Prediction of Water Saturation from Well Log Data using Deep Learning Algorithms

Minsoo Ji; Seoyoon Kwon; Gayoung Park; Baehyun Min; Xuan Huy Nguyen

doi:10.32390/ksmer.2021.58.3.215

All Issue

2021 Vol.58, Issue 3 Preview Page Next Page

Research Paper

Prediction of Water Saturation from Well Log Data using Deep Learning Algorithms 물리검층자료를 활용한 딥러닝 기반 수포화도 예측

30 June 2021. pp. 215-226

PDF XML

Abstract

This study develops a surrogate model to predict water saturation from well log data using neural-network-based deep learning algorithms. The model performance is evaluated by comparing the water saturation estimates obtained using deep learning algorithms and Archie’s law. The surrogate model evaluates the water saturation of a target reservoir using four well-log data types (density, porosity, resistivity, and gamma ray). Long Short-Term Memory (LSTM) is employed as the deep neural network algorithm, and its performance is compared with that of a multi-layer artificial neural network. Prediction via the LSTM based model showed outstanding results with the coefficient of determination above 0.7. Sensitivity analysis is conducted through sequence tuning, switching of well type, and k-fold cross-validation. The applicability of the model has been validated for the Volve oilfield in the North Sea and an offshore oilfield in Vietnam.

Keywords

Well log data

Water saturation

Long Short-Term Memory

Sensitivity analysis

이 연구는 다양한 물리검층자료를 학습한 딥러닝 알고리듬을 이용하여 저류층의 수포화도를 예측하는 대리 모델을 구축한다. 딥러닝 알고리듬으로 계산한 수포화도 추정치를 Archie 방정식 결과와 비교함으로써 개발 모델의 성능 평가를 수행하였다. 이 연구는 4가지 물리검층자료(밀도, 공극률, 비저항, 감마선)를 심층신경망의 입력인자로 활용하여 수포화도를 평가하였다, 심층신경망 기법으로는 장단기메모리학습법을 사용하였으며 전형적인 다층 인공신경망과의 비교를 통해 성능을 확인하였다. 장단기메모리학습법을 기반으로 수포화도를 예측한 결과, 결정계수의 값이 0.7 이상으로 우수한 성능을 보이는 것으로 확인하였다. 모델의 민감도 분석으로는 시퀀스 조정, 유정 역할 전환, k-폴드 교차검증을 시행하였다. 모델의 적용 가능성은 북해 Volve 유전과 베트남 해상 유전에 적용하여 성능을 검증하였다.

키워드

물리검층자료

수포화도

장단기메모리학습법

민감도 분석

References

Agatonovic-Kustrin, S. and Beresford, R., 2000. Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research, Journal of Pharmaceutical and Biomedical Analysis, 22(5), p.717-727. 10.1016/S0731-7085(99)00272-1

Agbasi, O.E., 2013. Estimation of water saturation using a modeled equation and Archie's equation from wire-line logs, Niger Delta Nigeria, IOSR Journal of Applied Physics, 3, p.66-71. 10.9790/4861-0346671

Akinnikawe, O., Lyne, S., and Roberts, J., 2018. Synthetic well log generation using machine learning techniques. Unconventional Resources Technology Conference, Houston, Texas, USA, July 23-25. 10.15530/urtec-2018-2877021

Al-Bulushi, N., King, P.R., Blunt, M.J., and Kraaijveld, M., 2009. Development of artificial neural network models for predicting water saturation and fluid distribution, Journal of Petroleum Science and Engineering, 68(3-4), p.197-208. 10.1016/j.petrol.2009.06.017

Archie, G.E., 1952. Classification of carbonate reservoir rocks and petrophysical considerations, AAPG Bulletin, 36(2), p.278-298. 10.1306/3D9343F7-16B1-11D7-8645000102C1865D

Chitsazan, N., Nadiri, A.A., and Tsai, F.T.C., 2015. Prediction and structural uncertainty analyses of artificial neural networks using hierarchical Bayesian model averaging, Journal of Hydrology, 528, p.52-62. 10.1016/j.jhydrol.2015.06.007

Dalvand, M. and Falahat, R., 2020. A new rock physics model to estimate shear velocity log, Journal of Petroleum Science and Engineering, 196, 107697. 10.1016/j.petrol.2020.107697

Equinor, 2019.02.19, https://data-equinor-com.azurewebsites.net/dataset/volve

Gardner, G.H.F., Gardner, L.W., and Gregory, A.R., 1974. Formation velocity and density-The diagnostic basics for stratigraphic traps, Geophysics, 39(6), p.770-780. 10.1190/1.1440465

Hochreiter, S. and Schmidhuber, J., 1997. Long short-term memory, Neural Computation, 9(8), p.1735-1780. 10.1162/neco.1997.9.8.17359377276

Ki, S., Seo, J., Kwon, O., and Jang, I., 2019. Prediction of missing tubing head pressure using recurrent neural network, Journal of The Korean Society of Mineral and Energy Resources Engineers, 56(5), p.416-426. 10.32390/ksmer.2019.56.5.416

Kwon, S., Park, G., Min, B., Kim, K., Lee, T., and Han, J., 2020. Evaluation of CO2-EOR efficiency in carbonate reservoirs using multiple nonlinear regression analysis, Journal of The Korean Society of Mineral and Energy Resources Engineers, 57(2), p.185-194. 10.32390/ksmer.2020.57.2.185

