Application of Machine Learning Technologies for optimizing CO2 EOR-Storage Processes

Won Suk Lee; Youngjun Hong

doi:10.32390/ksmer.2020.57.6.564

All Issue

2020 Vol.57, Issue 6 Preview Page Next Page

Research Paper

Application of Machine Learning Technologies for optimizing CO₂ EOR-Storage Processes 이산화탄소 회수증진-저장 최적화를 위한 머신러닝 기법 적용연구

31 December 2020. pp. 564-574

PDF XML

Abstract

This paper investigates an applicability and efficiency of machine learning algorithm in CCS-EOR(Carbon Capture & Storage-Enhanced Oil Recovery) optimization processes. By using simulation results of 105 cases according to variation of selected 8 influencing factors in the reference, all cases reaching to 2,916 were predicted by developed proxy model. For improved training and testing accuracy, the hyperopt algorithm was adopted and in case of objective function NPV, the testing accuracy is achieved above 92%. However, in cases of other objective functions such as recovery factor, CO₂ stored, it is required to re-select influencing factors more sensitive to respective objective functions. Machine learning optimization process suggested in this paper, can be utilized as conventional optimization methods, especially, it can be more efficient procedure in complex optimization processes with additional influencing factors.

Keywords

CCS-EOR

Machine learning

Proxy model

Optimization

이 연구에서는 CCS-EOR 저류층 최적화 분석을 위한 머신러닝 기법 적용성 및 효율성을 검토하였다. 기존 문헌에서 수행된 8개 인자 변화에 따른 105개의 경우의 수에 대한 시뮬레이션 결과를 활용하여, 개발된 프록시 모델을 적용하여 2,916개에 달하는 모든 시뮬레이션 경우의 수를 예측하였다. 머신러닝 모델 개발에 있어 초매개변수(hyper-parameter) 선정 최적화 과정을 도입하여 학습 및 예측 과정을 향상시켰으며, 목적함수 NPV의 경우 평균 적합도 92% 이상의 정확도를 확보하였다. 그러나 회수율 및 저장량 등의 목적함수에 대한 최적화 수행 결과, 보다 목적함수에 민감한 영향인자 재선정이 필요함을 알 수 있었다. 목적함수에 대한 적절한 영향인자 선정 및 학습자료가 확보될 경우, 머신러닝 최적화 기법은 기존의 최적화 과정을 대체할 수준의 매우 효과적인 방법임을 확인하였으며, 영향인자가 추가되어 경우의 수가 증가할 경우 보다 효과적으로 최적화 분석에 이용될 수 있을 것으로 판단된다.

키워드

CCS-EOR

머신러닝

프록시 모델

최적화

References

Brochu, E., Cora, V.M., and de Freitas, N., 2010. A tutorial on bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning. arXiv: 1012.2599v1.

Clarkson, C.R. and Pedersen, P.K., 2011. Production analysis of western canadian unconventional light oil plays. Presented at the Canadian Unconventional Resources Conference, Calgary, Alberta, Canada, 15-17 November, SPE-149005. 10.2118/149005-MS

Ertekin, T. and Sun, Q., S.L., 2019. Artificial intelligence applications in reservoir engineering: a status check. Energies, 12, p.1-22. 10.3390/en12152897

Ettehadtavakkol, A., Lake, L.W., and Bryant, S.L., 2014. CO₂-EOR and Storage Design Optimization. International Journal of Greenhouse Gas Contrel, 25, p.79-92. 10.1016/j.ijggc.2014.04.006

Géron, A., 2019. Hands-on Machine Learning with Scikit- Learn, Keras, and Tensorflow, 2^nd Edition, O'reilly Media, Inc.

Ghaderi, S.M., Clarkson, C.R., and Chen, S., 2012. Optimiztion of WAG process for coupled CO₂ EOR-Storage in tight oil formation: an experimental design approach. Presented at the SPE Canadian Unconventional Resources Conference, Calgary, Alberta, Canada, 30 October -1 November, SPE-161884. 10.2118/161884-MS

Godec, M., Kuuskraa, V., Leeuwen, T., Melzer, L.S., and Wildgust, N., 2011. CO₂ Storage in depleted oil fields: the worldwide potential for carbon dioxide enhance oil recovery. Energy Procedia, 4, p.2162-2169. 10.1016/j.egypro.2011.02.102

Kim, J, Kang, J., Park, C., Ahn, S., and Min, B., 2017. History matching of gas production rates integrated an artificial neural network with distance-based candidate selection. Journal of The Korean Society of Mineral and Energy Resources Engineers, 54(4), p.416-428. 10.12972/ksmer.2017.54.4.416

Kovscek, A.R. and Cakici, M.D., 2005. Geologic storage of carbon dioxide and enhanced oil recovery II: Co-optimization of storage and recovery. Energy Conversion and Management, 46, p.1941-1956. 10.1016/j.enconman.2004.09.009

Min, B, Kwon, S., Park, G., Jeong, D., and Lee, H., 2020. Current status and prospects of artificial intelligence in the oil and gas exploration and production business. Journal of The Korean Society of Mineral and Energy Resources Engineers, 57(3), p.295-308. 10.32390/ksmer.2020.57.3.295

Montgomery, D.C., 2013. Design and Analysis of Experiments, 8th Edition, John Wiley & Sons, Inc.

Perera, M.S.A., Gamage, R.P.G., Rathnaweera, T.D., Ranathunga, A.S., Koay, A., and Choi, X., 2016. A Review of CO₂- Enhanced Oil Recovery with a Simulated Sensitivity Analysis. Energies, 9, p.481. 10.3390/en9070481

Scikit-learn Machine Learning in Python, 2020.10.02., https://scikit-learn.org

Information

Publisher :The Korean Society of Mineral and Energy Resources Engineers
Publisher(Ko) :한국자원공학회
Journal Title :Journal of the Korean Society of Mineral and Energy Resources Engineers
Journal Title(Ko) :한국자원공학회지
Volume : 57
No :6
Pages :564-574
Received Date : 2020-10-14
Revised Date : 2020-12-04
Accepted Date : 2020-12-22
DOI :https://doi.org/10.32390/ksmer.2020.57.6.564

Journal of the Korean Society of Mineral and Energy Resources Engineers ISSN:2288-0291(Print) 2288-2790(Online) 한국자원공학회지

All Issue