Streamflow Prediction Using Long Shot-Term Memory Models for Optimized Irrigation Management
Preprint
- 18 December 2025
- preprint
- Published by Springer Nature in Research Square
Abstract
This study investigates the application of hybrid deep learning architectures—specifically LSTM-GRU models—for daily streamflow forecasting under varying hydrological conditions. Using long-term streamflow and rainfall records from two observation points in a tropical watershed, the models were evaluated across different rolling window lengths and input configurations: streamflow-only, streamflow with rainfall, and streamflow with real-time data assimilation. The results indicate that input type and temporal window selection significantly influence predictive performance. The LSTM-GRU model with real-time data integration consistently achieved the lowest Root Mean Square Error (RMSE ≈ 18.0) and the highest Nash–Sutcliffe Efficiency (NSE > 0.45) for short window sizes (1-year), outperforming both the rainfall-augmented and baseline configurations. Conversely, the model with rainfall input required longer training windows (up to 6 years) to reach optimal accuracy, reflecting delayed hydrological responses. Extending the forecast horizon from one to two years led to a notable decline in model performance across all configurations, though the real-time model remained the most robust and stable. The models also demonstrated strong spatio-temporal transferability, maintaining predictive accuracy across different sub-catchments despite local heterogeneity in watershed behavior. Importantly, integrating LSTM-based forecasts into rotational irrigation systems proved effective in optimizing planting schedules and water allocation, especially during transitional hydrological phases. Overall, the findings underscore the potential of LSTM-GRU models to capture nonlinear, non-stationary hydrological dynamics with high predictive skill. Their capacity to integrate multi-source temporal inputs and adapt to evolving hydrometeorological signals supports more informed, flexible, and resilient water resource planning under climatic uncertainty.Keywords
All Related Versions
This publication has 78 references indexed in Scilit:
- Irrigation Water Management in a Water-Scarce Environment in the Context of Climate ChangeWater, Air, & Soil Pollution, 2024
- A boosting ensemble learning based hybrid light gradient boosting machine and extreme gradient boosting model for predicting house pricesEngineering Reports, 2022
- Managing Risks of Climate Change on Irrigation Water in Arid RegionsWater Resources Management, 2022
- Irrigation efficiency optimization at multiple stakeholders’ levels based on remote sensing data and energy water balance modellingIrrigation Science, 2022
- Comparative performance of eight ensemble learning approaches for the development of models of slope stability predictionActa Geotechnica, 2022
- Machine learning for hydrologic sciences: An introductory overviewWIREs Water, 2021
- The application of artificial neural networks in metabolomics: a historical perspectiveMetabolomics, 2019
- Non-parametric characterization of long-term rainfall time seriesMeteorology and Atmospheric Physics, 2018
- Temporal Change Analysis Based on Data Characteristics and Nonparametric TestWater Resources Management, 2013
- Quantifying time lag of epikarst-spring hydrograph response to rainfall using correlation and spectral analysesHydrogeology Journal, 2013