@Article{SantosFrBaSoDiLiSt:2023:NeNeHy,
               author = "Santos, Leonardo Bacelar Lima and Freitas, Cintia Pereira de and 
                         Bacelar, Luiz and Soares, Jaqueline Aparecida Jorge Papini and 
                         Diniz, Michael M. and Lima, Glauston R. T. and Stephany, Stephan",
          affiliation = "{Centro Nacional de Monitoramento e Alertas de Desastres Naturais 
                         (CEMADEN)} and {Instituto Nacional de Pesquisas Espaciais (INPE)} 
                         and {Duke University} and {Instituto Nacional de Pesquisas 
                         Espaciais (INPE)} and Instituto Federal de Educa{\c{c}}{\~a}o, 
                         Ci{\^e}ncia e Tecnologia de S{\~a}o Paulo (IFSP) and {Centro 
                         Nacional de Monitoramento e Alertas de Desastres Naturais 
                         (CEMADEN)} and {Instituto Nacional de Pesquisas Espaciais 
                         (INPE)}",
                title = "A Neural Network-Based Hydrological Model for Very High-Resolution 
                         Forecasting Using Weather Radar Data",
              journal = "Eng",
                 year = "2023",
               volume = "4",
               number = "3",
                pages = "1787--1796",
                month = "Sept.",
             keywords = "hydrologic prediction, hydrological prediction, hydrology, neural 
                         networks, weather radar.",
             abstract = "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., NashSutcliffe 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 models robustness, considering different seeds 
                         for random number generating, and spacial applicability, looking 
                         at maps of weights.",
                  doi = "10.3390/eng4030101",
                  url = "http://dx.doi.org/10.3390/eng4030101",
                 issn = "2673-4117",
             language = "en",
           targetfile = "eng-04-00101-v2.pdf",
        urlaccessdate = "04 maio 2024"
}