Building robust models for identification of adulteration in olive oil using FT-NIR, PLS-DA and variable selection

Being a product with a high market value, olive oil undergoes adulterations. Therefore, studies that make the verification of the authenticity of olive oil more efficient are necessary. The aim of this study was to develop a robust model using FT-NIR and PLS-DA to discriminate extra virgin olive oil samples and build individual models to differentiate adulterated extra virgin olive oil samples. The best PLS-DA-OPS classification model for olive oils showed specificity (Spe) and accuracy (Acc) values higher than 99.7% and 99.9%. For the classification of adulterants, PLS-DA-OPS models presented values of Spe at 96.0% and Acc above 95.5% for varieties. For the blend, the best PLS-DA-GA model presented Acc and Spe values greater than 98.2% and 98.8%. Reliable and robust models have been built, allowing differentiation from seven adulterants to genuine extra virgin olive oils.

Automated summary

This study successfully developed a model using FT-NIR and PLS-DA to efficiently distinguish the authenticity of extra virgin olive oil and differentiate adulterated samples. Different models showed strong performance in classifying olive oils and various types of adulterants, with high accuracy and specificity values. Reliable and robust models were built allowing for differentiation between seven adulterants and genuine extra virgin olive oils.