딥러닝 알고리듬을 활용한 고해상도 물리검층 자료의 생성 연구
Generation of High-Resolution Well Log Data by Using a Deep-Learning Algorithm
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
이 연구는 정확도 높은 유·가스 저류층 특성화를 위하여 원시 물리검층 자료로부터 암석 코어자료와 부합하는 고해상도의 합성 물리검층 자료를 생성하는 딥러닝 기반 방법을 제안한다. 제안한 방법의 신뢰도는 노르웨이 Volve 유전을 대상으로 세 가지 유형의 딥러닝 알고리듬(심층신경망, 합성곱신경망, 장단기메모리)을 적용하여 평가하였다. 위 알고리듬들은 타 물리검층 자료로부터 음파 검층 자료를 고해상도로 추정하였다. 전반적으로 각 딥러닝 알고리듬의 성능이 우수하였다. 특히, 장단기메모리 알고리듬의 예측 성능은 원시해상도 대비 2배, 5배, 10배의 고해상도 자료를 생성한 경우에 대해 결정계수가 0.9 이상으로 우수하게 나타났다. 제안한 모델은 향후 코어 기반 저류층인자와 부합하는 물리검층 기반 저류층 인자의 도출에 활용할 수 있을 것으로 기대한다.
Abstract
This study proposed a deep-learning-based approach that generates synthetic high-resolution log data from original-resolution log data for accurate reservoir characterization, where the resolution of the synthetic data is comparable to that of core data. The reliability of the proposed approach was tested with application to the Volve oil field in Norway using three deep-learning algorithms (i.e., deep neural network, convolutional neural network, and long short-term memory). These deep-learning algorithms were employed to generate high-resolution sonic log data from other log-type data. The overall performance of each algorithm was acceptable. In particular, the long short-term memory algorithm yields a coefficient of determination greater than 0.9 when the high-to-original-resolution ratios are two, five, and ten. We anticipate that the proposed model can be used to derive logging-based reservoir parameters with a resolution that is comparable to that of core-based reservoir parameters.
참고문헌 (33)
- Alimohammadi, H., "Single and multi-well synthetic well log generation using multivariate analysis", SPE Abu Dhabi International Petroleum Exhibition & Conference, pp.1~14 (2020)
- Bateman, R.M., "Openhole Log Analysis and Formation Evaluation", pp.647~ (1986), Schlumberger
- Da Costa Filho, C. A., "Imaging strategies using focusing functions with applications to a North Sea field", Geophysical Journal International, 213(1), pp.561~573 (2018)
- Dong, S., "Fracture identification and evaluation using conventional logs in tight sandstones: a case study in the Ordos Basin, China", Energy Geoscience, 1(3-4), pp.115~123 (2020)
- Trends in U.S. Oil and Natural Gas Upstream Costs, "EIA", 1~141 (2016)
- Gaymard, R., "Response of neutron and formation density logs in hydrocarbon bearing formations", The Log Analyst, 9(5), pp.3~20 (1968)
- Horozal, S., "Core and sediment Physical property correlation of the second Ulleung Basin Gas Hydrate Drilling Expedition (UBGH2) results in the East Sea (Japan Sea)", Marine and Petroleum Geology, 59, pp.535~562 (2015)
- 지민수, "물리검층자료를 활용한 딥러닝 기반 수포화도 예측", 한국자원공학회지, 58(3), pp.215~226 (2021), 한국자원공학회
- 김길영, "미고결 퇴적층내 가스하이드레이트 포화도 계산", 지구물리와 물리탐사, 15(2), pp.102~115 (2012), 한국지구물리.물리탐사학회[DOI]
- Kim, S., "Generation of synthetic density log data using deep learning algorithm at the Golden field in Alberta, Canada", Geofluids, 2020, pp.1~26 (2020)
- 김영민, "동해 울릉분지 UBGH2-6 하이드레이트 지층 및 포화율 분포 특성을 고려한 시뮬레이션 연구", 한국자원공학회지, 59(1), pp.69~90 (2022), 한국자원공학회
