RANDOM FOREST MODEL TO PREDICT THE HEIGHT OF EUCALYPTUS

Eucalyptus (Eucalyptus urograndis) production has significantly advanced over the past few years in Brazil, especially with regard to acreage and productivity. Machine learning made significant advances most varied fields of agrarian sciences. In this context, study aimed use physicochemical variables soil as well climatic dendrometric eucalyptus predict its height using random forest algorithm. The was conducted municipality Três Lagoas, Mato Grosso do Sul, Brazil. original database consisted 49 collected at 0–0.20 m 0.20–0.40 m, two four variables, one response variable related eucalyptus. A correlation matrix applied select variables. Furthermore, modeling performed algorithm, which (r = 0.98, R2 0.96) predicting Overall, important plant included diameter breast (DBH), phosphorus content (P1), gravimetric moisture (GM1) a depth between 0.00 0.20 exchangeable aluminum (Al2) 0.40 soil.