发表机构
Politecnico di Milano; China Three Gorges University; Delft University of Technology; Qinhuangdao Hydrological Survey and Research Center of Hebei Province; Dalian University of Technology; TU Dresden University of Technology; Ningbo University; China IPPR International Engineering Co., Ltd.; Hohai University; Nanjing University; Cornell University; Tongji University; Zhejiang Institute of Hydraulics and Estuary; Ghent University; University of British Columbia; Beijing Normal University; Karlsruhe Institute of Technology (KIT)（米兰理工大学; 三峡大学; 代尔夫特理工大学; 河北省秦皇岛水文勘测研究中心; 大连理工大学; 德累斯顿工业大学; 宁波大学; 中国市政工程华北设计研究总院有限公司; 河海大学; 南京大学; 康奈尔大学; 同济大学; 浙江省水利河口研究院; 根特大学; 不列颠哥伦比亚大学; 北京师范大学; 卡尔斯鲁厄理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对业务洪水预报中隐性预报员专业知识难形式化等问题，提出HydroAgent框架，将大语言模型嵌入洪水预报工作流程，经实验验证其有效性，能转化隐性知识为可审核流程，辅助决策并展示规则引导语言模型推理补充物理模拟的作用。
AI 中文摘要
业务洪水预报依赖难以形式化、审核和转移的隐性预报员专业知识。尽管人工智能方法推动了洪水预测和模型误差校正，但多数现有研究未明确表示将模型输出与业务预警决策联系起来的隐性专家规则、审查检查点和工作流程约束。为解决此问题，我们提出HydroAgent，一个将大语言模型（LLMs）嵌入模型驱动洪水预报工作流程的技能编排代理框架，其中每个技能编码明确规则以限制LLM推理。我们在南亚姆希尔河流域使用五个最先进的LLMs验证了其有效性。结果表明，先验判断在14个事件中的10个和11个事件中以5%的容差捕获了观测到的峰值流量和洪水量，在129个事件上进行5折交叉验证产生的皮尔逊相关系数为0.62和0.84。基于高基线方案库（平均KGE 0.890），引导方案选择进一步将KGE提高了0.023 - 0.154，在14个事件中的14个和13个事件中模拟的峰值流量和洪水量落在先验判断范围内。所有五个测试的LLMs成功执行HydroAgent工作流程且具有相当的判断准确性（40% - 80%），同时表现出适度的性能差异和显著的成本差异。HydroAgent并非旨在取代人类预报员；相反，它将他们的隐性专业知识转化为可审核和可重复的工作流程，简化分析步骤并支持更明智的决策。这种技能编排范式展示了明确的规则边界如何引导语言模型推理以补充下一代洪水预报中基于物理的模拟。
英文摘要
Operational flood forecasting depends on tacit forecaster expertise that is difficult to formalize, audit, and transfer. Although artificial intelligence methods have advanced flood prediction and model-error correction, most existing studies have not explicitly represented the tacit expert rules, review checkpoints, and workflow constraints that connect model outputs to operational warning decisions. To address this issue, we propose HydroAgent, a skill-orchestrated agent framework that embeds Large Language Models (LLMs) into a model-driven flood forecasting workflow, where each skill encodes explicit rules to bound LLM reasoning. We validated its effectiveness using five state-of-the-art LLMs in the South Yamhill River basin. Our results demonstrate that prior judgment captures observed peak flow and flood volume within 5% tolerance in 10 and 11 out of 14 events, with 5-fold cross-validation over 129 events yielding Pearson correlations of 0.62 and 0.84. Building on a high-baseline scheme library (average KGE 0.890), the guided scheme selection further improves KGE by 0.023-0.154, with simulated peak flow and flood volume falling within the prior judgment ranges for 14 and 13 out of 14 events. All five tested LLMs successfully execute the HydroAgent workflow with comparable judgment accuracy (40%-80%), while showing moderate performance variation and substantial cost differences. HydroAgent does not aim to replace human forecasters; instead, it translates their tacit expertise into an auditable and reproducible workflow, streamlining analytical steps and supporting more informed decision-making. This skill-orchestrated paradigm demonstrates how explicit rule boundaries can guide language model reasoning to complement physically based simulation in next-generation flood forecasting.
