发表机构
Cornell University; Colinas Farming Company（康奈尔大学; 科利纳斯农业公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究评估了加州葡萄园精准病害控制中两种人机交互工作流，验证了Aleks多智能体系统在红叶症状预测和病毒检测采样中的有效性，显示模型可提升巡查效率，但计划需补充实施细节。
AI 中文摘要
我们在加利福尼亚州葡萄园的一个精准病害控制项目中评估了两种实时人机交互的价值。该项目测试了2021至2024年间的商业巡查记录和覆盖140公顷的遥感测量数据，能否支持2025年红叶症状预测，以进行优先巡查和病毒检测。在工作流1中，多智能体研究系统Aleks v1通过迭代式人工优化开发了预测模型。我们将Aleks的2024年藤蔓尺度模型应用于更新的2025年预测因子，并依据独立的2025年巡查数据评估了红叶预测效果。在覆盖所有藤蔓位置45%的回顾性模拟中，将模型信息驱动的行优先排序加入自适应巡查后，新记录红叶观测的发现比例从85.8%提升至94.1%。区块内巡查比较表明，该模型主要改善了区块间的巡查分配。尽管在训练/测试分割前因合成过采样导致2024年内部性能估计不可靠，Aleks仍在145分钟内开发了一个信息丰富的藤蔓尺度模型，提高了吞吐量并回答了我们的研究问题。在工作流2中，我们评估了模型得分较高的藤蔓是否具有更高的病毒检出频率，以及Aleks能否从包含数据和文献的通用提示中推断出这一采样目标。Aleks的计划优先考虑葡萄园和模型得分的均衡覆盖，而我们的计划则优先考虑现场效率和高模型得分过采样。Aleks的计划和我们的计划分别采样了50株中的41株（82%）和100株中的97株（97%）。Aleks的计划遗漏了替换缺失藤蔓的指令，限制了其实施和操作价值。在采样的137株藤蔓中，有5株检测出葡萄藤红叶斑驳病毒阳性（模型得分ROC AUC为0.735）。这些发现支持根据AI交互在实时、项目特定约束下推进实地研究目标的程度来评估其价值。
英文摘要
We assessed the value of two live human-AI interactions in a precision disease control project in California vineyards. The project tested whether 2021-2024 commercial scouting records and remote-sensing measurements across 140 hectares could support 2025 red-leaf symptom forecasting for prioritized scouting and virus testing. In Workflow 1, Aleks v1, a multi-agent research system, developed forecasting models with iterative human refinement. We applied Aleks's 2024 vine-scale model to updated 2025 predictors and evaluated red-leaf forecasts against independent 2025 scouting. In retrospective simulations surveying 45% of all vine positions, adding model-informed row prioritization to adaptive scouting increased the encountered proportion of newly recorded red-leaf observations from 85.8% to 94.1%. Within-block scouting comparisons suggested the model mainly improved scouting allocation among blocks. Despite unreliable internal 2024 performance estimates from synthetic oversampling before train/test splitting, Aleks developed an informative vine-scale model in 145 minutes, increasing throughput and answering our research questions. In Workflow 2, we assessed whether higher model-score vines had more frequent virus detection, and whether Aleks could infer this sampling goal from a general prompt with data and literature. Aleks's plan prioritized balanced vineyard and model score coverage, while our plan prioritized field efficiency and high-model-score oversampling. Aleks's and our plans yielded 41/50 (82%) and 97/100 (97%) sampled vines. Aleks's plan omitted instructions for replacing missing vines, limiting implementation and operational value. Five of 137 sampled vines tested positive for grapevine red blotch virus (model score ROC AUC 0.735). These findings support assessing AI interactions by how well they advance field research objectives under live, project-specific constraints.
Comments35 pages, including supplementary materials. Supporting files S1-S4: https://doi-org.proxy.library.cornell.edu/10.5281/zenodo.23142108
