Selection of Optimal Diagnostic Positions for Early Nutrient Deficiency in Cucumber Leaves Based on Spatial Distribution of Raman Spectra

Abstract

Accurate diagnosis of crop nutritional status is critical for optimizing yield and quality in modern agriculture. This study enhances the accuracy of Raman spectroscopy-based nutrient diagnosis, improving its application in precision agriculture. We propose a method to identify optimal diagnostic positions on cucumber leaves for early detection of nitrogen (N), phosphorus (P), and potassium (K) deficiencies, thereby providing a robust scientific basis for high-throughput phenotyping using Raman spectroscopy (RS). Using a dot-matrix approach, we collected RS data across different leaf positions and explored the selection of diagnostic positions through spectral cosine similarity analysis. These results provide critical insights for developing rapid, non-destructive methods for nutrient stress monitoring in crops. Results show that spectral similarity across positions exhibits higher instability during the early developmental stages of leaves or under short-term (24 h) nutrient stress, with significant differences in the stability of spectral data among treatment groups. However, visual analysis of the spatial distribution of positions with lower similarity values reveals consistent spectral similarity distribution patterns across different treatment groups, with the lower similarity values predominantly observed at the leaf margins, near the main veins, and at the leaf base. Excluding low-similarity data significantly improved model performance for early (24 h) nutrient deficiency diagnosis, resulting in higher precision, recall, and F1 scores. Based on these results, the efficacy of the proposed method for selecting diagnostic positions has been validated. It is recommended to avoid collecting RS data from areas near the leaf margins, main veins, and the leaf base when diagnosing early nutrient deficiencies in plants to enhance diagnostic accuracy.

Keywords: Raman spectroscopy; cucumbers; leaf position; nitrogen; nutrient deficiency; phosphorus; potassium; precision agriculture.

Figure 1

Template for spectral acquisition using a dot-matrix method on leaf surfaces.

Figure 2

Trends in N, P, and K content in cucumber leaves over time after stress induction. Each bar represents the mean ± S.E.M. (n = 3). (A) N content in ND vs. CK. (B) P content in PD vs. CK. (C) K content in KD vs. CK.

Figure 3

Box plot of spectral similarities across cucumber leaf positions. The boxes represent the interquartile range, and the lines inside the boxes represent the medians. The whiskers denote the lowest and highest values within 1.5 times the interquartile range, while points below the lower whisker represent outliers in similarity values.

Figure 4

Spatial distribution of low-similarity spectral positions across cucumber leaves. CK (control-check), ND (nitrogen-deficient), PD (phosphorus-deficient), and KD (potassium-deficient).

Figure 5

Workflow of spectral data preprocessing. (A) Raw spectra; (B) Fitted baseline; (C) Baseline-corrected spectra; (D) Normalized spectra after baseline correction; (E) Normalized raw spectra.

Figure 6

Confusion matrices for test sets under different stress durations.

Figure 7

Distribution of excluded low-similarity spectral positions. Green indicates retained spectral data points, while gray indicates excluded positions.