EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Productivity prediction of shale reservoirs based on machine learning methods

Jian Yao

Thermal Science · 2026 · 30 (5 Part A) · 3253-3258

DOI: 10.2298/tsci250820127y ↗

Kurz gefasst

Fachartikel in der Zeitschrift Thermal Science, 2026. Verfasst von Jian Yao. Die Arbeit nennt 9 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With increasing difficulty in oil and gas field development, accurate prediction of well productivity has become crucial. Traditional methods such as analytical solutions and numerical simulations have limited accuracy under heterogeneous and complex flow conditions. This study develops a CNN-LSTM model combining convolutional neural networks (CNN) and long short-term memory networks (LSTM) based on measured data from well J-1 in a shale oil block in eastern China for short-term multi-dimensional time series production forecasting. The model integrates CNN’s feature extraction with LSTM’s temporal modelling, using inputs including production rate, oil pressure, casing pressure, and production time. Compared with the traditional random forest model, the CNN-LSTM outperforms across R², MAE, MAPE, and RMSE metrics, achieving an R² of 0.9707 and MAPE below 5.1% on the test set. Results demonstrate strong fitting and predictive capabilities, indicating good applicability and potential for broader use in shale oil production forecasting.

Zitieren

APA

Yao, J. (2026). Productivity prediction of shale reservoirs based on machine learning methods. Thermal Science, 30(5 Part A), 3253-3258. https://doi.org/10.2298/tsci250820127y

Vancouver

Yao J. Productivity prediction of shale reservoirs based on machine learning methods. Thermal Science. 2026;30(5 Part A):3253-3258. doi:10.2298/tsci250820127y

BibTeX
@article{Yao2026,
  author = {Yao, Jian},
  title = {Productivity prediction of shale reservoirs based on machine learning methods},
  journal = {Thermal Science},
  year = {2026},
  volume = {30},
  number = {5 Part A},
  pages = {3253--3258},
  doi = {10.2298/tsci250820127y}
}
Kostenlos starten →