Machine-Learning-Assisted Carbon Dots: From Algorithms to Applications and Beyond

Carbon dots (CDs) have emerged as frontier materials in multidisciplinary research owing to their unique optical properties and physicochemical characteristics. However, issues such as the reliance on trial-and-error experimentation for synthetic preparation and the difficulty in systematically revealing structure-activity relationships persist. In recent years, machine learning (ML) has provided a new paradigm for CD research through its powerful predictive and decision-making capabilities. This review first introduces the fundamental workflow of ML and the operational principles of several representative ML algorithms. It then summarizes the ML applications in CDs, including ML-optimized CD synthesis, ML-assisted detection in CD sensors, ML-based performance prediction, and ML-driven mechanism studies. Finally, the review outlines the future prospects for applications in this field, aiming to further advance the development of nanomaterials science.