Building an ensemble neural network optimized using uncertainty quantification for predicting metal oxide spectrograms from scanned metal oxide images.
Optical absorption spectroscopy is an important characterization of materials for applications such as solar energy generation. The purpose of the study is to build an ensemble neural network for pred..
Optical absorption spectroscopy is an important characterization of materials for applications such as solar energy generation. The purpose of the study is to build an ensemble neural network for predicting metal oxide spectrograms from images of metal oxide that have been scanned. With an ensemble network, several models are trained to produce a variety of predictions. By averaging these predictions, an even more accurate prediction can be made. Furthermore, uncertainty quantification will be applied by measuring the variance between the predictions, allowing more useful statistical analysis to be done such as producing confidence intervals to determine how accurate the results are. The study is done through a quantitative empirical research method. The research is a collaboration with Nevada National Security Site.
