Optimizing Deep Learning Models for Shear Wave Velocity Estimation Utilizing Petrophysical Logs: A Case Study on an Oil Reservoir in Southern Iran

مقالات آماده انتشار

نوع مقاله : مقاله پژوهشی

نویسندگان

1 کارشناس ارشد، مهندسی نفت، دانشگاه بین المللی امام خمینی

2 استادیار گروه مهندسی معدن و نفت، دانشگاه بین المللی امام خمینی

3 دپارتمان مهندسی نفت دانشگاه آزاد اسلامی واحد مسجد سلیمان

4 استادیار دانشکده مهندسی معدن، نفت و ژئوفیزیک، دانشگاه صنعتی شاهرود

5 دانشجوی کارشناسی مهندسی معدن، دانشگاه بین المللی امام خمینی

چکیده

Full identification and understanding of hydrocarbon reservoirs depends on knowing the mechanical properties. One of the main parameters that indicates mechanical properties is shear wave velocity. Bipolar sound recorder is among thee best tools for measuring shear wave velocity. This tool is not very popular due to the high costs of driving in the well despite the high accuracy. Shear wave velocity estimation methods include three main branches of experimental methods, regression and the use of machine learning algorithms or in other words artificial neural networks. The studied formation in this research is Sarvak in one of the oil fields in the south of Iran. The input data of the estimator model is the usual petrophysical logs that are driven and measured in many wells, and the output data is obtained from the DSI tool. In this research, data are pre-processed by removing noise effects. Then, to improve the estimation effectiveness, data with a high correlation coefficient are selected as input data. After that, shear wave velocity is estimated from petrophysical data with three types of multi-layer perceptron (MLP), multi-layer perceptron optimized by particle swarm optimization (MLP-PSO), and the introduction of a relatively new method of multi-layer perceptron-social ski drive (MLP-SSD). To compare the efficiency of the neural network method, two traditional experimental and regression methods used. The validation results show the better performance of the MLP-SSD method.

کلیدواژه‌ها

عنوان مقاله [English]

Optimizing Deep Learning Models for Shear Wave Velocity Estimation Utilizing Petrophysical Logs: A Case Study on an Oil Reservoir in Southern Iran

نویسندگان [English]

  • Fatemeh Eil Saadatmand 1
  • Andisheh Alimoradi 2
  • Mirhassan Moosavi 3
  • Mohammad Mehrad 4
  • Mohammad Ali Davari 1
  • Parisa Rezakhani 5
1 Department of Mining Engineering, Faculty of Engineering, Imam Khomeini International University, Qazvin, Iran.
2 Department of Mining Engineering, Faculty of Engineering, Imam Khomeini International University
3 Department of petroleum Engineering, Masjed-Soleiman Branch, Islamic Abad University
4 Department of Mining, Petroleum and Geophysics, Shahrood University of Technology, Semnan, Iran.
5 Imam Khomeini International University, Qazvin, Iran.
چکیده [English]

Full identification and understanding of hydrocarbon reservoirs depends on knowing the mechanical properties. One of the main parameters that indicates mechanical properties is shear wave velocity. Bipolar sound recorder is among thee best tools for measuring shear wave velocity. This tool is not very popular due to the high costs of driving in the well despite the high accuracy. Shear wave velocity estimation methods include three main branches of experimental methods, regression and the use of machine learning algorithms or in other words artificial neural networks. The studied formation in this research is Sarvak in one of the oil fields in the south of Iran. The input data of the estimator model is the usual petrophysical logs that are driven and measured in many wells, and the output data is obtained from the DSI tool. In this research, data are pre-processed by removing noise effects. Then, to improve the estimation effectiveness, data with a high correlation coefficient are selected as input data. After that, shear wave velocity is estimated from petrophysical data with three types of multi-layer perceptron (MLP), multi-layer perceptron optimized by particle swarm optimization (MLP-PSO), and the introduction of a relatively new method of multi-layer perceptron-social ski drive (MLP-SSD). To compare the efficiency of the neural network method, two traditional experimental and regression methods used. The validation results show the better performance of the MLP-SSD method.

