Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 10, 2025Engineering Research Express

A Physics-Constrained Two-Stage GAN for Reservoir Data Generation: Enhancing Predictive Accuracy

View Full Paper
Ask AI
Bookmark
Share

Authors

JLJianping LiYMYanyi MengJXJean Xia

Discussion

Loading...

Member takes

Overview

A two-stage model improves dynamic production prediction in reservoir management, suggesting robust data generation.

Key Points

  • The proposed PC-CGAN framework generates high-fidelity static reservoir properties and dynamic production data.
  • Experiments show significant improvements in predictive accuracy for reservoir management using the model.
  • The framework incorporates differentiable physical constraints into the generators to ensure physical consistency.
  • This method effectively addresses data scarcity, enhancing the reliability of reservoir characterization.

Cite This Study

Li et al. (2025) studied this question.

synapsesocial.com/papers/68c1b18b54b1d3bfb60e88ddhttps://doi.org/10.1088/2631-8695/adf797
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. 1Cross‐Dimensional Generative Adversarial Networks (CDGAN) Geomodeling: Bridging 2D Geological Figures and 3D Reservoir Modeling2026
  2. 2From simulator to surrogate: GANs for spatiotemporal modeling of subsurface flow in porous media2026
  3. 3Generative Adversarial Network for Modeling of CO2 Plume Evolution in Geological Carbon Storage Systems2025 · 2 citations
  4. 4Dynamic Reservoir Geological Mapping Using Generative AI and Satellite Data2025
  5. 5Geomodelling of multi-scenario non-stationary reservoirs with enhanced GANSim2025 · 3 citations