智慧农业（中英文）2025，Vol.7Issue(1)：11-19,9.DOI:10.12133/j.smartag.SA202410007
基于大语言模型的个性化作物水肥管理智能决策方法
Intelligent Decision-Making Method for Personalized Vegetable Crop Water and Fertilizer Management Based on Large Language Models
摘要
Abstract
[Objective]The current crop management faces the challenges of difficulty in capturing personalized needs and the lack of flexibility in the decision-making process.To address the limitations of conventional precision agriculture systems,optimize key aspects of agricultural production,including crop yield,labor efficiency,and water and fertilizer use,while ensure sus-tainability and adaptability to diverse farming conditions,in this research,an intelligent decision-making method was presents for personalized vegetable crop water and fertilizer management using large language model(LLM)by integrating user-specific pref-erences into decision-making processes through natural language interactions. [Methods]The method employed artificial intelligence techniques,combining natural language processing(NLP)and reinforcement learning(RL).Initially,LLM engaged users through structured dialogues to identify their unique preferences related to crop produc-tion goals,such as maximizing yield,reducing resource consumption,or balancing multiple objectives.These preferences were then modeled as quantifiable parameters and incorporated into a multi-objective optimization framework.To realize this framework,proxi-mal policy optimization(PPO)was applied within a reinforcement learning environment to develop dynamic water and fertilizer man-agement strategies.Training was conducted in the gym-DSSAT simulation platform,a system designed for agricultural decision sup-port.The RL model iteratively learned optimal strategies by interacting with the simulation environment,adjusting to diverse condi-tions and balancing conflicting objectives effectively.To refine the estimation of user preferences,the study introduced a two-phase process comprising prompt engineering to guide user responses and adversarial fine-tuning for enhanced accuracy.These refinements ensured that user inputs were reliably transformed into structured decision-making criteria.Customized reward functions were devel-oped for RL training to address specific agricultural goals.The reward functions account for crop yield,resource efficiency,and labor optimization,aligning with the identified user priorities.Through iterative training and simulation,the system dynamically adapted its decision-making strategies to varying environmental and operational conditions. [Results and Discussions]The experimental evaluation highlighted the system's capability to effectively personalize crop management strategies.Using simulations,the method demonstrated significant improvements over traditional approaches.The LLM-based model accurately captured user-specific preferences through structured natural language interactions,achieving reliable preference modeling and integration into the decision-making process.The system's adaptability was evident in its ability to respond dynamically to chang-es in user priorities and environmental conditions.For example,in scenarios emphasizing resource conservation,water and fertilizer use were significantly reduced without compromising crop health.Conversely,when users prioritized yield,the system optimized irri-gation and fertilization schedules to enhance productivity.These results showcased the method's flexibility and its potential to balance competing objectives in complex agricultural settings.Additionally,the integration of user preferences into RL-based strategy develop-ment enabled the generation of tailored management plans.These plans aligned with diverse user goals,including maximizing produc-tivity,minimizing resource consumption,and achieving sustainable farming practices.The system's multi-objective optimization capa-bilities allowed it to navigate trade-offs effectively,providing actionable insights for decision-making.The experimental validation al-so demonstrated the robustness of the PPO algorithm in training the RL model.The system's strategies were refined iteratively,result-ing in consistent performance improvements across various scenarios.By leveraging LLM to capture nuanced user preferences and combining them with RL for adaptive decision-making,the method bridges the gap between generic precision agriculture solutions and personalized farming needs. [Conclusions]This study established a novel framework for intelligent decision-making in agriculture,integrating LLM with reinforce-ment learning to address personalized crop management challenges.By accurately capturing user-specific preferences and dynamical-ly adapting to environmental and operational variables,the method offers a transformative approach to optimizing agricultural produc-tivity and sustainability.Future work will focus on expanding the system's applicability to a wider range of crops and environmental contexts,enhancing the interpretability of its decision-making processes,and facilitating integration with real-world agricultural sys-tems.These advancements aim to further refine the precision and impact of intelligent agricultural decision-making systems,support-ing sustainable and efficient farming practices globally.关键词
作物管理/大语言模型/多目标决策/个性化决策/PPO算法Key words
crop management/large language model/multi-objective decision/personalized decision/proximal policy optimization分类
农业工程引用本文复制引用
吴华瑞,李静晨,杨雨森..基于大语言模型的个性化作物水肥管理智能决策方法[J].智慧农业（中英文）,2025,7(1):11-19,9.基金项目
国家重点研发计划(2021ZD0113604) （2021ZD0113604）
财政部和农业农村部国家现代农业产业技术体系建设专项(CARS-23-D07) （CARS-23-D07）
中央引导地方科技发展资金项目(2023ZY1-CGZY-01) National Key R&D Program of China(2021ZD0113604) （2023ZY1-CGZY-01）
China Agriculture Research System of MOF and MARA Grant(CARS-23-D07) （CARS-23-D07）
Central Guiding Local Science and Technology Development Fund Projects(2023ZY1-CGZY-01) （2023ZY1-CGZY-01）
