Data fusion of FT-NIR and ATR-FTIR spectra for accurate authentication of geographical indications for Gastrodia elata Blume

Gastrodia elata Blume (G. elata Bl.), with its excellent nutritional and medicinal value from Zhaotong, has been protected by geographical indication (GI). Accurate certification of its origin is a prerequisite to safeguard consumer interests and maintain the market. Four different regions and three varieties of G. elata Bl. from Zhaotong were used in this study (n = 262). Tri-step infrared spectroscopy was used for ATR-FTIR spectral analysis to filter out fingerprint regions for data fusion with FT-NIR spectra, after which conventional discriminant models (PLS-DA and GS-SVM) were built. The second derivative (SD), multiple scattering correction (MSC), and Savitzky-Golay (SG) preprocessing were also performed on the spectra, and it was found that the preprocessing improved the performance of the PLS-DA model. The optimal model results in GS-SVM, based on mid-level data fusion of principal components (PCs) and latent variables (LVs), with sensitivity, specificity, accuracy, and Matthews correlation coefficient (MCC) of 1 for the test set. Furthermore, the residual convolutional neural network (ResNet) models were built, based on FT-NIR full spectra, band 3600−2700 cm−1 (MFA) and band 1750−500 cm−1 (MFB). Their accuracy in both train and test sets exceeds 97%, and the loss function curve is close to 0, which indicates that these three bands can be used as a fingerprint area to verify the GI of Zhaotong G. elata Bl. This study provides a fast, non-invasive method for the authentication of food or medicinal plant GI.