Hyper-parameter optimization for improving the performance of localization in an iterative ensemble smoother

doi:10.1016/j.geoen.2023.212404

CORC > 力学研究所 > 中国科学院力学研究所 > 非线性力学国家重点实验室

	Hyper-parameter optimization for improving the performance of localization in an iterative ensemble smoother
	Luo, Xiaodong 5; Cruz, William C.4; Zhang, Xin-Lei 2,3; Xiao, Heng 1
刊名	GEOENERGY SCIENCE AND ENGINEERING
	2023-12-01
卷号	231 页码:20
关键词	Ensemble data assimilation Iterative ensemble smoother (IES) Automatic and adaptive localization (AutoAdaLoc) Parameterized localization Continuous hyper-parameter OPtimization (CHOP)
ISSN号	2949-8929
DOI	10.1016/j.geoen.2023.212404
通讯作者	Luo, Xiaodong(xluo@norceresearch.no)
英文摘要	This work aims to help improve the performance of an iterative ensemble smoother (IES) in reservoir data assimilation problems, by introducing a data-driven procedure to optimize the choice of certain algorithmic hyper-parameters in the IES. Generally speaking, algorithmic hyper-parameters exist in various data assimilation algorithms. Taking IES as an example, localization is often useful for improving its performance, yet applying localization to an IES also introduces a certain number of algorithmic hyper-parameters, such as localization length scales, in the course of data assimilation. While different methods have been developed in the literature to address the problem of properly choosing localization length scales in various circumstances, many of them are tailored to specific problems under consideration, and may be difficult to directly extend to other problems. In addition, conventional hyper-parameter tuning methods determine the values of localization length scales based on either empirical (e.g., using experience, domain knowledge, or simply the practice of trial and error) or analytic (e.g., through statistical analyses) rules, but few of them use the information of observations to optimize the choice of hyper-parameters. The current work proposes a generic, data driven hyper-parameter tuning strategy that has the potential to overcome the aforementioned issues. With this proposed strategy, hyper-parameter optimization is converted into a conventional parameter estimation problem, in such a way that observations are utilized to guide the choice of hyper-parameters. One noticeable feature of the proposed hyper-parameter tuning strategy is that it iteratively estimates an ensemble of hyper parameters. In doing so, the resulting hyper-parameter tuning procedure receives some practical benefits inherent to conventional ensemble data assimilation algorithms, including the nature of being derivative free, the ability to provide uncertainty quantification to some extent, and the capacity to handle a large number of hyper-parameters. Through 2D and 3D case studies, it is shown that when the proposed hyper parameter tuning strategy is applied to tune a set of localization length scales (up to the order of 103) in a parameterized localization scheme, superior data assimilation performance is obtained in comparison to an alternative hyper-parameter tuning strategy without utilizing the information of observations.
资助项目	Equinor Energy AS ; Lundin Energy Norway AS ; Repsol Norge AS ; Shell Global Solutions International B.V. ; TotalEnergies EP Norge AS ; Wintershall Dea Norge AS ; Research Council of Norway ; National Centre for Sustainable Subsurface Utilization of the Norwegian Continental Shelf[295002] ; National Centre for Sustainable Subsurface Utilization of the Norwegian Continental Shelf[NCS2030] ; National IOR centre of Norway[331644] ; RCN[230303] ; ConocoPhillips ; Aker BP ; Var Energi ; Equinor ; Neptune Energy ; Lundin ; Halliburton ; Schlumberger ; Wintershall Dea
WOS关键词	KALMAN FILTER ; DATA ASSIMILATION ; ADAPTIVE LOCALIZATION ; MODELS
WOS研究方向	Energy & Fuels ; Engineering
语种	英语
WOS记录号	WOS:001113990800001
资助机构	Equinor Energy AS ; Lundin Energy Norway AS ; Repsol Norge AS ; Shell Global Solutions International B.V. ; TotalEnergies EP Norge AS ; Wintershall Dea Norge AS ; Research Council of Norway ; National Centre for Sustainable Subsurface Utilization of the Norwegian Continental Shelf ; National IOR centre of Norway ; RCN ; ConocoPhillips ; Aker BP ; Var Energi ; Equinor ; Neptune Energy ; Lundin ; Halliburton ; Schlumberger ; Wintershall Dea
内容类型	期刊论文
源URL	[http://dspace.imech.ac.cn/handle/311007/93628]
专题	力学研究所_非线性力学国家重点实验室
通讯作者	Luo, Xiaodong
作者单位	1.Univ Stuttgart, Stuttgart Ctr Simulat Sci SC SimTech, Stuttgart, Germany 2.Univ Chinese Acad Sci, Sch Engn Sci, Beijing, Peoples R China 3.Chinese Acad Sci, Inst Mech, State Key Lab Nonlinear Mech, Beijing, Peoples R China 4.Univ Stavanger, Kjell Arholms Gate 41, N-4021 Stavanger, Norway 5.Norwegian Res Ctr NORCE, Nygardsgaten 112, N-5008 Bergen, Norway
推荐引用方式 GB/T 7714	Luo, Xiaodong,Cruz, William C.,Zhang, Xin-Lei,et al. Hyper-parameter optimization for improving the performance of localization in an iterative ensemble smoother[J]. GEOENERGY SCIENCE AND ENGINEERING,2023,231:20.
APA	Luo, Xiaodong,Cruz, William C.,Zhang, Xin-Lei,&Xiao, Heng.(2023).Hyper-parameter optimization for improving the performance of localization in an iterative ensemble smoother.GEOENERGY SCIENCE AND ENGINEERING,231,20.
MLA	Luo, Xiaodong,et al."Hyper-parameter optimization for improving the performance of localization in an iterative ensemble smoother".GEOENERGY SCIENCE AND ENGINEERING 231(2023):20.