Evaluating empirical and machine learning approaches for reference evapotranspiration estimation using limited climatic variables in Nepal

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 104254 - 104254

Published: Feb. 1, 2025

Language: Английский

---

Using Deep Learning in Ensemble Streamflow Forecasting: Exploring the Predictive Value of Explicit Snowpack Information

Journal of Advances in Modeling Earth Systems, Journal Year: 2025, Volume and Issue: 17(3)

Published: March 1, 2025

Abstract The Ensemble Streamflow Prediction (ESP) framework combines a probabilistic forecast structure with process‐based models for water supply predictions. However, require computationally intensive parameter estimation, increasing uncertainties and limiting usability. Motivated by the strong performance of deep learning models, we seek to assess whether Long Short‐Term Memory (LSTM) model can provide skillful forecasts replace within ESP framework. Given challenges in implicitly capturing snowpack dynamics LSTMs streamflow prediction, also evaluated added skill explicitly incorporating information improve hydrologic memory representation. LSTM‐ESPs were under four different scenarios: one excluding snow three including varied representations. LSTM trained using from 664 GAGES‐II basins during WY1983–2000. During testing period, WY2001–2010, 80% exhibited Nash‐Sutcliffe Efficiency (NSE) above 0.5 median NSE around 0.70, indicating satisfactory utility simulating seasonal supply. LSTM‐ESP then tested WY2011–2020 over 76 western US operational Natural Resources Conservation Services (NRCS) forecasts. A key finding is that high regions, simplified ablation assumptions performed worse than those snow, highlighting data do not consistently performance. incorporated past years' accumulation comparably NRCS better entirely. Overall, integrating an shows promise highlights important considerations forecasting.

Language: Английский

---

Meta-Water-Modelling (Meta-WaM): A new framework for increasing applicability of digital water modelling

Knowledge-Based Systems, Journal Year: 2025, Volume and Issue: unknown, P. 113543 - 113543

Published: April 1, 2025

Language: Английский

---

Ensemble learning of catchment-wise optimized LSTMs enhances regional rainfall-runoff modelling − case Study: Basque Country, Spain

Journal of Hydrology, Journal Year: 2024, Volume and Issue: unknown, P. 132269 - 132269

Published: Oct. 1, 2024

Language: Английский

---