PhenoIntel：一种生命周期对齐的多智能体Web应用，用于经过验证、易于使用的植物表型分析
PhenoIntel: A Lifecycle-Aligned Multi-Agent Web Application for Verified, Accessible Plant Phenotype Analysis
浏览论文内容
中文总结 AI 辅助
PhenoIntel是一款生命周期对齐的多智能体Web平台，通过分阶段的专用智能体实现可靠易用的植物表型分析，具备校准不确定性、验证统计等优势，模型性能优异且可在标准硬件上运行。
中文摘要 AI 辅助
现有的对话式植物表型平台对植物科学家而言难以使用，且缺乏科学研究所需的可靠性：分析失败会被报告为有效测量值而非标记为缺失，统计测试未检查假设就运行，预测未附带不确定性估计，专用硬件限制了可访问性。我们提出PhenoIntel，这是一种生命周期对齐的多智能体Web平台，将完整的机器学习工作流转化为可靠、用户友好的表型分析系统。九个专用智能体将分析划分为多个阶段，从图像采集到模型选择、推理和报告，而非将整个任务交给一个AI管理器。各阶段之间通过独立检查进行分离，每个智能体都从一个共享的固定结构记录中读取和写入数据，因此某一阶段的不一致输出会在进入下一阶段前被捕获。不确定性会根据每个模型家族进行匹配，采用共形预测、检测置信度分布或蒙特卡洛失活，而非统一应用，且质量阈值会根据作物和任务进行调整，而非使用单一全局 cutoff。当不存在合适的模型时，PhenoIntel可自行提议、验证并集成新模型。模型仓库涵盖五种作物、四种成像模态的十个训练模型。分类模型达到0.78-0.996的Macro F1；目标检测模型达到0.96 mAP@50，计数误差比未优化基线降低54%；时间序列模型达到保留样本的Macro F1为0.7050。PhenoIntel在标准硬件的浏览器中运行，无需GPU，且有1200项测试的自动化套件确认完整流水线执行。每个结果都附带校准后的不确定性、经过验证的统计数据以及符合FAIR原则的溯源信息，这是现有对话式表型工具所不具备的组合。
英文摘要
Existing conversational plant-phenotyping platforms are difficult for plant scientists to use and lack the reliability scientific research demands: failed analyses are reported as valid measurements rather than flagged as missing, statistical tests run without checking assumptions, predictions carry no uncertainty estimate, and specialised hardware limits accessibility. We present PhenoIntel, a lifecycle-aligned multi-agent web platform that turns the full machine-learning workflow into a reliable, user-friendly phenotyping system. Nine specialised agents divide the analysis into stages, from image collection through model selection, inference, and reporting, rather than handing the whole task to one AI manager. Independent checks separate these stages, and every agent reads from and writes to one shared, fixed-structure record, so an inconsistent output from one stage is caught before it reaches the next. Uncertainty is matched to each model family, conformal prediction, detection-confidence spread, or Monte Carlo Dropout, rather than applied uniformly, and quality thresholds adapt to crop and task instead of one global cutoff. When no suitable model exists, PhenoIntel can propose, validate, and integrate a new one on its own. The model repository spans ten trained models across five crops and four imaging modalities. Classification models reach Macro F1 of 0.78-0.996; object-detection models reach 0.96 mAP@50 with a 54% reduction in counting error over an unoptimised baseline; and a temporal model reaches held-out Macro F1 of 0.7050. PhenoIntel runs in a browser on standard hardware, requiring no GPU, and a 1,200-test automated suite confirms complete pipeline execution. Every result carries calibrated uncertainty, validated statistics, and FAIR-compliant provenance, a combination existing conversational phenotyping tools do not offer.
发表机构
- VIT Bhopal University（维特博帕尔大学）
- Centre of Studies in Resources Engineering（资源工程研究中心）
- Indian Institute of Technology Bombay（印度理工学院孟买分校）
机构由 AI 辅助整理，请以论文原文为准。
