YZYanhua Zhao

Yanhua Zhao

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yanhua Zhao has a total of 35 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Alfalfa-Yolo: a boundary-aware lightweight framework for real-time weed detection in alfalfa fields

    by Jingyi Wang, Kai Li, Tao Zhou, Yuanjun Xu, Yiwen Gao, Changzhong Li, Yanhua Zhao

    Accurate weed detection in alfalfa fields is hindered by morphological similarity between crops and weeds at the seedling stage, substantial scale variation across weed targets, and degradation of fine spatial information during feature resampling. To address these challenges, Alfalfa-Yolo is proposed as a boundary-aware compact detection framework integrating three complementary components. The Edge-Perception Global Transfer Network (EPGTNet) uses bidirectional Sobel responses and cross-layer transmission to preserve edge-related high-frequency cues in deeper semantic features. The Multi-Scale Adaptive Feature Pyramid Network (MSAFPN) replaces static concatenation with attention-guided aggregation to adaptively regulate multi-scale contributions. The Enhanced Channel Shuffle Upsampling Module (ECSM) combines depthwise convolution, channel shuffle, and spatial shift to enhance local spatial representation after upsampling. On the self-constructed alfalfa-field dataset comprising 1,100 independent original field images, Alfalfa-Yolo achieves 77.6% mAP@0.5 and 55.9% mAP@0.5:0.95 with 2.67 M parameters. Independent-dataset benchmarking on CottonWeedDet12 and ImageWeeds confirms that the architecture remains competitive after target-dataset retraining, while a separate zero-shot cross-dataset protocol directly evaluates transfer without target-domain training. Deployment tests on NVIDIA RTX 4090, NVIDIA Orin NX, and RK3588 further characterize the accuracy-efficiency trade-off under different hardware and quantization settings. These results indicate that Alfalfa-Yolo provides a compact and practically deployable solution for real-time weed localization in alfalfa fields.


  • Open Access

    LGB-YOLOv11n: A Position-Specific Lightweight Detector for Shiitake Appearance Pre-Grading on Edge Devices

    by Huili Zhang, Zhengchang Xue, Siyuan Chen, Zhenchao Zhang, Borui Geng, Yanhua Zhao

    Automated shiitake pre-grading in forest-understory production environments is challenged by non-uniform illumination, cluttered backgrounds, occlusion, fine-grained appearance differences, and limited edge-computing resources. This study proposes LGB-YOLOv11n, a lightweight detector that assigns modules to feature levels according to their processing roles. Large-kernel separable attention is placed at the P4/16 backbone level and P3/8 detection branch to strengthen contour, texture, edge, and local-deformation representation. Ghost modules compress the P4/16 and P5/32 detection branches, while BiFPN-inspired weighted fusion replaces four neck fusion nodes. On a held-out test set, the model achieved 97.51% mAP@0.5 and 86.62% mAP@0.5:0.95, improvements of 1.21 and 5.62 percentage points over YOLOv11n, respectively. It used 2.39 M parameters, 7.72% fewer than the baseline. Gains were retained in all three leave-one-acquisition-date-out folds, and three random-seed runs yielded 86.49% ± 0.09% mAP@0.5:0.95. Cross-domain single-class evaluation on 222 external images yielded 89.52% AP@0.5 and 63.71% AP@0.5:0.95, compared with 86.73% and 59.84% for YOLOv11n. On an NVIDIA Jetson Orin NX with TensorRT FP16, LGB-YOLOv11n achieved 134.3 ± 6.73 FPS with a mean inference pipeline latency of 7.47 ± 0.39 ms. These results demonstrate a favorable accuracy–complexity trade-off and support real-time model inference for edge-based shiitake appearance pre-grading.

  • Open Access

    Siberian Wildrye (Elymus sibiricus) Seed Vigor Estimation for the Prediction of Emergence Performance under Diverse Environmental Conditions

    by Qibo Tao, Jiayi Xing, Fansheng Meng, Yaqi Zhang, Xinyu Liu, Shuo Guo, Ye Shan, Shangzhi Zhong, Juan Sun, Yanhua Zhao

