An improved tandem neural network architecture for inverse modeling of multicomponent reactive transport in porous media

J Chen, Z Dai, Z Yang, Y Pan, X Zhang… - Water Resources …, 2021 - Wiley Online Library
Parameter estimation for reactive transport models (RTMs) is important in improving their
predictive capacity for accurately simulating subsurface hydrogeochemical processes. This …

Randomized algorithms for low-rank matrix approximation: Design, analysis, and applications

JA Tropp, RJ Webber - arXiv preprint arXiv:2306.12418, 2023 - arxiv.org
This survey explores modern approaches for computing low-rank approximations of high-
dimensional matrices by means of the randomized SVD, randomized subspace iteration …

Review of machine learning methods applied to enhanced geothermal systems

L Wang, Z Yu, Y Zhang, P Yao - Environmental Earth Sciences, 2023 - Springer
The objective of this study was to summarize the progress in the application of machine
learning (ML) to enhanced geothermal systems (EGSs), including the entire process of EGS …

A stochastic subspace approach to gradient-free optimization in high dimensions

D Kozak, S Becker, A Doostan, L Tenorio - … Optimization and Applications, 2021 - Springer
We present a stochastic descent algorithm for unconstrained optimization that is particularly
efficient when the objective function is slow to evaluate and gradients are not easily …

Stochastic subspace descent

D Kozak, S Becker, A Doostan, L Tenorio - arXiv preprint arXiv …, 2019 - arxiv.org
We present two stochastic descent algorithms that apply to unconstrained optimization and
are particularly efficient when the objective function is slow to evaluate and gradients are not …

Randomized algorithms for scientific computing (RASC)

A Buluc, TG Kolda, SM Wild, M Anitescu… - arXiv preprint arXiv …, 2021 - arxiv.org
Randomized algorithms have propelled advances in artificial intelligence and represent a
foundational research area in advancing AI for Science. Future advancements in DOE Office …

Closed-loop field development with multipoint geostatistics and statistical performance assessment

MG Shirangi - Journal of Computational Physics, 2019 - Elsevier
Closed-loop field development (CLFD) optimization is a comprehensive framework for
optimal development of subsurface resources. CLFD involves three major steps: 1) …

Determination of relative permeability curve under combined effect of polymer and surfactant

W Zhang, J Hou, Y Liu, K Zhou, Z Li, Q Du - Journal of Petroleum Science …, 2022 - Elsevier
Relative permeability of surfactant-polymer (SP) flooding is determined by an inversion
method based on numerical simulation and unsteady-state coreflooding experiment …

Pass-efficient randomized algorithms for low-rank matrix approximation using any number of views

EK Bjarkason - SIAM Journal on Scientific Computing, 2019 - SIAM
This paper describes practical randomized algorithms for low-rank matrix approximation that
accommodate any budget for the number of views of the matrix. The presented algorithms …

Modeling unobserved geothermal structures using a physics-informed neural network with transfer learning of prior knowledge

A Shima, K Ishitsuka, W Lin, EK Bjarkason, A Suzuki - Geothermal Energy, 2024 - Springer
Deep learning has gained attention as a potentially powerful technique for modeling natural-
state geothermal systems; however, its physical validity and prediction inaccuracy at …