Well placement optimization for carbon dioxide capture and storage via CMA-ES with mixed integer support

Miyagi, Atsuhiro; Akimoto, Youhei; Yamamoto, Hajime

doi:10.1145/3205651.3205706

Cited by 11 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CMA-ES is gaining popularity and is becoming the benchmark algorithm in metaheuristic optimization. It has been successfully applied to several engineering disciplines including: environmental engineering [32], acoustics [33], electronics [34], hydrogeology [35], medicine [36], thermal and fluid flow [37], structural mechanics and failure [38], and many others. CMA-ES is particularly efficient for non-convex, poorly conditioned, multimodal optimization problems and with noisy evaluations of the objective function.…”

Section: Cmaes Algorithmmentioning

confidence: 99%

Parameter Identification by High-Resolution Inverse Numerical Model Based on LBM/CMA-ES: Application to Chalk Aquifer (North of France)

Zouhri

Kaidi

Smaoui

2021

Water

View full text Add to dashboard Cite

The present paper proposes the numerical solution of an inverse problem in groundwater flow (Darcy’s equation). This solution was achieved by combining a high-resolution new code HYSFLO-LBM (Hydrodynamic of Subsurface Flow by Lattice Boltzmann Method), based on LBM, to solve the direct problem, and the metaheuristic optimization algorithm CMA-ES ES (Covariance Matrix Adaptation-Evolution Strategy) to solve the optimization step. The integrated optimization algorithm which resulted from this combination, HYSFLO-LBM/CMA-ES, was applied to the hydrogeological experimental site of Beauvais (Northern France), instrumented by a set of sensors distributed over 20 hydrogeological wells. Hydrogeological parameters measured by the sensors are necessary to understand the aquifer functioning and to serve as input data for the identification of the transmissivity field by the HYSFLO-LBM/CMA-ES code. Results demonstrated an excellent concordance between the integrated optimization algorithm and hydrogeological applied methods (pumping test and magnetic resonance sounding). The spatial distribution of the transmissivity and hydraulic conductivity are related to the heterogeneous distribution of aquifer formations. The LBM and CMA-ES were chosen for their proven excellent performance and lesser cost, in terms of both money and time, unlike the geophysical survey and pumping test. The model can be used and developed as a decision support tool for integrated water resources management in the region.

show abstract

Section: Cmaes Algorithmmentioning

confidence: 99%

Parameter Identification by High-Resolution Inverse Numerical Model Based on LBM/CMA-ES: Application to Chalk Aquifer (North of France)

Zouhri

Kaidi

Smaoui

2021

Water

View full text Add to dashboard Cite

show abstract

“…The mixed-integer black-box optimization (MI-BBO) problem is the problem of simultaneously optimizing continuous and integer variables under the condition that the objective function is not differentiable and not available in the explicit functional form. The MI-BBO problems often appear in real-world applications such as, material design [11,17], topology optimization [4,16], placement optimization for CO 2 capture and storage [13], and hyper-parameter optimization of machine learning [9,10]. Several algorithms have been designed for MI-BBO so far, e.g., the extended evolution strategies [12] and surrogate model-based method [3].…”

Section: Introductionmentioning

confidence: 99%

“…In particular, the step-size tends to decrease with each iteration, which promotes trapping on the plateau of the integer variables. To address this plateau problem in the integer variable treatment, Hansen [5] proposed the injection of mutations into a sample of elements corresponding to integer variables in the CMA-ES, and Miyagi et al [13] used this modification for the real-world MI-BBO problem. Although this mutation injection is effective on certain problem classes, Hansen [5] mentioned that it is not suitable for binary variables or 𝑘-ary integers in 𝑘 < 10.…”

Section: Introductionmentioning

confidence: 99%

CMA-ES with Margin: Lower-Bounding Marginal Probability for Mixed-Integer Black-Box Optimization

Hamano,

Saito,

Nomura

et al. 2022

Preprint

View full text Add to dashboard Cite

This study targets the mixed-integer black-box optimization (MI-BBO) problem where continuous and integer variables should be optimized simultaneously. The CMA-ES, our focus in this study, is a population-based stochastic search method that samples solution candidates from a multivariate Gaussian distribution (MGD), which shows excellent performance in continuous BBO. The parameters of MGD, mean and (co)variance, are updated based on the evaluation value of candidate solutions in the CMA-ES. If the CMA-ES is applied to the MI-BBO with straightforward discretization, however, the variance corresponding to the integer variables becomes much smaller than the granularity of the discretization before reaching the optimal solution, which leads to the stagnation of the optimization. In particular, when binary variables are included in the problem, this stagnation more likely occurs because the granularity of the discretization becomes wider, and the existing modification to the CMA-ES does not address this stagnation. To overcome these limitations, we propose a simple modification of the CMA-ES based on lower-bounding the marginal probabilities associated with the generation of integer variables in the MGD. The numerical experiments on the MI-BBO benchmark problems demonstrate the efficiency and robustness of the proposed method. CCS CONCEPTS• Mathematics of computing → Mixed discrete-continuous optimization.

show abstract

A review of intelligent decision-making strategy for geological CO2 storage: Insights from reservoir engineering

Mao,

Jahanbani Ghahfarokhi

2024

Geoenergy Science and Engineering

View full text Add to dashboard Cite

Well placement optimization for carbon dioxide capture and storage via CMA-ES with mixed integer support

Cited by 11 publications

References 9 publications

Parameter Identification by High-Resolution Inverse Numerical Model Based on LBM/CMA-ES: Application to Chalk Aquifer (North of France)

Parameter Identification by High-Resolution Inverse Numerical Model Based on LBM/CMA-ES: Application to Chalk Aquifer (North of France)

CMA-ES with Margin: Lower-Bounding Marginal Probability for Mixed-Integer Black-Box Optimization

A review of intelligent decision-making strategy for geological CO2 storage: Insights from reservoir engineering

Contact Info

Product

Resources

About