Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
June 14, 2026Computational GeosciencesOpen Access

From simulator to surrogate: GANs for spatiotemporal modeling of subsurface flow in porous media

View Full Paper
Ask AI
Bookmark
Share

Authors

ZTZeeshan TariqZFZhao FengBYBicheng Yan

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates accurate modeling of subsurface flow in porous media, indicating GANs' advantages over traditional methods.

Key Points

  • This research aims to explore the effectiveness of GANs in modeling CO2 saturation and pressure buildup in subsurface flow.
  • Developed physics-based numerical simulation models for geological carbon storage phases.
  • Utilized Latin-Hypercube sampling to create a simulation database of reservoir parameters.
  • Trained GANs with Mean Squared Error and spatial derivative-based loss functions on two different reservoir scenarios.
  • GAN performance showed R2 values of 0.989 for saturation prediction and 0.996 for pressure buildup prediction.
  • Normalized Absolute Relative Error was consistently around 1% across all predictions.
  • GANs achieved prediction times of 0.01 s, compared to 1000 s for traditional physics-based simulations.

Cite This Study

Tariq et al. (2026) studied this question.

synapsesocial.com/papers/6a2e482cb1cc60ccdea8c6aahttps://doi.org/10.1007/s10596-026-10440-7
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Generative Adversarial Network for Modeling of CO2 Plume Evolution in Geological Carbon Storage Systems2025 · 2 citations
  2. 2Predicting multiphase flow behavior of methane in shallow unconfined aquifers using conditional deep convolutional generative adversarial network2024 · 7 citations
  3. 3The U-Net Enhanced Graph Neural Network for Multiphase Flow Prediction: An Implication to Geological Carbon Sequestration2024
  4. 4Geomodelling of multi-scenario non-stationary reservoirs with enhanced GANSim2025 · 3 citations
  5. 5Characterizing CO2 Sequestration Dynamics in Complex Geological Formations: Surrogate-Based Uncertainty Quantification Approach2026