Machine learning-driven graphene quantum dot fluorescence array for rapid heavy metal ions detection and...

The growing threat of heavy metal ions (HMIs) to human health and the ecological environment has underscored the need for advanced sensor technologies capable of effectively detecting these pollutants. In this study, we developed a simple yet efficient fluorescence array composed of three nitrogen-doped graphene quantum dot (GQDs) probes, which enables rapid detection and identification of HMIs. The fluorescence array achieves detection within 3 min and demonstrates excellent cost-effectiveness. We observed that different HMIs induce distinct fluorescence quenching effects on the GQDs, leading to unique fluorescence response patterns. Leveraging this phenomenon, we constructed a GQDs-based fluorescence array. Experimental results revealed that each of the five tested HMIs exhibited a unique response pattern, and machine learning algorithms achieved 100 % identification accuracy in both buffer solutions and real water samples. This study successfully establishes a robust and straightforward HMIs fingerprint recognition platform, offering a significant technological advancement for environmental monitoring applications.