고갈 가스전에서의 CO2 저장관련인자 분석을 통한 기계학습 기반 저장효율지수 예측
Prediction of Storage Efficiency Index Based on Machine Learning: CO2 Storage Factor Analysis of Depleted Gas Fields
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
최근 CO2 지중저장이 탄소중립 달성을 위한 기술 중 하나로 부상하고 있다. 대상 저장소 중 고갈 가스전은 무결성과 안정성이 높아 저장에 용이하나 고갈 가스전에서 잔류 및 용해 포획을 통한 저장안정성 및 효율 분석 연구는 전무하다. 이 연구에서는 고갈 가스전에 대한 주입 시뮬레이션을 통해CO2 저장안정성 및 효율에 영향을 미치는 저장관련인자를 입력자료로 한 기계학습 기반의 저장효율지수 예측모델을 구축하여 신뢰성을 평가하였다. 그 결과 주입률, 최대 저류층압력, 공극률, 유체투과도, 온도의 영향을 확인하였으며, 저장효율지수 예측 시 랜덤 포레스트, 서포트 벡터머신, 익스트림 그래디언트 부스팅, 합성곱 신경망의 적용성을 검토하였다. 이는 향후 현장 고갈 가스전 정보를 기반으로 신뢰성 있는 저장효율지수 예측을 위한 사전연구로서 유의미하다고 판단된다.
Abstract
Recently, CO2 geological storage has been increasingly utilized as a technical solution for achieving carbon neutrality. Depleted gas fields are particularly beneficial because of their integrity and stability. However, no analyses have been conducted regarding storage stability and efficiency through residual and solubility trapping. In this study, injection simulations on a depleted gas reservoir model were performed to identify the factors affecting CO2 storage. Machine learning models were developed and evaluated using these data to reliably predict the storage efficiency index. The results confirmed the impact of the injection rate, maximum reservoir pressure, porosity, permeability, and temperature on storage efficiency. The applicability of random forests, support vector machines, extreme gradient boosting, and convolutional neural networks for predicting the storage efficiency index was reviewed. This study provides foundational data for the reliable prediction of storage efficiency using information from depleted gas fields.
참고문헌 (27)
- Agartan, E., "CO2 storage in depleted oil and gas fields in the gulf of mexico", International Journal of Greenhouse Gas Control, 72, pp.38~48 (2018)
- Allinson, W. G., "CO2-Storage capacity-combining geology, engineering and economics", 2014 SPE Economics &Management, pp.13~ (2014)
- "Analytics Vidhya" (2023)[URL]
- Bachu, S., "CO2storage capacity estimation: methodology and gaps", International Journal of Greenhouse Gas Control, 1(4), pp.430~443 (2007)
- "BOEM" (2023)[URL]
- Breiman, L., "Random Forests, 45", pp.5~32 (2001), Kluwer Academic Publishers
- Cao, C., "A review of CO2 storage in view of safety and cost-effectiveness", Energies, 13(3), pp.45~ (2020)
- Chen, T., "Xgboost: A scalable tree boosting system", Proceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining, pp.785~794 (2016), ACM
- Davoodi, S., "Machine-learning predictions of solubility and residual trapping indexes of carbon dioxide from global geological storage sites", Expert Systems With Applications, 222, pp.18~ (2023)
- Hughes, D. S., "Carbon storage in depleted gas fields: Key challenges", Energy Procedia, 1(1), pp.3007~3014 (2009)
- Iglauer, S, "Mass Transfer-Advanced Aspects", pp.233~262 (2011), Intechopen
- Ismail, I., "Carbon capture, utilization, and storage in saline aquifers: subsurface policies, development plans, well control strategies and optimization approaches-a review", Clean Technologies, 5(2), pp.609~637 (2023)
- Kaldas, M. N., "CO2 Sequestration in a limited-data depleted gas reservoir for reservoir capacity assessment and injection optimization -case study", SPE Reservoir Characterisation and Simulation Conference and Exhibition, pp.17~ (2023), SPE
- Khan, N. A., "CO2 Storage in Depleted Gas Field Reservoir Model and Sensitivity Analysis using Numerical Simulation Techniques", MS, pp.2022
- Kim, J. S., "A numerical modeling of CO2 injection into the depleted Donghae-1 gas field", Journal of the Korean Society of Mineral and Energy Resources Engineers, 60(5), pp.429~443 (2023)
- Kim, Y. M., "Prediction of storage efficiency on CO2 sequestration in deep saline aquifers using artificial neural network", Applied Energy, 185(1), pp.916~928 (2017)
- Kutz, J. N., "Deep learning in fluid dynamics, 814", pp.1~4 (2017), Cambridge University Press
- Moreira, D., "Human activity recognition for indoor localization using smartphone inertial sensors", Sensors, 21(18), pp.19~ (2021)
- Nghiem, L., "Simulation and optimization of trapping processes for CO2 storage in saline aquifers", Journal of Canadian Petroleum Technology, 49(8), pp.8~ (2010)
- Park, Y. C., "A proposal for the korean classification system of CO2 geological storage resources", Journal of the Korean Society of Mineral and Energy Resources Engineers, 50(1), pp.170~177 (2013)
- Raza, A., "Assessment of CO2 residual trapping in depleted reservoirs used for geosequestration", Journal of Natural Gas Science and Engineering, 43, pp.137~155 (2017)
- Rycroft, L., "Deployment of Carbon Capture and Storage", pp.133~266 (2024), Woodhead Publishing
- Safaei-Farouji, M., "Exploring the power of machine learning to predict carbon dioxide trapping efficiency in saline aquifers for carbon geological storage project", Journal of Cleaner Production, 372, pp.15~ (2022)
- Song, Y. S., "Application of an artificial neural network in predicting the effectiveness of trapping mechanisms on CO2 sequestration in saline aquifers", International Journal of Greenhouse Gas Control, 98, pp.14~ (2020)
- Vo-Thanh, H., "Application of machine learning to predict CO2 trapping performance in deep saline aquifers", Energy, 239, pp.14~ (2022)
- Whitson, C. H., "Phase Behavior", pp.233~ (2000), Henry L. Doherty Memorial Fund of AIME
- Zhang, F., "Machine Learning:Methods and Applications to Brain Disorders", pp.123~140 (2020), Academic Press