Deep neural networks for understanding noisy data applied to physical property extraction in scanning probe microscopy

Nikolay Borodinov, Sabine Neumayer, Sergei V. Kalinin, Olga S. Ovchinnikova, Rama K. Vasudevan, Stephen Jesse

Research output: Contribution to journalArticlepeer-review

55 Scopus citations

Abstract

The rapid development of spectral-imaging methods in scanning probe, electron, and optical microscopy in the last decade have given rise for large multidimensional datasets. In many cases, the reduction of hyperspectral data to the lower-dimension materials-specific parameters is based on functional fitting, where an approximate form of the fitting function is known, but the parameters of the function need to be determined. However, functional fits of noisy data realized via iterative methods, such as least-square gradient descent, often yield spurious results and are very sensitive to initial guesses. Here, we demonstrate an approach for the reduction of the hyperspectral data using a deep neural network approach. A combined deep neural network/least-square approach is shown to improve the effective signal-to-noise ratio of band-excitation piezoresponse force microscopy by more than an order of magnitude, allowing characterization when very small driving signals are used or when a material’s response is weak.

Original languageEnglish
Article number25
Journalnpj Computational Materials
Volume5
Issue number1
DOIs
StatePublished - Dec 1 2019

Funding

This research was conducted at the Center for Nanophase Materials Sciences, which is a DOE Office of Science User facility. Data analysis effort (NB, RKV, SJ) was sponsored by the Laboratory Directed Research and Development Program (as a part of the AI Initiative) of Oak Ridge National Laboratory, managed by UT-Battelle, LLC, for the U.S. Department of Energy (DOE). This research used resources of the Compute and Data Environment for Science (CADES) at the Oak Ridge National Laboratory, which is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC05-00OR22725

Fingerprint

Dive into the research topics of 'Deep neural networks for understanding noisy data applied to physical property extraction in scanning probe microscopy'. Together they form a unique fingerprint.

Cite this