Rice leaf diseases critically threaten global rice production by reducing crop yield and quality. Efficient disease detection in complex field environments remains a persistent challenge for sustainable agriculture. Existing deep learning-based methods for rice leaf disease detection struggle with inadequate sensitivity to subtle disease features, high computational complexity, and degraded accuracy under complex field conditions, such as background interference and fine-grained disease variations. To address these limitations, this research aims to develop a lightweight yet high-accuracy detection model tailored for complex field environments that balances computational efficiency with robust performance. We propose RDRM-YOLO, an enhanced YOLOv5-based network, integrating four key improvements: (i) a cross-stage partial network fusion module (Hor-BNFA) is integrated within the backbone network’s feature extraction stage to enhance the model’s ability to capture disease-specific features; (ii) a spatial depth conversion convolution (SPDConv) is introduced to expand the receptive field, enhancing the extraction of fine-grained features, particularly from small disease spots; (iii) SPDConv is also integrated into the neck network, where the standard convolution is replaced with a lightweight GsConv to increase the accuracy of disease localization, category prediction, and inference speed; and (iv) the WIoU Loss function is adopted in place of CIoU Loss to accelerate convergence and enhance detection accuracy. The model is trained and evaluated utilizing a comprehensive dataset of 5930 field-collected and augmented sample images comprising four prevalent rice leaf diseases: bacterial blight, leaf blast, brown spot, and tungro. Experimental results demonstrate that our proposed RDRM-YOLO model achieves state-of-the-art performance with a detection accuracy of 94.3%, and a recall of 89.6%. Furthermore, it achieves a mean Average Precision (mAP) of 93.5%, while maintaining a compact model size of merely 7.9 MB. Compared to Faster R-CNN, YOLOv6, YOLOv7, and YOLOv8 models, the RDRM-YOLO model demonstrates faster convergence and achieves the optimal result values in Precision, Recall, mAP, model size, and inference speed. This work provides a practical solution for real-time rice disease monitoring in agricultural fields, offering a very effective balance between model simplicity and detection performance. The proposed enhancements are readily adaptable to other crop disease detection tasks, thereby contributing to the advancement of precision agriculture technologies.

Wind turbine blade damage detection is crucial for advancing wind energy as a sustainable alternative to fossil fuels. Existing methods based on image processing technologies face challenges such as limited adaptability to complex environments, trade-offs between model accuracy and computational efficiency, and inadequate real-time inference capabilities. In response to these limitations, we put forward MSWindD-YOLO, a lightweight real-time detection model for wind turbine blade damage. Building upon YOLOv5s, our work introduces three key improvements: (1) the replacement of the Focus module with the Stem module to enhance computational efficiency and multi-scale feature fusion, integrating EfficientNetV2 structures for improved feature extraction and lightweight design, while retaining the SPPF module for multi-scale context awareness; (2) the substitution of the C3 module with the GBC3-FEA module to reduce computational redundancy, coupled with the incorporation of the CBAM attention mechanism at the neck network’s terminus to amplify critical features; and (3) the adoption of Shape-IoU loss function instead of CIoU loss function to facilitate faster model convergence and enhance localization accuracy. Evaluated on the Wind Turbine Blade Damage Visual Analysis Dataset (WTBDVA), MSWindD-YOLO achieves a precision of 95.9%, a recall of 96.3%, an mAP@0.5 of 93.7%, and an mAP@0.5:0.95 of 87.5%. With a compact size of 3.12 MB and 22.4 GFLOPs inference cost, it maintains high efficiency. After TensorRT acceleration on Jetson Orin NX, the model attains 43 FPS under FP16 quantization for real-time damage detection. Consequently, the proposed MSWindD-YOLO model not only elevates detection accuracy and inference efficiency but also achieves significant model compression. Its deployment-compatible performance in edge environments fulfills stringent industrial demands, ultimately advancing sustainable wind energy operations through lightweight lifecycle maintenance solutions for wind farms.