Comparação de distribuições de probabilidade e estimativa da precipitação provável para região de Barbacena, MG

Abstract

Probabilistic studies involving climatic variables are of extreme importance for farming activities, construction, tourism, among others. Seeking to contribute for the planning of irrigate agriculture, this work had as objectives to compare adjusted probability distribution models to the monthly and decennial historical series and to estimate the probable rainfall for the Barbacena County, Minas Gerais State, Brazil. Rainfall data of December, January and February, from 1942 to 2003, were studied, constituting historical series with 62 years of observations. Daily rainfall depths were added for 10 and 30 days, applying Gama, log-Normal 2 and log-Normal 3 parameters probability distribution models. Probability distributions models, were compared with Qui-square statistical test, at 5% significance level. Probable rainfall was estimated for each period, using the best distribution, which was evaluated based on the smallest Qui-square value, for the probability occurrence levels of 75, 90 and 98%. Gama probability distribution was the most adequate model.