Figure 2
From: Machine learning techniques in disease forecasting: a case study on rice blast prediction
Observed and predicted mean disease severity based comparison of prediction accuracy of multiple regression (REG), backpropagation neural network (BPNN), generalized regression neural network (GRNN) and support vector machine (SVM) approaches for 'cross-year models' at Palampur-I (early transplanting) (A); at Palampur-II (normal transplanting) (B); at Palampur-III (late transplanting) (C); at Rice Research Station, Malan (D); and at farmers' fields, Pharer (E).