Fig. 3
From: Predicting yellow rust in wheat breeding trials by proximal phenotyping and machine learning
Recursive feature elimination of predictors. Results of recursive feature elimination in two datasets of yellow rust disease scores and high-throughput phenotyping data collected under field conditions. The dashed vertical lines indicate the selected optimal number of model predictors based on training (blue) and test set (red) Root Mean Square Error (RMSE), the grey dashed line indicates the number of features selected for the final model. a Disease score and HTPP data collected on 2020-07-02 (N = 351), b Disease and HTPP data collected on 2020-07-09 (N = 404)