MnEdgeNet -- Accurate Decomposition of Mixed Oxidation States for Mn XAS and EELS L2,3 Edges without Reference and Calibration
This provides a calibration-free method for researchers in materials science, particularly for electronic and energy storage applications, though it is incremental as it applies existing deep learning techniques to a specific domain problem.
The study tackled the challenge of accurately decomposing mixed Mn oxidation states from XAS and EELS spectra without needing reference measurements, by developing a deep learning model trained on a physics-informed dataset of 1.2 million spectra, achieving 85% accuracy on validation data and robustness against noise and plural scattering.
Accurate decomposition of the mixed Mn oxidation states is highly important for characterizing the electronic structures, charge transfer, and redox centers for electronic, electrocatalytic, and energy storage materials that contain Mn. Electron energy loss spectroscopy (EELS) and soft X-ray absorption spectroscopy (XAS) measurements of the Mn L2,3 edges are widely used for this purpose. To date, although the measurement of the Mn L2,3 edges is straightforward given the sample is prepared properly, an accurate decomposition of the mix valence states of Mn remains non-trivial. For both EELS and XAS, 2+, 3+, 4+ reference spectra need to be taken on the same instrument/beamline and preferably in the same experimental session because the instrumental resolution and the energy axis offset could vary from one session to another. To circumvent this hurdle, in this study, we adopted a deep learning approach and developed a calibration-free and reference-free method to decompose the oxidation state of Mn L2,3 edges for both EELS and XAS. To synthesize physics-informed and ground-truth labeled training datasets, we created a forward model that takes into account plural scattering, instrumentation broadening, noise, and energy axis offset. With that, we created a 1.2 million-spectrum database with a three-element oxidation state composition label. The library includes a sufficient variety of data including both EELS and XAS spectra. By training on this large database, our convolutional neural network achieves 85% accuracy on the validation dataset. We tested the model and found it is robust against noise (down to PSNR of 10) and plural scattering (up to t/λ = 1). We further validated the model against spectral data that were not used in training.