Lee, K., Lim, J., Yoon, D., and Jung, H., 2019. Prediction of Shale-Gas Production at Duvernay Formation Using Deep- Learning Algorithm, SPE Journal, 24(6), p.2423-2437. 10.2118/195698-PA

Lin, G. and Shen, W., 2018. Research on convolutional neural network based on improved Relu piecewise activation function, Procedia Computer Science, 131, p.977-984. 10.1016/j.procs.2018.04.239

McCulloch, W.S. and Pitts, W., 1943. A logical calculus of the ideas immanent in nervous activity, Bulletin of Mathematical Biology, 5(4), p.115-133. 10.1007/BF02478259

Miah, M.I., Zendehboudi, S., and Ahmed, S., 2020. Log data-driven model and feature ranking for water saturation prediction using machine learning approach, Journal of Petroleum Science and Engineering, 194, 107291. 10.1016/j.petrol.2020.107291

Moradi, S., Moeini, M., Al-Askari, M.K.G., and Mahvelati, E.H., 2016. Determination of shale volume and distribution patterns and effective porosity from well log data based on cross-plot approach for a shaly carbonate gas reservoir. IOP Conf. Series: Earth and Environmental Science, 44(042002), p.1755-1315. 10.1088/1755-1315/44/4/042002

Onalo, D., Adedigba, S., Khan, F., James, L.A., and Butt, S., 2018. Data driven Model for Sonic Well Log Prediction, Journal of Petroleum Science and Engineering, 170, p.1022- 1037. 10.1016/j.petrol.2018.06.072

Osarogiagbon, A., Oloruntobi, O., Khan, F., Venkatesan, R., and Butt, S., 2020. Gamma ray log generation from drilling parameters using deep learning, Journal of Petroleum Science and Engineering, 195, 107906. 10.1016/j.petrol.2020.107906

Park, G., Kwon, S., Ji, M., Min, B., Huy, N.X., Kim, K., Kim, S., Lee, K.B., 2021. A review on deep learning applications in logging data to model gas-hydrate-bearing sediments, Journal of The Korean Society of Mineral and Energy Resources Engineers, 58(2), p.161-178. 10.32390/ksmer.2021.58.2.161

Pham, N., Wu, X., and Zabihi Naeini, E., 2020. Missing well log prediction using convolutional long short-term memory network, Geophysics, 85(4), p.WA159-WA171. 10.1190/geo2019-0282.1

Ravasi, M., Vasconcelos, I., Curtis, A., and Kristi, A., 2015. Vector-acoustic reverse time migration of Volve ocean-bottom cable data set without up/down decomposed wavefields, Geophysics, 80(4), p.S137-S150. 10.1190/geo2014-0554.1

Samo, A.O., 2020. Reservoir Characterization of the Volve Field North Sea, using rock-physics modeling, MS Thesis, Texas A&M University-Kingsville, USA.

Sen, S. and Ganguli, S. S., 2019. Estimation of Pore Pressure and Fracture Gradient in Volve Field, Norwegian North Sea. SPE Oil and Gas India Conference and Exhibition, Mumbai, India, April 9-11. 10.2118/194578-MS

Sherstinsky, A., 2020. Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network, Physica D: Nonlinear Phenomena, 404, 132306. 10.1016/j.physd.2019.132306

Simandoux, P., 1963. Dielectric measurements on porous media, application to the measurements of water saturation: study of behavior of argillaceous formations, Revue de l'Institut Francais du Petrol, 18(suppl), p.93-215.

Sun, J., Ma, X., and Kazi, M., 2018. Comparison of decline curve analysis DCA with recursive neural networks RNN for production forecast of multiple wells. SPE Western Regional Meeting, California, USA, April 22-26. 10.2118/190104-MS

Szabó, N.P., 2011. Shale volume estimation based on the factor analysis of well-logging data, Acta Geophysica, 59(5), 935. 10.2478/s11600-011-0034-0

Temizel, C., Canbaz, C.H., Saracoglu, O., Putra, D., Baser, A., Erfando, T., Krishna S., and Saputelli, L., 2020. Production forecasting in shale reservoirs through conventional DCA and machine/deep learning methods. Unconventional Resources Technology Conference, Virtual, July 20-22. 10.15530/urtec-2020-2878PMC7869042

Zhang, D., Chen, Y., and Meng, J., 2018. Synthetic well logs generation via recurrent neural networks, Petroleum Exploration and Development, 45(4), p.629-639. 10.1016/S1876-3804(18)30068-5

Information

Publisher :The Korean Society of Mineral and Energy Resources Engineers
Publisher(Ko) :한국자원공학회
Journal Title :Journal of the Korean Society of Mineral and Energy Resources Engineers
Journal Title(Ko) :한국자원공학회지
Volume : 58
No :3
Pages :215-226
Received Date : 2021-04-14
Revised Date : 2021-06-22
Accepted Date : 2021-06-25
DOI :https://doi.org/10.32390/ksmer.2021.58.3.215

Journal of the Korean Society of Mineral and Energy Resources Engineers ISSN:2288-0291(Print) 2288-2790(Online) 한국자원공학회지

All Issue