Artificial Intelligence smelling machines based on multidimensional gas chromatography: Capturing extra-virgin olive oil aroma blueprint and unique identity

Comprehensive two-dimensional gas chromatography coupled to time-of-flight mass spectrometry (GC×GC-TOF MS) has been recently applied as core technology of a Sensomics-based expert system (SEBES) capable to predict key-aroma signatures of food without using human olfaction. The strategy, also referred to as Artificial Intelligence Smelling, conceptually opens many different opportunities for odorants pattern detection, accurate quantification avoiding time-consuming sample preparation/extraction steps, and samples sensory qualification/discrimination based on computer vision strategies. The contribution illustrates the potentials of GC×GC platforms in the context of Artificial Intelligence Smelling for extra-virgin olive oils selected within high-quality productions from Italy and Brazil. In particular, by accurate quantification of key-aroma compounds and potent odorants strongly correlated to sensory defects, samples’ aroma bluperint is captured and used to discriminate oils based on their peculiar hedonic features. The application of combined untargeted and targeted (UT) fingerprinting strategy of 2D-data patterns enables effective discrimination between oils produced in different Italian Regions and between oils from Italy and Brazil independently by processing technologies and olives cultivars. This identitation process has great potentials being an effective fingerprinting strategy while providing, at the same time, high level information on chemical composition as a detailed profiling.