EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Lightweight grading method for potato late blight severity based on enhanced YOLOv8-Unet3Plus network

Peisen Yuan, Lushuo Jiang, Zhanghao Cheng, Yixi Tan, Yujia Yang, Cheng He

Frontiers in Plant Science · 02.09.2025 · 16

DOI: 10.3389/fpls.2025.1616864 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Plant Science, online erschienen am 02.09.2025. Verfasst von Peisen Yuan und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Artificial Intelligence, Nanjing Agricultural University, Nanjing, China. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Artificial intelligence for science is a methodology that integrates artificial intelligence into scientific research to improve the precision and efficiency of data analysis and experimental processes. Specifically in potato late blight severity grading, due to the demand for both accuracy and cost-effective deployment, traditional methods are limited by subjective evaluation and timeconsuming manual measurement. In this paper, a lightweight grading model based on an enhanced YOLOv8-UNet3Plus network is proposed to enable objective and accurate potato late blight severity grading. In detail, the YOLOv8 network is optimized by integrating Spatial and Channel Reconstruction Convolution module, Bi-directional Feature Pyramid Network and Powerful-IoU loss, the UNet3Plus network is optimized by embedding Ghost convolution and Multi-Scale Local Response Attention. Experiments on real-world potato late blight datasets demonstrate that our model achieves an precision of 95.73% for leaf localization and an mean Intersection over Union of 82.65% for infected region segmentation with reduced parameters and computational cost. This AI4Science-based model provides an effective solution for potato late blight severity grading.

Schlagwörter

Stichwörter der Autor:innen

AI for sciencedeep learningfeature fusionlightweight modelplant disease phenotypingpotato late blight

Autor:innen und Institutionen

  • College of Artificial Intelligence, Nanjing Agricultural University, Nanjing, China.
  • State Key Laboratory of Agricultural and Forestry Biosecurity, College of Plant Protection, Nanjing Agricultural University, Nanjing, China.

Förderung

  • National Key Research and Development Program of China

Zitieren

APA

Yuan, P., Jiang, L., Cheng, Z., Tan, Y., Yang, Y., & He, C. (2025). Lightweight grading method for potato late blight severity based on enhanced YOLOv8-Unet3Plus network. Frontiers in Plant Science, 16. https://doi.org/10.3389/fpls.2025.1616864

Vancouver

Yuan P, Jiang L, Cheng Z, Tan Y, Yang Y, He C. Lightweight grading method for potato late blight severity based on enhanced YOLOv8-Unet3Plus network. Frontiers in Plant Science. 2025;16. doi:10.3389/fpls.2025.1616864

BibTeX
@article{Yuan2025,
  author = {Yuan, Peisen and Jiang, Lushuo and Cheng, Zhanghao and Tan, Yixi and Yang, Yujia and He, Cheng},
  title = {Lightweight grading method for potato late blight severity based on enhanced YOLOv8-Unet3Plus network},
  journal = {Frontiers in Plant Science},
  year = {2025},
  volume = {16},
  doi = {10.3389/fpls.2025.1616864}
}
Kostenlos starten →