EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Crop GraphRAG: pest and disease knowledge base Q&A system for sustainable crop protection

Hao Wu, Nengfu Xie, Xiaoli Wang, Jingchao Fan, Yonglei Li, Zhibo Meng

Frontiers in Plant Science · 05.01.2026 · 16

DOI: 10.3389/fpls.2025.1696872 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Plant Science, online erschienen am 05.01.2026. Verfasst von Hao Wu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Agricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing, China. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Intelligent prevention and control of crop diseases and pests is a critical link in safeguarding food security. However, agricultural practitioners often face fragmented information and low retrieval efficiency when seeking accurate, actionable knowledge. Furthermore, general-purpose large language models (LLMs) are prone to providing inaccurate or erroneous answers when applied to these specialized domains. To address these challenges, we assembled a large-scale corpus of knowledge on crop diseases and pests. Via entity and relation extraction, we constructed a multi-relational knowledge graph covering crops, diseases, pests, symptoms, and control measures. We subsequently designed Crop GraphRAG, a new framework that integrates knowledge graphs with retrieval-augmented generation (RAG). This system enables local knowledge-base question answering by retrieving adjacency subgraphs for relevant entities alongside summary-based passage retrieval. To evaluate performance, we curated a domain-specific test suite of question–answer pairs and conducted comparative and ablation experiments. Our experiments demonstrate that the Crop GraphRAG framework offers distinct advantages in answer accuracy and coverage compared to baselines. Crucially, the framework effectively suppresses hallucinated content, a common issue in generative models. These results verify the practical utility of the Crop GraphRAG framework for vertical-domain question answering. By mitigating the limitations of large language models in specialized agricultural contexts, this study provides a pragmatic tool for intelligent QA in the agricultural domain and advances the application of AI in crop protection.

Schlagwörter

Stichwörter der Autor:innen

RAGcrop protectiondiseases and pestsintelligent question answering systemknowledge graph

Autor:innen und Institutionen

  • Agricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing, China.
  • Key Laboratory of Agricultural Blockchain Application, Ministry of Agriculture and Rural Affairs, Beijing, China.

Zitieren

APA

Wu, H., Xie, N., Wang, X., Fan, J., Li, Y., & Meng, Z. (2026). Crop GraphRAG: pest and disease knowledge base Q&A system for sustainable crop protection. Frontiers in Plant Science, 16. https://doi.org/10.3389/fpls.2025.1696872

Vancouver

Wu H, Xie N, Wang X, Fan J, Li Y, Meng Z. Crop GraphRAG: pest and disease knowledge base Q&A system for sustainable crop protection. Frontiers in Plant Science. 2026;16. doi:10.3389/fpls.2025.1696872

BibTeX
@article{Wu2026,
  author = {Wu, Hao and Xie, Nengfu and Wang, Xiaoli and Fan, Jingchao and Li, Yonglei and Meng, Zhibo},
  title = {Crop GraphRAG: pest and disease knowledge base Q&A system for sustainable crop protection},
  journal = {Frontiers in Plant Science},
  year = {2026},
  volume = {16},
  doi = {10.3389/fpls.2025.1696872}
}
Kostenlos starten →