Data Sheet 1_Novel estimation of tomato soluble solids content using linearly transformed reflectance-based spectral indices.pdf

Rapid and non-destructive estimation of soluble solids content (SSC) is essential for tomato quality evaluation, yet the generalization ability of many existing spectral models remains limited when applied across multiple cultivars. In this study, hyperspectral reflectance was combined with a genetic algorithm (GA)–based optimization strategy to develop a robust SSC prediction framework applicable to diverse tomato types. Spectral reflectance and SSC (°Brix) were measured for 152 fruits representing 13 cultivars, including large red, medium red, red cherry, and yellow cherry types. To overcome the structural rigidity of conventional fixed-form spectral indices, reflectance spectra were linearly transformed to construct three novel indices: the linearly transformed difference spectral index (ltDSI), linearly transformed normalized difference spectral index (ltNDSI), and linearly transformed ratio spectral index (ltRSI). For each index, GA was employed to simultaneously optimize wavelength combinations and transformation coefficients. Under identical calibration and validation datasets, the GA-optimized indices consistently outperformed conventional two-band spectral indices as well as full-spectrum partial least squares models, while exhibiting markedly reduced sensitivity to tomato type. Across all validation datasets, the proposed models achieved coefficients of determination of approximately 0.80, with root mean square errors around 0.6°Brix and mean relative errors close to 10%. These results demonstrate that joint optimization of spectral index structure and parameters is an effective strategy for improving model robustness and transferability. The proposed framework provides a scalable solution for non-destructive SSC assessment and offers practical guidance for the development of low-cost, field-deployable spectral sensing tools for fruit quality phenotyping across cultivars and growing conditions.