Application of Convolutional Neural Network in Quantifying Reservoir Channel Characteristics
Abstract
:1. Introduction
2. Channel width Quantization Method Based on Deep Learning
2.1. Deep Convolutional Neural Networks
2.2. Methodology
- (1)
- Input the conditional data C of the actual work area, which is essentially a set containing K points.
- (2)
- Input M candidate models; Wm represents the m candidate model, where m = 1, …, M.
- (3)
- Define the number of times to sample from the candidate model as n.
- (4)
- Define the training dataset PS for convolutional deep learning.
- (5)
- Select k points randomly from Wm to get the point set Pm(i).
- (6)
- Add the label {m} to Pm(i) as the identity of the ith candidate model Wm.
- (7)
- Add Pm(i) to PS.
- (8)
- Increase i by 1 each time; if i ≤ n, go to steps (5), (6), (7); otherwise, go to step (9).
- (9)
- Increase m by 1 each time; if m ≤ M then go to step (8); otherwise, go to step (10).
- (10)
- Training the PS using CNN based on migration learning, to obtain the trained model CNNPS.
- (11)
- Using CNNPS to test C, identify the model that best matches C from M candidate models.
2.3. Methodology Testing
2.4. Comparison with Other Algorithms
3. Application
3.1. Geological Setting
3.2. Channel Candidate Models of Different Widths
3.3. Analysis of Underwater Distributary Channel Width
4. Conclusions
- (1)
- A deep convolutional neural network implemented the channel width optimization method, taking the candidate model as the population and randomly sampling it many times, ensuring that the sampling density is equal to the conditional data density. If the difference between the spatial characteristics of the sample points and the conditional data is smaller, the spatial characteristics of the model and the conditional data are considered to be more similar. After testing, the candidate models with different widths were identified as the corresponding channel width models, with over 95% accuracy in the 2D model. Compared to the two-dimensional model, the accuracy of the model training of the method in three-dimensional space was lower, but still above 80%. This shows that the method is sensitive to river channel width.
- (2)
- A comparison of the method with the MDevD-based method was carried out to verify the practicality and reliability of the method, and it was demonstrated that the recognition rate of this paper’s method closely matches the MDevD method’s recognition rate, indicating the reliability of the proposed method. In the process of conducting 100 tests, using the MDevD method took a lot of time, with the total time consumption reaching 13.7 h, while the method proposed in this paper took 53 s, indicating that the algorithm in this paper marks a great improvement in computational efficiency, and has a high degree of practicality. It can be used to analyze the channel width of the actual work area, and provide more accurate guidance for oilfield development to formulate a more reasonable development plan.
- (3)
- Based on the geological understanding and previous experience, the approximate range of channel width in the study area was determined to be between 100 and 250 m, and accordingly, candidate models with channel widths of 100 m, 130 m, 160 m, 190 m, 220 m, and 250 m were designed. Using the deep convolutional network-based channel width optimization method, candidate models for different channel widths in the research area were compared and analyzed, and the results showed that when the channel width was 160 m, it was most compatible with the conditional data in the research area. The quantitative analysis of the width of the underwater diversion channel provides a basis for the study of the fine inhomogeneity of the reservoir, which is of practical significance for the inverse deduction of the width of the river sands and the distribution characteristics of the actual workings based on the well-point data, and also provides a basis for multi-point geostatistical stochastic modeling.
