Optimization of subsurface CO₂ injection based on neural network surrogate modeling

DOI10.1007/S10596-021-10092-9MaRDI QIDQ2065809zbMATH OpenOpenAlexFDO

Authors Zhuang Sun, D. Nicolas Espinoza, Matthew T. Balhoff, Jianping Xu

Publication date 13 January 2022

Published in Computational Geosciences (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10596-021-10092-9

zbMATH Keywords

Brugge fieldcoupled reservoir flowfault reactivationgeological carbon storagegeomechanics simulation

Mathematics Subject Classification ID

Mathematical modeling or simulation for problems pertaining to geophysics (86-10) Inverse problems in geophysics (86A22)

Recommendations

• Optimization of \(\mathrm{CO_2}\) injection using multi-scale reconstruction of composition transport
• Robust optimization of subsurface flow using polynomial chaos and response surface surrogates
• On obtaining optimal well rates and placement for CO\(_2\) storage
• A stochastic inversion workflow for monitoring the distribution of \(\text{CO}_{2}\) injected into deep saline aquifers
• Geochemical equilibrium determination using an artificial neural network in compositional reservoir flow simulation

Cites work

• Compositional flow modeling using a multi-point flux mixed finite element method
• Geochemical equilibrium determination using an artificial neural network in compositional reservoir flow simulation
• scientific article; zbMATH DE number 568891 (Why is no real title available?)
• Linearized reduced-order models for subsurface flow simulation

Cited in

(8)

• Robust optimization of subsurface flow using polynomial chaos and response surface surrogates
• Modelling and optimization of \(\mathrm{CO}_{2}\) absorption in pneumatic contactors using artificial neural networks developed with clonal selection-based algorithm
• Optimization of \(\mathrm{CO_2}\) injection using multi-scale reconstruction of composition transport
• A quasi-Newton trust-region method for optimization under uncertainty using stochastic simplex approximate gradients
• Multi-objective optimization of subsurface \(\mathrm{CO}_2\) capture, utilization, and storage using sequential quadratic programming with stochastic gradients
• An integrated framework for optimal monitoring and history matching in \(\mathrm{CO}_2\) storage projects
• Nonlinearly constrained well placement optimization for geologic \(\mathrm{CO_2}\) storage using iterative Latin hypercube sampling
• Recurrent transformer U-Net surrogate for flow modeling and data assimilation in subsurface formations with faults

Describes a project that uses

Uses Software

• Neural Network Toolbox

This page was built for publication: Optimization of subsurface \(\mathrm{CO_2}\) injection based on neural network surrogate modeling

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2065809)