Gold nanoclusters and amino-modified mesoporous silica-encapsulated carbon dot fluorescence nanosensors combined with LightGBM algorithm for ultra-fast detection of Co2+

In this study, we develop a novel ratiometric fluorescent nanosensor for the detection excess Co in soil. This fluorescent nanosensor is fabricated using mesoporous silica-encapsulated nitrogen-doped carbon dots (N-CDs@mSiO) and gold nanoclusters stabilized by bovine serum albumin (BSA-AuNCs). The green fluorescence of the carbon dots within the mesoporous silica spheres (mSiO) serves as an internal reference signal. The red fluoresence BSA-AuNCs are covalently connected onto the surface of amino-functionalized nanospheres (N-CDs@mSiO-NH), providing the response signal. This nanosensor has dual emission peaks at 520 nm and 650 nm under excitation wavelength of 380 nm. The addition of Co to this nanosensor causes the fluorescence quenching at 650 nm while the green fluorescence at 520 nm remains unchanged, resulting in fluorescence color change from yellow to green. The developed ratiometric fluorescence nanosensor exhibits excellent selectivity to Co with a range of 2.00–200.00 μM and a detection limit as low as 0.74 μM. In addition, a Co prediction model is developed using the Light Gradient Boosting Machine (LightGBM) algorithm. The entire detection process is within 10 s and the model prediction value is as high as 0.991 on average. This shows that the proposed fluorescent nanosensor, optimized with the LightGBM algorithm, provides an efficient, environmentally friendly and potentially practical solution for Co detection.