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Zhang, H. Analysis of reservoir types and formation control factors in Zhangqiang Depression. J. Oil Gas Technol. 2007, 6, 7–12. [Google Scholar]
- Chen, Y. Research on Reservoir Structure and Remaining Oil Distribution in Delta. Master’s Thesis, Yangtze University, Jingzhou, China, 2021. [Google Scholar]
- Miall, A.D. Reservior heterogenerity in fluvial sandstone. AAPG Bull. 1988, 72, 682–697. [Google Scholar]
- Wang, J.; Chen, H.; Zhou, J.; Zhou, X.; Du, Y. Characterization of reservoir configuration at the front edge of the fan delta—The case of Yulou in the western Liaohe depression. Daqing Pet. Geol. Dev. 2016, 35, 20–28. [Google Scholar]
- Wang, R. Identification and distributional characteristics of the internal interbeds in the thick sandbodies of the braided river. Daqing Pet. Geol. Dev. 2016, 35, 83–87. [Google Scholar]
- Lin, C.; Yu, C.; Dong, C.; Wang, Y.; Liu, W.; Ma, C.; Liu, H.; Song, B. Residual oil distribution in an old oil field—Residual oil enrichment in the forks of a submerged diversion channel. Pet. J. 2011, 32, 829–835. [Google Scholar]
- Chen, T.; Hu, W.; Li, X.; Tang, X. Preparation of sedimentary microphase plan from dense well network area to exploratory evaluation well area. Fault-Block Oil Gas Field 2014, 21, 545–549. [Google Scholar]
- Yue, D. The Study on Analysis Analysis and Remaining Oil Distribution Patterns of Meandering River Reservoir. Ph.D. Thesis, China University of Petroleum, Beijing, China, 2006. [Google Scholar]
- Yu, H. Internal configuration of the Braided River reservoir finely characterized and residual oil distribution. Daqing Pet. Geol. Dev. 2015, 34, 73–77. [Google Scholar]
- Zhou, Y.; Wu, S.; Yue, D.; Liu, Z.; Liu, J.; Zhong, X. Delineation of a single channel within a sand body of a composite diversion channel—An example of the Sa II 1+2b minor layer in the North Second West Zone of the Sa Bei Oilfield. Pet. Geol. Recovery Effic. 2010, 17, 4–8+111. [Google Scholar]
- Liu, H.; Gao, Z.; Wu, J.; Zhang, C. Identification and quantitative characterization of a single channel sand body at the leading edge of the fan delta. Daqing Pet. Geol. Dev. 2017, 36, 17–21. [Google Scholar]
- Wang, N.; Wang, J.; Wang, F.; Fang, Z.; Zhang, P. Anatomical study and application of internal configuration of sand body in submerged diversion channel zone—A case study of Chang 8 section in Wuqi area, Ordos Basin. Pet. Geol. Eng. 2021, 35, 23–29. [Google Scholar]
- Wei, K. Research on the Simulation and Control Factors of Underwater Diversion Channel in Lake Delta. Master’s Thesis, China University of Geosciences, Beijing, China, 2018. [Google Scholar]
- Ma, S.; Zhang, Y. Application of remote sensing information images to study the river types of modern underwater diversion channels. Geol. Front. 2012, 19, 24–31. [Google Scholar]
- Xiang, C. Determination of underwater distributary channel width and drilled probability by multiple-point geostatistics. Fault-Block Oil Gas Field 2015, 22, 164–167. [Google Scholar]
- Othman, A.; Fathy, M.; Mohamed, I.A. Application of Artificial Neural Network in seismic reservoir characterization: A case study from Offshore Nile Delta. Earth Sci Inf. 2021, 14, 669–676. [Google Scholar] [CrossRef]
- Saikia, P.; Baruah, R.D.; Singh, S.K.; Chaudhuri, P.K. Artificial Neural Networks in the domain of reservoir characterization: A review from shallow to deep models. Comput. Geosci. 2020, 135, 104357. [Google Scholar] [CrossRef]
- Yadav, D.; Kim, M.C. Theoretical and numerical analyses on the onset and growth of convective instabilities in a horizontal anisotropic porous medium. J. Porous Media 2014, 17, 1061–1074. [Google Scholar] [CrossRef]
- Yadav, D.; Nair, S.B.; Awasthi, M.K.; Ragoju, R.; Bhattacharyya, K. Linear and nonlinear investigations of the impact of chemical reaction on the thermohaline convection in a permeable layer saturated with Casson fluid. Phys. Fluids 2024, 36, 014106. [Google Scholar] [CrossRef]
- Fan, L.; Zhao, H.; Zhao, H.; Hu, H.; Wang, Z. A review of target detection research based on deep convolutional neural network. Opt. Precis. Eng. 2020, 28, 1152–1164. [Google Scholar]
