Integrating geographic data and the SCS-CN method with LSTM networks for enhanced runoff forecasting in a complex mountain basin

Frontiers in Water

Water

Rolando Célleri¹  Paul Muñoz¹  María José Merizalde²  David F. Muñoz³  Esteban Samaniego⁴  Gerald Corzo⁵ 

[1] Departamento de Recursos Hídricos y Ciencias Ambientales, Universidad de Cuenca, Cuenca, Ecuador;Departamento de Recursos Hídricos y Ciencias Ambientales, Universidad de Cuenca, Cuenca, Ecuador;Facultad de Ingeniería, Universidad de Cuenca, Cuenca, Ecuador;Department of Civil and Environmental Engineering, Virginia Tech, Blacksburg, VA, United States;Center for Coastal Studies, Virginia Tech, Blacksburg, VA, United States;Facultad de Ingeniería, Universidad de Cuenca, Cuenca, Ecuador;Hydroinformatics Chair Group, IHE Delft Institute for Water Education, Delft, Netherlands;

关键词: hydrological forecasting;    SCS-CN method;    machine learning;    feature engineering;    GSMaP;    tropical Andes;   

DOI  :  10.3389/frwa.2023.1233899

 received in 2023-06-02, accepted in 2023-09-05,  发布年份 2023

来源: Frontiers

【 摘 要 】

IntroductionIn complex mountain basins, hydrological forecasting poses a formidable challenge due to the intricacies of runoff generation processes and the limitations of available data. This study explores the enhancement of short-term runoff forecasting models through the utilization of long short-term memory (LSTM) networks.MethodsTo achieve this, we employed feature engineering (FE) strategies, focusing on geographic data and the Soil Conservation Service Curve Number (SCS-CN) method. Our investigation was conducted in a 3,390 km2 basin, employing the GSMaP-NRT satellite precipitation product (SPP) to develop forecasting models with lead times of 1, 6, and 11 h. These lead times were selected to address the needs of near-real-time forecasting, flash flood prediction, and basin concentration time assessment, respectively.Results and discussionOur findings demonstrate an improvement in the efficiency of LSTM forecasting models across all lead times, as indicated by Nash-Sutcliffe efficiency values of 0.93 (1 h), 0.77 (6 h), and 0.67 (11 h). Notably, these results are on par with studies relying on ground-based precipitation data. This methodology not only showcases the potential for advanced data-driven runoff models but also underscores the importance of incorporating available geographic information into precipitation-ungauged hydrological systems. The insights derived from this study offer valuable tools for hydrologists and researchers seeking to enhance the accuracy of hydrological forecasting in complex mountain basins.

【 授权许可】

Unknown   
Copyright © 2023 Merizalde, Muñoz, Corzo, Muñoz, Samaniego and Célleri.