Brazil's Southeast region has been facing water supply challenges, especially concerning the metropolitan region of São Paulo, since 2014. We adressed the water crisis from the disaster's point of view, considering that one of the guiding features to characterize a disaster is the amount of affected people and the losses associated. In the situation under review, there are people directly affected, because of intermittent house water supply, and indirectly affected by the increase of prices for goods, since their production and manufacturing depend on the availability of water. We presented each of the stages of a disaster risk management: prevention, mitigation, preparedness, response and recovery. The risk of water scarcity in São Paulo is only one aspect of the discussion involving the effectiveness of management processes and the need for investments in the area, especially in reducing wasteful distribution.

Flash floods are critical events for emergency management, yet their modeling remains highly challenging, even in smart cities approaches. Physically based hydrological models are often unsuitable at small spatiotemporal scales due to their computational complexity and dependence on detailed local parameters, which are rarely available during flash floods. With the growing availability of hydrological data, machine learning (ML) has emerged as a promising alternative. This work performs a Systematic Literature Review (SLR) to improve our understanding of the research landscape on ML applications for flash flood forecasting, a significant subset of flash flood modeling. From more than 1,200 papers published until January 2024 in Web of Science, SCOPUS/Elsevier, Springer/Nature, and Wiley, 50 were selected following PRISMA guidelines. The inclusion and exclusion criteria removed reviews, retractions, papers focused on post-flood damage assessment (not forecasting), and those with time resolutions of 6 hours or more, retaining only studies with fine-scale temporal data (<6 hours). For each paper, we extracted information on forecasting horizon, study area size, input data, ML techniques, and outcomes (regression or classification). Results show a sharp rise in ML-based flash flood research, with China leading (38%). Nearly all studies rely on rainfall, discharge, and water level data - often in combination. Long short-term memory (LSTM) networks dominate (60%). Unfortunately, only 10% of the selected studies provide access to their datasets. This lack of transparency poses a major barrier to reproducibility, inhibits fair comparative evaluation of models, and ultimately slows methodological progress in flash flood forecasting. Furthermore, our review highlights that no method consistently outperforms others. This variability in performance is likely influenced by factors such as regional hydrological characteristics (e.g., differences between arid and tropical basins), variations in input data quality, and the length of the forecast horizon (e.g., 1- vs. 6-hour prediction). Lastly, we recommend advancing this field through integration with early warning systems, creation of benchmarks, open data practices, and stronger multidisciplinary collaboration.

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.

Quando se fala em desastres relacionados à água no Brasil, faz-se uma associação direta com as inundações, que são responsáveis por muitos registros de mortes e pessoas afetadas no país. Entretanto, há outras extensões da interface entre água e desastres que merecem atenção. O extremo oposto das inundações, por exemplo, se traduz em seca efetiva e seca agrícola (seca verde), ambas com sérias consequências para a população atingida. A erosão hídrica e as implicações do manejo da água em questões de fragilidade ambiental, por sua vez, relacionam-se a desastres de caráter ambiental. Outro aspecto importante são os desdobramentos do desastre hidrológico em si, pois há efeitos que surgem e se mantêm no período pós-desastre, como epidemias e ingestão de água imprópria para o consumo humano. Neste artigo foram apontados os principais desafios para diminuir os riscos relacionados a desastres e recursos hídricos e sugerimos ações para um gerenciamento integrado de recursos hídricos, saúde pública e desastres.