The production of healthy agricultural products has increased the demand for innovative and sustainable plant protection technologies. RNA interference (RNAi), described as post-transcriptional gene silencing, offers great opportunities for developing RNA pesticides for sustainable disease and pest control. Compared with traditional synthesized pesticides, RNA pesticides possess many advantages, such as strong targeting, good environmental compatibility, and an easy development process. In this review, we systematically introduce the development of RNAi technology, highlight the advantages of RNA pesticides, and illustrate the challenges faced in developing high-efficiency RNA pesticides and the benefits of nanocarriers. Furthermore, we introduce the process and mechanism of nanocarrier-mediated RNAi technology, summarize the applications of RNA pesticides in controlling plant pathogens and pests, and finally outline the current challenges and future prospects. The current review provides theoretical guidance for the in-depth research and diversified development of RNA pesticides, which can promote the development and practice of nanocarrier-mediated RNAi.

Various nano-delivery systems have been designed to deliver synthetic/botanical pesticides for improved bioactivity. However, the enhanced toxicity of nanocarrier-loaded pesticides may injure the natural enemies, and their selective toxicity should be evaluated before the large-scale application. In this context, a star polymer (SPc)-based cyantraniliprole (CNAP) nano-delivery system was constructed, and its selective toxicity was evaluated using pest Frankliniella occidentalis (WFT) and predator Orius sauteri. The amide NH of CNAP could assemble with carbonyl groups or tertiary amines of SPc through hydrogen bonds to form CNAP/SPc complex spontaneously. The above self-assembly decreased the particle size of CNAP from 808 to 299 nm. With the help of SPc, the lethal concentration 50 (LC₅₀) values of CNAP decreased from 99 to 54 mg/L and 230 to 173 mg/L toward WFTs and O. sauteri due to the enhancement of broad-spectrum bioactivity. Interestingly, the toxicity selective ratio (TSR) of CNAP increased from 2.33 to 3.23 with the help of SPc, revealing the higher selectivity of SPc-loaded CNAP. To our knowledge, it was the first successful exploration of the selective toxicity of nanocarrier-loaded pesticides, and the higher selective toxicity of SPc-loaded CNAP was beneficial for alleviating the negative impacts on predators.

In this study, a deep learning-based system for apple defect detection and quality grading was developed, integrating various advanced image-processing technologies and machine learning algorithms to enhance the automation and accuracy of apple quality monitoring. Experimental validation demonstrated the superior performance of the proposed model in handling complex image tasks. In the defect-segmentation experiments, the method achieved a precision of 93%, a recall of 90%, an accuracy of 91% and a mean Intersection over Union (mIoU) of 92%, significantly surpassing traditional deep learning models such as U-Net, SegNet, PSPNet, UNet++, DeepLabv3+ and HRNet. Similarly, in the quality-grading experiments, the method exhibited high efficiency with a precision of 91%, and both recall and accuracy reaching 90%. Additionally, ablation experiments with different loss functions confirmed the significant advantages of the Jump Loss in enhancing model performance, particularly in addressing class imbalance and improving feature learning. These results not only validate the effectiveness and reliability of the system in practical applications but also highlight its potential in automating the detection and grading processes in the apple industry. This integration of advanced technologies provides a new automated solution for quality control of agricultural products like apples, facilitating the modernization of agricultural production.

The widespread use of pesticides plays a vital role in safeguarding crop yields and ensuring global food security. However, their improper application has led to serious challenges, including environmental pollution, pesticide residues, and increasing insect resistance. Traditional chemical pesticides are no longer sufficient to meet the demands for sustainable modern agriculture. Recent advances in nanotechnology offer innovative strategies for improving pesticide delivery, bioavailability, and selectivity. This review systematically summarizes the current progress in nano-insecticides, including their definitions, classification, preparation techniques, synergistic mechanisms, insecticidal performance, and safety evaluation. In addition, emerging strategies, such as multi-stimuli responsive systems, co-delivery with multiple agents or genetic materials, and integration with biological control, are discussed. Finally, future perspectives are proposed to guide the design/development of intelligent, efficient, and eco-friendly nano-insecticides for sustainable pest management in modern agriculture.

The application of nanotechnology in agriculture can break through many traditional problems of synthetic pesticides, especially for increasing bioactivity and reducing application amount. However, the safety and selective toxicity of nanocarrier-loaded pesticides should be clarified toward natural predators. In this context, an efficient spirotetramat nanodelivery system was successfully constructed based on a star polymer (SPc). Spirotetramat could complex with SPc through hydrogen bonding and van der Waals forces spontaneously. The self-assembly of the spirotetramat/SPc complex decreased the particle size of spirotetramat from 1292 to 710 nm. After the complexation with SPc, the lethal concentration 50 (LC₅₀) values of spirotratemat decreased from 252.064 to 108.871 and 332.079 to 189.257 mg/L toward target pest Frankliniella occidentalis and nontarget predator Orius sauteri with the synergic ratios of 2.315 and 1.755, respectively. The possible reason might be due to the enhancement of the broad-spectrum toxicity of SPc-loaded pesticides. Importantly, the selective toxicity ratio (STR) of spirotetramat increased from 1.32 to 1.73 with the help of SPc, indicating the higher selectivity of the spirotratemat/SPc complex toward predators. Meanwhile, the safety coefficient (SC) of spirotratemat was not significantly changed after complexation with SPc, and the spirotratemat/SPc complex belonged to the medium risk pesticide. Overall, the assembly with SPc could not only improve the control efficacy of spirotetramat but also increase its selectivity as well as alleviate its negative effects on predators. The current study is beneficial for understanding the enhancement of broad-spectrum toxicity and the selective toxicity of nanocarrier-loaded pesticides.

This study proposes a model for leafy vegetable disease detection and segmentation based on a few-shot learning framework and a prototype attention mechanism, with the aim of addressing the challenges of complex backgrounds and few-shot problems. Experimental results show that the proposed method performs excellently in both object detection and semantic segmentation tasks. In the object detection task, the model achieves a precision of 0.93, recall of 0.90, accuracy of 0.91, mAP@50 of 0.91, and mAP@75 of 0.90. In the semantic segmentation task, the precision is 0.95, recall is 0.92, accuracy is 0.93, mAP@50 is 0.92, and mAP@75 is 0.92. These results show that the proposed method significantly outperforms the traditional methods, such as YOLOv10 and TinySegformer, validating the advantages of the prototype attention mechanism in enhancing model robustness and fine-grained feature expression. Furthermore, the prototype loss function, which optimizes the distance relationship between samples and category prototypes, significantly improves the model’s ability to discriminate between categories. The proposed method shows great potential in agricultural disease detection, particularly in scenarios with few samples and complex backgrounds, offering broad application prospects.