Accurate identification of plant diseases is a critical task in agricultural production. The existing deep learning crop disease recognition methods require a large number of labeled images for training, limiting the implementation of large-scale detection. To overcome this limitation, this study explores the application of self-supervised learning (SSL) in plant disease recognition. We propose a new model that combines a masked autoencoder (MAE) and a convolutional block attention module (CBAM) to alleviate the harsh requirements of large amounts of labeled data. The performance of the model was validated on the CCMT dataset and our collected dataset. The results show that the improved model achieves an accuracy of 95.35% and 99.61%, recall of 96.2% and 98.51%, and F1 values of 95.52% and 98.62% on the CCMT dataset and our collected dataset, respectively. Compared with ResNet50, ViT, and MAE, the accuracies on the CCMT dataset improved by 1.2%, 0.7%, and 0.8%, respectively, and the accuracy of our collected dataset improved by 1.3%, 1.6%, and 0.6%, respectively. Through experiments on 21 leaf diseases (early blight, late blight, leaf blight, leaf spot, etc.) of five crops, namely, potato, maize, tomato, cashew, and cassava, our model achieved accurate and rapid detection of plant disease categories. This study provides a reference for research work and engineering applications in crop disease detection.

To address the current problem of the difficulty of extracting the phenotypic parameters of tomato plants in a non-destructive and accurate way, we proposed a method of stem and leaf segmentation and phenotypic extraction of tomato plants based on skeleton extraction and supervoxel clustering. To carry out growth and cultivation experiments on tomato plants in a solar greenhouse, we obtained multi-view image sequences of the tomato plants to construct three-dimensional models of the plant. We used Laplace’s skeleton extraction algorithm to extract the skeleton of the point cloud after removing the noise points using a multi-filtering algorithm, and, based on the plant skeleton, searched for the highest point path, height constraints, and radius constraints to separate the stem from the leaf. At the same time, a supervoxel segmentation method based on Euclidean distance was used to segment each leaf. We extracted a total of six phenotypic parameters of the plant: height, stem diameter, leaf angle, leaf length, leaf width and leaf area, using the segmented organs, which are important for the phenotype. The results showed that the average accuracy, average recall and average F1 scores of the stem and leaf segmentation were 0.88, 0.80 and 0.84, and the segmentation indexes were better than the other four segmentation algorithms; the coefficients of determination between the measurement values of the phenotypic parameters and the real values were 0.97, 0.84, 0.88, 0.94, 0.92 and 0.93; and the root-mean-square errors were 2.17 cm, 0.346 cm, 5.65°, 3.18 cm, 2.99 cm and 8.79 cm². The measurement values of the proposed method had a strong correlation with the actual values, which could satisfy the requirements of daily production and provide technical support for the extraction of high-throughput phenotypic parameters of tomato plants in solar greenhouses.

Considering the harvesting of prey and stocking of predator impulsively at different fixed moments of time, this paper studies the dynamics of a seasonally competitive m-prey and n-predator impulsive system, which is focused more specifically in four areas as follows: (i) we emphasize the dynamics of m-prey and n-predator in the ecosystem with a view to understanding how the present work may be able to apply to real environment applications; (ii) this work uses the general functional response instead of using specific impulse responses; (iii) considering the intra- and inter-competitions between species and (iv) the system is subjected to the influences of seasonal factors which imposes direct impacts to the delicate balance of biological systems. By using the comparison techniques and the Floquet theorems, the sufficient conditions for the ecosystem permanence and the asymptotic stabilities of the global and local prey-free periodic solutions have been subsequently obtained. This work is concluded with an in-depth discussion of the biological significance of the results obtained in this research. The obtained results can provide theoretical support for protecting endangered species and to help maintain the ecological balance, especially when it is applied to practical pest management, such as rodent controls in the farmland.

Quantitative investigation of the utilization characteristics of precipitation resources and the production capacity of the intercropping production system under the soybean maize intercropping mode in northern China is of great significance for improving the resource utilization rate of dryland agriculture and regional sustainable development. This study adopted a completely randomized block design, and six planting modes were set up: soybean monoculture, maize monoculture, and four soybean maize intercropping modes. Plant height and grain yield data were observed, and precipitation resource utilization efficiency was calculated. Based on the FAO-56 recommended crop coefficients, the crop coefficients were corrected according to the actual growth of crops in the experimental area; combined with meteorological data, the crop water demand under different planting modes was estimated based on the Penman-Monteith principle. The results showed that crops' daily growth water demand under different planting modes was generally deficient in water in the early and middle stages of growth, and surplus in the later stages. Compared with the monoculture mode, there were significant differences in precipitation resource utilization efficiency under different intercropping modes (P < 0.05), with soybeans reduced by 67.50% ~ 89.56%, and corn reduced by 43.99% ~ 61.05%. Based on the semi-humid and semi-arid area of the eastern Loess Plateau, an appropriate irrigation system needs to be designated for soybean and corn intercropping systems in the early and middle stages of crop growth. Under a certain proportion of water resource supply, different modes have different water resource utilization efficiency and final production capacity for the intercropping system.

The automated detection of persimmons in orchards is hindered by two primary factors: fruits of the same cultivar possess nearly identical color, causing adjacent instances to be easily merged, and heavy occlusion by leaves and stems hides large portions of the fruit surface. These challenges often co-occur and severely degrade detection performance. To address them jointly, we propose PersimmonDet, a collaborative framework that integrates a dual-path modulation fusion module (MFM) for color–occlusion decoupling, a modulation-guided dynamic upsampling operator (M-DySample) that preserves boundaries under occlusion, a scale-aware lightweight detection head (MB_Head), and a repulsion-enhanced Wise-IoU loss. The key innovation is an implicit coordination mechanism: the loss function generates strong gradients based on difficult samples, and these gradients flow back to train the fusion and upsampling modules, forming a closed optimization loop. Experiments on a self-built persimmon dataset show that PersimmonDet achieves an mAP@0.5 of 96.13% and mAP@0.5:0.95 of 84.42%, outperforming multiple lightweight detectors. The largest gains occur based on heavily occluded and densely clustered fruits. Ablation studies reveal a clear improvement when all four components are combined, confirming their complementary contributions. The same architecture, retrained on a winter jujube dataset without modification, delivers consistent advantages, demonstrating cross-crop transferability. These results indicate that combining problem-aware modulation, boundary-preserving upsampling, and difficulty-focused training is a promising approach for robust fruit detection in orchard environments.

The establishment of crop growth models enables the simulation of the impacts of environmental changes on crop growth, providing theoretical guidance for exploring the relationship between environmental factors and crop growth. The model used the growth cycle (GC) as the simulation time step and was built upon four sub-models: topology, photosynthesis, biomass allocation, and geometric morphology. It was quantitatively utilized the concept of effective accumulated temperature (EAT) and parameters such as sink and expansion rate were used to explain the allometric growth relationships among different organs. The R2 values for the geometric morphological parameters such as leaf length, leaf width, leaf area, and internode volume ranged from 0.78 to 0.94, while the F-values for the regression equations ranged from 1533.53 to 13949.51. The R2 values for simulating leaf, internode, and earhead biomass were 0.62-0.94, 0.74-0.97, and 0.98, respectively, with RMSE values ranging from 0.02 to 0.13 g for leaf biomass, 0.03 to 0.13 g for internode biomass, and 1.71 g for earhead biomass. The results indicated that the model exhibited good performance and reliability in simulating the growth and development of leaves, internodes, and earheads. This provides a solid foundation for the development of a millet model with functional-structural feedback.