An algorithm to predict shear wave velocity using well log data and deep learning algorithms

Document Type : Research Paper

Authors

School of Mining Engineering, College of Engineering, University of Tehran, Tehran, Iran.

10.22059/ijmge.2025.377703.595173

Abstract

Shear wave velocity (Vs) is one of the most critical parameters for determining geomechanical properties to predict reservoir behavior. Determining shear wave velocity (Vs) through methods, such as core analysis requires a significant amount of time and cost. Additionally, due to the scarcity of core samples and the heterogeneity of reservoir rocks, determining this parameter using conventional methods is often not very accurate. While many empirical methods have been developed for estimating Vs, their applicability across different regions is often limited. Therefore, estimating Vs using conventional well logs is crucial. An efficient method for predicting Vs is the use of intelligent algorithms, which offer low-cost and accurate predictions. It is feasible to predict Vs using well log data. In this study, Vs was predicted using empirical relations and some deep learning (DL) algorithms in one of the hydrocarbon fields in southern Iran. In order to use the DL methods, the autoencoders deep network was used to select the effective features in predicting the Vs, and then, with multi-layer perceptron (MLP), long-short term memory (LSTM), convolutional neural network (CNN), and convolutional neural network + long-short term memory (CNN+LSTM) networks, Vs was predicted. The performance of these models was tested by a blind data set that the models had not seen before. Furthermore, the results were checked and evaluated by set of statistical measures, including MAE, MAPE, MSE, RMSE, NRMSE, and R2 values calculated for train, test, and blind datasets. It was found that all four deep learning models used in this study well performed effectively for Vs prediction, but the combined CNN+LSTM model results indicated that the least root mean squared error (RMSE) was equal to 0.0243 (2.43%) and the best coefficient of determination (R2) equal to 0.9993 for blind dataset. We found that Vs can be predicted from a series of well log data by considering their variation trends and context information with depth by means of DL algorithms. This approach is particularly suitable for problems involving various series data, such as Vs prediction. By comparing the results obtained from DL algorithms with those from conventional empirical methods and processing real petrophysical well log data, it can be concluded that deep learning algorithms not only offer more predictive accuracy and robustness but also hold promising use prospects in Vs prediction studies. The results showed that the used CNN and CNN+LSTM networks, as new deep learning algorithms, are able to predict Vs adequately.

