Impact Assessment of Coupling Mode of Hydrological Model and Machine Learning Model on Runoff Simulation: A Case of Washington DOI Creative Commons
Junqi Zhang, Jing Li, Hua Zhao

et al.

Atmosphere, Journal Year: 2024, Volume and Issue: 15(12), P. 1461 - 1461

Published: Dec. 7, 2024

The inherent uncertainties in traditional hydrological models present significant challenges for accurately simulating runoff. Combining machine learning with is an essential approach to enhancing the runoff modeling capabilities of models. However, research on impact mixed simulation capability limited. Therefore, this study uses model Simplified Daily Hydrological Model (SIMHYD) and Long Short Term Memory (LSTM) construct two coupled models: a direct coupling dynamically improved predictive validity hybrid model. These were evaluated using US CAMELS dataset assess combination methods capabilities. results indicate that both compared individual models, combined forecasting dynamic prediction effectiveness (DPE) demonstrating optimal capability. Compared LSTM, showed median increase 12.8% Nash Sutcliffe efficiency (NSE) daily during validation period, 12.5% SIMHYD. In addition, LSTM model, high flow increased by 23.6%, SIMHYD, it 28.4%. At same time, stability low was significantly improved. performance testing involving varying training period lengths, DPE trained 12 years exhibited best performance, showing 3.5% 1.5% NSE periods 6 18 years, respectively.

Language: Английский

Hybrid deep learning downscaling of GCMs for climate impact assessment and future projections in Oman DOI
Erfan Zarei, Mohammad Reza Nikoo, Ghazi Al-Rawas

et al.

Journal of Environmental Management, Journal Year: 2025, Volume and Issue: 376, P. 124522 - 124522

Published: Feb. 15, 2025

Language: Английский

Citations

1
Improving index-based coastal vulnerability assessment using machine learning in Oman DOI
Malik Al-Wardy, Erfan Zarei, Mohammad Reza Nikoo

et al.

The Science of The Total Environment, Journal Year: 2025, Volume and Issue: 976, P. 179311 - 179311

Published: April 9, 2025

Language: Английский

Citations

0
Impact Assessment of Coupling Mode of Hydrological Model and Machine Learning Model on Runoff Simulation: A Case of Washington DOI Creative Commons
Junqi Zhang, Jing Li, Hua Zhao

et al.

Atmosphere, Journal Year: 2024, Volume and Issue: 15(12), P. 1461 - 1461

Published: Dec. 7, 2024

The inherent uncertainties in traditional hydrological models present significant challenges for accurately simulating runoff. Combining machine learning with is an essential approach to enhancing the runoff modeling capabilities of models. However, research on impact mixed simulation capability limited. Therefore, this study uses model Simplified Daily Hydrological Model (SIMHYD) and Long Short Term Memory (LSTM) construct two coupled models: a direct coupling dynamically improved predictive validity hybrid model. These were evaluated using US CAMELS dataset assess combination methods capabilities. results indicate that both compared individual models, combined forecasting dynamic prediction effectiveness (DPE) demonstrating optimal capability. Compared LSTM, showed median increase 12.8% Nash Sutcliffe efficiency (NSE) daily during validation period, 12.5% SIMHYD. In addition, LSTM model, high flow increased by 23.6%, SIMHYD, it 28.4%. At same time, stability low was significantly improved. performance testing involving varying training period lengths, DPE trained 12 years exhibited best performance, showing 3.5% 1.5% NSE periods 6 18 years, respectively.

Language: Английский

Citations

0