EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Fracture Development Probability Prediction in Tight Oil Reservoirs by Integrating Fracture Response Mapping with Triangular Topology-Optimized BiLSTM

Jianchao Shi, Jiwei Wang, Xiaoke Li, Yongjian Feng, Qiang Liu, Wenyan Yang, Shuai Duan, Xinyu Li

Processes · 31.07.2026 · 14 (15) · 2475

DOI: 10.3390/pr14152475 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Processes, online erschienen am 31.07.2026. Verfasst von Jianchao Shi und 7 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Oil & Gas Major Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Natural fractures strongly influence fluid flow, hydraulic-fracturing performance, and production heterogeneity in tight oil reservoirs. Their identification from conventional logs remains challenging because image-log and core coverage is limited, fracture-related logging responses are non-unique, and discrete fracture interpretations are difficult to align with regularly sampled logging sequences. This study used conventional logging data and electrical image-log interpretations from 17 wells in the Xifeng Oilfield, Ordos Basin, together with core observations from selected intervals, to develop a fracture response mapping and triangular topology-optimized bidirectional long short-term memory model (FRM-BiLSTM-TTAO). After sliding-window construction and density-based undersampling, 1713 samples were retained and partitioned at the well level into 14 training wells and three independent test wells, yielding an approximate training-to-test sample ratio of 75:25. FRM extracts lithologic-background, local-abrupt-change, multiscale-fluctuation, and integrated fracture response features; BiLSTM captures bidirectional depth dependencies; and TTAO selects fracture response features and optimizes the network architecture and training parameters. On the test set, the model achieved a ROC-AUC of 0.9079, a recall of 0.8671, and an F1-score of 0.8464, outperforming CNN, MLP, ResNet1D, XGBoost, and the corresponding ablation models. The predicted high-probability intervals were generally consistent with image-log interpretations and core observations, indicating the feasibility of the proposed method for identifying fracture-prone intervals within the study area.

Förderung

  • Oil & Gas Major Project

Zitieren

APA

Shi, J., Wang, J., Li, X., Feng, Y., Liu, Q., Yang, W., Duan, S., & Li, X. (2026). Fracture Development Probability Prediction in Tight Oil Reservoirs by Integrating Fracture Response Mapping with Triangular Topology-Optimized BiLSTM. Processes, 14(15), 2475. https://doi.org/10.3390/pr14152475

Vancouver

Shi J, Wang J, Li X, Feng Y, Liu Q, Yang W, et al. Fracture Development Probability Prediction in Tight Oil Reservoirs by Integrating Fracture Response Mapping with Triangular Topology-Optimized BiLSTM. Processes. 2026;14(15):2475. doi:10.3390/pr14152475

BibTeX
@article{Shi2026,
  author = {Shi, Jianchao and Wang, Jiwei and Li, Xiaoke and Feng, Yongjian and Liu, Qiang and Yang, Wenyan and Duan, Shuai and Li, Xinyu},
  title = {Fracture Development Probability Prediction in Tight Oil Reservoirs by Integrating Fracture Response Mapping with Triangular Topology-Optimized BiLSTM},
  journal = {Processes},
  year = {2026},
  volume = {14},
  number = {15},
  pages = {2475},
  doi = {10.3390/pr14152475}
}
Kostenlos starten →