Managing Uncertainties in Hydrological Event Forecasting with AI: An Approach Based on Optimized Allocation of Rain Gauges

Vol 55, 2023 - 160419
Resumo Estendido
Favoritar este trabalho
Como citar esse trabalho?
Resumo

This work proposes a methodology for optimizing rain gauge station allocation in São José dos Campos/SP. The methodology consists of collecting data from existing rain gauge stations, using the inverse distance interpolation technique to estimate values at un-sampled points and grouping the data into groups using the K-Means algorithm. The goal is to maximize the coverage of the rain area and provide more accurate and reliable information about the amount and intensity of rainfall in the region. With this approach, we hope to contribute to improving rainfall monitoring in Brazil, representing an essential step towards reducing the damage caused by socio-environmental disasters associated with rainfall. The proposed methodology resulted in an average improvement of 11.6\% in rainfall detection compared to the previous arrangement, making it an effective solution to improve the prevention and mitigation of the impacts of hydrological events.

Compartilhe suas ideias ou dúvidas com os autores!

Sabia que o maior estímulo no desenvolvimento científico e cultural é a curiosidade? Deixe seus questionamentos ou sugestões para o autor!

Faça login para interagir

Tem uma dúvida ou sugestão? Compartilhe seu feedback com os autores!

Instituições
  • 1 Universidade Federal de São Paulo
  • 2 Centro Nacional de Monitoramento e Alertas de Desastres Naturais (Cemaden/MCTI)
Eixo Temático
  • 11. IC – Inteligência Computacional
Palavras-chave
optimized allocation; rain gauge station; rainfall monitoring