Untitled

Jones, Donald R.; Schonlau, Matthias; Welch, William J.

doi:10.1023/a:1008306431147

Cited by 5,921 publications

(1,298 citation statements)

References 27 publications

Supporting

Mentioning

1,292

Contrasting

Unclassified

Order By: Relevance

“…The EGO strategy (Jones et al, 1998) consists of an iterative procedure for detecting the global optimum of a loss function defined in a bounded multidimensional domain. In this geomechanical application, the loss function measures the difference between the ground displacements computed by the geomechanical model and those provided by the SAR technology.…”

Section: Efficient Global Optimizationmentioning

confidence: 99%

“…If we denote with ϕ the probability density function of the standard normal distribution, and with Φ its cumulative distribution function, the expected improvement can be expressed in closed form as (Jones et al, 1998) E½IðcÞ…”

Section: Efficient Global Optimizationmentioning

confidence: 99%

“…For problems of relatively large dimension (up to 10 uncertain parameters), the forward efficient global optimization (EGO) approach (Jones et al, 1998) has proven a very efficient procedure, becoming largely used for mechanical engineering applications in recent years (Jones, 2001;Wang and Shan, 2007;Lovison and Rigoni, 2010). Owing to exact convergence properties and small computational burden, EGO has the potential to be an effective optimization method also for geomechanical applications.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Efficient global optimization of reservoir geomechanical parameters based on synthetic aperture radar-derived ground displacements

et al. 2016

View full text Add to dashboard Cite

When large volumes of fluids are removed from or injected into underground formations for, e.g., hydrocarbon and water production, CO 2 storage, gas storage, and geothermal energy exploitation, monitoring of surface deformations coupled to numerical modeling improves our understanding of reservoir behavior. The ability to accurately simulate surface displacements, however, is often impaired by limited information on reservoir geometry, waterdrive strength, and fluid-geomechanical parameters characterizing the geologic formations of interest. We have investigated the ability of efficient global optimization (EGO) to reduce the parameter uncertainties usually affecting geomechanical modeling. EGO is used to identify the parameter set that minimizes the difference in land displacements obtained from synthetic aperture radar (SAR)-derived measurements and 3D geomechanical modeling. We have tested the approach on the Tengiz giant oil field, Kazakhstan, where large uncertainties affect our knowledge of geomechanical parameters and pore pressure evolution. SqueeSAR on ENVISAT and RADARSAT-1 images acquired between 2004 and 2007 provided a set of high-precision, high-areal-density subsidence measurements of the test site. Based on the available information, a 3D geomechanical model of the reservoir has been developed using the elastoplastic finite-element code GEPS3D. Our results indicated that EGO efficiently identifies the global optimum in the parameter space, yielding a significant reduction in the difference between modeled and measured land subsidence. The match between simulated and SAR-measured horizontal displacements was developed as validation of the EGO calibration, which thus proved an effective and rather inexpensive method for the simultaneous management of several uncertainties and the reliable quantification of the rock properties.

show abstract

Section: Efficient Global Optimizationmentioning

confidence: 99%

Section: Efficient Global Optimizationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Efficient global optimization of reservoir geomechanical parameters based on synthetic aperture radar-derived ground displacements

et al. 2016

View full text Add to dashboard Cite

show abstract

“…In machine learning communities, Bayesian Optimization (BO), aka kriging, has become a very popular tool for optimization problems recently [15][16][17]. BO is a sequential design strategy to optimize an expensive black-box function f (s).…”

Section: Bayesian Optimizationmentioning

confidence: 99%

Machine Learning-Based Experimental Design in Materials Science

Dieb

Tsuda

2018

Nanoinformatics

View full text Add to dashboard Cite

In materials design and discovery processes, optimal experimental design (OED) algorithms are getting more popular. OED is often modeled as an optimization of a black-box function. In this chapter, we introduce two machine learningbased approaches for OED: Bayesian optimization (BO) and Monte Carlo tree search (MCTS). BO is based on a relatively complex machine learning model and has been proven effective in a number of materials design problems. MCTS is a simpler and more efficient approach that showed significant success in the computer Go game. We discuss existing OED applications in materials science and discuss future directions.

show abstract

“…Here we follow the method laid out by Jones et al [58] The kriging method is given fully in earlier works [59] and so only its key concepts are covered here. The kriging method creates a relationship between a molecule's features (geometry) and output (multipole moments),ŷ x Ã ð Þ, which can be expressed as sum of the global term,l, and a so-called error (the summed term) as shown in eq.…”

Section: Machine Learningmentioning

confidence: 99%

Toward amino acid typing for proteins in FFLUX

Fletcher¹,

Popelier

2016

J Comput Chem

View full text Add to dashboard Cite

Continuing the development of the FFLUX, a multipolar polarizable force field driven by machine learning, we present a modern approach to atom-typing and building transferable models for predicting atomic properties in proteins. Amino acid atomic charges in a peptide chain respond to the substitution of a neighboring residue and this response can be categorized in a manner similar to atom-typing. Using a machine learning method called kriging, we are able to build predictive models for an atom that is defined, not only by its local environment, but also by its neighboring residues, for a minimal additional computational cost. We found that prediction errors were up to 11 times lower when using a model specific to the correct group of neighboring residues, with a mean prediction of $0.0015 au. This finding suggests that atoms in a force field should be defined by more than just their immediate atomic neighbors. When comparing an atom in a single alanine to an analogous atom in a deca-alanine helix, the mean difference in charge is 0.026 au. Meanwhile, the same difference between a trialanine and a deca-alanine helix is only 0.012 au. When compared to deca-alanine models, the transferable models are up to 20 times faster to train, and require significantly less ab initio calculation, providing a practical route to modeling large biological systems.

show abstract

Untitled

Cited by 5,921 publications

References 27 publications

Efficient global optimization of reservoir geomechanical parameters based on synthetic aperture radar-derived ground displacements

Efficient global optimization of reservoir geomechanical parameters based on synthetic aperture radar-derived ground displacements

Machine Learning-Based Experimental Design in Materials Science

Toward amino acid typing for proteins in FFLUX

Contact Info

Product

Resources

About