Summary: Convolutional neural networks (CNNs) are a powerful tool for plant image analysis, but challenges remain in making them more accessible to researchers without a machine‐learning background. We present RootPainter, an open‐source graphical user interface based software tool for the rapid training of deep neural networks for use in biological image analysis. We evaluate RootPainterby training models for root length extraction from chicory (Cichorium intybusL.) roots in soil, biopore counting, and root nodule counting. We also compare dense annotations with corrective ones that are added during the training process based on the weaknesses of the current model. Five out of six times the models trained using RootPainterwith corrective annotations created within 2 h produced measurements strongly correlating with manual measurements. Model accuracy had a significant correlation with annotation duration, indicating further improvements could be obtained with extended annotation. Our results show that a deep‐learning model can be trained to a high accuracy for the three respective datasets of varying target objects, background, and image quality with < 2 h of annotation time. They indicate that, when using RootPainter, for many datasets it is possible to annotate, train, and complete data processing within 1 d.

Three genotypes of wheat grown at two CO₂ concentrations were used in a drought experiment, where water was withheld from the pots at anthesis until stomatal conductance (g_s) dropped below 10% of the control and photosynthesis (A) approached zero. The genotypes had different leaf area (Gladius < LM19 < LM62) and while photosynthesis and shoot growth were boosted by elevated CO₂, the water use and drying rate were more determined by canopy size than by stomatal density and conductance. The genotypes responded differently regarding number of fertile tillers, seeds per spike and 1000 kernel weight and, surprisingly, the largest genotype (LM62) with high water use showed the lowest relative decrease in grain yield. The maximum photochemical efficiency of photosystem II (F_v/F_m) was only affected on the last day of the drought when the stomata were almost closed although some variation in A was still seen between the genotypes. A close correlation was found between F_v/F_m and % loss of grain yield. It indicates that the precise final physiological stress level measured by F_v/F_m at anthesis/early kernel filling could effectively predict percentage final yield loss, and LM62 was slightly less stressed than the other genotypes, due to only a small discrepancy in finalising the drying period. Therefore, F_v/F_m can be used as a proxy for estimating the yield performance of wheat after severe drought at anthesis.