Evaluating human-AI workflows for field research in viticulture

2026-10-05

AI Summary

This study addresses the need for a systematic evaluation of the practical utility of human–AI collaboration in precision disease management within vineyards. To this end, it proposes a novel AI interaction evaluation paradigm oriented toward advancing field research. The approach leverages Aleks, a multi-agent system that integrates remote sensing and scouting data to predict red leaf symptoms, while combining machine learning with adaptive sampling algorithms to optimize field strategies. Experimental results demonstrate that the model-guided row-prioritization strategy increases the discovery rate of new observations to 94.1%. These findings effectively validate the significant potential of AI-driven approaches in enhancing the efficiency of field-based scientific research.

Abstract

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.

Problem

• human-AI workflows
• precision disease control
• viticulture
• symptom forecasting
• field research

Innovation

• Multi-agent system
• Human-AI workflow
• Precision viticulture
• Disease forecasting
• Adaptive scouting