    Seed vigor is an important aspect of seed quality. It is critical to predict seed vigor and plant seedling emergence under diverse environmental conditions using the laboratory vigor test. Accordingly, laboratory experiments were conducted to determine the standard germination (SG), early individual counts of radicle emergence (RE), mean germination time (MGT), and vigor index (VI) for 16 commercially available seed lots of Siberian wildrye (Elymus sibiricus), an economically and ecological important grass species. The field emergence (FE) for seed lots was explored using a three-year field trial from 2021 to 2023. Meanwhile, pot experiments were carried out to determine the seedling emergence performance under different environmental conditions, including control, drought, and salinity stress. The correlation and regression analysis were done to investigate the links between laboratory vigor test with emergence performance under both field and pot conditions. The results showed that the SG of 16 seed lots were high, similar, and did not differ significantly between seed lots. However, the seedling emergence performance (emergence percentage, seedling dry weight, and simplified vigor index) differed significantly between seed lots under both field and pot conditions. The SG was not significantly correlated with seedling emergence performance under either the field or pot conditions. The counts of RE at selected timing, MGT, and VI showed a significant relationship with seed vigor as reflected by seedling emergence performance under diverse environmental conditions, and we found that RE at 108 h was highly predictive of seed vigor and seedling emergence. The RE at 108 h and VI were positively related to seed vigor, while MGT was negatively related. The seed lots with low vigor had lower RE at 108 h and VI but longer MGT. Overall, both RE at 108 h, MGT, and VI can be used to estimate seed vigor and predict seedling emergence under different environmental conditions, and we highly recommend RE at 108 h as a quick, precise, and convenient vigor test and early warning sign for seed storage of E. sibiricus. These results will enable seed researchers, plant breeders, farmers, and government program directors to target higher seed vigor more effectively for E. sibiricus and similar grass species.


  • Open Access

    The Responses of Stem and Leaf Functional Traits of Medicago sativa and Bromus inermis to Different Mixed Planting Patterns

    by Fuhong Miao, Xiaoxu Yu, Xinkai Tang, Xindi Liu, Wei Tang, Yanhua Zhao, Chao Yang, Yufang Xu, Guofeng Yang, Juan Sun

    This study investigated the differences in stem and leaf growth characteristics of Medicago sativa and Bromus inermis in the Jiaozhou region of China during 2019–2020 under three different planting modes of the two forages: monoculture, mixed species sowing in the same rows, and mixed species sowing in alternating rows. No special management of the experimental plots was carried out in this study to simulate as much as possible the growth of forages in their natural state. The stem and leaf characteristics influencing the dry matter weight were calculated using grey correlation. These characteristics included leaf length, leaf width, leaf thickness, leaf area, leaf fresh weight, stem length, stem diameter, stem fresh weight, stem–leaf ratio, fresh matter yield, dry matter yield, and protein yield of M. sativa and B. inermis under different sowing methods in different years. The results showed that the weight pattern of the characteristics affecting the yield of M. sativa and B. inermis production was leaf area > stem diameter > leaf length > stem length > leaf width > leaf thickness, leaf area > leaf length > stem length > leaf width > leaf thickness > stem diameter. Considering all the growth factors, the production capacity was ranked as mixed sowing in alternating rows > mixed sowing in same rows > monoculture. Thus, the suitable mode for M. sativa–B. inermis sowing was mixed sowing in alternating rows.


  • Open Access

    Comprehensive analysis of grazing intensity impacts alpine grasslands across the Qinghai-Tibetan Plateau: A meta-analysis

    by Zhenchao Zhang, Yiran Zhao, Hao Lin, Yanpeng Li, Jinmin Fu, Yingxin Wang, Juan Sun, Yanhua Zhao

    Livestock grazing is a dominant practice in alpine grasslands and plays a crucial role in the ecosystem service of the Qinghai-Tibetan Plateau. The effects of grazing on alpine grasslands highly depends on grazing intensity. Up to now, we still lack comprehensive understanding of the general responses of alpine grasslands to different grazing intensities over broad geographic scales across the Qinghai-Tibetan Plateau. Here, we conducted a meta-analysis to explore the responses of plant characteristics and soil properties to grazing intensity in alpine grasslands of the Qinghai-Tibetan Plateau based on 52 peer-reviewed literatures. The results showed that grazing did not change the belowground biomass, while significantly increased the ratio of root to shoot (P< 0.05). Light grazing exhibited no significant effects on the plant richness, Shannon-Wiener diversity, soil water content, soil bulk density, nutrients, microbial biomass carbon, and microbial biomass nitrogen (P > 0.05). Moderate grazing significantly increased the plant richness and Shannon-Wiener diversity, while significantly decreased the soil organic carbon and total nitrogen (P< 0.05). Heavy grazing significantly decreased the plant richness, Shannon-Wiener diversity, water content, soil organic carbon, total nitrogen, microbial biomass carbon, and microbial biomass nitrogen, and significantly increased the soil bulk density (P< 0.05). These findings suggest that overgrazing is closely associated with grassland degradation, and moderate grazing is a sustainable practice to provide animal production and simultaneously maintain ecological functions for alpine grasslands on the Qinghai-Tibetan Plateau.