Decoding the shift-invariant data: applications for band-excitation scanning probe microscopy
This work addresses the challenge of analyzing shift-invariant spectral data for researchers in scanning probe microscopy and related fields, offering a universal method applicable to various spectroscopic techniques, though it appears incremental as it builds on existing VAE frameworks.
The authors tackled the problem of analyzing spectral data with parameter axis shifts by developing a shift-invariant variational autoencoder (shift-VAE), which disentangles shifts from other latent variables and was validated on synthetic data to match ground truth parameters. They applied it to band-excitation piezoresponse force microscopy (BE-PFM) data, achieving model-free unsupervised disentanglement of resonance frequency shifts from peak shape parameters, with extensions for denoising and dimensionality reduction.
A shift-invariant variational autoencoder (shift-VAE) is developed as an unsupervised method for the analysis of spectral data in the presence of shifts along the parameter axis, disentangling the physically-relevant shifts from other latent variables. Using synthetic data sets, we show that the shift-VAE latent variables closely match the ground truth parameters. The shift VAE is extended towards the analysis of band-excitation piezoresponse force microscopy (BE-PFM) data, disentangling the resonance frequency shifts from the peak shape parameters in a model-free unsupervised manner. The extensions of this approach towards denoising of data and model-free dimensionality reduction in imaging and spectroscopic data are further demonstrated. This approach is universal and can also be extended to analysis of X-ray diffraction, photoluminescence, Raman spectra, and other data sets.