- 권서윤, "북해 Volve 유전 현장자료의 공공데이터화와 저류층 모델에 대한 분석", 한국자원공학회지, 58(4), pp.353~363 (2021), 한국자원공학회
- Facies prediction from well logs in the Precipice Sandstone and Evergreen Formation in the Surat Basin, "La Croix, A.", The University of Queensland, 46~ (2019)
- Lee, M.W., "In-situ gas hydrate hydrate saturation estimated from various well logs at the Mount Elbert Gas hydrate stratigraphic test well, Alaska North Slope", Marine and Petroleum Geology, 28(2), pp.439~449 (2011)
- Mahmoudi, S., "Water saturation and porosity prediction using back-propagation artificial neural network (BPANN) from well log data", Journal of Engineering and Technology, 5(2), pp.1~8 (2014)
- Maiti, S., "Neural network modelling and classification of lithofacies using well log data: a case study from KTB borehole site", Geophysical Journal International, 169(2), pp.733~746 (2007)
- Miah, M. I., "Log data-driven model and feature ranking for water saturation prediction using machine learning approach", Journal of Petroleum Science and Engineering, 194, pp.1~19 (2020)
- 민배현, "석유가스 개발사업의 인공지능기술 활용 현황 및 전망", 한국자원공학회지, 57(3), pp.295~308 (2020), 한국자원공학회
- Mukherjee, B., "Prediction of reservoir parameters in gas hydrate sediments using artificial intelligence (AI): a case study in Krishna-Godavari Basin (NGHP Exp-02)", Journal of Earth System Science, 128(7), pp.1~14 (2019)
- Onalo, D., "Data driven model for sonic well log prediction", Journal of Petroleum Science and Engineering, 170, pp.1022~1037 (2018)
- Onalo, D., "Data-driven model for shear wave transit time prediction for formation evaluation", Journal of Petroleum Exploration and Production Technology, 10, pp.1429~1447 (2020)
- 박가영, "가스하이드레이트 저류층 모델링을 위한 심층학습 기반 물리검층 해석의 최신 기술동향 분석", 한국자원공학회지, 58(2), pp.161~178 (2021), 한국자원공학회
- Park, G.Y., "High-resolution Estimation of Reservoir Parameters with the Deep-learning-based Interpretation of Well Logging Data", MS, pp.2021
- Pham, N., "Missing well log prediction using convolutional long short-term memory network", Geophysics, 85(4), pp.1~55 (2020)
- Rolon, L., "Using artificial neural networks to generate synthetic well logs", Journal of Natural Gas Science and Engineering, 1(4-5), pp.118~133 (2009)
- Salehi, M. M., "Estimation of the non records logs from existing logs using artificial neural networks", Egyptian Journal of Petroleum, 26(4), pp.957~968 (2017)
- Saputro, O. D., "Porosity log prediction using artificial neural network", Journal of Physics: Conference Series, 739, pp.1~6 (2016)
- Schlumberger, "Well Evaluation Conference Middle East, vol 1, Text vol 2, Examples 2" (1967), Schlumberger
- Discovery Evaluation Report, Well 15, "9-19 SR, Theta Vest Structure", Statoil, 1993, pp.195~
- Final Well Report Well NO 15, "9-F-11, F-11 T2, F-11 A, F-11 B Volve Field", Statoil, 2013
- Final Well Report Well NO 15, "9-F-1, F-1 A, F-1 B Volve Field", Statoil, 2014
- Wyllie, M. R. J., "An experimental investigation of factors affecting elastic wave velocities in porous media", Geophysics, 23(3), pp.459~493 (1958)
- Zhang, D., "Synthetic well logs generation via recurrent neural networks", Petroleum Exploration and Development, 45(4), pp.629~639 (2018)