کلیدواژه‌ها [English]

  • Shear wave velocity
  • Petrophysical logs
  • Deep learning
  • Multi-layer perceptron
  • Particle swarm optimization
  • Social ski drive
  • Sarvak formation

مراجع

[1] Mohaghegh, S. D., (2005), “Recent Developments in Application of Artificial Intelligence in Petroleum Engineering,” Journal of Petroleum Technology, 57, 04, pp. 86–91.
[2] Russell, B. H., (2004), "The Application of Multivariate Statistics and Neural Networks to the Prediction of Reservoir Parameters Using Seismic Attributes", PhD Thesis, Department of Geology and Geophysics, Calgary, Alberta.
[3] Moatazedian, I., Rahimpour-Bonab, H., Kadkhodaie-Ilkhchi, A., and 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, pp. 1–17.
[4] Alimoradi, A., Shahsavani, H., and Rouhani, A. K., (2011), “Prediction of Shear Wave Velocity in Underground Layers Using SASW and Artificial Neural Networks.”
[5] Güllü, H., (2013), “On the Prediction of Shear Wave Velocity at Local Site of Strong Ground Motion Stations: An Application Using Artificial Intelligence,” Bulletin of Earthquake Engineering, 11, 4, pp. 969–997.
[6] Zoveidavianpoor, M., Samsuri, A., and Shadizadeh, S. R., (2013), “Adaptive Neuro Fuzzy Inference System for Compressional Wave Velocity Prediction in a Carbonate Reservoir,” J Appl Geophy, 89, pp. 96–107.
[7] Maleki, S., Moradzadeh, A., Riabi, R. G., Gholami, R., and Sadeghzadeh, F., (2014), “Prediction of Shear Wave Velocity Using Empirical Correlations and Artificial Intelligence Methods,” NRIAG Journal of Astronomy and Geophysics, 3, 1, pp. 70–81.
[8] Singh, S., and Kanli, A. I., (2016), “Estimating Shear Wave Velocities in Oil Fields: A Neural Network Approach,” Geosciences Journal, 20, pp. 221–228.
[9] Asoodeh, M., and Bagheripour, P., (2014), “ACE Stimulated Neural Network for Shear Wave Velocity Determination from Well Logs,” J Appl Geophy, 107, pp. 102–107.
[10] Nourafkan, A., and Kadkhodaie-Ilkhchi, A., (2015), “Shear Wave Velocity Estimation from Conventional Well Log Data by Using a Hybrid Ant Colony–Fuzzy Inference System: A Case Study from Cheshmeh–Khosh Oilfield,” J Pet Sci Eng, 127, pp. 459–468.
[11] Mehrgini, B., Izadi, H., and Memarian, H., (2019), “Shear Wave Velocity Prediction Using Elman Artificial Neural Network,” Carbonates Evaporites, 34, pp. 1281–1291.
[12] Elkatatny, S., Tariq, Z., Mahmoud, M., Mohamed, I., and Abdulraheem, A., (2018), “Development of New Mathematical Model for Compressional and Shear Sonic Times from Wireline Log Data Using Artificial Intelligence Neural Networks (White Box),” Arab J Sci Eng, 43, pp. 6375–6389.
[13] Anemangely, M., Ramezanzadeh, A., and 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, pp. 373–387.
[14] Yang, H., Xu, Y., Peng, G., Yu, G., Chen, M., Duan, W., Zhu, Y., Cui, Y., and Wang, X., (2017), “Particle Swarm Optimization and Its Application to Seismic Inversion of Igneous Rocks,” Int J Min Sci Technol, 27, 2, pp. 349–357.
[15] Tharwat, A., and Gabel, T., (2020), “Parameters Optimization of Support Vector Machines for Imbalanced Data Using Social Ski Driver Algorithm,” Neural Comput Appl, 32, pp. 6925–6938.
[16] Zhang, Y., Zhang, C., Ma, Q., Zhang, X., and Zhou, H., (2022), “Automatic Prediction of Shear Wave Velocity Using Convolutional Neural Networks for Different Reservoirs in Ordos Basin,” J Pet Sci Eng, 208, p. 109252.
[17] Rajabi, M., Hazbeh, O., Davoodi, S., Wood, D. A., Tehrani, P. S., Ghorbani, H., Mehrad, M., Mohamadian, N., Rukavishnikov, V. S., and Radwan, A. E., (2023), “Predicting Shear Wave Velocity from Conventional Well Logs with Deep and Hybrid Machine Learning Algorithms,” J Pet Explor Prod Technol, 13, 1, pp. 19–42.
