Decoding the shift-invariant data: applications for band-excitation scanning probe microscopy

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 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.

[1]  U. Hartmann.  Magnetic force microscopy , 1990 .

[2]  Sergei V. Kalinin,et al.  Deep data analysis via physically constrained linear unmixing: universal framework, domain examples, and a community-wide platform , 2018, Advanced Structural and Chemical Imaging.

[3]  Guillaume Desjardins,et al.  Understanding disentangling in $\beta$-VAE , 2018, 1804.03599.

[4]  Stephen Jesse,et al.  Principal component and spatial correlation analysis of spectroscopic-imaging data in scanning probe microscopy , 2009, Nanotechnology.

[5]  Sergei V. Kalinin,et al.  Bayesian inference in band excitation scanning probe microscopy for optimal dynamic model selection in imaging , 2020, 2002.08391.

[6]  Stephen Jesse,et al.  Band excitation in scanning probe microscopy: sines of change , 2011 .

[7]  John H. Davis,et al.  Noncontact scanning probe microscope potentiometry of surface charge patches: Origin and interpretation of time-dependent signals , 1998 .

[8]  Sergei V. Kalinin,et al.  Resolution theory, and static and frequency-dependent cross-talk in piezoresponse force microscopy , 2010, Nanotechnology.

[9]  Gerber,et al.  Atomic Force Microscope , 2020, Definitions.

[10]  Sergei V. Kalinin,et al.  Off-the-shelf deep learning is not enough, and requires parsimony, Bayesianity, and causality , 2021, npj Computational Materials.

[11]  O. Vatel,et al.  Kelvin probe force microscopy for potential distribution measurement of semiconductor devices , 1995 .

[12]  A. Gruverman,et al.  Scanning force microscopy of domain structure in ferroelectric thin films: Imaging and control , 1997 .

[13]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[14]  Amit Kumar,et al.  Measuring oxygen reduction/evolution reactions on the nanoscale. , 2011, Nature chemistry.

[15]  A. Tagantsev,et al.  Suppressed polar distortion with enhanced Curie temperature in in-plane 90°-domain structure of a-axis oriented PbTiO3 Film , 2015 .

[16]  A. Gruverman,et al.  Nanoscale visualization and control of ferroelectric domains by atomic force microscopy. , 1995, Physical review letters.

[17]  Sergei V. Kalinin,et al.  Probing charge screening dynamics and electrochemical processes at the solid–liquid interface with electrochemical force microscopy , 2014, Nature Communications.

[18]  Maxim Ziatdinov,et al.  Toward Decoding the Relationship between Domain Structure and Functionality in Ferroelectrics via Hidden Latent Variables. , 2021, ACS applied materials & interfaces.

[19]  H. K. Wickramasinghe,et al.  Kelvin probe force microscopy , 1991 .

[20]  Sergei V. Kalinin,et al.  Electromechanical Imaging and Spectroscopy of Ferroelectric and Piezoelectric Materials: State of the Art and Prospects for the Future , 2009 .

[21]  Sergei V. Kalinin,et al.  Half-harmonic Kelvin probe force microscopy with transfer function correction , 2012 .

[22]  Ute Rabe,et al.  Acoustic microscopy by atomic force microscopy , 1994 .

[23]  Bernhard Schölkopf,et al.  Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations , 2018, ICML.

[24]  O. Vatel,et al.  Kelvin probe force microscopy for characterization of semiconductor devices and processes , 1996 .

[25]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[26]  Stephen Jesse,et al.  The band excitation method in scanning probe microscopy for rapid mapping of energy dissipation on the nanoscale , 2007, 0708.4248.

[27]  Stephen Jesse,et al.  G-mode magnetic force microscopy: Separating magnetic and electrostatic interactions using big data analytics , 2016 .

[28]  W. Arnold,et al.  High-frequency response of atomic-force microscope cantilevers , 1997 .

[29]  Stephen Jesse,et al.  Open-loop band excitation Kelvin probe force microscopy , 2012, Nanotechnology.

[30]  Stephen Jesse,et al.  Space- and time-resolved mapping of ionic dynamic and electroresistive phenomena in lateral devices. , 2013, ACS nano.