Accurate determination of nano-confined minimum miscible pressure to aid CO2 enhanced oil recovery and storage in unconventional reservoirs
Abstract view|0|times PDF download|0|times
Abstract
The precise determination of minimum miscible pressure is of great importance for CO2 enhanced oil recovery and storage as it directly influences the efficiency of pore-scale oil displacement and CO2 trapping. In this study, an interpretable machine learning framework is developed, enabling the reliable evaluation of nano-confined minimum miscible pressure. Four machine learning algorithms (Random Forest, Multi-layer Perceptron, Support Vector Regression, and eXtreme Gradient Boosting) are employed to accurately predict the nano-confined minimum miscible pressure of a CO2-oil system. The results demonstrate that, excluding support vector regression, the determination coefficients for all models surpass 94%, signifying the robust predictive performance of our model. Subsequently, Shapley Additive exPlanations is used to analyze the feature importance ranking and the impact of each input feature on minimum miscible pressure in these models. Based on the interpretation results, our multi-layer perceptron model is superior in mining the input-output relationship and reflecting the petrophysical laws, rendering it highly suitable for predicting the minimum miscible pressure while considering nano-confinement. In addition, it is found that pore size significantly influences minimum miscible pressure prediction and that minimum miscible pressure decreases with decreasing pore size when the pore size is ≤75 nm. Single-factor sensitivity analysis is applied to validate the trend patterns between input features and minimum miscible pressure in the multi-layer perceptron model.
Document Type: Original article
Cited as: He, Y., Wei, B., Zhao, J. You, J., Kadet, V., Lu, J. Accurate determination of nano-confined minimum-miscible-pressure to aid CO2 enhanced oil recovery and storage in unconventional reservoirs. Advances in Geo-Energy Research, 2024, 12(2): 141-155. https://doi.org/10.46690/ager.2024.05.06
Keywords
Full Text:
PDFReferences
Alharthy, N., Teklu, T., Kazermi, H., et al. Enhanced oil recovery in liquid-rich shale reservoirs: Laboratory to field. SPE Reservoir Evalation & Engineering, 2018, 21(1): 137-159.
Bo, B., Feng, J., Qiu, J., et al. Direct measurement of minimum miscibility pressure of decane and CO2 in nanoconfined channels. ACS Omega, 2021, 6(1): 943- 953.
Breiman, L. Random forests. Machine Learning, 2001, 45: 5-32.
Cai, J., Xu, K., Zhu, Y., et al. Prediction and analysis of net ecosystem carbon exchange based on gradient boosting regression and random forest. Applied Energy, 2020, 262: 114566.
Chemmakh, A., Merzoug, A., Ouadi, H., et al. Machine learning predictive models to estimate the minimum miscibility pressure of CO2-oil system. Paper SPE 207865 Presented at Abu Dhabi International Petroleum Exhibition & Conference, Abu Dhabi, UAE, 15-18, November, 2021.
Chen, G., Fu, K., Liang, Z., et al. The genetic algorithm based back propagation neural network for MMP prediction in CO2-EOR process. Fuel, 2014, 126: 202-212.
Chen, H., Zhang, C., Yu, H., et al. Application of machine learning to evaluating and remediating models for energy and environmental engineering. Applied Energy, 2022, 320: 119286.
Dargahi-Zarandi, A., Hemmati-Sarapardeh, A., Shateri, M., et al. Modeling minimum miscibility pressure of pure/impure CO2-crude oil systems using adaptive boosting support vector regression: Application to gas injection processes. Journal of Petroleum Science and Engineering, 2020, 184: 106499.
Dehghani, S. A. M., Sefti, M. V., Ameri, A., et al. Minimum miscibility pressure prediction based on a hybrid neural genetic algorithm. Chemical Engineering Research and Design, 2008, 86(2): 173-185.
Feng, Q., Xu, S., Xing, X., et al. Advances and challenges in shale oil development: A critical review. Advances in Geo-Energy Research, 2020, 4(4): 406-418.
