arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2506.04571cs.AI
收藏

OpenAg:推动农业智能的平民化

OpenAg: Democratizing Agricultural Intelligence

Institute of Applied Artificial Intelligence and Robotics (IAAIR)(应用人工智能与机器人研究所)

Srikanth Thudumu, Jason Fisher

AI总结:

本研究提出OpenAg框架,结合多类技术构建农业通用人工智能系统,以解决现有农业智能系统的不足,助力符合当地实际的农业决策。

摘要:

农业正经历着由人工智能(AI)、机器学习和知识表示技术驱动的重大变革。然而,当前的农业智能系统往往缺乏情境理解、可解释性和适应性,尤其对资源有限的小农户而言更是如此。通用大语言模型(LLM)虽功能强大,但通常缺乏实际农业决策支持所需的领域特定知识和情境推理能力,往往会生成过于通用或不符合实际应用的建议。为应对这些挑战,我们提出OpenAg——一个旨在推进农业通用人工智能(AGI)的综合框架。OpenAg结合了领域特定基础模型、神经知识图谱、多智能体推理、因果可解释性和自适应迁移学习,以提供情境感知、可解释且可行动的洞察。该系统包含:(i)整合科学文献、传感器数据和农户生成知识的统一农业知识库;(ii)用于结构化推理和推断的神经农业知识图谱;(iii)AI智能体在农业领域内专业化并协作的自适应多智能体推理系统;(iv)确保AI建议可解释、有科学依据且符合实际约束的因果透明机制。OpenAg旨在弥合科学知识与经验农户的隐性专业知识之间的差距,以支持可扩展且符合当地实际的农业决策制定。

英文摘要:

Agriculture is undergoing a major transformation driven by artificial intelligence (AI), machine learning, and knowledge representation technologies. However, current agricultural intelligence systems often lack contextual understanding, explainability, and adaptability, especially for smallholder farmers with limited resources. General-purpose large language models (LLMs), while powerful, typically lack the domain-specific knowledge and contextual reasoning needed for practical decision support in farming. They tend to produce recommendations that are too generic or unrealistic for real-world applications. To address these challenges, we present OpenAg, a comprehensive framework designed to advance agricultural artificial general intelligence (AGI). OpenAg combines domain-specific foundation models, neural knowledge graphs, multi-agent reasoning, causal explainability, and adaptive transfer learning to deliver context-aware, explainable, and actionable insights. The system includes: (i) a unified agricultural knowledge base that integrates scientific literature, sensor data, and farmer-generated knowledge; (ii) a neural agricultural knowledge graph for structured reasoning and inference; (iii) an adaptive multi-agent reasoning system where AI agents specialize and collaborate across agricultural domains; and (iv) a causal transparency mechanism that ensures AI recommendations are interpretable, scientifically grounded, and aligned with real-world constraints. OpenAg aims to bridge the gap between scientific knowledge and the tacit expertise of experienced farmers to support scalable and locally relevant agricultural decision-making.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