Predictive modeling of a leaf conceptual midpoint quasi-color (CMQ) using an artificial neural network

Authors: Simko, Ivan

Submitted to: Sensors
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 7/13/2020
Publication Date: 7/15/2020
Citation: Simko, I. 2020. Predictive modeling of a leaf conceptual midpoint quasi-color (CMQ) using an artificial neural network. Sensors. 20(14):3938. https://doi.org/10.3390/s20143938.
DOI: https://doi.org/10.3390/s20143938

Interpretive Summary: Pigments in plant leaves play a critical role in biological functions, such as capturing light energy for photosynthesis or mitigating stresses caused by biotic and abiotic factors. The amount and combination of pigments in leaves affects visual perception of their color, the trait that is vital to consumers of leafy vegetables and growers of ornamental plants. Moreover, plant pigments have a beneficial effect on human health, making them a highly desirable target of plant breeding programs. Predictive modeling is therefore valuable to producers, breeders, and researchers in their effort to achieve desirable leaf color. The present work describes a novel concept based on combining color data from both leaf surfaces to account for the effect of chlorophylls (green color) and anthocyanins (red-purple color). Modeling of leaf color using artificial neural network confirmed very close match between predicted and observed values for color.

Technical Abstract: Color of plant leaves is moderated by the content of pigments. Studies that associate the content of pigments with leaf coloration usually employ statistical approaches with restrictive assumptions and focus on adaxial surfaces only. However, leaves of many plant species show considerable dorsiventral distribution of pigments and coloration. Two typical examples are leafy vegetables and ornamentals where red and green color surfaces can be seen on the same leaf. The proof of concept is provided for predictive modeling of a leaf conceptual mid-point quasi-color (CMQ) from the content of pigments. The CMQ idea is based on the hypothesis that the content of pigments in leaves is associated with the combined color from both surfaces. The CMQ, that is calculated from CIELab color coordinates at adaxial and abaxial antipodes, is thus not an actual color, but a notion that can be used in modeling. The CMQ coordinates predicted from the content of chlorophylls and anthocyanins by the means of an artificial neural network (ANN) matched well with the CMQ coordinates found empirically on photosynthetically active leaves of lettuce (Lactuca sativa L.), but also other plant species with comparable leaf attributes. Modeled values of lightness (qL*) decreased with the increasing content of both pigments, while redness or greenness (qa*), and yellowness or blueness (qb*) of CMQ were affected more by a relative content of chlorophylls and anthocyanins in leaves. The highest vividness of quasi-colors (qC*) was modeled for leaves with a high content of either pigment alone. The model predicted a substantially duller quasi-color for leaves with chlorophylls and anthocyanins present together, particularly when both pigments were at very high content. The results of predictive modeling demonstrate how combinations of chlorophyll and anthocyanins affects CIELab coordinates for CMQ and why visually estimating their content in leaves may be problematic when both pigments are present in samples simultaneously at more than minute quantities. This novel modeling concept and the mathematical formulas provided in this paper may be added to the arsenal of approaches used for studying phenotypic diversity of leaves.