גיא שני

Chronic nutrient stress, whether deficiency or excess, alters trees’ physiology and disrupts their growth. Because growth and hydraulics co-determine stem diameter dynamics, we hypothesize that stem diameter variation (SDV, measured by point dendrometers) carries identifiable signatures of nutrient stress that can be detected and classified. We evaluated our hypothesis by an SDV time series from a controlled experiment of nitrogen (N), phosphorus (P), and potassium (K) deficiency, optimal levels, and excess in citrus trees. We extracted temporal features from hourly SDV measurements and trained a hierarchical machine learning framework that first detected stress, then separated deficiency from excess, and finally attributed the nutrient axis (if possible). The framework substantially outperformed flat baselines. It achieved more than 70% precision for nutrient-specific classification under the full hierarchy and nearly 90% accuracy with a modified variant in which the deficiency and excess branches were each decomposed into potassium vs. {nitrogen, phosphorus} without further subdivision of nitrogen and phosphorus. Accuracy stabilized within one to two weeks of temporal aggregation, indicating an agronomically actionable detection horizon. Dendrometer-derived SDV enables noninvasive nutrient stress detection. Hierarchical ML outperforms flat baselines for NPK stress classification. Two-week temporal voting stabilizes accuracy at actionable timescales.