Keywords

Main Subjects

References

[1] Castagna, J.P., Batzle, M.L., Eastwood, R.L., (1985). Relationships between compressional wave and shear-wave velocities in clastic silicate rocks. Geophysics 50 (4), 571–581.
[2] Eskandari, H., Rezaee, M.R., Mohammadnia, M., (2004). Application of multiple regression and artificial neural network techniques to predict shear wave velocity from wireline log data for a carbonate reservoir, South Iran. Can. Soc. Explor. Geophys. (CSEG) Rec. 29, 42–48.
[3] Coello, C.C., (2007). Evolutionary algorithms for solving multiobjective problems: Springer Science & Business Media. https:// link.springer.com/book/10.1007%2F978-0-387-36797-2.
[4] Bengio, Y., Simard, P., Frasconi, P. (1994). Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Network. 5 (2), 157–166.
[5] Krizhevsky, A., Sutskever, I., E. Hinton, G. (2017). ImageNet classification with deep convolutional neural networks. Commun ACM 60:84–90. https://doi. org/10.1145/3065386.
[6] Kacprzyk. J., (2008). Studies in Computational Intelligence, Volume 121.
[7] He. K, X. Zhang, S. Ren, and J. Sun. (2016). Deep residual learning for image recognition, Paper read at Proceedings of the IEEE conference on computer vision and pattern recognition.
[8] Rezaee, MR., Kadkhodaei, A., Barabadi, A. (2007). Prediction of shear wave velocity from petrophysical data utilizing intelligent systems: An example from a sandstone reservoir of Carnarvon Basin, Australia. J Petrol Sci Eng 55:201–212. https://doi.org/10.1016/j.petrol.2006.08.008.
[9] Rajabi, M., Bohloli, B., Hangar, E.  (2010). Intelligent approaches for prediction of compressional, shear and Stoneley wave velocities from conventional well log data: A case study from the Sarvak carbonate reservoir in the Abadan Plain (Southwestern Iran). Comput Geosci 36:647–664. https://doi.org/10.1016/
j.cageo.2009.09.008.
[10] Moatazedian, I., Rahimpour-Bonab, H., Kadkhodaie-Ilkhchi, A., & Rajoli, M. (2011). Prediction of shear and Compressional Wave Velocities from petrophysical data utilizing genetic algorithms technique: A case study in Hendijan and Abuzar fields located in Persian Gulf. Geopersia, 1(1), 1-17.
[11] Asoodeh, M., Bagheripour, P. (2012). Prediction of compressional, shear, and stonely wave velocities from conventional well log data using a committee machine with intelligent systems. Rock mechanics and rock engineering 45, 45–63. https://doi.org/10. 1007/s00603-011-0181-2.
[12] Asoodeh, M., Bagheripour, P. (2013). Neuro-fuzzy reaping of shear wave velocity correlations derived by hybrid genetic algorithm pattern search technique. Open Geosciences 5, 272–284. https:// doi.org/10.2478/s13533-012-0129-4.
[13] Asoodeh, M., Bagheripour, P. (2014). ACE stimulated neural network for shear wave velocity determination from well logs. J Apply Geophysics 107:102–107. https://doi.org/10.1016/
j.jappgeo.2014. 05.014.
[14] Maleki, Sh., Moradzadeh, A., Ghavami Riabi, R., Gholami, R., Sadeghzadeh, F. (2014). Prediction of shear wave velocity using empirical correlations and artificial intelligence methods. NRIAG J Astron Geophys 3:70–81. https://doi.org/10.1016/
j.nrjag.2014.05.001.
[15] Gholami, R., Moradzadeh, A., Rasouli, V., Hanachi, J. (2014). Shear wave velocity prediction using seismic attributes and well log data. Acta Geophysica 62, 818–848. https://doi.org/10.2478/
s11600-013-0200-7.
[16] Akhundi, H., Ghafoori, M., Lashkaripour, G.R. (2014). Prediction of shear wave velocityusing artificial neural network technique, multiple regression and petrophysical data:a case study in asmari reservoir (SW Iran). Open J. Geol. 4, 303–313.
[17] Kadkhodaie-Ilkhchi., A. (2015). A systematic approach for estimation of reservoir rock properties using Ant Colony Optimization. Geopersia, 5(1), 7-17.
[18] Bagheripour., P., Gholami., A., Asoodeh., M., & Vaezzadeh-Asadi., M. (2015). Support vector regression based determination of shear wave velocity. Journal of Petroleum Science and Engineering, 125, 95-99.
[19] Al-Dousari, M., Garrouch, A.A., Al-Omair, O. (2016). Investigating the dependence of shear wave velocity on petrophysical parameters. J. Petrol. Sci. Eng. 146, 286–296.
[20] Singh, S., Kanli, A.I. (2016). Estimating shear wave velocities in oil fields: a neural network approach. Geosciences Journal 20, 221–228. https:// link.springer.com/article/10.1007%2Fs12303-015-0036-z.
[21] Behnia, D., Ahangari, K., Moeinossadat, S. R. (2017). Modeling of shear wave velocity in limestone by soft computing methods. Int J Min Sci Technol 27:423–430. https://doi.org/10.1016/
j.ijmst.2017.03.006.
[22] Shiroodi, SK., Ghafoori, M., Ansari, H. R., Lashkaripour, G., Ghanadian, M. (2017). Shear wave prediction using committee fuzzy model constrained by lithofacies, Zagros basin, SW Iran. J Afr Earth Sc 126:123–135. https://doi.org/10.1016/
j.jafrearsci.2016.11.016.
