이산화탄소 지중저장을 위한 기계학습 기반 4-D 탄성파자료 통합 및 배사구조 채널대수층 특성화
Machine Learning-based 4-D Seismic Data Integration and Characterization of Channelized Anticline Aquifer for Geological Carbon Sequestration
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
본 연구에서는 채널대수층의 이산화탄소 지중저장에서 4-D 탄성파자료를 통합해 불확실성을 정량화하고 신뢰도를 향상하기 위해 기계학습의 하나인 Pix2Pix 기반의 4-D 탄성파자료 통합기법을제안한다. 다점지구통계 기법으로 다양한 지질학적 시나리오를 따르는 2차원 채널대수층 모델을바탕으로 Pix2Pix을 학습시킨 후, 참조 채널대수층의 4-D 탄성파 변화를 입력하여 채널대수층 모델을 특성화한다. Pix2Pix을 구성하는 인공신경망 모델의 일부 연결을 끊는 (1) dropout을 이용하는방법과 (2) 인공신경망의 입력층에 랜덤 노이즈 맵을 추가하는 방법을 이용해 주어진 자료를 만족하며 지질학적 사실성을 보전하는 다양한 모델을 생성하고 이들로부터 불확실성을 정량화 한다. Pix2Pix을 이용해 생성된 채널대수층은 참조 모델의 채널 방향성과 암상분포의 예측을 개선하였고, 나아가 미래 이산화탄소 액적군의 이동을 정확하게 예측한다. 제안한 방법은 채널대수층에서이산화탄소 지중저장을 하는 경우 4-D 탄성파자료를 통합해 불확실성을 평가함으로 이산화탄소지중저장의 모니터링기술로 활용될 수 있다.
Abstract
This study introduces a 4-D seismic data integration approach based on Pix2Pix to quantify uncertainty and enhance reliability in subsurface CO2 storage within channelized aquifers. We address geological uncertainties, such as the azimuth of channel direction, using multi-point statistics to generate diverse channelized aquifer models, to form the Pix2Pix training dataset. After successfully training the Pix2Pix, we realize the channelized aquifer models by assimilating 4-D seismic data changes from a reference channelized aquifer. The Pix2Pix dataset is crafted with (1) disconnections in artificial neural networks using dropout and (2) the addition of random noise to the input layer, yielding an ensemble of models that align with the provided data for quantifying uncertainty. Generating channelized aquifers using the suggested method improves prediction of channel direction, facies distribution, and accurate forecasts of future CO2 plume movement. As an advanced monitoring technology, our method integrates 4-D seismic data for effective CO2 storage in channelized aquifers.
참고문헌 (34)
- Ahn, Y., "Reliable channel reservoir characterization and uncertainty quantification using variational autoencoder and ensemble smoother with multiple data assimilation", Journal of Petroleum Science and Engineering, 209, pp.109816~ (2022)
- Bennion, D. B., "Relative permeability characteristics for supercritical CO2 displacing water in a variety of potential sequestration zones in the western Canada sedimentary basin", SPE Annual Technical Conference and Exhibition (2005)
- Bennion, D. B., "Permeability and relative permeability measurements at reservoir conditions for CO2-water systems in ultralow-permeability confining caprocks", SPE Europec featured at EAGE Conference and Exhibition (2007)
- Cheong, S., "Test processing of seismic monitoring using Sleipner 4D data", Journal of the Korean Society of Mineral and Energy Resources Engineers, 59(1), pp.31~41 (2022)
- Computer Modelling Group, "GEM user's guide version 2020", CMG, ~ (2020)
- Deutsch, C.V., "Geostatistical software library and user’s guide", New York, 119(147), pp.578~ (1992)
- Furre, A. K., "20 years of monitoring CO2-injection at Sleipner", Energy procedia, 114, pp.3916~3926 (2017)
- Goodfellow, I., "Generative adversarial nets", Neural Information Processing Systems, pp.2672~2680 (2014)
- He, K., "Deep residual learning for image recognition", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.770~778 (2016)
- Hovorka, S. D., "Frio brine pilot: field validation of numerical simulation of CO2 storage", Abstract, AAPG Annual Convention, pp.1~23 (2005)
- International Energy Agency(IEA), "Net zero roadmap a global pathway to keep the 1.5°C goal in reach", IEA, 226~ (2023)
