Forecast of monthly mean temperatures in Uberlândia, Minas Gerais, Brazil using time series models

Revista Brasileira de Engenharia Agrícola e Ambiental

Guimarães, Ednaldo C.²  Silva, Maria I. S.¹  Tavares, Marcelo² 

[1] UFLA, Lavras;UFU, Uberlândia

关键词: regression;    SARIMA model;    seasonality;    trend    INTRODUÇÃO Uma série temporal é um conjunto de observações ordenadas em intervalos de tempo;    comumente iguais;   

DOI  :  10.1590/S1415-43662008000500006

学科分类：农业科学（综合）

来源: Universidade Federal de Campina Grande * Centro de Ciencias e Tecnologia

【 摘 要 】

Time series models have been used for climatological variables such as temperature and rainfall. In this paper, time series of monthly mean temperatures for the municipality of Uberlândia, Minas Gerais, were analyzed describing their components and making forecasts using the SARIMA models. The analysis showed trend and seasonality components. The SARIMA model was adjusted by AIC (Akaike Information Criterion), BIC (Bayesian Information Criterion) and MSE (Mean Square Error) criterion. The results showed that the SARIMA (3,1,0)(0,1,1) was a good model for forecasting.

【 授权许可】

CC BY-NC