用AI助手统一监控内河水质，一句提问生成专业报告。
Naiad: Novel Agentic Intelligent Autonomous System for Inland Water Monitoring
- 构建基于大模型的智能代理，整合遥感数据与分析工具
- 在多类用户测试中准确率超77%，相关性达85%以上
- 适合环保人员、科研工作者快速获取水体健康评估
内陆水体监测对保障公共健康与生态系统至关重要，可实现风险及时干预。现有方法通常孤立处理蓝藻、叶绿素等单一指标。NAIAD提出一种智能代理系统，利用大语言模型（LLM）与外部分析工具，结合地球观测（EO）数据，提供一体化内河监测解决方案。系统支持专家与非专业人士，通过单次自然语言提问即可生成可行动见解。基于检索增强生成（RAG）、LLM推理、外部工具调度、计算图执行与智能反思机制，从精选知识源中提取并融合信息，生成定制化报告。集成天气数据、哨兵-2影像、遥感指数计算（如NDCI）、叶绿素-a估算及CyFi等平台。在涵盖多用户专业水平的专用基准上，正确率超过77%，相关性达85%以上。初步结果表明系统对各类查询具有强适应性与鲁棒性。对不同LLM主干的消融研究显示，Gemma 3（27B）与Qwen 2.5（14B）在计算效率与推理性能间表现最佳。
原文摘要 · Abstract (English)
Inland water monitoring is vital for safeguarding public health and ecosystems, enabling timely interventions to mitigate risks. Existing methods often address isolated sub-problems such as cyanobacteria, chlorophyll, or other quality indicators separately. NAIAD introduces an agentic AI assistant that leverages Large Language Models (LLMs) and external analytical tools to deliver a holistic solution for inland water monitoring using Earth Observation (EO) data. Designed for both experts and non-experts, NAIAD provides a single-prompt interface that translates natural-language queries into actionable insights. Through Retrieval-Augmented Generation (RAG), LLM reasoning, external tool orchestration, computational graph execution, and agentic reflection, it retrieves and synthesizes knowledge from curated sources to produce tailored reports. The system integrates diverse tools for weather data, Sentinel-2 imagery, remote-sensing index computation (e.g., NDCI), chlorophyll-a estimation, and established platforms such as CyFi. Performance is evaluated using correctness and relevancy metrics, achieving over 77% and 85% respectively on a dedicated benchmark covering multiple user-expertise levels. Preliminary results show strong adaptability and robustness across query types. An ablation study on LLM backbones further highlights Gemma 3 (27B) and Qwen 2.5 (14B) as offering the best balance between computational efficiency and reasoning performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。