In this study, a deep-learning-based intelligent detection model was designed and implemented to rapidly detect cotton pests and diseases. The model integrates cutting-edge Transformer technology and knowledge graphs, effectively enhancing pest and disease feature recognition precision. With the application of edge computing technology, efficient data processing and inference analysis on mobile platforms are facilitated. Experimental results indicate that the proposed method achieved an accuracy rate of 0.94, a mean average precision (mAP) of 0.95, and frames per second (FPS) of 49.7. Compared with existing advanced models such as YOLOv8 and RetinaNet, improvements in accuracy range from 3% to 13% and in mAP from 4% to 14%, and a significant increase in processing speed was noted, ensuring rapid response capability in practical applications. Future research directions are committed to expanding the diversity and scale of datasets, optimizing the efficiency of computing resource utilization and enhancing the inference speed of the model across various devices. Furthermore, integrating environmental sensor data, such as temperature and humidity, is being considered to construct a more comprehensive and precise intelligent pest and disease detection system.

An innovative framework for peach tree disease recognition and segmentation is proposed in this paper, with the aim of significantly enhancing model performance in complex agricultural settings through deep learning techniques and data fusion strategies. The core innovations include a tiny feature attention mechanism backbone network, an aligned-head module, a Transformer-based semantic segmentation network, and a specially designed alignment loss function. The integration of these technologies not only optimizes the model’s ability to capture subtle disease features but also improves the efficiency of integrating sensor and image data, further enhancing the accuracy of the segmentation tasks. Experimental results demonstrate the superiority of this framework. For disease detection, the proposed method achieved a precision of 94%, a recall of 92%, and an accuracy of 92%, surpassing classical models like AlexNet, GoogLeNet, VGGNet, ResNet, and EfficientNet. In lesion segmentation tasks, the proposed method achieved a precision of 95%, a recall of 90%, and an mIoU of 94%, significantly outperforming models such as SegNet, UNet, and UNet++. The introduction of the aligned-head module and alignment loss function provides an effective solution for processing images lacking sensor data, significantly enhancing the model’s capability to process real agricultural image data. Through detailed ablation experiments, the study further validates the critical role of the aligned-head module and alignment loss function in enhancing model performance, particularly in the attention-head ablation experiment where the aligned-head configuration surpassed other configurations across all metrics, highlighting its key role in the overall framework. These experiments not only showcase the theoretical effectiveness of the proposed method but also confirm its practical value in agricultural disease management practices.

Accurate identification of predator–pest relationships is essential for implementing effective and sustainable biological control in agriculture. However, existing image-based methods struggle to recognize insect co-occurrence under complex field conditions, limiting their ecological applicability. To address this challenge, we propose a hybrid deep learning framework that integrates convolutional neural networks (CNNs) and Transformer architectures for multi-label recognition of predator–pest combinations. The model leverages a novel co-occurrence attention mechanism to capture semantic relationships between insect categories and employs a pairwise label matching loss to enhance ecological pairing accuracy. Evaluated on a field-constructed dataset of 5,037 images across eight categories, the model achieved an F1-score of 86.5%, mAP50 of 85.1%, and demonstrated strong generalization to unseen predator–pest pairs with an average F1-score of 79.6%. These results outperform several strong baselines, including ResNet-50, YOLOv8, and Vision Transformer. This work contributes a robust, interpretable approach for multi-object ecological detection and offers practical potential for deployment in smart farming systems, UAV-based monitoring, and precision pest management.

The development of smart agriculture has created an urgent demand for efficient and accurate weed recognition and detection technologies. However, the diverse and complex morphology of weeds, coupled with the scarcity of labeled data in agricultural scenarios, poses significant challenges to traditional supervised learning methods. To address these issues, a weed detection model based on a semi-supervised diffusion generative network is proposed. This model integrates a generative attention mechanism and semi-diffusion loss to enable the efficient utilization of both labeled and unlabeled data. Experimental results demonstrate that the proposed method outperforms existing approaches across multiple evaluation metrics, achieving a precision of 0.94, recall of 0.90, accuracy of 0.92, and mAP@50 and mAP@75 of 0.92 and 0.91, respectively. Compared to traditional methods such as DETR, precision and recall are improved by approximately 10% and 8%, respectively. Additionally, compared to the enhanced YOLOv10, mAP@50 and mAP@75 are increased by 1% and 2%, respectively. The proposed semi-supervised diffusion weed detection model provides an efficient and reliable solution for weed recognition and introduces new research perspectives for the application of semi-supervised learning in smart agriculture. This framework establishes both theoretical and practical foundations for addressing complex target detection challenges in the agricultural domain.