Air temperature estimation techniques in Minas Gerais state, Brazil, Cwa and Cwb climate regions according to the Köppen-Geiger climate classification system

ABSTRACT Air temperature significantly affects the processes involving agricultural and human activities. The knowledge of a given location is essential for planning. It also helps to make decisions regarding However, it not always possible determine this variable. necessary precise estimate, using methods that are capable detecting existing variations. aim study was develop models multiple linear regression (MLR), artificial neural network (ANN), random forest (RF) estimate mean (Tmean), maximum (Tmax), minimum (Tmin) monthly air temperatures as function geographic coordinates altitude different localities in Minas Gerais state, Brazil, with climatic classification Cwa or Cwb. average data (Tmean, Tmax, Tmin), over period 30 years, were collected from 20 climatological stations. MLR able Tmax accuracy. predictive capacity estimating Tmean Tmin low. algorithms RF ANN used Tmean, high best results obtained model.