Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/126575
Citations
Scopus Web of Science® Altmetric
?
?
Type: Conference paper
Title: Accelerating CMA-ES in history matching problems using an ensemble of surrogates with generation-based management
Author: Sayyafzadeh, M.
Koochak, R.
Barley, M.
Citation: Proceedings of the 16th European Conference on the Mathematics of Oil Recovery 2018 (ECMOR XVI), 2018 / pp.1592-1606
Publisher: European Association of Geoscientists & Engineers (EAGE)
Publisher Place: Netherlands
Issue Date: 2018
ISBN: 9781510869455
Conference Name: 16th European Conference on the Mathematics of Oil Recovery 2018 (ECMOR XVI) (03 Sep 2018 - 06 Sep 2018 : Barcelona, Catalonia, Spain)
Statement of
Responsibility: 
M. Sayyafzadeh, R. Koochak and M. Barley
Abstract: Because of the quasi-gradient update embedded in CMA-ES algorithm, it can outperform most of the population-based algorithms, from a convergence speed standpoint. However, due to the computationally expensive fitness function associated with history matching, the reduction of function (simulation) calls can be favourable. In this study, an ensemble of surrogates (proxies) with generation-based model-management is proposed to reduce the number of simulation calls efficaciously. Since the fitness function is highly nonlinear, an ensemble of surrogates (Gaussian process) is utilised. The likelihood term is divided into multiple functions, and each is represented via a separate surrogate. This improved the response surface fitting. In generation-based management, a stochastically selected measure (surrogate or reservoir-simulation) should be used to evaluate all the individuals of each generation. CMA-ES requires ranking of the individuals to select the parents. Therefore, the generation-based model-management fits well in CMA-ES, as surrogates are normally better in ranking the individuals than approximating the fitness. History matching for a real problem with 59 variables and PUNQ-S3 with eight variables was conducted via a standard CMA-ES and the proposed surrogate-assisted CMA-ES. The results showed that up to 65% and 50% less simulation calls for case#1 and case#2 were required.
Rights: © EAGE Publications BV
RMID: 0030100671
DOI: 10.3997/2214-4609.201802139
Published version: https://www.earthdoc.org/content/proceedings/barcelona2018-ecmor
Appears in Collections:Australian School of Petroleum

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.