Rice leaf diseases are critical factors affecting rice yield and quality, and their effective detection is crucial for ensuring stable production. However, existing detection models exhibit limitations in capturing irregular and fine-grained lesion features and are susceptible to interference from complex backgrounds. To address these challenges, this study proposes an Efficient Attention-Guided Network (EAG-YOLOv11n) for rice leaf disease detection. Specifically, an EMA-C3K2 module is proposed to enhance the network’s feature extraction capability. It integrates Efficient Multi-Scale Attention (EMA) into the shallow C3K2 layers, enabling the network to extract richer low-level feature representations. In addition, a Global Local Complementary Attention module (GLC-PSA) is proposed, which integrates a Local Importance Attention (LIA) branch to enhance the local feature representation of the original C2PSA. This design strengthens the perception of lesion regions while effectively suppressing background interference. Furthermore, an Adaptive Threshold Focal Loss (ATFL) is employed to guide the optimization of model parameters during training, alleviating sample imbalance and adaptively emphasizing the learning of challenging samples. Experimental results demonstrate that EAG-YOLOv11n achieves a mean Average Precision (mAP) of 87.3%, representing a 2.7% improvement over the baseline. Furthermore, compared with existing mainstream detection methods, including RT-DETR-L, YOLOv7tiny, YOLOv8n, YOLOv9tiny, YOLOv10n, and YOLOv12n, EAG-YOLOv11n improves mAP by 4.2%, 4.3%, 1.9%, 1.1%, 8.7%, and 2.9%, respectively. Overall, these results highlight its superior effectiveness in rice leaf disease detection, providing reliable technical support for stable yield and sustainable agricultural development.

Rice yield is a complex quantitative trait. Although a lot of genes for yield have been cloned, their genetic basis remains unknown. In the present study, a set of chromosome segment substitution line population (CSSL) was developed, derived from the indica variety Huanghuazhan as the recipient parent and the Aus variety N22 as the donor parent, and a high-density bin map containing 609 bins was constructed by resequencing. The CSSL population comprised 155 families with an average background recovery rate of 93.02%. Nine yield-related traits, including plant height, panicle number, panicle length, primary branch number, spikelet number per panicle, grain number per panicle, seed setting rate, 1000-grain weight, and grain yield per plant, were evaluated across four environments. The results showed significant differences in yield-related traits between the two parents across four environments. All nine traits showed continuous distribution with transgressive segregation. Spikelet number per panicle, grain number per panicle and 1000-grain weight showed strong correlations with each other, whereas panicle number had weak correlations with them. A total of 80 main-effect quantitative trait loci (QTLs) affecting yield-related traits were identified, among which 13 QTLs were repeatedly detected in multiple environments, 45 QTLs were located in 8 pleiotropic QTL regions, and 47 QTLs showed significant interactions with environments. In addition, 260 pairs of epistatic QTLs underlying yield-related traits were identified, of which 2 pairs stably expressed across different environments, and 11 pairs controlled more than two traits. These findings provide a theoretical basis for clarifying the genetic differentiation between indica and Aus and cloning yield-related genes, and offer valuable gene resources for molecular breeding of high-yield rice varieties.