Ge, D., Cheng, H., Cai, M., et al. A new predictive method for CO2-oil minimum miscibility pressure. Geofluids, 2021, 2021: 8868592.
Hamada, Y., Koga, K., Tanaka, H. Phase equilibria and interfacial tension of fluids confined in narrow pores. The Journal of Chemical Physics, 2007, 127: 084908.
Hao, M., Liao, S., Yu, G., et al. Performance optimization of CO2 huff-n-puff for multifractured horizontal wells in tight oil reservoirs. Geofluids, 2020, 2020: 8840384.
Hawthorne, S. B., Miller, D. J., Jin, L., et al. Rapid and simple capillary-rise/vanishing interfacial tension method to determine crude oil minimum miscibility pressure: pure and mixed CO2, methane and ethane. Energy & Fuels, 2016, 30(8): 6365-6372.
Huang, C., Tian, L., Wu, J., et al. Prediction of minimum miscibility pressure (MMP) of the crude oil-CO2 systems within a unified and consistent machine learning framework. Fuel, 2023, 337: 127194.
Li, L., Qiao, J., Yu, G., et al. Interpretable tree-based ensemble model for predicting beach water quality. Water Research, 2022, 211: 118078.
Li, S., Luo, P. Experimental and simulation determination of minimum miscibility pressure for a Bakken tight oil and different injection gases. Petroleum, 2017, 3(1): 79-86.
Liang, M., Yuan, H., Yang, Y., et al. Research progress on miscible gas displacement and determination of minimum miscibility pressure. Journal of Southwest Petroleum University (Science & Technology Edition), 2017, 39(5): 101-112. (in Chinese)
Liao, C., Liao, X., Chen, J., et al. Correlations of minimum miscibility pressure for pure and impure CO2 in low permeability oil reservoir. Journal of the Energy Institute, 2014, 87(3): 208-214.
Lu, H., Xu, Y., Duan, C., et al. Experimental study on capillary imbibition of shale oil in nanochannels. Energy & Fuels, 2022, 36(10): 5267-5275.
Lundberg, S. M., Lee, S. A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 2017, 30: 4768-4777.
Lv, Q., Zheng, R., Guo, X., et al. Modelling minimum miscibility pressure of CO2-crude oil systems using deep learning, tree-based, and thermodynamic models: Application to CO2 sequestration and enhanced oil recovery. Separation and Purification Technology, 2023, 310: 123086.
Ma, X., Hou, M., Zhan, J., et al. Interpretable predictive modeling of tight gas well productivity with SHAP and LIME techniques. Energies, 2023, 16: 3653.
Min, C., Wen, G., Gou, L., et al. Interpretability and causal discovery of the machine learning models to predict the production of CBM wells after hydraulic fracturing. Energy, 2023, 285: 129211.
Molnar, C. Interpretable machine learning, 2020. Nguyen, P., Mohaddes, D., Riordon, J., et al. Fast fluorescence-based microfluidic method for measuring minimum miscibility pressure of CO2 in crude oils. Analytical Chemistry, 2015, 87(6): 3160-3164.
Novosad, Z., Sibbald, L. R., Costain, T. G. Design of miscible solvents for a rich gas drive-comparison of slim tube and rising bubble tests. Journal of Canadian Petroleum Technology, 1990, 29(1): 37-42.
Safaei, A., Riazi, M., Shariat, S. A novel experimental-theoretical method to improve MMP estimation using VIT technique. Journal of Petroleum Science and Engineering, 2023, 220: 111182.
Sambo, C., Liu, N., Shaibu, R., et al. A technical review of CO2 for enhanced oil recovery in unconventional oil reservoirs. Geoenergy Science and Engineering, 2023, 221: 111185.
