Carbon nanosensors and machine learning algorithms for simultaneous measurement of pH and temperature of aqueous media

The research focuses on the creation of a fluorescent carbon dots -based nanosensor that performs simultaneous measurement of environmental temperature and pH using machine learning algorithms. A comparative analysis of multiple methods application - linear regression, the method of partial least squares, artificial neural networks, random forest, and gradient boosting - showed that multilayer perceptron with 2 hidden layers containing 128 and 64 neurons provided the lowest error in determining the temperature and pH of the liquid medium containing carbon dots.