Thomas Penfold - Towards automated analysis of X-ray spectra using deep neural networks

X-ray spectroscopy delivers strong impact across the physical and biological sciences by providing end users with highly detailed information about the electronic and geometric structure of matter. To decode this information in challenging cases, e.g., in operando catalysts, batteries, and temporally evolving systems [1], advanced theoretical calculations are necessary. The complexity and resource requirements often render these out of reach for end users, and therefore, the data are often not interpreted exhaustively, leaving a wealth of valuable information unexploited. In this talk, I will discuss our recent progress applying machine learning to the prediction and interpretation of X-ray spectroscopy [2,3]. Our DNN, XANESNET [4], is able to predict X-ray absorption and emission spectra in less than a second with information obtained quickly from the geometric information about the local environment of the absorption site. We predict peak positions with sub-eV accuracy and peak intensities with errors over an order of magnitude smaller than the spectral variations that the model is engineered to capture. I will also outline extensions of the model to interpret the performance of the network and demonstrate how the uncertainty arising from predictions can be estimated. Finally, I will highlight areas on which future developments should focus.