Abstract
Well logging data plays an important role in reservoir description and O&G resource evaluation. In the era of artificial intelligence (AI), intelligent well logs interpretation driven by AI can greatly improve the efficiency of well logs interpretation, save time and effort of domain experts, and reduce costs. To achieve intelligent well logs interpretation, the training of AI models requires a large amount of labeled data. However, the current situation is small amounts of labelled data, high cost and strong subjectivity of expert annotation. On the basis of the physical models of well logs, this paper proposes a domain knowledge-based approach for synthetic well logs generation. The generated well logs are employed to help train AI models. The shortcomings of existing methods are considered comprehensively, and a joint deep learning model driven by domain knowledge is established for geological parameter inversion and well logs generation. Various types of well logs can be generated by using the proposed approach. Experimental results show that the proposed method can generate high-quality labeled well logs. Moreover, the generated well logs are useful for improving the performance of AI models of intelligent well logs interpretation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Darling, T.: Well Logging and Formation Evaluation. Elsevier, Amsterdam (2005)
Li, Z., Wang, Z., Wei, Z., et al.: Cross-oilfield reservoir classification via multi-scale sensor knowledge transfer (2021)
Yang, T., Wang, Q., Liu, Y., et al.: A review of application of machine learning in wireline logging formation evaluation (2020)
Liu, Y.: A self-adaptive optimization solution to petrophysical properties inversion from well logs. In: CSPG/CSEG/CWLS GeoConvention (2008)
Eskandari, H., Rezaee, M.R., Mohammadnia, M.: Application of multiple regression and artificial neural network techniques to predict shear wave velocity from wireline log data for a carbonate reservoir South-West Iran. CSEG Rec. 42, 48 (2004)
Zhang, D., Yuntian, C., Jin, M.: Synthetic well logs generation via recurrent neural networks. Pet. Explor. Dev. 45(4), 629–639 (2018)
Rolon, L., Mohaghegh, S.D., Ameri, S., et al.: Using artificial neural networks to generate synthetic well logs. J. Nat. Gas Sci. Eng. 1(4–5), 118–133 (2009)
Long, W., Chai, D., Aminzadeh, F.: Pseudo density log generation using artificial neural network. In: SPE Western Regional Meeting. Society of Petroleum Engineers (2016)
Korjani, M., Popa, A., Grijalva, E., et al.: A new approach to reservoir characterization using deep learning neural networks. In: SPE Western Regional Meeting. Society of Petroleum Engineers (2016)
Salehi, M.M., Rahmati, M., Karimnezhad, M., et al.: Estimation of the non records logs from existing logs using artificial neural networks. Egypt. J. Pet. 26(4), 957–968 (2017)
Alkinani, H.H., Al-Hameedi, A.T.T., Dunn-Norman, S., et al.: Applications of artificial neural networks in the petroleum industry: a review. In: SPE Middle East Oil and Gas Show and Conference. Society of Petroleum Engineers (2019)
Gowida, A., Elkatatny, S., Al-Afnan, S., et al.: New computational artificial intelligence models for generating synthetic formation bulk density logs while drilling. Sustainability 12(2), 686 (2020)
Chen, Y., Zhang, D.: Physics-constrained deep learning of geomechanical logs. IEEE Trans. Geosci. Remote Sens. 58(8), 5932–5943 (2020)
Chen, Y., Chang, H., Meng, J., et al.: Ensemble Neural Networks (ENN): a gradient-free stochastic method. Neural Netw. 110, 170–185 (2019)
Chen, Y., Zhang, D.: Well log generation via ensemble long short‐term memory (EnLSTM) network. Geophys. Res. Lett. 47(23), e2020GL087685 (2020)
Angelini, E., Ludovici, A.: CDS Evaluation model with neural networks. J. Serv. Sci. Manage. 2(01), 15 (2009)
Gu, J., Wang, Z., Kuen, J., et al.: Recent advances in convolutional neural networks. Pattern Recogn. 77, 354–377 (2018)
Mo, X., Li, X., Zhang, Q.: The variation step adaptive Glowworm swarm optimization algorithm in optimum log interpretation for reservoir with complicated lithology. In: 2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), pp. 1044–1050. IEEE (2016)
Duan, Y.N., Pan, B.Z., Han, X., et al.: Porosity calculation of tight sand gas reservoirs with GACM hybrid optimization log interpretation method. J. Geosci. Environ. Prot. 2(3), 92–98 (2014)
Tong, B., Klinkigt, M., Iwayama, M., et al.: Learning to generate rock descriptions from multivariate well logs with hierarchical attention. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 2031–2040 (2017)
Holdaway, K.R.: Harness Oil and Gas Big Data with Analytics: Optimize Exploration and Production with Data-Driven Models. Wiley, New York (2014)
Zhang, G., Patuwo, B.E., Hu, M.Y.: Forecasting with artificial neural networks: the state of the art. Int. J. Forecast. 14(1), 35–62 (1998)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Hou, Sl. et al. (2022). Domain Knowledge-Based Well Logs Generation and Its Application in AI Modeling. In: Lin, J. (eds) Proceedings of the International Field Exploration and Development Conference 2021. IFEDC 2021. Springer Series in Geomechanics and Geoengineering. Springer, Singapore. https://doi.org/10.1007/978-981-19-2149-0_130
Download citation
DOI: https://doi.org/10.1007/978-981-19-2149-0_130
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-2148-3
Online ISBN: 978-981-19-2149-0
eBook Packages: Earth and Environmental ScienceEarth and Environmental Science (R0)