Shen, B., Yang, S., Gao, X., et al. Interpretable knowledge-guided framework for modeling minimum miscible pressure of CO2-oil system in CO2-EOR projects. Engineering Applications of Artificial Intelligence, 2023, 118: 105687.
Shokir, E. M. E. CO2-oil minimum miscibility pressure model for impure and pure CO2 streams. Journal of Petroleum Science and Engineering, 2007, 58(1-2): 173-185.
Sun, H., Li, H. Minimum miscibility pressure determination in confined nanopores considering pore size distribution of tight/shale formations. Fuel, 2021, 286: 119450.
Teklu, T. W., Alharthy, N., Kazemi, H., et al. Vanishing interfacial tension algorithm for MMP determination in unconventional reservoirs. Paper SPE 169517 presented at SPE Western North American and Rocky Mountain Joint Meeting, Denver, Colorado, 17-18 April, 2014a.
Teklu, T. W., Alharthy, N., Kazemi, H., et al. Phase behavior and minimum miscibility pressure in nanopores. SPE Reservior Evalation & Engineering, 2014b, 17(3): 396- 403.
Tovar, F. D., Barrufet, M. A., Schechter, D. S. Enhanced oil recovery in the Wolfcamp shale by carbon dioxide or nitrogen injection: An experimental investigation. SPE Journal, 2021, 26(1): 515-537.
Wang, S., Ma, M., Chen, S. Application of PC-SAFT equation of state for CO2 minimum miscibility pressure prediction in nanopores. Paper SPE 179535 Presented at SPE Improved Oil Recovery Conference, Tulsa, Oklahoma, USA, 11-13 April, 2016.
Wei, B., Liu, J., Zhang, X., et al. Advances of enhanced oil recovery method and theory in tight reservoirs. Journal of Southwest Petroleum University (Science & Technology Edition), 2021, 43(1): 91-102. (in Chinese)
Wei, B., Zhong, M., Wang, L., et al. Oil recovery dynamics of natural gas huff ‘n’ puff in unconventional oil reservoirs considering the effects of nanopore confinement and its proportion: A mechanistic study. SPE Reservoir Evalation & Engineering, 2022a, 25(4): 667-683.
Wei, B., Zhong, M., Zhao, J., et al. Prediction method for the minimum miscibility pressure of crude oil and natural gas in micro-nano confined space. Acta Petrolei Sinica, 2022b, 43(11): 1604-1613. (in Chinese)
Yang, L., Shami, A. On hyperparameter optimization of machine learning algorithms: Theory and practice. Neuro-computing, 2020, 415: 295-316.
You, J., Ampomah, W., Sun, Q., et al. Machine learning based co-optimization of carbon dioxide sequestration and oil recovery in CO2-EOR project. Journal of Cleaner Production, 2020, 260: 120866.
ZareNezhad, B. A new correlation for predicting the minimum miscibility pressure regarding the enhanced oil recovery processes in the petroleum industry. Petroleum Science and Technology, 2016, 34 (1): 56-62.
Zhang, K., Jia, N., Zeng, F., et al. A new diminishing interface method for determining the minimum miscibility pressures of light oil-CO2 systems in bulk phase and nanopores. Energy & Fuels, 2017, 31(11): 12021-12034.
Zhang, K., Jia, N., Zeng, F., et al. A review of experimental methods for determining the oil-gas minimum miscibility pressures. Journal of Petroleum Science and Engineering, 2019, 183: 106366.
Zhao, H., Fang, Z. Improved multiple-mixing-cell method for accelerating minimum miscibility pressure calculations. SPE Journal. 2020, 25(4): 1681-1696.
Zhao, J., Jin, L., Azzolina N. A., et al. Investigating enhanced oil recovery in unconventional reservoirs based on field case review, laboratory, and simulation studies. Energy & Fuels, 2022, 36(24): 14771-14788.
DOI: https://doi.org/10.46690/ager.2024.05.06
Refbacks
- There are currently no refbacks.
Copyright (c) 2024 The Author(s)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.