A machine learning-assisted fluorescent sensor array utilizing silver nanoclusters for coffee discrimination

Coffee is a globally consumed commodity of substantial commercial significance. In this study, we constructed a fluorescent sensor array based on two types of polymer templated silver nanoclusters (AgNCs) for the detection of organic acids and coffees. The nanoclusters exhibited different interactions with organic acids and generated unique fluorescence response patterns. By employing principal component analysis (PCA) and random forest (RF) algorithms, the sensor array exhibited good qualitative and quantitative capabilities for organic acids. Then the sensor array was used to distinguish coffees with different processing methods or roast degrees and the recognition accuracy achieved 100%. It could also successfully identify 40 coffee samples from 12 geographical origins. Moreover, it demonstrated another satisfactory performance for the classification of pure coffee samples with their binary and ternary mixtures or other beverages. In summary, we present a novel method for detecting and identifying multiple coffees, which has considerable potential in applications such as quality control and identification of fake blended coffees.