Machine learning in analytical chemistry: From synthesis of nanostructures to their applications in luminescence sensing

Abstract

Over the past decade, the wide-scale adoption of artificial intelligence (AI) and machine learning (ML) has transformed the landscape of scientific research and development, which extends their influence across various scientific disciplines. Analytical chemistry has benefited significantly from these advances, with ML techniques proving to be valuable tools for researchers involved in the design, synthesis, and optimization of nanomaterials, as well as for the development of sensing platforms and data analysis for the detection of diverse analytes. In this review, we survey the practical applications of ML in the development of luminescent sensing approaches by analyzing recent publications on the synthesis of luminescent nanomaterials and ML-assisted electrochemiluminescence, fluorescence, and chemi- and bio-luminescent sensors. Our analysis illustrates how ML techniques can enhance the efficiency, sensitivity, and selectivity of luminescent sensing platforms, thereby paving the way for future innovations in this field.