Machine Learning-Guided Synthesis of Room-Temperature Phosphorescent Carbon Dots for Enhanced Phosphorescence Lifetime and Information Encryption

Room-temperature phosphorescent (RTP) carbon dots (CDs) have been increasingly used in many applications, including anticounterfeiting and information encryption. However, synthesizing RTP CDs with a specific average lifetime of phosphorescence remains a formidable challenge. A breakthrough is needed in formulating the synthesis process to find a suitable synthesis formulation to produce CDs with an optimal lifetime of phosphorescence. Machine learning (ML) has recently been successfully used for guiding material synthesis and offering insight into the prediction, optimization, and acceleration of the CDs' synthesis process. A regression ML model on microwave-assisted CD synthesis is established to reveal the relationship between various synthesis parameters and enhance the average lifetime of phosphorescence of CDs in the solid-state phase. RTP CDs exhibit a blue emission when irradiating with UV and a green emission afterglow after the UV is turned off. These green emissions can last for 7 s, are easily observed by the naked eye, and show an ultralong phosphorescence lifetime of up to 1.6 s. Moreover, designed and guided by ML, this afterglow feature was explored to achieve multilevel anticounterfeiting and information encryption to encrypt and decrypt secret information in dynamic time-dependent displays. Our results provide a strategy for synthesizing RTP CDs with a specific lifetime and extending their application scope to high-level information security.