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.

A hyperspectral maize nitrogen content prediction model is proposed, integrating a dynamic spectral–spatiotemporal attention mechanism with a graph neural network, with the aim of enhancing the accuracy and stability of nitrogen estimation. Across multiple experiments, the proposed method achieved outstanding performance on the test set, with $R^2=0.93$, RMSE of 0.35, and MAE of 0.48, significantly outperforming comparative models including SVM, RF, ResNet, and ViT. In experiments conducted across different growth stages, the best performance was observed during the grain-filling stage, where $R^2$ reached 0.96. In terms of accuracy, recall, and precision, the proposed model exhibited an average improvement exceeding 15%, demonstrating strong adaptability to temporal variation and generalization across spatial conditions. These results provide robust technical support for large-scale, nondestructive nitrogen monitoring in agricultural applications.

This study introduces a novel high-accuracy fruit fly detection model based on the Transformer structure, specifically aimed at addressing the unique challenges in fruit fly detection such as identification of small targets and accurate localization against complex backgrounds. By integrating a step attention mechanism and a cross-loss function, this model significantly enhances the recognition and localization of fruit flies within complex backgrounds, particularly improving the model’s effectiveness in handling small-sized targets and its adaptability under varying environmental conditions. Experimental results demonstrate that the model achieves a precision of 0.96, a recall rate of 0.95, an accuracy of 0.95, and an F1-score of 0.95 on the fruit fly detection task, significantly outperforming leading object detection models such as YOLOv8 and DETR. Specifically, this research delves into and optimizes for challenges faced in fruit fly detection, such as recognition issues under significant light variation, small target size, and complex backgrounds. Through ablation experiments comparing different data augmentation techniques and model configurations, the critical contributions of the step attention mechanism and cross-loss function to enhancing model performance under these complex conditions are further validated. These achievements not only highlight the innovativeness and effectiveness of the proposed method, but also provide robust technical support for solving practical fruit fly detection problems in real-world applications, paving new paths for future research in object detection technology.