EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Accurate and Interpretable Prediction of Exploration Input–Output Matching Under Data Scarcity: An Ensemble Learning Framework

Xiao Chen, Hui Liu, Weiyun Zhan, Haitao Li, Yu Cao, Yuan Liang

Applied Sciences · 06.08.2026 · 16 (15) · 7859

DOI: 10.3390/app16157859 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 06.08.2026. Verfasst von Xiao Chen und 5 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Chengdu University of Technology, 2024 Natural Science Foundation of Sichuan Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate prediction of input–output relationships in natural gas exploration is essential for improving exploration efficiency and optimizing investment allocation. However, this task is severely hindered by data sparsity and strong nonlinear characteristics inherent in oil and gas exploration systems, rendering conventional statistical methods and single machine learning models ineffective. This study develops a novel integrated framework combining data augmentation, nonlinear feature engineering, and ensemble learning to achieve accurate and interpretable prediction of exploration input–output matching under limited data constraints. Taking four core exploration indicators—including the number of exploration wells, total drilling depth, reserve abundance, and proven reserves—as input variables, adaptive prediction models were constructed for seven typical hydrocarbon basin exploration systems. To ensure comprehensive algorithmic exploration, nine advanced algorithms, including mainstream ensemble methods (RandomForest), few-shot neural networks (FewShot_NN), and kernel-based regressions, were systematically benchmarked. Furthermore, SHapley Additive exPlanations (SHAPs) was adopted to enhance model interpretability, and non-parametric Wilcoxon signed-rank tests were introduced to rigorously validate statistical significance. The results demonstrate that the optimal predictive pathway varies across different geological systems. Specifically, RandomForest and GBDT exhibit superior performance in systems with moderate heterogeneity (e.g., Jialingjiang and Changxing–Feixianguan Formations), whereas FewShot_NN and Kernel Ridge achieve the highest accuracy under extreme data sparsity and volatility (e.g., Xujiahe Formation and Lower Permian). The established framework yields a coefficient of determination (R2) greater than 0.96 for the majority of study cases, with overall absolute percentage errors heavily minimized. SHAP analysis further verifies that drilling depth and reserve abundance are the dominant controlling factors. This data-driven framework provides a robust and interpretable technical tool for the intelligent management of energy resources.

Förderung

  • State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation
  • Chengdu University of Technology
  • 2024 Natural Science Foundation of Sichuan Province

Zitieren

APA

Chen, X., Liu, H., Zhan, W., Li, H., Cao, Y., & Liang, Y. (2026). Accurate and Interpretable Prediction of Exploration Input–Output Matching Under Data Scarcity: An Ensemble Learning Framework. Applied Sciences, 16(15), 7859. https://doi.org/10.3390/app16157859

Vancouver

Chen X, Liu H, Zhan W, Li H, Cao Y, Liang Y. Accurate and Interpretable Prediction of Exploration Input–Output Matching Under Data Scarcity: An Ensemble Learning Framework. Applied Sciences. 2026;16(15):7859. doi:10.3390/app16157859

BibTeX
@article{Chen2026,
  author = {Chen, Xiao and Liu, Hui and Zhan, Weiyun and Li, Haitao and Cao, Yu and Liang, Yuan},
  title = {Accurate and Interpretable Prediction of Exploration Input–Output Matching Under Data Scarcity: An Ensemble Learning Framework},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {15},
  pages = {7859},
  doi = {10.3390/app16157859}
}
Kostenlos starten →