数字农科院2.0

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

文献类型： 外文期刊

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

作者机构：

关键词： diseases and pests;knowledge graph;RAG;intelligent question answering system;crop protection

期刊名称： FRONTIERS IN PLANT SCIENCE

ISSN： 1664-462X

年卷期： 2026 年 16 卷

页码：

收录情况： SCIE（2025版）

摘要： 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.

分类号：

  • 相关文献

[1]Cloud-Based Video Monitoring System Applied in Control of Diseases and Pests in Orchards. Xia, Xue,Qiu, Yun,Hu, Lin,Fan, Jingchao,Guo, Xiuming,Zhou, Guomin. 2016

[2]Research And Construction Of Semantic R.etrieval Based On Knowledge G raph. Huang, Yongwen,Xian, Guojian,Li, Jiao,Kou, Yuantao,Kou, Yuantao. 2018

[3]Text classification on heterogeneous information network via enhanced GCN and knowledge. 李慧,,阎琰,,王烁,,刘娟,,崔运鹏. 2023

[4]A new model construction based on the knowledge graph for mining elite polyphenotype genes in crops. Dandan Zhang,Ruixue Zhao,Guojian Xian,Yuantao Kou,Weilu Ma. 2024

[5]Knowledge graph of agricultural engineering technology based on large language model. Haowen Wang,Ruixue Zhao. 2024

[6]Research and Implementation of Agronomic Entity and Attribute Extraction Based on Target Localization. Xiuming Guo,Yeping Zhu,Shijuan Li,Sheng Wu,E. Yue,Shengping Liu. 2025

[7]A knowledge graph dataset for broiler farming automatically constructed based on a large language model. Nan Ma,Fantao Kong,Jifang Liu,Chenyang Zhang,Chenxv Zhao,Shanshan Cao,Wei Sun. 2025

[8]Relational subgraphs fused with complete subgraphs based on the knowledge graph for mining protein complexes. Ruixue Zhao,Dandan Zhang,Yuantao Kou,Guojian Xian,Xiao Yang. 2025

[9]New host resistances in Brassica napus and Brassica juncea from Australia, China and India: Key to managing Sclerotinia stem rot (Sclerotinia sclerotiorum) without fungicides. Barbetti, M. J.,Li, C. X.,You, M. P.,Barbetti, M. J.,You, M. P.,Banga, S. S.,Banga, S. K.,Sandhu, P. S.,Singh, D.,Singh, R.,Liu, S. Y..

[10]Ecology, invasion history and biodiversity-driven management of the coconut black-headed caterpillar Opisina arenosella in Asia. Hui Lu,Baoqian Lyu,Jihong Tang,Qiqi Wu,Kris A.G. Wyckhuys,Khac Hoang Le,Patchareewan Chongchitmate,Haiyan Qiu,Qikai Zhang. 2023

[11]Influence of nozzle enabling strategy on spray deposition of crop protection unmanned aerial system. Wei Gu,Xinyu Xue,Chen Chen,Qingqing Zhou,Songchao Zhang,Bin Peng. 2021

[12]Optimal spraying task assignment problem in crop protection with multi-UAV systems and its order irrelevant enumeration solution. Yang Li,Yang Xu,Xinyu Xue,Xuemei Liu,Xinghua Liu. 2022

[13]A Fast Analysis of Pesticide Spray Dispersion by an Agricultural Aircraft Very near the Ground. King, Ji,Xue, Xinyu,Yao, Weixiang,Jin, Zhen. 2022

[14]Design and experiment of a hydraulic lifting wind field test platform for crop protection uas. Songchao Zhang,Wei Gu,Baijing Qiu,Xinyu Xue,Lixin Zhou. 2021

[15]Plastid-mediated RNA interference: A potential strategy for efficient pest control. Li, Shengchun,Kim, Dae Sung,Zhang, Jiang. 2023

[16]An experimental study of acoustic bird repellents for reducing bird encroachment in pear orchards. Qing Chen,Jingjing Xie,Qiang Yu,Can Liu,Wenqin Ding,Xiaogang Li,Hongping Zhou. 2024

[17]In Vivo Production of dsRNA Using Bacteriophage ϕ6 in Pseudomonas syringae Cit7 Cells. Jinguang Yang. 2024

[18]Effects of Climatic Conditions and Agronomic Practices on Health, Tuber Yield, and Mineral Composition of Two Contrasting Potato Varieties Developed for High and Low Input Production Systems. Gultekin Hasanaliyeva,Ourania Giannakopoulou,Juan Wang,Marcin Barański,Enas Khalid Sufar,Daryl Knutt,Jenny Gilroy,Peter Shotton,Halima Leifert,Dominika Średnicka-Tober,Ismail Cakmak,Levent Ozturk,Bingqiang Zhao,Per Ole Iversen,Nikolaos Volakakis,Paul Bilsborrow,Carlo Leifert,Leonidas Rempelos. 2025

[19]Leveraging RNA interference technology for selective and sustainable crop protection. Hong Yue Qi,Dan Dan Zhang,Binhui Liu,Jie Yin Chen,Dongfei Han,Dan Wang. 2025

[20]Potato expressing Cry3A and Cry3B confers resistance to the 28-spotted ladybeetle, Henosepilachna vigintioctopunctata. Zhou, Zaihui,Yan, Junjie,Gatehouse, Angharad M. R.,Ma, Weihua,Gao, Yulin. 2026

作者其他论文 更多>>