Gutemberg Borges França, V. T. X. de Almeida, Mônica Carneiro Alves Senna, Enio Pereira de Souza, Madson Tavares Silva, Thaís Regina Benevides Trigueiro Aranha, Maurício Soares da Silva, Afonso Augusto Magalhães de Araújo, Manoel Valdonel de Almeida, Haroldo Fraga de Campos Velho, Maurício Nogueira Frota, Juliana Aparecida Anochi, Emanuel Alexander Moreno Aldana, Lude Quieto Viana
This study introduces the Hybrid Hydrological Forecast System (HHFS), a dual-stage, data-driven framework for monthly streamflow forecasting at the Santa Branca outlet in the upper Paraíba do Sul River Basin, Brazil. The system combines two nonlinear regressors, Multi-Layer Perceptron (MLP) and extreme Gradient Boosting (XGB), calibrated through a structured four-step evolutionary procedure in GA1 (hydrological weighting, dual-regime Ridge fusion, rolling bias correction, and monthly mean–variance adjustment) and a hydro-adaptive probabilistic optimization in GA2. SHAP-based analysis provides physical interpretability of the learned relations. The regressive stage (GA1) generates a bias-corrected and climatologically consistent central forecast. After the full four-step optimization, GA1 achieves robust generalization skill during the independent test period (2020–2023), yielding NSE = 0.77 ± 0.05, KGE = 0.85 ± 0.05, R2 = 0.77 ± 0.05, and RMSE = 20.2 ± 3.1 m3 s−1, representing a major improvement over raw MLP/XGB outputs (NSE ≈ 0.5). Time-series, scatter, and seasonal diagnostics confirm accurate reproduction of wet- and dry-season dynamics, absence of low-frequency drift, and preservation of seasonal variance. The probabilistic stage (GA2) constructs a hydro-adaptive prediction interval whose width (max-min streamflow) and asymmetry evolve with seasonal hydrological regimes. The optimized configuration achieves comparative coverage COV = 0.86 ± 0.00, hit rate p = 0.96 ± 0.04, and relative width r = 2.40 ± 0.15, correctly expanding uncertainty during wet-season peaks and contracting during dry-season recessions. SHAP analysis reveals a coherent predictor hierarchy dominated by streamflow persistence, precipitation structure, temperature extremes, and evapotranspiration, jointly explaining most of the predictive variance. By combining regressive precision, probabilistic realism, and interpretability within a unified evolutionary architecture, the HHFS provides a transparent, physically grounded, and operationally robust tool for reservoir management, drought monitoring, and hydro-climatic early-warning systems in data-limited regions.