Forecasting of in situ electron energy loss spectroscopy

Abstract

Forecasting models are a central part of many control systems, where high-consequence decisions must be made on long latency control variables. These models are particularly relevant for emerging artificial intelligence (AI)-guided instrumentation, in which prescriptive knowledge is needed to guide autonomous decision-making. Here we describe the implementation of a long short-term memory model (LSTM) for forecasting in situ electron energy loss spectroscopy (EELS) data, one of the richest analytical probes of materials and chemical systems. We describe key considerations for data collection, preprocessing, training, validation, and benchmarking, showing how this approach can yield powerful predictive insight into order-disorder phase transitions. Finally, we comment on how such a model may integrate with emerging AI-guided instrumentation for powerful high-speed experimentation.

Structural degeneracy and formation of crystallographic domains in epitaxial LaFeO3 films revealed by machine-learning assisted 4D-STEM

“…Both paradigms have demonstrated notable success in data-driven microscopy analyses, with supervised learning excelling in mimicking the intricate neural structure of the human brain and identifying features of interest from microscopy data 29 , 30 . While unsupervised learning ML has proven valuable in exploratory tasks, such as unveiling internal structure and denoising hyperspectral data 31 – 36 .…”

Prediction of Frequency-Dependent Optical Spectrum for Solid Materials: A Multioutput and Multifidelity Machine Learning Approach

“…The dielectric function, a fundamental spectral output from ab initio calculations, determines the material's response to electromagnetic waves. It also enables the calculation of crucial practical frequency-dependent optical properties, such as the refractive index, electron energy loss spectra, 22 quality factors for localized surface plasmon resonances and surface plasmon polaritons, 23 and the quantum efficiency of optical sensors and PV cells. 24 For material spectral properties such as phonon or electronic density of states, the full-energy density of occupied states is characterized by a known integral for each material, attributed to its atom or electron count.…”

“…The dielectric function, a fundamental spectral output from ab initio calculations, determines the material’s response to electromagnetic waves. It also enables the calculation of crucial practical frequency-dependent optical properties, such as the refractive index, electron energy loss spectra, quality factors for localized surface plasmon resonances and surface plasmon polaritons, and the quantum efficiency of optical sensors and PV cells …”

Deep learning for automated materials characterisation in core-loss electron energy loss spectroscopy

“…Unsupervised techniques, like K-means clustering 4 , non-negative matrix factorization 5 , 6 and auto-encoders 7 have been extensively applied in EELS for spectral decomposition. Supervised techniques, like NN and support vector machines, allow for more generic EELS applications like oxidation state determination 8 – 10 , zero-loss peak determination 11 , spectral deconvolution 12 and phase-transition forecasting 13 . NN have also been successfully applied in many techniques similar to EELS like X-ray diffraction 14 , vibrational spectroscopy 15 , X-ray fluorescence spectroscopy 16 , energy-dispersive X-ray spectroscopy 17 and molecular excitation spectroscopy 18 .…”