Frequency-Domain Convolutional Network With Historical Data Fusion Module for Regional Streamflow Prediction
- 2 September 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-14
Abstract
Accurate runoff prediction is essential for effective water resource management, particularly in addressing flood control and monitoring drought conditions. However, the diverse nature of land types and varying climate conditions often complicate this task, requiring frequent adaptations to prediction models for local applications. Existing methods primarily focus on modeling for individual regions, while regional runoff prediction models often cannot learn long-term patterns, limiting their regional adaptability. To overcome this challenge, we present the temporal fusion runoff network (TFRN), a new framework designed to enhance long short-term memory (LSTM) models by enabling them to incorporate distant historical information. This innovation offers a promising framework for regional runoff prediction by enhancing model performance and minimizing computational demands. In this study, the proposed TFRN utilizes convolutional networks to extract and integrate both long- and short-term trends from input sequences, and by merging the strengths of LSTM and Transformer architectures, the TFRN achieves a thorough integration of historical data. Specifically, our method employs convolutional networks across both time and frequency domains to capture multiscale features. In the Transformer component, we introduce an adaptive fusion module to improve the integration of historical information. We validated the effectiveness of our model using two extensive hydrological datasets for a seven-day runoff prediction task. The results underscore the superiority of our approach, demonstrating its advantages over several leading methods. The source code is available at https://github.com/redtea-code/TFRNKeywords
Funding Information
- China Ministry of Education Humanities and Social Sciences Research-Planning Fund Project (23YJA910007)
- Zhejiang Provincial Philosophy and Social Sciences Planning Project-Major Project (23SYS12ZD)
- First Class Discipline of Zhejiang-A
- Basic and Applied Basic Research Foundation of Guangdong Province (2025A1515011617, 2022A1515110570)
- Innovation Teams of Youth Innovation in Science and Technology of High Education Institutions of Shandong province (2021KJ088)
This publication has 49 references indexed in Scilit:
- Parameter estimation and uncertainty quantification of rainfall-runoff models using data assimilation methods based on deep learning and local ensemble updatesEnvironmental Modelling & Software, 2025
- Assessing the Influence of Zero‐Flow Threshold Choice for Characterising Intermittent Stream HydrologyHydrological Processes, 2024
- A state-of-the-art review of long short-term memory models with applications in hydrology and water resourcesApplied Soft Computing, 2024
- DeepGR4J: A deep learning hybridization approach for conceptual rainfall-runoff modellingEnvironmental Modelling & Software, 2023
- A novel feature attention mechanism for improving the accuracy and robustness of runoff forecastingJournal of Hydrology, 2023
- RR-Former: Rainfall-runoff modeling based on TransformerJournal of Hydrology, 2022
- Runoff Modeling in Ungauged Catchments Using Machine Learning Algorithm-Based Model Parameters Regionalization MethodologyEngineering, 2022
- Rainfall-runoff modeling using LSTM-based multi-state-vector sequence-to-sequence modelJournal of Hydrology, 2021
- Appraisal of Runoff Through BPNN, RNN, and RBFN in Tentulikhunti Watershed: A Case Study2019
- Singular Spectrum Analysis and ARIMA Hybrid Model for Annual Runoff ForecastingWater Resources Management, 2011