Generation of fruit's spectra with hundreds of wavelengths from obtained multi-spectra and spectral application using deep learning.

•A generation method on spectra with hundreds of wavelengths from multi-spectra was proposed.•The generated spectra were highly similar to the ‘real’ spectra.•The generated spectra predicted internal quality of fruit more precisely than multi-spectra.•Deep learning method outperformed traditional method in predicting internal quality of fruit.