@InProceedings{VerdelhoBeCaCaOlZa:2022:QuPrEs,
author = "Verdelho, F. and Beneti, C. and Calvetti, L. and Calheiros, R. and
Oliveira, L. and Zanata, M.",
affiliation = "SIMEPAR and SIMEPAR and {Universidade Federal do Paran{\'a}
(UFPR)} and SIMEPAR and {Universidade Federal do Paran{\'a}
(UFPR)} and {Universidade Federal do Paran{\'a} (UFPR)}",
title = "Quantitative precipitation estimation using weather radar and rain
gauge data fusion with machine learning",
booktitle = "Anais...",
year = "2022",
organization = "Encontro dos Alunos de P{\'o}s Gradua{\c{c}}{\~a}o em
Meteorologia (EPGMET), 21.",
note = "{Resumo simples}",
keywords = "precipitation, radar, machine learning, nowcasting.",
abstract = "Quality data in quantitative precipitation estimation (QPE) is an
important tool for many applications such as flash flood
forecasting and hydropower generation management. Precipitation
estimates have benn generated using differente radar Z-R and
polarimetric relationships, both from the literature and locally
adjusted,with reasonable adjustments with rain gauges and
distrometers, considering data filtering, range from radar,
orography, signal propagations among other factos that may affect
the estimates. We have developed and used operationally a QPE
multi-sensor fusion approach with the usage of weather radar,
satellite and rain gauge data which does not require frequent
processing to update the weights of the data sources, as in other
schemes.",
conference-location = "Cachoeira Paulista",
conference-year = "24-27 out. 2022",
language = "en",
targetfile = "EPGMET_Simples_Fernanda_Verdelho - Fernanda Verdelho.pdf",
urlaccessdate = "16 jun. 2024"
}