EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Physics-Constrained Meta-Embedded Neural Network for Bottom-Hole Pressure Prediction in Radial Oil Flow Reservoirs

Linhao Qiu, Yuxi Yang, Yunxiu Sai, Youyou Cheng

Processes · 26.12.2025 · 14 (1) · 89

DOI: 10.3390/pr14010089 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Processes, online erschienen am 26.12.2025. Verfasst von Linhao Qiu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the CNPC Innovation Found, Shaanxi Provincial Natural Science Basic Research Program, National Key Research and Development Program of China: Efficient Development Technology for Fractured-Porous Carbonate Gas Reservoirs.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the advancement of petroleum engineering, the increasing complexity of formations and unpredictable conditions make wellbore pressure prediction more challenging. Accurate bottom-hole pressure (BHP) prediction is crucial for the safe and stable development of oil and gas reservoirs. Solving the partial differential equations (PDEs) governing fluid flow is key to this prediction. As deep learning becomes widespread in scientific and engineering applications, physics-informed neural networks (PINNs) have emerged as powerful tools for solving PDEs. However, traditional PINNs face challenges such as insufficient fitting accuracy, large errors, and gradient explosion. This study introduces MetaPress, a novel physics-informed neural network structure, to address inaccurate formation pressure prediction. MetaPress incorporates a meta-learning-based embedding function that integrates spatial information into the input and forget gates of Long Short-Term Memory networks. This enables the model to capture complex spatiotemporal features of flow problems, improving its generalization and nonlinear modeling capabilities. Using the MetaPress architecture, we predicted BHP under single-phase flow conditions, achieving an error of less than 2% for L2. This approach offers a novel method for solving seepage equations and predicting BHP, providing new insights for subsequent studies on reservoir fluid flow processes.

Förderung

  • the CNPC Innovation Found
  • Shaanxi Provincial Natural Science Basic Research Program
  • National Key Research and Development Program of China: Efficient Development Technology for Fractured-Porous Carbonate Gas Reservoirs

Zitieren

APA

Qiu, L., Yang, Y., Sai, Y., & Cheng, Y. (2025). Physics-Constrained Meta-Embedded Neural Network for Bottom-Hole Pressure Prediction in Radial Oil Flow Reservoirs. Processes, 14(1), 89. https://doi.org/10.3390/pr14010089

Vancouver

Qiu L, Yang Y, Sai Y, Cheng Y. Physics-Constrained Meta-Embedded Neural Network for Bottom-Hole Pressure Prediction in Radial Oil Flow Reservoirs. Processes. 2025;14(1):89. doi:10.3390/pr14010089

BibTeX
@article{Qiu2025,
  author = {Qiu, Linhao and Yang, Yuxi and Sai, Yunxiu and Cheng, Youyou},
  title = {Physics-Constrained Meta-Embedded Neural Network for Bottom-Hole Pressure Prediction in Radial Oil Flow Reservoirs},
  journal = {Processes},
  year = {2025},
  volume = {14},
  number = {1},
  pages = {89},
  doi = {10.3390/pr14010089}
}
Kostenlos starten →