EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Hybrid Deep Learning Model with Spatial-Temporal Feature Fusion for Geothermal Production Prediction

Xin Huang, Mengxiao Ma, Zhiming Hu, Chuanxia Ruan, Shuo Xiao, Shuo Li, Wenjie Jiang, Wenwen Yang

Applied Sciences · 08.06.2026 · 16 (12) · 5783

DOI: 10.3390/app16125783 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 08.06.2026. Verfasst von Xin Huang und 7 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Open Fund of Observation and Research Station of Tianjin Low-Medium Temperature Geo-thermal Resources, MNR, the National Science Foundation of China, the Natural Science Foundation of Tianjin.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Geothermal energy, a clean and reliable renewable resource, is attracting growing global attention. Predicting geothermal productivity is essential for the sustainable management of geothermal systems in conventional pumping tests, but the water level has a highly nonlinear correlation with reservoir physical conditions, and traditional numerical simulation methods fail to capture their intrinsic relationship. This study proposes a novel hybrid deep learning model of Graph Convolutional Networks (GCN) and Transformers for geothermal pumping tests, which efficiently predicts water level under nonlinear physical constraints: GCN learns the nonlinear mapping between water level depth and physical constraints, while Transformer preserves the temporal sequence correlations of production data via self-attention mechanism. Validation with test data showed that the model achieved an R2 of 0.97 and an RMSE of 0.1635 m for production wells, and an R2 of 0.94 and an RMSE of 3.9057 m for reinjection wells under different geological conditions. Its R2 showed improvements of 13.82%, 7.83%, and 5.95% compared with the LSTM, Transformer, and GCN–LSTM models, respectively. This study provides an accurate and efficient technical approach for geothermal productivity prediction, supporting the optimization of pumping test schemes and production capacity evaluation in preliminary geothermal resource development.

Förderung

  • the Open Fund of Observation and Research Station of Tianjin Low-Medium Temperature Geo-thermal Resources, MNR
  • the National Science Foundation of China
  • the Natural Science Foundation of Tianjin
  • the Doctoral Foundation of Tianjin Normal University

Zitieren

APA

Huang, X., Ma, M., Hu, Z., Ruan, C., Xiao, S., Li, S., Jiang, W., & Yang, W. (2026). A Hybrid Deep Learning Model with Spatial-Temporal Feature Fusion for Geothermal Production Prediction. Applied Sciences, 16(12), 5783. https://doi.org/10.3390/app16125783

Vancouver

Huang X, Ma M, Hu Z, Ruan C, Xiao S, Li S, et al. A Hybrid Deep Learning Model with Spatial-Temporal Feature Fusion for Geothermal Production Prediction. Applied Sciences. 2026;16(12):5783. doi:10.3390/app16125783

BibTeX
@article{Huang2026,
  author = {Huang, Xin and Ma, Mengxiao and Hu, Zhiming and Ruan, Chuanxia and Xiao, Shuo and Li, Shuo and Jiang, Wenjie and Yang, Wenwen},
  title = {A Hybrid Deep Learning Model with Spatial-Temporal Feature Fusion for Geothermal Production Prediction},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {12},
  pages = {5783},
  doi = {10.3390/app16125783}
}
Kostenlos starten →