Predictability as a probe of manifest and latent physics: The case of atomic scale structural, chemical, and polarization behaviors in multiferroic Sm-doped BiFeO3

Machine learning and artificial intelligence (ML/AI) are rapidly becoming an indispensable part of physics research, with domain applications ranging from theory and materials prediction to high-throughput data analysis. In parallel, the recent successes in applying ML/AI methods for autonomous systems from robotics through self-driving cars to organic and inorganic synthesis are generating enthusiasm for the potential of these techniques to enable automated and autonomous experiment (AE) in imaging. Here, we aim to analyze the major pathways towards AE in imaging methods with sequential image formation mechanisms, focusing on scanning probe microscopy (SPM) and (scanning) transmission electron microscopy ((S)TEM). We argue that automated experiments should necessarily be discussed in a broader context of the general domain knowledge that both informs the experiment and is increased as the result of the experiment. As such, this analysis should explore the human and ML/AI roles prior to and during the experiment, and consider the latencies, biases, and knowledge priors of the decision-making process. Similarly, such discussion should include the limitations of the existing imaging systems, including intrinsic latencies, non-idealities and drifts comprising both correctable and stochastic components. We further pose that the role of the AE in microscopy is not the exclusion of human operators (as is the case for autonomous driving), but rather automation of routine operations such as microscope tuning, etc., prior to the experiment, and conversion of low latency decision making processes on the time scale spanning from image acquisition to human-level high-order experiment planning. Overall, we argue that ML/AI can dramatically alter the (S)TEM and SPM fields; however, this process is likely to be highly nontrivial, be initiated by combined human-ML workflows, and will bring new challenges both from the microscope and ML/AI sides. At the same time, these methods will enable fundamentally new opportunities and paradigms for scientific discovery and nanostructure fabrication.

show abstract

Section: General Considerationsmentioning

confidence: 99%

Automated and Autonomous Experiments in Electron and Scanning Probe Microscopy

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…The error map for full data sets in Figure a is relatively structureless and does not show similarity to the original domain structure or the PCA loading maps, suggesting that the im2spec network captures the relationship between the domain structure and the local hysteresis behavior well on average. Note that the regions with strong deviations from the network prediction can be considered as locations where novel physical behaviors can emerge, as was proposed earlier …”

Section: Resultsmentioning

confidence: 97%

“…Note that the regions with strong deviations from the network prediction can be considered as locations where novel physical behaviors can emerge, as was proposed earlier. 69 The comparison of the predicted and ground truth hysteresis loops shown in Figure 4a−d. Here, the left column shows the chosen subimages representing easily recognizable elements of the domain structure, namely, the domain walls at different separation from the location at which the hysteresis loop is acquired (image center). The central column compares the predicted hysteresis loops to the experimentally measured ones.…”

Section: ■ Results and Discussionmentioning

confidence: 99%

Toward Decoding the Relationship between Domain Structure and Functionality in Ferroelectrics via Hidden Latent Variables

Kalinin

Kelley

Vasudevan

et al. 2021

ACS Appl. Mater. Interfaces

Self Cite

View full text Add to dashboard Cite

Polarization switching mechanisms in ferroelectric materials are fundamentally linked to local domain structure and the presence of the structural defects, which both can act as nucleation and pinning centers and create local electrostatic and mechanical depolarization fields affecting wall dynamics. However, the general correlative mechanisms between domain structure and polarization dynamics are only weakly explored, precluding insight into the associated physical mechanisms. Here, the correlation between local domain structures and switching behavior in ferroelectric materials is explored using convolutional encoder–decoder networks, enabling image to spectral (im2spec) and spectral to image (spec2im) translations via encoding of latent variables. The latter reflect the assumption that the relationship between domain structure and polarization switching is parsimonious, i.e., is based upon a small number of local mechanisms. The analysis of latent variables distributions and their real-space representations provides insight into the predictability of the local switching behavior and hence associated physical mechanisms. We further pose that the regions where these correlative relationships are violated, i.e., predictability of the polarization dynamics from domain structure is reduced, represent the obvious target for detailed studies, e.g., in the context of automated experiments. This approach provides a workflow to establish the presence of correlation between local spectral responses and local structure and can be universally applied to spectral imaging techniques such as piezoresponse force microscopy (PFM), scanning tunneling microscopy (STM) and spectroscopy, and electron energy loss spectroscopy (EELS) in scanning transmission electron microscopy (STEM).

