Abstract
Geomechanical characterization is one of the significant steps in subsurface studies. Stiffness (M) and lambda parameters are two critical factors commonly used to evaluate rocks. There are some ways to masseur them which they are classified by two main methods, including direct and indirect methods. Direct methods are done on coring samples by laboratory test; however, some problems limit these methods. For example, obtaining cores in some situations is difficult or impossible. In this paper, using Deep Artificial Neural Network (DANN) based on seismic velocities, we predict stiffness and lame parameters. Finally, all results are evaluated by (R), Root Mean Square Error (RMSE), and Mean Square Error (MSE). The results prove that the DANN method should be considered a suitable tool for predicting target parameters with R=0.97 and 0.98 for stiffness and lambda parameters, respectively. Furthermore, RMSE and MSE for lame prediction are less than that of stiffness.
Keywords: Soft computing approaches, Deep learning neural network, rock stiffness, lame parameters, seismic velocities, porous media.
Download Full Text
References
[1] BADAKHSHAN, Ehsan, et al. Application of Particle Stiffness Fabric Tensor for Modeling Inherent Anisotropy in Rocks. Rock Mechanics and Rock Engineering, 2021, 1-17.
[2] XIE, Heping, et al. Experimental study on rock mechanical behavior retaining the in situ geological conditions at different depths. International Journal of Rock Mechanics and Mining Sciences, 2021, 138: 104548.
[3] BULUT, Berrak, et al. Determination of matrix composition for diamond cutting tools according to the hardness and abrasivity properties of rocks to be cut. International Journal of Refractory Metals and Hard Materials, 2021, 95: 105466.
[4] MA, Shaosen; CHEN, Weizhong; ZHAO, Wusheng. Mechanical properties and associated seismic isolation effects of foamed concrete layer in rock tunnel. Journal of Rock Mechanics and Geotechnical Engineering, 2019, 11.1: 159-171.
[5] Zoback, M. D. (2010). Reservoir geomechanics. Cambridge university press.
[6] GAO, Mei-ben, et al. Identifying crack initiation stress threshold in brittle rocks using axial strain stiffness characteristics. Journal of Mountain Science, 2018, 15.6: 1371-1382.
[7] HUNZIKER, Jürg, et al. Seismic attenuation and stiffness modulus dispersion in porous rocks containing stochastic fracture networks. Journal of Geophysical Research: Solid Earth, 2018, 123.1: 125-143.
[8] GORDIN, Y., et al. Rock Physics Application for Predicting Thermal Maturation of Organic-Rich Carbonates. In: 55th US Rock Mechanics/Geomechanics Symposium. OnePetro, 2021.
[9] Avseth, P., & Veggeland, T. Seismic screening of rock stiffness and fluid softening using rock-physics attributes. Interpretation, 3(4), SAE85-SAE93, 2015.
[10] Arabali, A., Khajehzadeh, M., Keawsawasvong, S., Mohammed, A. H., & Khan, B. (2022). An Adaptive Tunicate Swarm Algorithm for Optimization of Shallow Foundation. IEEE Access, 10, 39204-39219. doi:10.1109/ACCESS.2022.3164734 (link)
[11] Asgari, G. R., Arabali, A., Babaei, M., & Asemi, K. (2022). Dynamic Instability of Sandwich Beams Made of Isotropic Core and Functionally Graded Graphene Platelets- Reinforced Composite Face Sheets. International Journal of Structural Stability and Dynamics, 2250092. doi:10.1142/S0219455422500924 (link)
[12] Mostofizadeh, S., & Tee, K. F. (2019). Evaluation of impact of fly ash on the improvement on type II concrete strength. Evaluation, 9, 10th. (link)
[13] Mostofizadeh, S., & Tee, K. F. (2021). Static and Seismic Responses of Eco-Friendly Buried Concrete Pipes with Various Dosages of Fly Ash. Applied Sciences, 11(24), 11700. (link)
[14] F Ayatollah Zadeh Shirazi, F Ebrahinifar, A Gharagozlou, Counterexamples In Chaotic Generalized Shifts, Journal of Mahani Mathematical Research Center 5 (2), 85-97 (link)
[15]Hamidreza Jalili, S. K. (2022). Recent Advances in Water Resource Engineering: Rose Publication Melbourne. https://www.amazon.com/dp/0645461288/ref=olp-opf-redir?aod=1[16] Jalili;, A. H. D. H. (2014). Study of vortex flow extending around the reservoir sluice gate in order to increase in flushing efficiency. Iranian Water Research Journal, 08(15), 51-62.
[17] Bagherpour, R, Mozayani, N, Badnava, B. Improving demand-response scheme in smart grids using reinforcement learning. Int J Energy Res. 2021; 45( 15): 21082- 21095. doi:10.1002/er.7165
[18] Sihotang, S. M., & Herawati, I. Simultaneous Seismic Inversion for Reservoir Characterization at Poseidon Field, Browse Basin, Australia. Al-Fiziya: Journal of Materials Science, Geophysics, Instrumentation and Theoretical Physics, 4(1), 63-73, 2021.
[19] Najibi, A. R., Ghafoori, M., Lashkaripour, G. R., & Asef, M. R. ,Reservoir geomechanical modeling: In-situ stress, pore pressure, and mud design. Journal ofPetroleum Science and Engineering, 151, 31-39, 2017.
[20] Taheri, A., RahimiZadeh, K., & Rao, R. V. (2021). An efficient Balanced Teaching-Learning-Based optimization algorithm with Individual restarting strategy for solving global optimization problems. Information Sciences, 576, 68-104.
[21] Alizadeh, S. M., Ghazanfari, A., Ehyaei, M. A., Ahmadi, A., Jamali, D. H., Nedaei, N., & Davarpanah, A. (2020). Investigation the Integration of Heliostat Solar Receiver to Gas and Combined Cycles by Energy, Exergy, and Economic Point of Views. Applied Sciences, 10(15), 5307. Retrieved from https://www.mdpi.com/2076-3417/10/15/5307 (link)
[22] Goodway, B., Szelewski, C., Overell, S., Corbett, N., & Skrypnek, T. Calibrated AVO and LMR analysis using a new DHI flat-spot AVO class 6 fluid contact to mitigate reservoir risk at Stonehouse, offshore Nova Scotia. CSEG Recorder, 33, 22-32, 2008.