Prediction of the Soluble Solid Content of Citrus Based on the Fractional-Order Derivative and Optimal Band Combination Algorithm

Abstract

Abstract The soluble solid content (SSC) is a primary characteristic index for evaluating the internal quality of citrus fruits. The development of rapid and nondestructive SSC detection techniques can help address the current issues of postharvest quality grading in China's citrus industry. In this study, Three varieties of citrus were used as experimental materials. After obtaining the reflection spectra and SSCs,SNV-FOD (Standard Normal Variate - Fractional-Order Derivative) was used to process the spectra, and the optimal band combination algorithm (OBC) was introduced to select SSC-sensitive bands. Then, the obtained optimal dual-band combination was input into eight regression models for comparison, and the best-performing models stacked ensemble models was selected. Finally, the H-ELR (HyperOpt-optimized Ensemble Learning Regression) model, optimized using a Bayesian function, was applied for the effective prediction of citrus SSC. The results shows that (1) The SNV-FOD preprocessing method proposed in this paper improved the correlation coefficient with the SSC by 0.29 compared to that of the original spectrum; (2) The optimal dual-band combination (969 and 1069 nm) constructed by integrating the differential index (DI) and 1.2-order derivative yielded the most accurate results (RPD = 2.13); and (3) The H-ELR model, based on HyperOpt optimization, achieved good predictive performance (RPD = 2.46). This research contributes to the development of practical SSC prediction instruments with excellent universality and ease of application.