Research on Shale Oil Well Productivity Prediction Model Based on CNN-BiGRU Algorithm

Yuan Pan, Xuewei Liu, Fuchun Tian (), Liyong Yang, Xiaoting Gou, Yunpeng Jia, Quan Wang and Yingxi Zhang
Additional contact information
Yuan Pan: Petroleum Engineering Research Institute, PetroChina Dagang Oilfield Company, Tianjin 300280, China
Xuewei Liu: Petroleum Engineering Research Institute, PetroChina Dagang Oilfield Company, Tianjin 300280, China
Fuchun Tian: Petroleum Engineering Research Institute, PetroChina Dagang Oilfield Company, Tianjin 300280, China
Liyong Yang: Petroleum Engineering Research Institute, PetroChina Dagang Oilfield Company, Tianjin 300280, China
Xiaoting Gou: Petroleum Engineering Research Institute, PetroChina Dagang Oilfield Company, Tianjin 300280, China
Yunpeng Jia: Petroleum Engineering Research Institute, PetroChina Dagang Oilfield Company, Tianjin 300280, China
Quan Wang: Petroleum Engineering Research Institute, PetroChina Dagang Oilfield Company, Tianjin 300280, China
Yingxi Zhang: Petroleum Engineering Research Institute, PetroChina Dagang Oilfield Company, Tianjin 300280, China

Energies, 2025, vol. 18, issue 10, 1-17

Abstract: Unconventional reservoirs are characterized by intricate fluid-phase behaviors, and physics-based shale oil well productivity prediction models often exhibit substantial deviations due to oversimplified theoretical frameworks and challenges in parameter acquisition. Under these circumstances, data-driven approaches leveraging actual production datasets have emerged as viable alternatives for productivity forecasting. Nevertheless, conventional data-driven architectures suffer from structural simplicity, limited capacity for processing low-dimensional feature spaces, and exclusive applicability to intra-sequence learning paradigms (e.g., production-to-production sequence mapping). This fundamentally conflicts with the underlying principles of mechanistic modeling, which emphasize pressure-to-production sequence transformations. To address these limitations, we propose a hybrid deep learning architecture integrating convolutional neural networks with bidirectional gated recurrent units (CNN-BiGRU). The model incorporates dedicated input pathways: fully connected layers for feature embedding and convolutional operations for high-dimensional feature extraction. By implementing a sequence-to-sequence (seq2seq) architecture with encoder–decoder mechanisms, our framework enables cross-domain sequence learning, effectively bridging pressure dynamics with production profiles. The CNN-BiGRU model was implemented on the TensorFlow framework, with rigorous validation of model robustness and systematic evaluation of feature importance. Hyperparameter optimization via grid searching yielded optimal configurations, while field applications demonstrated operational feasibility. Comparative analysis revealed a mean relative error (MRE) of 16.11% between predicted and observed production values, substantiating the model’s predictive competence. This methodology establishes a novel paradigm for machine learning-driven productivity prediction in unconventional reservoir engineering.

Keywords: production prediction; neural network deep learning; shale oil reservoirs; fracturing horizontal wells (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/18/10/2523/pdf (application/pdf)
https://www.mdpi.com/1996-1073/18/10/2523/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:18:y:2025:i:10:p:2523-:d:1655044

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().