Over the past several decades, electron and scanning probe microscopes have become critical components of condensed matter physics, materials science and chemistry research. At the same time, the infrastructure for establishing a connection between microscopy observations and materials behaviour over a broader parameter space is lacking. In this work, we introduce AtomAI, an open-source software package bridging instrument-specific Python libraries, deep learning and simulation tools into a single ecosystem. AtomAI allows direct applications of deep neural networks for atomic and mesoscopic image segmentation converting image and spectroscopy data into class-based local descriptors for downstream tasks such as statistical and graph analysis. For atomically resolved imaging data, the output is types and positions of atomic species, with an option for subsequent refinement. AtomAI further allows the implementation of a broad range of image and spectrum analysis functions, including invariant variational autoencoders for disentangling structural factors of variation and im2spec type of encoder–decoder models for mapping structure–property relationships. Finally, our framework allows seamless connection to the first principles modelling with a Python interface on the inferred atomic positions.
Ziatdinov, Maxim, et al. "AtomAI framework for deep learning analysis of image and spectroscopy data in electron and scanning probe microscopy." Nature Machine Intelligence, vol. 4, no. 12, Dec. 2022. https://doi.org/10.1038/s42256-022-00555-8
Ziatdinov, Maxim, Ghosh, Ayana, Wong, Chun Yin, & Kalinin, Sergei V. (2022). AtomAI framework for deep learning analysis of image and spectroscopy data in electron and scanning probe microscopy. Nature Machine Intelligence, 4(12). https://doi.org/10.1038/s42256-022-00555-8
Ziatdinov, Maxim, Ghosh, Ayana, Wong, Chun Yin, et al., "AtomAI framework for deep learning analysis of image and spectroscopy data in electron and scanning probe microscopy," Nature Machine Intelligence 4, no. 12 (2022), https://doi.org/10.1038/s42256-022-00555-8
@article{osti_1905426,
author = {Ziatdinov, Maxim and Ghosh, Ayana and Wong, Chun Yin and Kalinin, Sergei V.},
title = {AtomAI framework for deep learning analysis of image and spectroscopy data in electron and scanning probe microscopy},
annote = {Over the past several decades, electron and scanning probe microscopes have become critical components of condensed matter physics, materials science and chemistry research. At the same time, the infrastructure for establishing a connection between microscopy observations and materials behaviour over a broader parameter space is lacking. In this work, we introduce AtomAI, an open-source software package bridging instrument-specific Python libraries, deep learning and simulation tools into a single ecosystem. AtomAI allows direct applications of deep neural networks for atomic and mesoscopic image segmentation converting image and spectroscopy data into class-based local descriptors for downstream tasks such as statistical and graph analysis. For atomically resolved imaging data, the output is types and positions of atomic species, with an option for subsequent refinement. AtomAI further allows the implementation of a broad range of image and spectrum analysis functions, including invariant variational autoencoders for disentangling structural factors of variation and im2spec type of encoder–decoder models for mapping structure–property relationships. Finally, our framework allows seamless connection to the first principles modelling with a Python interface on the inferred atomic positions.},
doi = {10.1038/s42256-022-00555-8},
url = {https://www.osti.gov/biblio/1905426},
journal = {Nature Machine Intelligence},
issn = {ISSN 2522-5839},
number = {12},
volume = {4},
place = {United States},
publisher = {Springer Nature},
year = {2022},
month = {12}}
Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part IIIhttps://doi.org/10.1007/978-3-319-24574-4_28