- Isola, P., "Image-toimage translation with conditional adversarial networks", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.1125~1134 (2017)
- Jo, H., "Machinelearning-based porosity estimation from multifrequency poststack seismic data", Geophysics, 87(5), pp.217~233 (2022)
- Jo, H., "History matching of channel reservoirs using ensemble Kalman filter with continuous update of channel information", Energy Exploration & Exploitation, 35(1), pp.3~23 (2017)
- Jo, H., "Machine learning assisted history matching for a deepwater lobe system", Journal of Petroleum Science and Engineering, 207, pp.109086~ (2021)
- Kim, J. W., "A review on monitoring the behavior and saturation of CO2 at a CO2 injection field, Nagaoka, Japan", Journal of the Korean Society for Geosystem Engineering, 49(5), pp.677~688 (2012)
- Kim, S., "Development of ensemble smoother–neural network and its application to history matching of channelized reservoirs", Journal of Petroleum Science and Engineering, 191, pp.107159~ (2020)
- LeCun, Y., "The handbook of brain theory and neural networks, 3361(10)", pp.255~258 (1995)
- Lee, K. B., "Uncertainty quantification of channelized reservoirs using ensemble smoother with a distance-based method", Journal of the Korean Society of Mineral and Energy Resources Engineers, 52(2), pp.139~147 (2015)
- Lee, K., "Iterative static modeling of channelized reservoirs using history-matched facies probability data and rejection of training image", Petroleum Science, 16, pp.127~147 (2019)
- Global carbon capture and storage (CCS) market insights, forecast to 2028, "Market Report Worlds", 115~ (2022)
- Pan, W., "Efficient subsurface modeling with sequential patch generative adversarial neural networks", SPE Annual Technical Conference and Exhibition (2023)
- Pan, W., "Hierarchical machine learning workflow for conditional and multiscale deep-water reservoir modeling", AAPG Bulletin, 106(11), pp.2163~2186 (2022)
- Park, H., "Carbon neutrality", green growth national strategy and the first national basic plan and carbon neutrality in the urban sector (in Korean), 2023, pp.10(3), 5~8
- "GeostatsPy python package" (2021)[URL]
- Ronneberger, O., "Convolutional networks for biomedical image segmentation", International Conference on Medical Image Computing and Computerassisted Intervention, pp.234~241 (2015)
- Sato, K., "Monitoring and simulation studies for assessing macro-and meso-scale migration of CO2 sequestered in an onshore aquifer: experiences from the Nagaoka pilot site, Japan", International Journal of Greenhouse Gas Control, 5(1), pp.125~137 (2011)
- Sharma, S., "Australia’s first geosequestration demonstration project—the CO2CRC Otway basin pilot project", The APPEA Journal, 47(1), pp.259~270 (2007)
- "Statista" (2023)[URL]
- Tang, H., "Deep learningaccelerated 3D carbon storage reservoir pressure forecasting based on data assimilation using surface displacement from InSAR", International Journal of Greenhouse Gas Control, 120, pp.103765~ (2022)
- Tang, H., "A deep learning-accelerated data assimilation and forecasting workflow for commercial-scale geologic carbon storage", International Journal of Greenhouse Gas Control, 112, pp.103488~ (2021)
- Wang, Z., "An investigation of CO2-responsive preformed particle gel for conformance control of CO2 flooding in reservoirs with fractures or fracture-like channels", SPE Journal, 24(05), pp.2398~2408 (2019)
- Xue, Z., "Estimation of CO2 saturation from time-lapse CO2 well logging in an onshore aquifer, Nagaoka, Japan", Exploration Geophysics, 37(1), pp.19~29 (2006)