Finding optimal carbon dots synthesis parameters for quantitative analysis of components in multi-component aqueous solutions using machine learningстатья
Статья опубликована в журнале из списка Web of Science и/или Scopus
Местоположение издательства:New York, N.Y., United States
Аннотация:This study focuses on identifying the optimal parameters of hydrothermal synthesis of carbon dots that ensure high-precision determination of the concentrations of specific heavy metal salts in aqueous solutions. Carbon dots were synthesized from citric acid and ethylenediamine under a wide range of precursor ratios, temperatures and reaction times. In total, 74 types of carbon dots were obtained. A water suspension of each type of carbon dots was mixed with aqueous solutions of Co(NO3)2 and Cu(NO3)2 at different salt concentrations. The photoluminescence excitation-emission spectra were registered for all prepared samples. To solve the stated “synthesis-properties” task, machine learning methods were applied. An artificial neural network based on a multilayer perceptron architecture was used to approximate the dependence of the target variable – the error in determining the concentrations of the studied heavy metal salts – on the carbon dots synthesis parameters. The target variable values for training the approximating model were obtained as a result of solving the inverse problem of determining the concentrations of heavy metal salts from the photoluminescence excitation-emission spectra of carbon dots by machine learning algorithms. The proposed two-step approach demonstrated the potential to successfully identify the optimal areas of carbon dots synthesis parameters that yield the desired accuracy in determining the concentrations of various components in multicomponent solutions.
