article · H2Open Journal
Accurate streamflow simulation is essential for sustainable water resources planning and watershed management. A comparative assessment between a deep learning model, Long Short-Term Memory (LSTM), and a physically based model, the Soil and Water Assessment Tool (SWAT), was conducted in the Abelti Watershed within Ethiopia's Omo-Gibe Basin. Using monthly streamflow data spanning 1992 to 2021, both tools were trained or calibrated on records from 1995 to 2015 and tested on observations from 2016 to 2021. Following systematic hyper-parameter tuning and window adjustments, the LSTM model demonstrated superior predictive accuracy and goodness-of-fit relative to SWAT. This performance reflected a stronger ability to capture complex, nonlinear rainfall-runoff dynamics. Although SWAT showed a slightly lower percentage bias during validation, the deep learning framework represents a strong alternative to process-based hydrological modelling.
Reliable streamflow forecasts are vital for managing water supplies, planning infrastructure, and mitigating flood hazards. Demonstrating that data-driven deep learning models can simulate river flows more accurately than traditional, resource-intensive physical models provides water authorities with an alternative tool. This helps improve resource planning by accurately capturing nonlinear relationships between rainfall and runoff.
This applied research could inform the development of analytical software for water basin managers, environmental consultancies, and hydrological forecasting agencies. The model is at an applied and tested stage using retrospective monthly data in one basin. Commercialisation or operational adoption would require embedding the architecture into automated, real-time prediction workflows and evaluating performance across diverse hydro-climatic conditions.
AI-generated from the published abstract. Always read the original work before citing.
ABSTRACT Accurate streamflow simulation is fundamental for effective watershed management and sustainable water resources planning. This study is a novel application of the Long Short-Term Memory (LSTM) models for streamflow simulation in the Abelti Watershed, Omo-Gibe Basin, Ethiopia. It also compares the performance of the LSTM model with the physically based Soil and Water Assessment Tool (SWAT) model. The analysis covered the period 1992–2021, with monthly streamflow data from 1992 to 1994 used for warm-up period, from 1995–2015 used for LSTM training and SWAT calibration, and data from 2016–2021 used for testing and validation. The LSTM model was optimized through systematic hyper-parameter tuning and window size adjustment. The LSTM model attained R², RMSE, MAE, NSE, and PBIAS values of 0.996, 0.13, 0.072, 0.94 and 0.33 during training, and 0.991, 0.14, 0.09, 0.97 and 0.58 during testing, respectively. The SWAT model achieved R², NSE, and PBIAS values of 0.79, 0.75, and 0.54 during calibration, and 0.79, 0.77, and 0.23 during validation, respectively. The results demonstrate that the LSTM model outperformed the SWAT model in streamflow prediction accuracy and goodness-of-fit, reflecting its stronger ability to capture complex nonlinear rainfall–runoff relationships. While both models exhibited low bias, SWAT showed slightly lower PBIAS during validation. Overall, the findings suggest that LSTM is a promising alternative to process-based hydrological models for streamflow simulation and warrants further evaluation under diverse hydro-climatic conditions.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1016/j.htopen.2026.100072
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
