EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

From Empirical Models to Physics‐Informed Neural Networks: The Evolution of Oil Production Forecasting

Shitan Yin, Erlong Yang, Xianjun Wang, Chi Dong

Journal of GeoEnergy · 2026-01 · 2026 (1)

DOI: 10.1155/jge5/6694015 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of GeoEnergy, online erschienen am 21.01.2026. Verfasst von Shitan Yin und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 169 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Production forecasting for oil and gas wells is a decisive element of field‐development planning because it directly guides recovery strategy design, production optimisation and risk management. Conventional methods, including empirical decline‐curve analysis (DCA) and full‐physics numerical simulation, are limited either by their inability to capture complex non‐linear flow behaviour or by prohibitive computational requirements. The rise of big data and artificial intelligence has introduced machine learning models such as support vector regression (SVR), random forests (RFs), XGBoost and multi‐layer perceptrons (MLPs), whose efficient non‐linear fitting has improved predictive accuracy; however, their black‐box nature and weak physical consistency now constrain further progress. Modern deep learning (DL) architectures—including long short‐term memory (LSTM) or gated recurrent unit (GRU) networks, CNN–LSTM hybrids, transformers, graph convolutional networks (GCNs) and kernel adaptive networks—extend modelling capability to long temporal sequences and systems with multiple interacting wells, fostering a technical shift from purely data‐driven learning toward physics‐enhanced intelligence. Of particular note, physics‐informed neural networks (PINNs) embed Darcy flow equations and related constraints directly in the loss function, which markedly strengthens extrapolation ability and interpretability while offering efficient support for history matching, surrogate modelling and closed‐loop reservoir management (CLRM). Nevertheless, these networks still face challenges involving the balance of loss‐term weights, multi‐scale coupling and training convergence; progress will rely on dynamic weighting schemes and a standardised library of physical priors. This review, therefore, synthesises the evolution from traditional machine learning to physics‐constrained approaches in production forecasting, assesses their respective advantages and limitations and identifies future research priorities in high‐quality dataset construction, cross‐field transfer learning, interpretability enhancement and system‐level intelligent optimisation in order to realise fully digital and closed‐loop intelligent oilfields.

Zitieren

APA

Yin, S., Yang, E., Wang, X., & Dong, C. (2026). From Empirical Models to Physics‐Informed Neural Networks: The Evolution of Oil Production Forecasting. Journal of GeoEnergy, 2026(1). https://doi.org/10.1155/jge5/6694015

Vancouver

Yin S, Yang E, Wang X, Dong C. From Empirical Models to Physics‐Informed Neural Networks: The Evolution of Oil Production Forecasting. Journal of GeoEnergy. 2026;2026(1). doi:10.1155/jge5/6694015

BibTeX
@article{Yin2026,
  author = {Yin, Shitan and Yang, Erlong and Wang, Xianjun and Dong, Chi},
  title = {From Empirical Models to Physics‐Informed Neural Networks: The Evolution of Oil Production Forecasting},
  journal = {Journal of GeoEnergy},
  year = {2026},
  volume = {2026},
  number = {1},
  doi = {10.1155/jge5/6694015}
}
Kostenlos starten →