A machine-learning-accelerated distributed LBFGS method for field development optimization: algorithm, validation, and applications

Alpak, Faruk O.; Gao, Guohua; Florez, Horacio; Shi, Steve; Vink, Jeroen C.; Blom, Carl; Saaf, Fredrik; Wells, Terence

doi:10.1007/s10596-023-10197-3

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

Publication Types

Select...

Article3

Other2

Relationship

Self Cite0

Independent5

Authors

Journals

Cited by 11 publications

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

An accelerated computational platform for optimal field developments with reduced footprint

Alpak,

Gao

2024

Geoenergy Science and Engineering

View full text Add to dashboard Cite

An accelerated computational platform for optimal field developments with reduced footprint

Alpak,

Gao

2024

Geoenergy Science and Engineering

View full text Add to dashboard Cite

TinyGC-Net: an extremely tiny network for calibrating MEMS gyroscopes

Chao,

Zhao,

Haihui

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

This paper introduces a learning-based calibration method tailored for microelectromechanical system (MEMS) gyroscopes.The proposed method integrates two linear networks, linked by a parametric rectified linear unit (PReLU), and boasts a compacted architecture with only 25 parameters.This simplicity allows for efficient training on a graphics processing unit (GPU) before deployment on resource-constrained microcontroller units (MCUs).The loss function has been carefully devised to strengthen the neural model by eliminating reliance on open-source datasets, and facilitates the swift collection of training data solely via a tri-axial manual rotation table.Furthermore, the proposed method has undergone rigorous validation through public datasets and real-world scenarios, which not only maintains its ultra-lightweight attributes but also outperforms other existing solutions in terms of accuracy.Experimental results demonstrate the method's practicality and efficacy, indicating its suitability for applications requiring inertial measurement units (IMUs).And the open-source implementation of this method is accessible at: https://github.com/tsuibeyond/TinyGC-Net

show abstract

The spectral conjugate gradient method in variational adjoint assimilation for model terrain correction III: convergence analysis

Tao,

2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

In the former parts of this paper, the spectral conjugate gradient (SCG) algorithm was proposed to identify the optimal bottom terrain used for predicting the meteorological fields. In this part, the convergence analysis of the SCG method is presented to verify its validity when solving a typical ill-posed inverse problem. The scaled cost function, the scaled gradient norm, the linear convergence rate, and the Hessian approximation condition number are evaluated for convergence analysis. The SCG method reduces the cost functional value and the gradient norm sufficiently. It always performs linear rates of convergence with a quickly reduced condition number of the Hessian matrix. Sometimes it provides very fast linear convergence rates. The SCG code with optimal step size and Andrei’s equation is effective on ill-posed test problems.

show abstract

A machine-learning-accelerated distributed LBFGS method for field development optimization: algorithm, validation, and applications

Cited by 11 publications

References 45 publications

An accelerated computational platform for optimal field developments with reduced footprint

An accelerated computational platform for optimal field developments with reduced footprint

TinyGC-Net: an extremely tiny network for calibrating MEMS gyroscopes

The spectral conjugate gradient method in variational adjoint assimilation for model terrain correction III: convergence analysis

Contact Info

Product

Resources

About