Optimization of Artificial Neural Network (ANN) Models Applied to Experimental Synthesis of Gold Nanoparticles (Au).

This paper presents the development and optimization of an Artificial Neural Network (ANN) model to accurately predict key parameters in the synthesis of gold nanoparticles (Au). The ANN, trained on experimental data, utilizes input variables including the NaCt/Au ratio, Au solution volume, reaction temperature, and stirring speed. The optimized model demonstrates high accuracy in predicting UV–Vis spectral features and optical properties, including absorption peak intensity, absorption wavelength, and full width at half maximum (FWHM), achieving an R2 value of 0.9785. The network configuration consists of three hidden layers with 16 neurons each, a learning rate of 0.01, the AdamW optimizer, and 200 training epochs. This optimized ANN model significantly reduces the time and cost associated with the experimental synthesis of Au nanoparticles. © 2025 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]