A Hybrid BiLSTM-TE Architecture for Spring Discharge Prediction in Data-Scarce Regions

Yan Liang, Shuai Gu, Chunmei Ma (), Yonghong Hao (), Huiqing Hao, Shilei Ma, Juan Zhang and Xueting Wang
Additional contact information
Yan Liang: School of Computer and Information Engineering, Tianjin Normal University, Tianjin 300387, China
Shuai Gu: School of Computer and Information Engineering, Tianjin Normal University, Tianjin 300387, China
Chunmei Ma: School of Computer and Information Engineering, Tianjin Normal University, Tianjin 300387, China
Yonghong Hao: Tianjin Key Laboratory of Water Resources and Environment, Tianjin Normal University, Tianjin 300387, China
Huiqing Hao: Tianjin Key Laboratory of Water Resources and Environment, Tianjin Normal University, Tianjin 300387, China
Shilei Ma: School of Computer and Information Engineering, Tianjin Normal University, Tianjin 300387, China
Juan Zhang: Tianjin Key Laboratory of Water Resources and Environment, Tianjin Normal University, Tianjin 300387, China
Xueting Wang: School of Computer and Information Engineering, Tianjin Normal University, Tianjin 300387, China

Sustainability, 2025, vol. 17, issue 12, 1-20

Abstract: Climate change and intensified human activities have increasingly threatened the sustainability of groundwater resources, especially in ecologically fragile karst regions. To address these challenges, this study proposes a karst spring discharge prediction model that integrates BiLSTM (Bidirectional Long Short-Term Memory) and the Transformer Encoder. The BiLSTM component captures both forward and backward information in spring discharge data, extracting trend-related features. The Transformer’s attention mechanism is employed to identify key precipitation factors influencing spring discharge. A patching preprocessing strategy divides monthly scale sequences into annual segments, reducing input length while enabling local modeling and global interaction. Experiments on Shentou Spring discharge show that the BiLSTM–Transformer Encoder outperforms other deep learning models across multiple evaluation metrics, with notable advantages in short-term forecasting. The patching strategy effectively reduces model parameters and improves efficiency. Attention visualization further confirms the model’s ability to capture critical hydrological drivers. This study not only provides a novel approach to sustainable water management in karst spring basins but also demonstrates an effective use of deep learning for long-term hydrological sustainability.

Keywords: spring discharge prediction; BiLSTM; transformer; patching preprocessing; attention mechanism; karst topography (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/17/12/5401/pdf (application/pdf)
https://www.mdpi.com/2071-1050/17/12/5401/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:17:y:2025:i:12:p:5401-:d:1676847

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().