Frankenstein's ROMster: Avoiding pitfalls of reduced-order model development

被引:21
作者
Chen, Bailian [1 ]
Harp, Dylan R. [1 ]
Pawar, Rajesh J. [1 ]
Stauffer, Philip H. [1 ]
Viswanathan, Hari S. [1 ]
Middleton, Richard S. [1 ]
机构
[1] Los Alamos Natl Lab, Earth & Environm Sci Div, Los Alamos, NM 87545 USA
关键词
Reduced-order models; Potential pitfall; Traditional ROMs; Combing ROMs; Geologic CO2 sequestration; GEOLOGICAL CO2 STORAGE; UNCERTAINTY QUANTIFICATION; RESERVOIR SIMULATION; RISK-ASSESSMENT; CARBON CAPTURE; BRINE LEAKAGE; SYSTEM MODEL; OIL-RECOVERY; SEQUESTRATION; IMPACTS;
D O I
10.1016/j.ijggc.2019.102892
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Reduced-order models (ROMs) are a widely used and powerful approach to reducing the complexity of predictive physics-based numerical simulations for a wide range of applications, including electronics and fluid mechanics such as geologic CO2 sequestration (GCS). ROMs are critical for optimization, sensitivity analysis, model calibration and uncertainty quantification where full-order models cannot be feasibly executed many times. Traditional approaches generate a single ROM for each simulated response (e.g., CO2 injection rates, pH changes) based on a set of training simulations. Here, we demonstrate that a single ROM can display excellent overall predictive statistics, but have predictions that dramatically and unacceptably deviate from simulator responses especially when the response variable has a large range (i.e., vary over multiple orders of magnitude). For example, we show that a traditional statistically-high-performing GCS ROM (coefficient of determination R-2 of 0.99) can have average absolute relative errors of over 200%. To address this, we propose a new and novel approach where a set of sub-ROMs are generated to overcome the potential pitfalls in traditional single ROM development. The effectiveness of the proposed approach-the ROMster framework-is demonstrated using a case study of predicted CO2 injection rates for GCS. We find our approach is a robust and general framework for ROM development, reducing the average "error" from 200% to only 4% in our case study.
引用
收藏
页数:7
相关论文
共 70 条
  • [11] National corridors for climate change mitigation: managing industrial CO2 emissions in France
    Bielicki, Jeffrey M.
    Calas, Guillaume
    Middleton, Richard S.
    Minh Ha-Duong
    [J]. GREENHOUSE GASES-SCIENCE AND TECHNOLOGY, 2014, 4 (03): : 262 - 277
  • [12] Basin-scale hydrogeologic impacts of CO2 storage: Capacity and regulatory implications
    Birkholzer, Jens T.
    Zhou, Quanlin
    [J]. INTERNATIONAL JOURNAL OF GREENHOUSE GAS CONTROL, 2009, 3 (06) : 745 - 756
  • [13] The impact of CO2 on the electrical properties of water bearing porous media - laboratory experiments with respect to carbon capture and storage
    Boerner, Jana H.
    Herdegen, Volker
    Repke, Jens-Uwe
    Spitzer, Klaus
    [J]. GEOPHYSICAL PROSPECTING, 2013, 61 : 446 - 460
  • [14] Self-healing of cement fractures under dynamic flow of CO2-rich brine
    Cao, Peilin
    Karpyn, Zuleima T.
    Li, Li
    [J]. WATER RESOURCES RESEARCH, 2015, 51 (06) : 4684 - 4701
  • [15] Key factors for determining groundwater impacts due to leakage from geologic carbon sequestration reservoirs
    Carroll, Susan A.
    Keating, Elizabeth
    Mansoor, Kayyum
    Dai, Zhenxue
    Sun, Yunwei
    Trainor-Guitton, Whitney
    Brown, Chris
    Bacon, Diana
    [J]. INTERNATIONAL JOURNAL OF GREENHOUSE GAS CONTROL, 2014, 29 : 153 - 168
  • [16] Status of CO2 storage in deep saline aquifers with emphasis on modeling approaches and practical simulations
    Celia, M. A.
    Bachu, S.
    Nordbotten, J. M.
    Bandilla, K. W.
    [J]. WATER RESOURCES RESEARCH, 2015, 51 (09) : 6846 - 6892
  • [17] Characterization of CO2 storage and enhanced oil recovery in residual oil zones
    Chen, Bailian
    Pawar, Rajesh J.
    [J]. ENERGY, 2019, 183 : 291 - 304
  • [18] Geologic CO2 sequestration monitoring design: A machine learning and uncertainty quantification based approach
    Chen, Bailian
    Harp, Dylan R.
    Lin, Youzuo
    Keating, Elizabeth H.
    Pawar, Rajesh J.
    [J]. APPLIED ENERGY, 2018, 225 : 332 - 345
  • [19] Uncertainty quantification and value of information assessment using proxies and Markov chain Monte Carlo method for a pilot project
    Chen, Bailian
    He, Jincong
    Wen, Xian-Huan
    Chen, Wen
    Reynolds, Albert C.
    [J]. JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING, 2017, 157 : 328 - 339
  • [20] Assessing the combined influence of fluid-rock interactions on reservoir properties and injectivity during CO2 storage in saline aquifers
    Cui, Guodong
    Wang, Yi
    Rui, Zhenhua
    Chen, Bailian
    Ren, Shaoran
    Zhang, Liang
    [J]. ENERGY, 2018, 155 : 281 - 296