To address the lack of rapid evaluation tools for multi-mechanism CO2 storage performance during CO2 injection in depleted oil and gas reservoirs,a three-dimensional reservoir model was developed based on the CMG-GEM platform.Latin Hypercube Sampling (LHS) was employed to generate 1520 parameter scenarios,enabling the simulation of the responses of three major trapping mechanisms,namely solubility trapping,residual trapping,and structural trapping.Key controlling parameters were identified using the Spearman rank correlation coefficient (SRCC),and a backpropagation neural network (BPNN) model was established to achieve rapid prediction of storage efficiency and the contributions of individual trapping mechanisms.The results indicate that the proposed model exhibits high predictive accuracy for all three indices (R2>0.98,RMSE<0.01),demonstrating its effectiveness in supporting storage scheme optimization and CO2 storage risk assessment.
随着全球气候变化问题日益严峻,碳捕集与封存(carbon capture and storage,CCS)被认为是实现“碳达峰”与“碳中和”目标的重要技术路径之一[1]。政府间气候变化专门委员会(IPCC)指出,为将全球升温控制在1.5℃以内,需在本世纪中叶前实现大规模CO2减排与封存[2]。通过CCS技术将CO2注入深层地质体以实现长期封存,是当前主要的负排放手段之一[3-4]。
BradshawJ, BachuS, BonijolyD, et al. CO2 storage capacity estimation:issues and development of standards[J]. International Journal of Greenhouse Gas Control, 2007, 1(1):62-68.
[2]
IPCC. Climate Change 2023:Synthesis rReport.Contribution of working groups ⅠⅡ and Ⅲ to the sixth assessment report of the intergovernmental panel on climate change[R]. Geneva:IPCC, 2023.
ZhuD, PengS, ZhaoS, et al. Comprehensive review of sealant materials for leakage remediation technology in geological CO2 capture and storage process[J]. Energy & Fuels, 2021, 35(6):4711-4742.
AlcaldeJ, FludeS, WilkinsonM, et al. Estimating geological CO2 storage security to deliver on climate mitigation[J]. Nature Communications, 2018, 9(1):2201.
ZhouX, WuY S, ChenH, et al. Review of carbon dioxide utilization and sequestration in depleted oil reservoirs[J]. Renewable and Sustainable Energy Reviews, 2024,202:114646.
[10]
WeiB, WangB, LiX, et al. CO2 storage in depleted oil and gas reservoirs:A review[J]. Advances in Geo-Energy Research, 2023, 9(2):76-93.
[11]
CaoC, LiuH, HouZ, et al. A review of CO2 storage in view of safety and cost-effectiveness[J]. Energies, 2020, 13(3):600.
[12]
KimY, JangH, KimJ, et al. Prediction of storage efficiency on CO2 sequestration in deep saline aquifers using artificial neural network[J]. Applied Energy, 2017,185:916-928.
[13]
LiuM, LiZ, QiJ, et al. Prediction of CO2 storage in different geological conditions based on machine learning[J]. Energy & Fuels, 2024, 38(22):22340-22350.
[14]
YamadaK, FernandesB R B, KalamkarA, et al. Development of a hydrate risk assessment tool based on machine learning for CO2 storage in depleted gas reservoirs[J]. Fuel, 2024,357:129670.
[15]
VoThanh H, SugaiY, SasakiK. Application of artificial neural network for predicting the performance of CO2 enhanced oil recovery and storage in residual oil zones[J]. Scientific Reports, 2020, 10(1):18204.
[16]
AbdulwarithA, AmmarM, DindorukB. Prediction/Assessment of CO2 EOR and storage efficiency in residual oil zones using machine learning techniques[C]. Proceedings of the 2024 Carbon Capture,Utilization,and Storage Conference (SPE/AAPG/SEG).Houston,USA, 2024-03-11—2024-03-13.
[17]
MetzB, DavidsonO, DeConinck H, et al. IPCC special report on carbon dioxide capture and storage[M]. Cambridge: Cambridge University Press, 2005.
[18]
NghiemL, ShrivastavaV, TranD, et al. Simulation of CO2 storage in saline aquifers[C]. SPE/EAGE Reservoir Characterization & Simulation Conference.Abu Dhabi,United Arab Emirates, 2009.
PDF
(4897KB)