[23] Mehrgini, B., Izadi, H., Memarian, H. (2019). Shear wave velocity prediction using Elman artificial neural network. Carbonates Evaporites 34 (4), 1281–1291.
[24] Alkinani, H.H., AL hamidi, S., Dunn norman, R. E., Flori, M. A., AL Alwani, A. R. (2019). Intelligent data-driven analytics to predict shear wave velocity in carbonate formations: comparison between recurrent and conventional neural networks. OnePetro. https://onepetro.org/conference-paper/ARMA-2019-0511.
[25] Zhang, Y., Zhong, H. R., Wu, Z., Zhou, H., Ma, Q. (2020). Improvement of petrophysical workflow for shear wave velocity prediction based on machine learning methods for complex carbonate reservoirs. J Petrol Sci Eng 192:107234. https://doi.org/10.1016/j.petrol.2020.107234.
[26] Wood, DA. (2020). Bakken stratigraphic and type well log learning network exploited to predict and data mine shear wave acoustic velocity. J Appl Geophys 173:103936. https://doi.org/10.1016/j. jappgeo.2019.103936.
 [27] Gholami, A., Seyedali, S M., Ansari, H. R. (2020). Estimation of shear wave velocity from post-stack seismic data through committee machine with cuckoo search optimized intelligence models. J Petrol Sci Eng 189:106939. https://doi.org/
10.1016/j.petrol.2020.106939.
[28] Wang, J., Cao, J., Liu, Z., Lei, X., Zhou, X. (2020). Method of well logging prediction prior to well drilling based onlong short-term memory recurrent neural network[J]. J. Chengdu Univ. Technol. (Sci. Technol. Ed.) 47 (2), 227–236.
[29] Ghorbani, H., Davoodi, S., Davarpanah, A. (2021). Accurate determination of shear wave velocity using LSSVM-GA algorithm based on petrophysical log, 1 ed. European Association of Geoscientists & Engineers, pp. 1–3. https://doi.org/10.3997/2214-4609.202137015.
[30] Olayiwola, T., Sanuade, OA. (2021). A data-driven approach to predict compressional and shear wave velocities in reservoir rocks. Petroleum 7:199–208. https://doi.org/10.1016/
j.petlm.2020.07.008.
[31] Ebrahimi, A., Izadpanahi, A., Ebrahimi, P., Ranjbar, A., (2022). Estimation of shear wave velocity in an Iranian oil reservoir using machine learning methods. J Petrol Sci Eng 209:109841. https://doi.org/10.1016/j.petrol.2021.109841.
[32] Gholami Vijouyeh, A., Kadkhodaie, A., Hassanpour Sedghi, M., (2022). A committee machine with intelligent experts (CMIE) for estimation of fast and slow shear wave velocities utilizing petrophysical logs. Computers & Geosciences. Volume 165, August 2022, 105149. https://doi.org/10.1016/j.cageo.2022.105149.
[33] Nasrnia, B., Falahat, R., Kadkhodaie, A., Gholami Vijouyeh, A., (2023). A committee machine-based estimation of shear velocity log by combining intelligent systems and rock-physics model using metaheuristic algorithms. Volume 126, Part A, November 2023, 106821. https://doi.org/10.1016/
j.engappai.2023.106821.
[34] Alavi, A.H., Gandomi, A.H., Mollahasani, A., Heshmati, A.A.R., Rashed, A., (2010). Modeling of maximum dry density and optimum moisture content of stabilized soil using artificial neural networks.
[35] Hochreiter, S., Schmidhuber, J. (1997). Long short-term memory. Neural Comput. 9 (8), 1735–1780.
[36] Gers, F.A., Schraudolph, N.N., Schmidhuber, J. (2003). Learning precise timing with lstm recurrent networks. J. Mach. Learn. Res. 3 (1), 115–143.
[37] Biranvand, N., Kikhai, M., Roein. (2019). presenting a method in the field of revealing targets in satellite images using deep learning and with remote sensing and GIS approach, Geographical
[38] Abad, B., Rajabi, A., Mousavi, S. M. V., Mohamadian, N., Wood, D., Ghorbani, H., Davoodi, Sh., Alvar, M., Shahbazi, Kh., 2021b. Hybrid machine learning algorithms to predict condensate viscosity in the near wellbore regions of gas condensate reservoirs. Journal of Natural Gas Science and Engineering 95,104210. https://doi.org/10.1016/j.jngse.2021.104210.
[39] Sezavar, A., Fersi, H., Mohamadzadeh, S. (2015). Image retrieval using deep learning. 4th International Conference on Applied Research in Computer Engineering and Signal Processing. Vol.3, No. 1, 28-42.
[40] Anemangely, M., Ramezanzadeh, A., Tokhmechi, B. (2017). Shear wave travel time estimation from petrophysical logs using ANFIS-PSO algorithm: a case study from Ab-Teymour Oilfield. J. Nat. Gas Sci. Eng. 38, 373–387.
[41] Kingma, D.P., Ba, J. (2014). Adam: A Method for Stochastic Optimization. https://arxiv. org/abs/1412.6980.
[42] Duchi, J., Hazan, E., Singer, Y. (2011). Adaptive subgradient methods for online learning and stochastic optimization. J.Machine Learning Research. 12 (Jul), 2121–2159.
[43] Tieleman, T., Hinton, G. (2012). Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude. COURSERA: Neural Networks for Machine Learning 4, 26–30.
International Journal of Mining and Geo-Engineering
Volume 59, Issue 1
March 2025
Pages 31-42

Files

Share

How to cite

Statistics