Fig. 7
From: Human limits in machine learning: prediction of potato yield and disease using soil microbiome data
Weighted F1 scores (y-axis) by random forest and Bayesian neural network (Bayesian NN) models for the pitted scab disease (Scabpit) by feature selection strategy (x-axis) including all OTUs (All-OTU), OTUs selected by the ML method (OTU-S1), the network comparison method (OTU-S2), both methods (OTU-S3), or neither method (OTU-S0)