A machine-learning-accelerated distributed LBFGS method for field development optimization: algorithm, validation, and applications
DOI10.1007/s10596-023-10197-3zbMath1520.86001MaRDI QIDQ6074257
Horacio Florez, Guohua Gao, Terence J. Wells, Jeroen C. Vink, Faruk Alpak, Fredrik J. F. E. Saaf, Steve Shi, Carl Blom
Publication date: 19 September 2023
Published in: Computational Geosciences (Search for Journal in Brave)
optimizationdistributed computingmachine learningsupport vector regressionSVRLBFGSwell location optimizationensemble optimizationD-LBFGSWLO
Learning and adaptive systems in artificial intelligence (68T05) Computational methods for problems pertaining to geophysics (86-08) Potentials, prospecting (86A20)
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Large-scale history matching with quadratic interpolation models
- Adjoint-based optimization of multi-phase flow through porous media -- a review
- Improved strategies for radial basis function methods for global optimization
- Recent progress in unconstrained nonlinear optimization without derivatives
- Theoretical connections between optimization algorithms based on an approximate gradient
- Distributed Gauss-Newton optimization method for history matching problems with multiple best matches
- Weighted least squares support vector machines: robustness and sparse approximation
- Least Frobenius norm updating of quadratic models that satisfy interpolation conditions
- Support-vector networks
- Support-vector regression accelerated well location optimization: algorithm, validation, and field testing
- Distributed quasi-Newton derivative-free optimization method for optimization problems with multiple local optima
- Gaussian mixture model fitting method for uncertainty quantification by conditioning to production data
- Recent progress on reservoir history matching: a review
- ORBIT: Optimization by Radial Basis Function Interpolation in Trust-Regions
- Numerical Optimization
- Radial Basis Functions
- Inverse Problem Theory and Methods for Model Parameter Estimation
- A Stochastic Simplex Approximate Gradient (StoSAG) for optimization under uncertainty
This page was built for publication: A machine-learning-accelerated distributed LBFGS method for field development optimization: algorithm, validation, and applications
