Accurate identification of rice diseases is crucial for improving rice yield and ensuring food security. In this study, we constructed an image dataset containing six classes of rice diseases captured under real field conditions to address challenges such as complex backgrounds, varying lighting, and symptom similarities. Based on the MobileViT-XXS architecture, we proposed an enhanced model named MobileViT-DAP, which integrates Channel Attention (CA), Efficient Channel Attention (ECA), and PoolFormer blocks to achieve precise classification of rice diseases. The experimental results demonstrated that the improved model achieved superior performance with 0.75 M Params and 0.23 G FLOPs, ensuring computational efficiency while maintaining high classification accuracy. On the testing set, the model achieved an accuracy of 99.61%, a precision of 99.64%, a recall of 99.59%, and a specificity of 99.92%. Compared to traditional lightweight models, MobileViT-DAP showed significant improvements in model complexity, computational efficiency, and classification performance, effectively balancing lightweight design with high accuracy. Furthermore, visualization analysis confirmed that the model’s decision-making process primarily relies on lesion-related features, enhancing its interpretability and reliability. This study provides a novel perspective for optimizing plant disease recognition tasks and contributes to improving plant protection strategies, offering a solution for accurate and efficient disease monitoring in agricultural applications.

In rice, infections caused by Pantoea ananatis or Enterobacter asburiae closely resemble the bacterial blight induced by Xanthomonas oryzae pv. oryzae, yet they differ in drug resistance and management strategies. This study explores the potential of combining hyperspectral imaging (HSI) with machine learning for the rapid and accurate detection of rice bacterial blight symptoms caused by various pathogens. One-dimensional convolutional neural networks (1DCNNs) were employed to construct a classification model, integrating various spectral preprocessing techniques and feature selection algorithms for comparison. To enhance model robustness and mitigate overfitting due to limited spectral samples, generative adversarial networks (GANs) were utilized to augment the dataset. The results indicated that the 1DCNN model, after feature selection using uninformative variable elimination (UVE), achieved an accuracy of 86.11% and an F1 score of 0.8625 on the five-class dataset. However, the dominance of Pantoea ananatis in mixed bacterial samples negatively impacted classification performance. After removing mixed-infection samples, the model attained an accuracy of 97.06% and an F1 score of 0.9703 on the four-class dataset, demonstrating high classification accuracy across different pathogen-induced infections. Key spectral bands were identified at 420–490 nm, 610–670 nm, 780–850 nm, and 910–940 nm, facilitating pathogen differentiation. This study presents a precise, non-destructive approach to plant disease detection, offering valuable insights into disease prevention and management in precision agriculture.

Paddy rice grain variety classification is essential for quality control, as different rice varieties exhibit significant variations in quality attributes, affecting both food security and market value. The integration of hyperspectral imaging with machine learning presents a promising approach for precise classification, though challenges remain in managing the high dimensionality and variability of spectral data, along with the need for model interpretability. To address these challenges, this study employs a CNN-Transformer model that incorporates Standard Normal Variate (SNV) preprocessing, Competitive Adaptive Reweighted Sampling (CARS) for feature wavelength selection, and interpretability analysis to optimize the classification of hybrid indica paddy rice grain varieties. The results show that the CNN-Transformer model outperforms baseline models, achieving an accuracy of 95.33% and an F1-score of 95.40%. Interpretability analysis reveals that the model’s ability to learn from key wavelength features is significantly stronger than that of the comparison models. The key spectral bands identified for hybrid indica paddy rice grain variety classification lie within the 400–440 nm, 580–700 nm, and 880–960 nm ranges. This study demonstrates the potential of hyperspectral imaging combined with machine learning to advance rice variety classification, providing a powerful and interpretable tool for automated rice quality control in agricultural practices.

In the field of smart plant protection, accurate early monitoring of winged aphids is critical, as it enables the interruption of viral disease transmission and reduces dependence on pesticides. In response to the core challenges of low efficiency in manual counting associated with current sticky trap-based monitoring, as well as the insufficient recognition accuracy and poor robustness of computer vision models in dense small-target scenarios, this study aims to develop a high-precision, highly reliable automated identification method for winged aphids. To achieve this, a specialized detection model named PCSNet is proposed. Based on YOLOv12, this model innovatively incorporates a coordinate attention mechanism to enhance the perception of spatial structures for small targets. Simultaneously, a shallow feature enhancement branch (SFEB) is introduced to enrich detailed information, and the Normalized Wasserstein Distance loss function is integrated to optimize bounding box regression. Comparative experiments conducted on a self-constructed dataset of sticky trap images encompassing complex field backgrounds demonstrate that the PCSNet model achieves optimal detection performance, with a mean average precision (mAP) of 0.791 and a precision of 0.866, significantly outperforming mainstream detection models and various attention mechanism variants. This research provides an effective technical solution for constructing a real-time and automated intelligent pest monitoring system, offering substantial application value for advancing the intelligent transformation of pest and disease monitoring and promoting practices in green prevention and control.