Many hydro-meteorological disasters in small and steep watersheds develop quickly and significantly impact human lives and infrastructures. High-resolution rainfall data and machine learning methods have been used as modeling frameworks to predict those events, such as flash floods. However, a critical question remains: How long must the rainfall input data be for an empirical-based hydrological forecast? The present article employed an artificial neural network (ANN)hydrological model to address this issue to predict river levels and investigate its dependency on antecedent rainfall conditions. The tests were performed using observed water level data and high-resolution weather radar rainfall estimation over a small watershed in the mountainous region of Rio de Janeiro, Brazil. As a result, the forecast water level time series only archived a successful performance (i.e., Nash–Sutcliffe model efficiency coefficient (NSE) > 0.6) when data inputs considered at least 2 h of accumulated rainfall, suggesting a strong physical association to the watershed time of concentration. Under extended periods of accumulated rainfall (>12 h), the framework reached considerably higher performance levels (i.e., NSE > 0.85), which may be related to the ability of the ANN to capture the subsurface response as well as past soil moisture states in the watershed. Additionally, we investigated the model’s robustness, considering different seeds for random number generating, and spacial applicability, looking at maps of weights.

Ionospheric scintillation refers to amplitude and phase fluctuations in radio signals due to electron density irregularities associated to structures named ionospheric plasma bubbles. The phenomenon is more pronounced around the magnetic equator where, after sunset, plasma bubbles of varying sizes and density depletions are generated by plasma instability mechanisms. The bubble depletions are aligned along Earth's magnetic field lines, and they develop vertically upward over the magnetic equator so that their extremities extend in latitude to north and south of the dip equator. Over Brazil, developing bubbles can extend to the southern peak of the Equatorial Ionization Anomaly, where high levels of ionospheric scintillation are common. Scintillation may seriously affect satellite navigation systems, such as the Global Navigation Satellite Systems. However, its effects may be mitigated by using a predictive model derived from a collection of extended databases on scintillation and its associated variables. This work proposes the use of a classification and regression decision tree to perform a study on the correlation between the occurrence of scintillation at the magnetic equator and that at the southern peak of the equatorial anomaly. Due to limited size of the original database, a novel resampling heuristic was applied to generate new training instances from the original ones in order to improve the accuracy of the decision tree. The correlation analysis presented in this work may serve as a starting point for the eventual development of a predictive model suitable for operational use.