Assessing contents of sugars, vitamins, and nutrients in baby leaf lettuce from hyperspectral data with machine learning models

Authors: ESHKABILOV, SULAYMON - North Dakota State University; Simko, Ivan

Submitted to: Agriculture
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 5/24/2024
Publication Date: 5/26/2024
Citation: Eshkabilov, S., Simko, I. 2024. Assessing contents of sugars, vitamins, and nutrients in baby leaf lettuce from hyperspectral data with machine learning models. Agriculture. 14(6). Article 834. https://doi.org/10.3390/agriculture14060834.
DOI: https://doi.org/10.3390/agriculture14060834

Interpretive Summary: Fresh lettuce is a desirable, but highly perishable product that shall be consumed almost immediately after harvest or maintained in the conditions that prevents its wilting, weight loss, enzymatic discoloration, senescence, and tissue deterioration. Evaluation of lettuce composition is important for determining its overall quality; however, laboratory analyses are slow and costly. Therefore, more rapid, less expensive, and non-destructive approaches based on (hyper)spectral reflectance are being developed to assess plant phenotypes, response to stress, and postharvest quality. We have tested five classification and regression machine learning models to be applied on the content of chlorophyll, anthocyanins, glucose, fructose, sucrose, vitamin C, ß-carotene, N, P, K, dry matter content, and plant fresh weight. The four applied classification models of machine learning demonstrated 100% accuracy in classifying the studied baby leaf lettuces by phenotype when certain fertilizer treatments were applied.

Technical Abstract: Lettuce (Lactuca sativa) is a leafy vegetable that provides a valuable source of phytonutrients for healthy human diet. Assessment of plant growth and composition is vital for determining crop yield and the overall quality, however, a classical laboratory analyses are slow and costly. Therefore, a new, less expensive, more rapid, and non-destructive approaches are being developed, including those based on (hyper)spectral reflectance. Additionally, it is also important to determine how plant phenotypes respond to fertilizer treatments and whether these differences in response can be detected from analyses of hyperspectral image data. In the current study we demonstrate the suitability of hyperspectral imaging in combination with machine learning models to estimate the content of chlorophyll (SPAD), anthocyanins (ACI), glucose, fructose, sucrose, vitamin C, ß-carotene, N, P, K, dry matter content, and plant fresh weight. The implemented five classification and regression machine learning models showed high accuracy in classifying the lettuces by the applied fertilizers treatments and estimating nutrient concentrations. To reduce the input (predictor data, i.e., hyperspectral data) dimension, 13 principal components were found and applied in models. The implemented artificial neural network models of machine learning algorithm demonstrated high accuracy (r = 0.85 ... 0.99) in estimating fresh leaf weight, and contents of chlorophyll, anthocyanins, N, P, K, and ß-carotene. The four applied classification models of machine learning demonstrated 100% accuracy in classifying the studied baby leaf lettuces by phenotype when certain fertilizer treatments were applied.