Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
August 5, 2025

Geomodelling of multi-scenario non-stationary reservoirs with enhanced GANSim

View Full Paper
Ask AI
Bookmark
Share

Authors

SSSuihong SongTMTapan MukerjiCSCéline Scheidt

Discussion

Loading...

Member takes

Overview

This work demonstrates improved facies models in non-stationary reservoirs, suggesting alternative workflows for GANSim applications.

Key Points

  • GANSim enhances geomodelling of multi-scenario non-stationary reservoirs, resolving local disconnection issues.
  • Two workflows for GANSim training are proposed: integrated scenario training and an explicit scenario falsification process.
  • Both workflows effectively generate realistic facies models while eliminating the local disconnection problem with single-pixel data.
  • Compared to traditional geostatistical methods, GANSim achieves simulations approximately 1000 times faster and with better geological pattern reproduction.

Cite This Study

Song et al. (2025) studied this question.

synapsesocial.com/papers/689a0f99e6551bb0af8d140ehttps://doi.org/10.31223/x5z73n
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. 1From simulator to surrogate: GANs for spatiotemporal modeling of subsurface flow in porous media2026
  2. 2Stochastic Modeling of Thin Mud Drapes Inside Point Bar Reservoirs With ALLUVSIM‐GANSim2024 · 5 citations
  3. 3Modeling of High-Sand-Ratio and Low-Connectivity Reservoirs Based on Self-Attention Single-Image Generative Adversarial Network2025
  4. 4Post‐Constrained Conditional Sedimentary Facies Simulation From a Single Training Image Using a Concurrent Multi‐Stage Generative Adversarial Network2025
  5. 5Generative Adversarial Network for Modeling of CO2 Plume Evolution in Geological Carbon Storage Systems2025 · 2 citations