Transfer Learning-Enhanced N-BEATSx for Multivariate Forecasting of Tight Gas Well Production
Electronics · 29.09.2025 · 14 (19) · 3875
DOI: 10.3390/electronics14193875 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 29.09.2025. Verfasst von Yangnan Shangguan und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Natural Science Basic Research Program of Shaanxi, National Science and Technology Major Project:Mechanisms and New Technologies for En-hancing Tight Gas Recovery.
Abstract (Originalsprache)
Tight gas reservoirs present unique forecasting challenges due to steep decline rates, nonlinear production dynamics, and sensitivity to operational conditions. Conventional decline-curve methods and reservoir simulations are limited either by oversimplifying assumptions or by the need for extensive input data, although univariate deep learning models fail to fully capture external influences on well performance. To address these limitations, this study develops a transfer learning–enhanced N-BEATSx (Neural Basis Expansion Analysis Time Series with exogenous variables) framework for multivariate forecasting of tight gas well production. The model integrates exogenous variables, particularly casing pressure, with production histories to jointly represent reservoir behavior and operational effects. A pretraining dataset, comprising more than 100,000-day records from Block S of the Sulige Gas Field, was used to initialize the model, which was subsequently applied in a zero-shot setting to wells A1 and A2. Comparative analysis with the transfer learning-enhanced N-BEATS model demonstrates that N-BEATSx achieves consistently higher accuracy, with RMSE reductions of 23.9%, 39.1%, and 33.1% for Well A1 in short-, medium-, and long-term forecasts, respectively. These advances establish N-BEATSx as a robust tool for multivariate production forecasting, with direct industrial value in optimizing resource allocation, guiding development strategies, and enhancing operational decision-making in unconventional gas fields.
Förderung
- the Natural Science Basic Research Program of Shaanxi
- National Science and Technology Major Project:Mechanisms and New Technologies for En-hancing Tight Gas Recovery
Zitieren
APA
Shangguan, Y., Jia, J., Xiong, W., Wang, J., Ma, X., Chang, S., & Zhang, Z. (2025). Transfer Learning-Enhanced N-BEATSx for Multivariate Forecasting of Tight Gas Well Production. Electronics, 14(19), 3875. https://doi.org/10.3390/electronics14193875
Vancouver
Shangguan Y, Jia J, Xiong W, Wang J, Ma X, Chang S, et al. Transfer Learning-Enhanced N-BEATSx for Multivariate Forecasting of Tight Gas Well Production. Electronics. 2025;14(19):3875. doi:10.3390/electronics14193875
BibTeX
@article{Shangguan2025,
author = {Shangguan, Yangnan and Jia, Junhong and Xiong, Weiliang and Wang, Jinghua and Ma, Xianlin and Chang, Shilong and Zhang, Zhenzihao},
title = {Transfer Learning-Enhanced N-BEATSx for Multivariate Forecasting of Tight Gas Well Production},
journal = {Electronics},
year = {2025},
volume = {14},
number = {19},
pages = {3875},
doi = {10.3390/electronics14193875}
}
EUVIMED