Estimation of biomass of forage sorghum (sorghum bicolor) Cv. Samurai-2 using support vector regression

One alternative to improve feed quality is combine the main with forages which are more economical in cost but contain high protein sources, such as sorghum. Production estimation essential because it will determine sustainability of feed. This study aimed estimate amount sorghum production using support vector regression (SVR). Several stages this research collecting data, preprocessing, modelling, and evaluation. The dataset used input for SVR algorithm model field observation data. kernels modelling linear, Polynomial, RBF. Sorghum has a performance evaluation value that refers root mean square error (RMSE). result obtained from can values R2, absolute (MAE), percentage (MAPE), RMSE. best results on Polynomial kernel R2=0.7841, MAE=0.0681, MAPE=0.46641, RMSE=0.1006. shows classification Kernel estimating production.