A hybrid approach to enhance streamflow simulation in data-constrained Himalayan basins: combining the Glacio-hydrological Degree-day Model and recurrent neural networks
<p>The Glacio-hydrological Degree-day Model (GDM) is a distributed model, but it is prone to uncertainties due to its conceptual nature, parameter estimation, and limited data in the Himalayan basins. To enhance accuracy without sacrificing interpretability, we propose a hybrid model approach...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2024-11-01
|
| Series: | Proceedings of the International Association of Hydrological Sciences |
| Online Access: | https://piahs.copernicus.org/articles/387/17/2024/piahs-387-17-2024.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | <p>The Glacio-hydrological Degree-day Model (GDM) is a distributed model, but it is prone to uncertainties due to its conceptual nature, parameter estimation, and limited data in the Himalayan basins. To enhance accuracy without sacrificing interpretability, we propose a hybrid model approach that combines GDM with recurrent neural networks (RNNs), hereafter referred to as GDM–RNN. Three RNN types – a simple RNN model, a gated recurrent unit (GRU) model, and a long short-term memory (LSTM) model – are integrated with GDM. Rather than directly predicting streamflow, RNNs forecast GDM's residual errors. We assessed performance across different data availability scenarios, with promising results. Under limited-data conditions (1 year of data), GDM–RNN models (GDM–simple RNN, GDM–LSTM, and GDM–GRU) outperformed standalone GDM and machine learning models. Compared with GDM's respective Nash–Sutcliffe efficiency (NSE), <span class="inline-formula"><i>R</i><sup>2</sup></span>, and percent bias (PBIAS) values of 0.80, 0.63, and <span class="inline-formula">−4.78</span>, the corresponding values for the GDM–simple RNN were 0.85, 0.82, and <span class="inline-formula">−6.21</span>; for GDM–LSTM, they were 0.86, 0.79, and <span class="inline-formula">−6.37</span>; and for GDM–GRU, they were 0.85, 0.8, and <span class="inline-formula">−5.64</span>. Machine learning models yielded similar results, with the simple RNN at 0.81, 0.7, and <span class="inline-formula">−16.6</span>; LSTM at 0.79, 0.65, and <span class="inline-formula">−21.42</span>; and GRU at 0.82, 0.75, and <span class="inline-formula">−12.29</span>, respectively. Our study highlights the potential of machine learning with respect to enhancing streamflow predictions in data-scarce Himalayan basins while preserving physical streamflow mechanisms.</p> |
|---|---|
| ISSN: | 2199-8981 2199-899X |