J., et al.: Fault classification of rolling bearing based on attention mechanism-inception CNN model. J. Vib. Shock 39(19), 84–93 (2020)
Roger, Z.L., et al.: Research on construction of deep prospecting prediction model based on PSO-CNN. J. Chengdu Univ. Technol. (Nat. Sci. Edn.) (09) (2020)
Zhang, J.F., Zhu, Y., Zhang, X.P., et al.: Developing a long short-term memory (LSTM) based model for predicting water table depth in agricultural areas. J. Hydrol. 6(561), 918–929 (2018)
Wu, Z., Zhang, X., Zhang, C., et al.: Lithologic reservoir identification method based on LSTM recurrent neural network. Litholog. Reserv. 33(3), 120–128 (2021)
Arps, J.J., Arps, J.L.: The subsurface telemetry problem - a practical solution. Soc. Petrol. Eng. (1964)
Tong, W., Zhao, R., Guo, C.: Limestone slurry density prediction based on grey relational analysis and mutual information theory. China Testing 06, 1–7 (2022)
Yan, D., Chen, B., Song, L., Wang, B.: Drilling fluid system of deep Wells in Huizhou area, South China Sea. Chem. Eng. Equip. 06, 109–110 (2021)
Wang, A., et al.: Characteristics and controlling factors of physical properties of deep tight sandstone reservoirs: a case study of the second lower Member of Xuerang Formation in Yuanba West area, Northeast Sichuan Basin. Acta Sedimentol. Sinica 40(02), 410–421 (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liu, Z., Yan, X., She, Y., Zhang, F., Shi, C., Wang, L. (2024). Lithology Identification Method Based on CNN-LSTM-Attention: A Case Study of Huizhou Block in South China Sea. In: Fang, L., Pei, J., Zhai, G., Wang, R. (eds) Artificial Intelligence. CICAI 2023. Lecture Notes in Computer Science(), vol 14474. Springer, Singapore. https://doi.org/10.1007/978-981-99-9119-8_31
Download citation
DOI: https://doi.org/10.1007/978-981-99-9119-8_31
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-9118-1
Online ISBN: 978-981-99-9119-8
eBook Packages: Computer ScienceComputer Science (R0)