Non-destructive estimation of maize carotenoids using reflectance-based spectral indices.

Abstract

This study investigates the relationship between maize leaf carotenoid content and spectral reflectance, evaluates existing carotenoid estimation indices, and develops new spectral indices and machine learning models for improved prediction. A strong positive correlation was observed between carotenoid and chlorophyll content, highlighting carotenoids' role in both light harvesting and photoprotection. Spectral analysis revealed that carotenoid concentration significantly affects leaf reflectance in the visible range, particularly between 500-650 nm. Existing carotenoid indices exhibited limited predictive performance for the studied samples, prompting the development of nine new indices based on principal component analysis. Among these, CAR 7 , CAR 8 , and CAR 9 demonstrated superior predictive ability across different training (2021-2022: R 2 = 0.72-0.76, NRMSE = 15-16%, 2021-2023: R 2 = 0.60-0.62, NRMSE = 11-12%, 2022-2023: R 2 = 0.42-0.49, NRMSE = 18.3-18.5%) and testing periods (2023: R 2 = 0.44-0.50, NRMSE = 14-19%, 2022: R 2 = 0.65-0.72, NRMSE = 13-16%, 2021: R 2 = 0.81-0.83, NRMSE = 18.28-24.65%). Machine learning models further improved carotenoid estimation, with REPTree providing the most reliable and balanced performance during testing (R 2 = 0.79, NRMSE = 13.84%). The findings suggest that the combination of targeted spectral indices and appropriate machine learning approaches enables accurate, non-destructive estimation of maize carotenoid content, offering potential for practical applications in crop monitoring and stress assessment.

Plant phenotyping relevance

トウモロコシ葉のカロテノイドという植物形質を、反射スペクトル指標と機械学習で非破壊推定する手法の開発・評価が研究の中心であるため。

Code and data availability

The supplied blocks describe maize carotenoid spectrophotometry, hyperspectral measurements, PCA-derived indices, and machine learning models, but contain no data availability statement, no public phenotype/spectral dataset deposit, and no author code or model release. The only URLs present (creativecommons.org license

No evidence-backed public reproduction asset is currently recorded.