The rapid and accurate identification of citrus leaf diseases is crucial for the sustainable development of the citrus industry. Because citrus leaf disease samples are small, unevenly distributed, and difficult to collect, we redesigned the generator structure of FastGAN and added small batch standard deviations to the discriminator to produce an enhanced model called FastGAN2, which was used for generating citrus disease and nutritional deficiency (zinc and magnesium deficiency) images. The performance of the existing model degrades significantly when the training and test data exhibit large differences in appearance or originate from different regions. To solve this problem, we propose an EfficientNet-B5 network incorporating adaptive angular margin (Arcface) loss with the adversarial weight perturbation mechanism, and we call it EfficientNet-B5-pro. The FastGAN2 network can be trained using only 50 images. The Fréchet Inception Distance (FID) and Kernel Inception Distance (KID) are improved by 31.8% and 59.86%, respectively, compared to the original FastGAN network; 8000 images were generated using the FastGAN2 network (2000 black star disease, 2000 canker disease, 2000 healthy, 2000 deficiency). Only images generated by the FastGAN2 network were used as the training set to train the ten classification networks. Real images, which were not used to train the FastGAN2 network, were used as the test set. The average accuracy rates of the ten classification networks exceeded 93%. The accuracy, precision, recall, and F1 scores achieved by EfficientNet-B5-pro were 97.04%, 97.32%, 96.96%, and 97.09%, respectively, and they were 2.26%, 1.19%, 1.98%, and 1.86% higher than those of EfficientNet-B5, respectively. The classification network model can be successfully trained using only the images generated by FastGAN2, and EfficientNet-B5-pro has good generalization and robustness. The method used in this study can be an effective tool for citrus disease and nutritional deficiency image classification using a small number of samples.

To address the lack of effective monitoring, evaluation, and prediction methods for water stress in citrus seedlings, we conducted 10 sets of water stress gradient experiments. Based on the experimental dataset, we constructed, trained, and improved an MLP classification model for citrus seedling water stress. In addition, we developed a monitoring, evaluation, and prediction system based on this model. The experiments demonstrated that 7 days of slight water stress can induce changes in overall root wilting and growth stagnation, and the chlorophyll content in the leaves can decrease by up to 11.78%. Furthermore, the optimal VWC for seedlings was [45%, 50%], the boundary of drought was [20%, 25%], and the boundary of waterlogging was [50%, 55%]. We validated the effectiveness of the system in assessing the growth status of seedlings over the past 7 days and predicting it after 7 days through testing sets and experiments on slight water stress. We found that the system achieved non-destructive remote monitoring, evaluation, and prediction of slight water stress in citrus seedlings, thus enhancing seedling quality. These research findings provide valuable insights into water stress management in citrus seedlings and other crops.

To create a digital unmanned orchard with automation of “picking, load and transportation” in the hills and mountains, it is vital to determine a cargo-carrying situation and monitor the real-time transport conditions. In this paper, a cargo-carrying analysis system based on RGB-D data was developed, taking citrus transportation as the scenario. First, the improved YOLOv7-tiny object detection algorithm was used to classify and obtain 2D coordinate information on the carried cargo, and a region of interest (ROI) was obtained from the coordinate information for cargo height measurement. Second, 3D information was driven by 2D detection results using fewer computing resources. A depth map was used to calculate the height values in the ROI using a height measurement model based on spatial geometry, which obtained the load volume of the carried cargo. The experimental results showed that the improved YOLOv7 model had an accuracy of 89.8% and an average detection time of 63 ms for a single frame on the edge-computing device. Within a horizontal distance of 1.8 m from the depth camera, the error of the height measurement model was ±3 cm, and the total inference time of the overall method was 75 ms. The system lays a technical foundation for generating efficient operation paths and intelligently scheduling transport equipment, which promote the intelligent and sustainable development of mountainous agriculture.