MODIS images during the year 2012 were used for modelling of the radiation and energy balance components with the application of the SAFER algorithm (Simple Algorithm for Evapotranspiration Retrieving) in the Brazilian Pantanal area. Pixels from the main sub-regions of Barão de Melgaço (BR), Paiaguás (PA) and Nhecolândia (NH) were extracted in order to process microclimatic comparisons. In general, the net radiation (R_n) relied much more on the global solar radiation (R_G) levels than on water conditions and ecosystem types, in accordance with the low R_n standard deviation values. The fraction of the available energy used as latent heat flux (λE) were, on average, 65, 50 and 49% for the BR, PA and NH sub-regions, respectively. Horizontal heat advection, identified by the negative values of sensible heat flux (H), made several pixels with λE values higher than those for R_n in the middle of the year. Taking the evaporative fraction (E_f) as a surface moisture indicator, the Tree-Lined Savanna (TLS) was considered the moister ecosystem class, with 58% of the available energy being used as λE, while the driest one was the modified ecosystem Anthropogenic Changes (AC), presenting a λE/R_n fraction of 0.46. According to the spatial and temporal consistencies, and after comparisons with other previous point and large-scale studies, the SAFER algorithm proved to have sensibility to quantify and compare the large-scale radiation and energy balance components in the different ecosystems of the Brazilian Pantanal. The algorithm is useful for monitoring the energy exchange dynamics among the different terrestrial and aquatic ecosystem types throughout the seasons of the year.

The escalating frequency of extreme hydrological events under environmental uncertainty poses a severe socio-economic threat to floodplains such as the Brazilian Pantanal, the world’s largest tropical wetland. Mitigating dynamic flooding and drying cycles is highly challenging due to a critical scarcity of in situ monitoring, leaving flood risks poorly understood. To address these data gaps, this study presents an advanced deep learning forecasting framework that integrates multisource environmental data, fusing satellite-derived precipitation (CHIRPS) and global land data assimilation evapotranspiration (GLDAS) data with historical river gauge telemetry. Multi-layered neural network architectures were optimized and combined with progressive moving average filters (10− and 15−day windows) to capture the complex hydrometeorological patterns of the data-scarce Miranda River Watershed. The optimal deep learning configuration, utilizing a robust two-hidden-layer topology (15 and 60 neurons), consistently outperformed standard baselines. Although purely exogenous data blocks successfully minimized satellite noise and captured seasonal trends (NSE ≥ 0.92), structural underestimation of peak flows was observed. When incorporating the previous day’s streamflow (lag t−1) as a physical anchor, this limitation was noticeably alleviated, increasing both the Nash–Sutcliffe Efficiency (NSE) and Coefficient of Determination (R²) values above 0.99. While this performance surge is driven by the strong temporal persistence inherent to the autoregressive lag, it introduces an operational trade-off by restricting the forecast to a reactive 24 h window. In this regard, an evaluation of the operational forecast horizons revealed that the exogenous deep learning blocks maximize warning lead times, providing a vital tool for proactive civil defense and disaster risk reduction. Ultimately, this multisource framework establishes a methodological foundation for automated decision support systems, providing the high-accuracy streamflow forecasting capability required to support future flood mitigation frameworks.