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

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, CAR₇, CAR₈, and CAR₉ demonstrated superior predictive ability across different training (2021-2022: R² = 0.72-0.76, NRMSE = 15-16%, 2021-2023: R² = 0.60-0.62, NRMSE = 11-12%, 2022-2023: R² = 0.42-0.49, NRMSE = 18.3-18.5%) and testing periods (2023: R² = 0.44-0.50, NRMSE = 14-19%, 2022: R² = 0.65-0.72, NRMSE = 13-16%, 2021: R² = 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 (R² = 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.