Hybrid Streamflow Forecasting with ERA5 and Machine Learning Across Daily and Monthly Time Scales
Authors:
- Gutemberg Borges FrançaGFGutemberg Borges França
- Vinícius Albuquerque de AlmeidaVAVinícius Albuquerque de Almeida
- Mônica Carneiro Alves SennaMônica Carneiro Alves Senna
- Enio Pereira de SouzaESEnio Pereira de Souza
- Madson Tavares SilvaMSMadson Tavares Silva
- Thaís Regina Benevides Trigueiro AranhaThaís Regina Benevides Trigueiro Aranha
- Maurício Soares da SilvaMSMaurício Soares da Silva
- Afonso Augusto Magalhães de AraujoAAAfonso Augusto Magalhães de Araujo
- Gabriel Titara Silva de MeloGMGabriel Titara Silva de Melo
- Manoel Valdonel de AlmeidaMAManoel Valdonel de Almeida
- Haroldo Fraga Campos VelhoHVHaroldo Fraga Campos Velho
- Mauricio Nogueira FrotaMFMauricio Nogueira Frota
Open Access
Abstract
This study presents an updated Hybrid Hydrological Forecasting System (HHFS) for streamflow prediction at the Santa Branca outlet, located in the upper Paraíba do Sul River Basin in southeastern Brazil, aiming to support hydropower-oriented water resources management. This paper is explicitly framed as a companion paper which introduced the original HHFS framework and demonstrated the feasibility of combining deterministic and probabilistic machine-learning approaches for monthly streamflow forecasting. Building upon that foundation, the present study develops and validates a substantially enhanced and operationally oriented version of the system. The upgraded HHFS replaces the original BR-DWGD forcing strategy—a Brazilian gridded meteorological dataset useful for research applications but not routinely updated for sustained operations—with ERA5, the fifth-generation global atmospheric reanalysis produced by the European Centre for Medium-Range Weather Forecasts (ECMWF), which provides temporally consistent and operationally updated meteorological fields. This transition renders the framework fully operational while preserving the original dual-stage architecture, composed of a deterministic forecasting module (GA1) and a hydro-adaptive uncertainty module (GA2). In addition, the study introduces a daily short-term forecasting extension using a single multi-output XGBoost 2.1.1 model to predict streamflow from D+1 to D+10. Predictive uncertainty is quantified using split conformal prediction, a distribution-free uncertainty method that provides valid prediction intervals with empirical coverage guarantees. Coverage represents the proportion of observed values falling within the prediction intervals and is used here as a reliability metric. For the monthly product, the ERA5-based methodology maintained and slightly improved deterministic skill relative to the original BR-DWGD benchmark, with independent-test NSE increasing to 0.798, KGE to 0.878, and RMSE decreasing to 18.778 m3/s. The probabilistic component preserved a high hit rate and similar relative width, although coverage declined modestly to 0.838, indicating slight undercoverage relative to the previous reliability target. For the daily forecasts, predictive skill decreased progressively with lead time, from NSE = 0.881 at D+1 to 0.394 at D+10, accompanied by coherent widening of the uncertainty intervals. Taken together, these results demonstrate that ERA5 is a robust and operationally practical forcing source for the HHFS, preserving monthly forecasting skill while enabling a promising multi-day extension for anticipatory streamflow prediction across multiple temporal scales.Keywords
Funding Information
- Agência Nacional de Energia Elétrica (PD 05161-0025/2024)
- National Electric Energy Agency of the Brazilian Government
This publication has 26 references indexed in Scilit:
- A review of hybrid deep learning applications for streamflow forecastingJournal of Hydrology, 2023
- New improved Brazilian daily weather gridded data (1961–2020)International Journal of Climatology, 2022
- Enhancing Streamflow Forecast and Extracting Insights Using Long‐Short Term Memory Networks With Data Integration at Continental ScalesWater Resources Research, 2020
- The ERA5 global reanalysisQuarterly Journal of the Royal Meteorological Society, 2020
- Probabilistic forecasting based on ensemble forecasts and EMOS method for TGR inflowFrontiers of Earth Science, 2019
- Large scale hydrologic and hydrodynamic modeling using limited data and a GIS based approachJournal of Hydrology, 2011
- Decomposition of the mean squared error and NSE performance criteria: Implications for improving hydrological modellingJournal of Hydrology, 2009
- Medium-range reservoir inflow predictions based on quantitative precipitation forecastsJournal of Hydrology, 2007
- A simple hydrologically based model of land surface water and energy fluxes for general circulation modelsJournal of Geophysical Research: Atmospheres, 1994
- River flow forecasting through conceptual models part I — A discussion of principlesJournal of Hydrology, 1970