[18] Davari, M. A., Senemari, S., Alimoradi, A., and Safavi, S. J., (2024), “Permeability Prediction from Log Data Using Machine Learning Methods,” Journal of Petroleum Geomechanics, 7, 3.
[19] Sarkheil, S., Hassani, H., Alinya, F., Enayati, A. A., and Motamedi, H., (2009), “A Forecasting System of Reservoir Fractures Based on Artificial Neural Network and Borehole Images Information-Exemplified by Reservoir Fractures in Tabnak Feild, Fars, Iran,” International Multidisciplinary Scientific GeoConference: SGEM, 1, p. 563.
[20] Sarkheil, H., Hassani, H., and Alinia, F., (2013), “Fractures Distribution Modeling Using Fractal and Multi-Fractal–Neural Network Analysis in Tabnak Hydrocarbon Field, Fars, Iran,” Arabian Journal of Geosciences, 6, pp. 945–956.
[21] Alimoradi, A., Hajkarimian, H., Hemati Ahooi, H., and Salsabili, M., (2022), “Comparison between the Performance of Four Metaheuristic Algorithms in Training a Multilayer Perceptron Machine for Gold Grade Estimation,” International Journal of Mining and Geo-Engineering, 56, 2, pp. 97–105.
[22] Azimi, Y., Talaeian, M., Sarkheil, H., Hashemi, R., and Shirdam, R., (2022), “Developing an Evolving Multi-Layer Perceptron Network by Genetic Algorithm to Predict Full-Scale‎ Municipal‎ Wastewater Treatment Plant Effluent,” J Environ Chem Eng, 10, 5, p. 108398.
[23] Bahri, E., Alimoradi, A., and Yousefi, M., (2023), “Investigating the Performance of Continuous Weighting Functions in the Integration of Exploration Data for Mineral Potential Modeling Using Artificial Neural Networks, Geometric Average and Fuzzy Gamma Operators,” International Journal of Mining and Geo-Engineering, 57, 4, pp. 405–412.
[24] Ebrahimi, A., Izadpanahi, A., Ebrahimi, P., and Ranjbar, A., (2022), “Estimation of Shear Wave Velocity in an Iranian Oil Reservoir Using Machine Learning Methods,” J Pet Sci Eng, 209, p. 109841.
[25] Kennedy, J., and Eberhart, R., (1995), “Particle Swarm Optimization,” Proceedings of ICNN’95-International Conference on Neural Networks, IEEE, pp. 1942–1948.
[26] Hemati Ahooi, H. R., (2021), “Optimizing Extreme Learning Machine Algorithm Using Particle Swarm Optimization to Estimate Iron Ore Grade,” Journal of Mining and Environment, 12, 2, pp. 397–411.
[27] Fathi, M., Alimoradi, A., and Hemati Ahooi, H. R., (2021), “Optimizing Extreme Learning Machine Algorithm Using Particle Swarm Optimization to Estimate Iron Ore Grade,” Journal of Mining and Environment, 12, 2, pp. 397–411.
[28] Omidi, R., Sadeghi, A., Hosseini-Barzi, M., and Akbar Bas Kelayeh, N., (2021), “New Findings in Biostratigraphy of the Sarvak and Ilam Formations of Abteymour Oil Field (Dezful Embayment),” Journal of Stratigraphy and Sedimentology Researches, 37, 1, pp. 23–44.
[29] Heydari, E., Hassanzadeh, J., Wade, W. J., and Ghazi, A. M., (2003), “Permian–Triassic Boundary Interval in the Abadeh Section of Iran with Implications for Mass Extinction: Part 1–Sedimentology,” Palaeogeogr Palaeoclimatol Palaeoecol, 193, 3–4, pp. 405–423.
[30] Rousseeuw, P. J., and Leroy, A. M., (2005), "Robust Regression and Outlier Detection", John wiley & sons.
[31] Pickett, G. R., (1963), “Acoustic Character Logs and Their Applications in Formation Evaluation,” Journal of Petroleum Technology, 15, 06, pp. 659–667.
[32] Castagna, J. P., Batzle, M. L., and Kan, T. K., (1993), “The Link between Rock Properties and AVO Response.”
[33] Brocher, T. M., (2005), “Empirical Relations between Elastic Wavespeeds and Density in the Earth’s Crust,” Bulletin of the seismological Society of America, 95, 6, pp. 2081–2092.
 
نشریه علمی ژئومکانیک نفت

مقالات آماده انتشار، پذیرفته شده
انتشار آنلاین از تاریخ 01 فروردین 1403

فایل ها

هم رسانی

ارجاع به این مقاله

آمار