EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Prediction of Carbonate Reservoir Porosity Based on CNN-BiLSTM-Transformer

Yingqiang Qi, Shuiliang Luo, Song Tang, Jifu Ruan, Da Gao, Qianqian Liu, Sheng Li

Applied Sciences · 21.03.2025 · 15 (7) · 3443

DOI: 10.3390/app15073443 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 21.03.2025. Verfasst von Yingqiang Qi und 6 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China Youth Fund Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Carbonate reservoirs are widely distributed and have great exploration potential. As a key indicator for reservoir characterization and evaluation, accurate and efficient porosity prediction is crucial for the exploration and development of oil and gas in carbonate reservoirs. To address the issues of low prediction accuracy and weak generalization ability in carbonate reservoir porosity prediction, a porosity prediction model (CNN-BiLSTM-Transformer) combining a convolutional neural network (CNN), bidirectional long short-term memory network (BiLSTM), and Transformer network is proposed. This model is applied to the Moxi gas field in the Sichuan Basin, using conventional logging curves as input feature variables for porosity prediction. Root mean square error (RMSE), mean absolute error (MAE), and the coefficient of determination (R²) are used as evaluation metrics for comprehensive analysis and comparison. The model extracts curve features through the CNN layer, captures both short- and long-term neighborhood information via the BiLSTM layer, and utilizes the Transformer layer with a self-attention mechanism to focus on temporal information and input features, effectively capturing global dependencies. The Adam optimization algorithm is employed to update the network’s weights, and hyperparameters are adjusted based on feedback from network accuracy to achieve precise porosity prediction in highly heterogeneous carbonate reservoirs. Compared with traditional machine learning and deep learning models, the improved model better captures domain-specific information, resulting in an R² increase of 0.23 and reductions in RMSE and MAE by 0.016 and 0.014, respectively. Experimental results show that the porosity prediction model based on the CNN-BiLSTM-Transformer algorithm achieves lower average relative error and better prediction performance. Therefore, the CNN-BiLSTM-Transformer model can effectively predict the porosity of carbonate reservoirs and offers valuable insights for carbonate reservoir parameter prediction.

Förderung

  • National Natural Science Foundation of China Youth Fund Project

Zitieren

APA

Qi, Y., Luo, S., Tang, S., Ruan, J., Gao, D., Liu, Q., & Li, S. (2025). Prediction of Carbonate Reservoir Porosity Based on CNN-BiLSTM-Transformer. Applied Sciences, 15(7), 3443. https://doi.org/10.3390/app15073443

Vancouver

Qi Y, Luo S, Tang S, Ruan J, Gao D, Liu Q, et al. Prediction of Carbonate Reservoir Porosity Based on CNN-BiLSTM-Transformer. Applied Sciences. 2025;15(7):3443. doi:10.3390/app15073443

BibTeX
@article{Qi2025,
  author = {Qi, Yingqiang and Luo, Shuiliang and Tang, Song and Ruan, Jifu and Gao, Da and Liu, Qianqian and Li, Sheng},
  title = {Prediction of Carbonate Reservoir Porosity Based on CNN-BiLSTM-Transformer},
  journal = {Applied Sciences},
  year = {2025},
  volume = {15},
  number = {7},
  pages = {3443},
  doi = {10.3390/app15073443}
}
Kostenlos starten →