EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Engineering-Constrained Explainable Machine Learning for Development Policy Optimization in the Y284 Tight Oil Block, Ordos Basin

Huanying Yang, Xiaoping An, Youwei Xu, Yunli Lu, Gang Hui, Hongchang Li, Jing Wang, Xiaohui Fan, Xueying Yu

Processes · 30.10.2026 · 14 (21) · 3478

DOI: 10.3390/pr14213478 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Processes, online erschienen am 30.10.2026. Verfasst von Huanying Yang und 8 weiteren Autor:innen. Die Arbeit nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: CNPC Changqing Oilfield Scientific Project “Re-evaluation of Development Performance and Study on Rational Development Modes for Chang 6 Tight Oil in Longdong….

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Tight-oil performance is controlled by a coupled reservoir-engineering system: reservoir quality, fracturing design, well pattern, and operating policy jointly determine whether geological potential becomes sustained production. This study develops an engineering-constrained, explainable machine-learning workflow for the Y284 block of the Longdong Chang 6 reservoir and identifies the controls on five-year cumulative oil. Four constraints are imposed: pre-decision and post-hoc variables are separated to avoid leakage; decline fitting, water-breakthrough classification, and injection-effect diagnosis serve as physical constraints; models are selected by accuracy and engineering plausibility; and SHAP controls are turned into field-readable policies. Of 939 well records, 338 with a complete geological and engineering record form the model-ready sample; five-fold cross-validation stratified by well type gives an out-of-fold R2 of 0.55 for the retained random forest. Engineering communication intensity, set by pump rate, stage count, and per-stage fluid and proppant volume, dominates production (69.9% of the mean absolute SHAP value), followed by geological storage capacity (21.6%) and injection and production control (8.6%); stage count and pump rate rank first. The framework is a block-scale screening and ranking tool, not a high-accuracy predictor.

Förderung

  • CNPC Changqing Oilfield Scientific Project “Re-evaluation of Development Performance and Study on Rational Development Modes for Chang 6 Tight Oil in Longdong…

Zitieren

APA

Yang, H., An, X., Xu, Y., Lu, Y., Hui, G., Li, H., Wang, J., Fan, X., & Yu, X. (2026). Engineering-Constrained Explainable Machine Learning for Development Policy Optimization in the Y284 Tight Oil Block, Ordos Basin. Processes, 14(21), 3478. https://doi.org/10.3390/pr14213478

Vancouver

Yang H, An X, Xu Y, Lu Y, Hui G, Li H, et al. Engineering-Constrained Explainable Machine Learning for Development Policy Optimization in the Y284 Tight Oil Block, Ordos Basin. Processes. 2026;14(21):3478. doi:10.3390/pr14213478

BibTeX
@article{Yang2026,
  author = {Yang, Huanying and An, Xiaoping and Xu, Youwei and Lu, Yunli and Hui, Gang and Li, Hongchang and Wang, Jing and Fan, Xiaohui and Yu, Xueying},
  title = {Engineering-Constrained Explainable Machine Learning for Development Policy Optimization in the Y284 Tight Oil Block, Ordos Basin},
  journal = {Processes},
  year = {2026},
  volume = {14},
  number = {21},
  pages = {3478},
  doi = {10.3390/pr14213478}
}
Kostenlos starten →