We hydroponically cultivated wheat and subjected them to mineral deficiency by a week-long exposure to Hoagland's solution minus one essential mineral. Chlorophyll fluorescence and P700+ absorbance were measured under a single 300 ms saturating light pulse (one-shot) or the conventional two pulses (two-shot). A machine learning-based multiclass classification model was developed to assess mineral deficiency diagnosis. The results indicated that partial least squares discriminant analysis (PLS-DA) was ineffective. Conversely, linear discriminant analysis (LDA) without principal components analysis (PCA) successfully identified 13 or 11 (with a class combining the control with Mo- and B-deficiencies; and ten other distinct classes for respective mineral deficiencies) classes of mineral deficiencies, achieving over 81 % diagnostic performance across all five macro metrics of precision, recall, specificity, accuracy, and F1 measure. The one-shot method exhibited only a slight decrease in performance compared to the two-shot method, highlighting the advantage of substantially reduced measurement time. Applying the developed LDA models to outdoor soil-grown leaf data revealed their practicality and limitations. In multiple deficiency scenarios, the model predicted one predominant deficiency or incorrectly diagnosed a different deficiency. This study is the first to quantitatively demonstrate the efficacy of ultra-fast nutritional diagnostic technology in identifying root zone mineral deficiencies using chlorophyll fluorescence and P700+ absorbance measurements. It delineates the requirements for constructing multilabel or quantitative calibration models for field deployment.
Read full abstract