Background Currently, the variable‐rate application (VA) of agrochemicals on fruit trees is based on canopy volume and biomass. The canopy volume has a significant relationship with disease resistance and degree of disease incidence. Therefore, this study proposes a VA method that uses deep convolutional neural networks for real‐time recognition of disease spots on pear trees. Furthermore, it specifies the limitations and application scenarios of the disease spot recognition. Field performance tests were conducted to verify the performance of the proposed VA system. Results The results showed a mean average precision, precision, and recall of 87.42%, 83.76%, and 87.23%, respectively. The spot recognition rate was 81.3% when the canopy sampling distance, spot diameter, and canopy porosity were 1.2 m, 4–8 mm, and 55.76%, respectively. The results indicate that the proposed VA system saved 51.9% spray volume compared to conventional methods while ensuring quality. Conclusion Compared to the traditional constant rate model, the proposed VA technology based on real‐time disease spot identification can reduce spraying in nondiseased areas, thereby abandoning the previous saturation application practice and significantly reducing pesticide use. © 2022 Society of Chemical Industry.

Background: The BAHD acyltransferase superfamily exhibits various biological roles in plants, including regulation the fruit quality; catalytic synthesis of terpene, phenolic and esters; improvement of stress resistance. However, the copy number, evolutionary history and potential functions of the BAHD superfamily genes in the genome sequenced Rosaceae species remains unclear. Results: Totally, 755 BAHD genes were obtained from the genomes of seven Rosaceae fruit species (Pyrus bretschneideri, Malus domestica, Prunus avium, Prunus persica, Fragaria vesca, Pyrus communis and Rubus occidentalis). Based on the classification results from model plants, we divided the BAHD family genes into seven subgroups (I-a, I-b, II-a, II-b, III-a, IV, V). Based on intra-species synteny analysis, 61 syntenic gene pairs were detected from the six Rosaceae species. Dispersed gene duplication occurred frequently in all investigated species. Different modes of duplicated gene pairs identified in each investigated species show that the Ka/Ks is less than one, indicating they evolved through purifying selection. Based on the correlation analysis between ester content and expression level of BAHD genes at different development stages, we selected five genes to perform qRT-PCR verification, and the results showed that Pbr020016.1, Pbr019034.1, Pbr014028.1 and Pbr029551.1 are the important candidate genes involved in aroma formation during pear fruit development. Conclusion: We have thoroughly annotated the BAHD superfamily genes and made a comprehensive comparative analysis of their colinearity, phylogenetic relationships and gene duplication patterns in the seven Rosaceae species, and also obtained four candidate genes might be involved in the aroma synthesis in the pear fruit. These presented results provide a theoretical basis for the future studies of the specific biological functions of BAHD superfamily members and the improvement of pear fruit quality. Keywords: BAHD, pear, evolution, Rosaceae, transcriptome, volatile esters