To investigate the effects of gibberellic acid (GA) on photosynthesis, nutrient partitioning and endogenous hormones at different leaf locations (1 and 6), Camellia oleifera was treated with four levels of GA (0, 100, 200 and 300 mg L⁻¹) during the flower bud physiological differentiation stage. GA increased the net photosynthetic rate (Pn), chlorophyll content and chlorophyll fluorescence parameters of 1st and 6th leaves. The 100 mg L⁻¹ dose was most effective for increasing the total chlorophyll content and Pn, which increased by 100.00% and 59.55%, respectively, in the 1st leaf, and 110.18% and 44.90%, respectively, in the 6th leaf compared with the control. The 100 and 200 mg L⁻¹ GA solutions decreased the starch and soluble sugar levels in both 1st and 6th leaves, but increased those of the 1st and 6th buds which suggested that exogenous GA promotes the transportation of photosynthetic products from leaves to buds with the regulation of a sink–source relationship. Endogenous levels of gibberellin and auxin increased, but abscisic acid decreased in the 1st and 6th leaves after GA applications. The Pn was positively correlated with the total chlorophyll content (0.922 for 1st leaf and 0.944 for 6th leaf) and fluorescence parameters, but negatively correlated with soluble sugar and starch contents in 1st (−0.940 and −0.875, respectively) and 6th (−0.866 and −0.854, respectively) leaves. The difference in responses of leaves at different positions to exogenous GA due to the physiological differences of the leaves themselves.

Cultivar identification is a basic task in oil tea (Camellia oleifera C.Abel) breeding, quality analysis, and an adjustment in the industrial structure. However, because the differences in texture, shape, and color under different cultivars of oil tea are usually inconspicuous and subtle, the identification of oil tea cultivars can be a significant challenge. The main goal of this study is to propose an automatic and accurate method for identifying oil tea cultivars. In this study, a new deep learning model is built, called EfficientNet-B4-CBAM, to identify oil tea cultivars. First, 4725 images containing four cultivars were collected to build an oil tea cultivar identification dataset. EfficientNet-B4 was selected as the basic model of oil tea cultivar identification, and the Convolutional Block Attention Module (CBAM) was integrated into EfficientNet-B4 to build EfficientNet-B4-CBAM, thereby improving the focusing ability of the fruit areas and the information expression capability of the fruit areas. Finally, the cultivar identification capability of EfficientNet-B4-CBAM was tested on the testing dataset and compared with InceptionV3, VGG16, ResNet50, EfficientNet-B4, and EfficientNet-B4-SE. The experiment results showed that the EfficientNet-B4-CBAM model achieves an overall accuracy of 97.02% and a kappa coefficient of 0.96, which is higher than that of other methods used in comparative experiments. In addition, gradient-weighted class activation mapping network visualization also showed that EfficientNet-B4-CBAM can pay more attention to the fruit areas that play a key role in cultivar identification. This study provides new effective strategies and a theoretical basis for the application of deep learning technology in the identification of oil tea cultivars and provides technical support for the automatic identification and non-destructive testing of oil tea cultivars.

ISHS VI International Symposium on In Vitro Culture and Horticultural Breeding CORRELATION BETWEEN BROWNING, TOTAL PHENOLIC CONTENT, POLYPHENOL OXIDASE AND SEVERAL ANTIOXIDATION ENZYMES DURING PISTACHIO TISSUE CULTURE

Tree shape can affect microclimate, which may directly influence fruit growth and development. Open center and round head are two tree canopy shapes that are generally used in Camellia oleifera Abel. cultivation. To study the effects of the two canopy shapes on the microclimate and fruit quality parameters inside the canopy and investigate the correlations between microclimate and oil yield characteristics, microclimates in different developmental periods and fruit quality parameters at maturity at different positions in the two canopy shapes were determined. In this study, the open-center shape increased the light intensity and temperature, and reduced the relative humidity within the canopy, and the microclimate was more uniformly distributed within the open-center canopy. Fruit quality parameters of open-center canopied trees were also significantly increased and had more uniform distributions, especially the oil yield parameters. The content ratio of the dry seed, oil content ratio of the fresh fruit, and oil yield increased by 43.55%, 59.30% and 79.01%, in the lower layer, respectively, and 27.33%, 41.75%, and 55.43%, in the inner canopy, respectively, compared to those of round-head canopied trees. For both canopy shapes, oil yield parameters had positive correlations with light intensity and temperature, but negative correlations with relative humidity, and the correlation coefficients between light intensity and temperature at different developmental stages and oil yield parameters in round-head canopies were greater than in the open-center canopies. Additionally, regression equations between the single microclimatic factor in different developmental periods and oil yield parameters could be used to estimate the latter in the two canopy shapes. The optimum light conditions for open-center and round-head canopy shapes were 916–1893 and 1108–1259 μmol·m²·s⁻¹, respectively. Overall, the open-center canopy had a more desirable microclimate and a more uniform microclimate distribution, especially the light intensity, which contributes to high uniform fruit quality parameters. Thus, an open-center canopy is the desirable shape in C. oleifera production.