JCSAI | Journal of Computer Science and Artificial Intelligence
← Back to Volume 5, Issue 1

Graph Neural Networks and Multi-Objective Hybrid Optimization: A Review of Intelligent Decision-Making Frameworks for Waterflood Reservoir Injection–Production Regulation

Ting Zhang, Wenhui Zhang, Yemeng Chen, Wenqi Wang, Lianzhuo Xie, Ganghao Hu, Chaoyu Zhang, Botao Liu
Vol. 5, No. 1, pp. 15-21, 2025 DOI: 10.54097/cgzkas62 November 25, 2025
Download PDF
Abstract.Real-time regulation of water-flooding injection–production systems is a crucial factor in enhancing reservoir development efficiency. However, in practical water-flooding operations, reservoir heterogeneity causes the inter-well fluid connectivity to vary dynamically over time. As a result, conventional regulation methods often require a considerable amount of time to adjust control schemes, leading to significant lag effects. When oilfields enter the medium- to high-water-cut stage, the geological structures and flow patterns become increasingly complex, making it difficult for traditional approaches to maintain real-time management. In recent years, Graph Neural Networks (GNNs) and hybrid multi-objective optimization algorithms such as Genetic Algorithm–Multi-Objective Particle Swarm Optimization (GA-MOPSO) have emerged as promising technologies in the field of reservoir development, demonstrating frontier applications in dynamic optimization and intelligent regulation of water-flooding systems [1-3]. GNNs can effectively model the graph structure of dynamic inter-well connectivity, accurately capturing the spatial–temporal evolution characteristics of the reservoir, while GA-MOPSO achieves a robust trade-off between maximizing the Net Present Value (NPV) and minimizing the Injection–Production Difference (IPD) [4]. In addition, recent studies have shown that surrogate models exhibit strong performance in predicting unseen geological configurations during heterogeneous multiphase flow simulations [5]. This paper provides a comprehensive review of GNN- and GA-MOPSO-based hybrid approaches for water-flooding regulation, with particular emphasis on the advantages of the Heterogeneous Spatiotemporal Fusion Model (HSTMF) in water-cut prediction. Furthermore, it discusses the key challenges and potential directions for future research in terms of model generalization, algorithmic robustness, and engineering deployment [6].
Keywords. Graph neural network (GNN) multi-objective optimization hybrid algorithm water-flooding reservoir intelligent decision-making closed-loop control
APA Citation Ting Zhang, Wenhui Zhang, Yemeng Chen, Wenqi Wang, Lianzhuo Xie, Ganghao Hu, Chaoyu Zhang, Botao Liu (2025). Graph Neural Networks and Multi-Objective Hybrid Optimization: A Review of Intelligent Decision-Making Frameworks for Waterflood Reservoir Injection–Production Regulation. Journal of Computer Science and Artificial Intelligence, 5(1), 15-21. https://doi.org/10.54097/cgzkas62

References

  1. Li, B.; Zhao, H.; Liu, B.; Xu, Y.; Tian, F.; Xia, J.; Chen, Y.; Dai, J. Graph Neural Networks and Hybrid Optimization for Water-Flooding Regulation. Physics of Fluids 2025, 37, 086609.
  2. Sori, A.; Sharifi, M.; Jabari, N. Robust Multi-Objective Optimization for Water Flooding under Geological Uncertainty. Discover Geoscience 2025, 3, 26.
  3. Sasal, L.; Busby, D.; Hadid, A. A Graph Neural Network-Based Approach for Complex Reservoirs Simulation Surrogate Modelling. Earthdoc 2024.
  4. Huang, H.; Huang, Z.-Q.; Wang, Z.-X.; Hu, H.-F.; et al. A Deep-Learning-Based Graph Neural Network-Long-Short-Term Memory Model for Reservoir Simulation and Optimization With Varying Well Controls. SPE Journal 2023.
  5. Jiang, J.; Chen, J.; Yang, Z. A Multigrid Graph U-Net Framework for Simulating Multiphase Flow in Heterogeneous Porous Media. arXiv preprint 2024, arXiv:2412.12757.
  6. Tang, H.; Durlofsky, L. Graph Network Surrogate Model for Subsurface Flow Optimization. Journal of Computational Physics 2024, 512, 113132.
  7. Li, B.; Zhao, H.; Liu, B.; Xu, Y.; Tian, F.; Xia, J.; Chen, Y.; Dai, J. Graph Neural Networks and Hybrid Optimization for Water-Flooding Regulation. Physics of Fluids 2025, 37, 086609.
  8. Sasal, L.; Busby, D.; Hadid, A. A Graph Neural Network-Based Approach for Complex Reservoir Simulation Surrogate Modelling. ECMOR 2024 / EAGE Conference Proceedings 2024.
  9. Nasir, Y.; Durlofsky, L. J. Multi-Asset Closed-Loop Reservoir Management Using Deep Reinforcement Learning [R]. arXiv preprint arXiv:2207.10376, 2022.
  10. Kim, Y. D.; Durlofsky, L. Convolutional-Recurrent Neural Network Proxy for Robust Optimization and Closed-Loop Reservoir Management [R]. arXiv preprint, 2022.
  11. Huang, Z.-Q.; Wang, Z.-X.; Hu, H.-F.; Zhang, S.-M. Dynamic Interwell Connectivity Analysis of Multi-Layer Waterflooding Reservoirs Based on an Improved Graph Neural Network. Petroleum Science 2024, 21, 233–247.
  12. Truong, H.; Maier, R.; Zavala, P. Graph Neural Networks for Pressure Estimation in Water Distribution and Subsurface Flow Systems. AGU Publications 2024.
  13. Wang, L.; Yao, Y.; Luo, X.; Adenutsi, C. A Critical Review on Intelligent Optimization Algorithms and Surrogate Models for Conventional and Unconventional Reservoir Production Optimization. Fuel 2023, 345, 128134.
  14. Abdollahfard, Y.; Sharifi, H. Assessing Proxy and AI Models Performance in Waterflooding Optimization. Scientific Reports 2025, 15, 9982.
  15. Gao, M.; Wei, C.; Zhao, X.; Huang, R.; Li, B. Intelligent Optimization of Gas Flooding Based on Multi-Objective Approach for Efficient Reservoir Management. Processes 2023, 11(7), 2226.
  16. Zhang, H.; Liu, Y.; Xu, X.; et al. Multiobjective Optimization of CO₂ Injection under Geomechanical Risk in High Water Cut Oil Reservoirs Using Artificial Intelligence Approaches. Scientific Reports 2025, 15, 11742.
  17. Gao, M.; Wei, C.; Zhao, X.; Huang, R.; Li, B. Intelligent Optimization of Gas Flooding Based on Multi-Objective Approach for Efficient Reservoir Management. Processes 2023, 11(7), 2226.
  18. Zhang, Z. P.; Fink, O. Algorithm-Informed Graph Neural Networks for Leakage Detection and Localization in Water Distribution Networks [J]. Reliability Engineering & System Safety, 2024.
  19. ] Kim, H. J.; Kim, J.; Park, H. J. Graph-Based Learning of Free Surface Dynamics in Generalized Newtonian Fluids using Smoothed Particle Hydrodynamics [R]. arXiv preprint, 2025.
  20. Sasal, L.; Busby, D.; Hadid, A. *A Graph Neural Network-Based Approach for Complex Reservoirs Simulation Surrogate Modelling.* ECMOR 2024, EAGE.