- Zhang, Y.; Zhang, Z. Research on the application of DenseNet in voiceprint recognition. Comput. Eng. Sci. 2022, 44, 132–137. [Google Scholar]
- Guo, C.; Chen, S.; Sima, H. Application analysis of artificial intelligence technology in unmanned vehicle. Times Automot. 2023, 21, 190–192. [Google Scholar]
- Anton, S.D.; Sinh, S.; Schotten, H.D. Anomaly-based Intrusion Detection in Industrial Data with SVM and Random Forests. In Proceedings of the International Conference on Software, Telecommunications and Computer Networks (Soft COM), Split, Croatia, 19–21 September 2019; pp. 1–6. [Google Scholar]
- Rajabi, M.M.; Javaran, M.R.; Bah, A.O.; Frey, G.; Le Ber, F.; Lehmann, F.; Fahs, M. Analyzing the efficiency and robustness of deep convolutional neural networks for modeling natural convection in heterogeneous porous media. Int. J. Heat Mass Transf. 2022, 183 Pt B, 122131. [Google Scholar] [CrossRef]
- Yang, L.; Sun, S.Z. Seismic horizon tracking using a deep convolutional neural network. J. Pet. Sci. Eng. 2020, 187, 106–109. [Google Scholar] [CrossRef]
- Waldeland, A.U.; Solberg, A.H.S.S. Salt Classification Using Deep Learning. In Proceedings of the 79th EAGE Conference and Exhibition 2017, Paris, France, 12–15 June 2017. [Google Scholar]
- Laloy, E.; Hérault, R.; Jacques, D. Training-image based geostatistical inversion using a spatial generative adversarial neural network. Water Resour. Res. 2018, 1, 381–406. [Google Scholar] [CrossRef]
- Li, Q.; Aguilera, R. Unsupervised Statistical Learning with Integrated Pattern-Based Geostatistical Simulation. In Proceedings of the SPE Western Regional Meeting 2009—Proceedings, Garden Grove, CA, USA, 22–26 April 2018. [Google Scholar]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Identity Mappings in Deep Residual Networks; Springer International Publishing: Cham, Switzerland, 2016. [Google Scholar]
- Yu, S.; Li, S. Training Image Optimization Method Based on Convolutional Neural Network and Its Application in Discrete Fracture Network Model Selection. Lithosphere 2021, 2021, 4963324. [Google Scholar] [CrossRef]
- Feng, W.; Wu, S.; Yin, Y.; Zhang, J.; Zhang, K. A training image evaluation and selection method based on minimum data event distance for multiple-point geostatistics. Comput. Geosci. 2017, 104, 35–53. [Google Scholar] [CrossRef]
Channel Model | NTG (%) | Amplitude (m) | Wavelength (m) | Width (m) | Thickness (m) |
---|---|---|---|---|---|
Models A, E | 50 | 150 | 320 | 50 | 1 |
Models B, F | 50 | 150 | 320 | 100 | 1 |
Models C, G | 50 | 150 | 320 | 150 | 1 |
Models D, H | 50 | 150 | 320 | 200 | 1 |
Channel Model | Min. Width (m) | Mean Width (m) | Max. Width (m) |
---|---|---|---|
Models A, E | 40 | 50 | 60 |
Models B, F | 90 | 100 | 110 |
Models C, G | 140 | 150 | 160 |
Models D, H | 190 | 200 | 210 |
Recognition Rate | 50 m Channel | 100 m Channel | 150 m Channel | 200 m Channel |
---|---|---|---|---|
cd_W1 | 99% | 1% | 0 | 0 |
cd_W2 | 0% | 96% | 2% | 2% |
cd_W3 | 0 | 7% | 94% | 1% |
cd_W4 | 0 | 0 | 1% | 99% |
Recognition Rate | 50 m Channel | 100 m Channel | 150 m Channel | 200 m Channel |
---|---|---|---|---|
cd_W1 | 96% | 4% | 0% | 0% |
cd_W2 | 4% | 90% | 4% | 2% |
cd_W3 | 0% | 12% | 80% | 8% |
cd_W4 | 0% | 0% | 14% | 86% |
Amplitude (m) | Wavelength (m) | Thickness (m) | Width (m) |
---|---|---|---|
400−1000 | 1500−3000 | 1−5 | 100−250 |
Channel Model | Min. Width (m) | Mean Width (m) | Max. Width (m) |
---|---|---|---|
Model a | 90 | 100 | 110 |
Model b | 120 | 130 | 140 |
Model c | 150 | 160 | 170 |
Model d | 180 | 190 | 200 |
Model e | 210 | 220 | 230 |
Model f | 240 | 250 | 260 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Wei, J.; Li, S. Application of Convolutional Neural Network in Quantifying Reservoir Channel Characteristics. Appl. Sci. 2024, 14, 2241. https://doi.org/10.3390/app14062241
Wei J, Li S. Application of Convolutional Neural Network in Quantifying Reservoir Channel Characteristics. Applied Sciences. 2024; 14(6):2241. https://doi.org/10.3390/app14062241
Chicago/Turabian StyleWei, Jie, and Shaohua Li. 2024. "Application of Convolutional Neural Network in Quantifying Reservoir Channel Characteristics" Applied Sciences 14, no. 6: 2241. https://doi.org/10.3390/app14062241