show abstract

“…As a static data set, presented in figure 1, we chose high-angle annular dark-field images of various materials which each contain different feature lengths. The dataset includes: NiO pillars in a La:SrMnO 3 (NiO-LSMO) matrix [49][50][51], sample of BiFeO 3 (BFO) [52][53][54] and Si-containing graphene [55,56]. Each of these images contain different information of interest, such as domain walls, defects, and dopants.…”

Section: Methodsmentioning

confidence: 99%

“…particle and grain boundary finding, determination of the ferroelectric domain walls, etc, allowing for generalization of this approach towards other (prior known) objects of interest. Furthermore, the training of the DCNNs is done for a specific target (type of lattice) and more details on the training of neural networks and their adaptation to new data can be found in works by Ghosh and Ziatdinov [52,57,58].…”

Section: Methodsmentioning

confidence: 99%

Towards automating structural discovery in scanning transmission electron microscopy ^*

Creange

Dyck

Vasudevan

et al. 2022

Mach. Learn.: Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Scanning transmission electron microscopy (STEM) is now the primary tool for exploring functional materials on the atomic level. Often, features of interest are highly localized in specific regions in the material, such as ferroelectric domain walls, extended defects, or second phase inclusions. Selecting regions to image for structural and chemical discovery via atomically resolved imaging has traditionally proceeded via human operators making semi-informed judgements on sampling locations and parameters. Recent efforts at automation for structural and physical discovery have pointed towards the use of ‘active learning’ methods that utilize Bayesian optimization with surrogate models to quickly find relevant regions of interest. Yet despite the potential importance of this direction, there is a general lack of certainty in selecting relevant control algorithms and how to balance a priori knowledge of the material system with knowledge derived during experimentation. Here we address this gap by developing the automated experiment workflows with several combinations to both illustrate the effects of these choices and demonstrate the tradeoffs associated with each in terms of accuracy, robustness, and susceptibility to hyperparameters for structural discovery. We discuss possible methods to build descriptors using the raw image data and deep learning based semantic segmentation, as well as the implementation of variational autoencoder based representation. Furthermore, each workflow is applied to a range of feature sizes including NiO pillars within a La:SrMnO3 matrix, ferroelectric domains in BiFeO3, and topological defects in graphene. The code developed in this manuscript are open sourced and will be released at github.com/creangnc/AE_Workflows.

show abstract

Predictability as a probe of manifest and latent physics: The case of atomic scale structural, chemical, and polarization behaviors in multiferroic Sm-doped BiFeO3

Cited by 8 publications

References 84 publications

Automated and Autonomous Experiments in Electron and Scanning Probe Microscopy

Automated and Autonomous Experiments in Electron and Scanning Probe Microscopy

Toward Decoding the Relationship between Domain Structure and Functionality in Ferroelectrics via Hidden Latent Variables

Towards automating structural discovery in scanning transmission electron microscopy ^*

Contact Info

Product

Resources

About

Predictability as a probe of manifest and latent physics: The case of atomic scale structural, chemical, and polarization behaviors in multiferroic Sm-doped BiFeO3

Cited by 8 publications

References 84 publications

Automated and Autonomous Experiments in Electron and Scanning Probe Microscopy

Automated and Autonomous Experiments in Electron and Scanning Probe Microscopy

Toward Decoding the Relationship between Domain Structure and Functionality in Ferroelectrics via Hidden Latent Variables

Towards automating structural discovery in scanning transmission electron microscopy *

Contact Info

Product

Resources

About

Towards automating structural discovery in scanning transmission electron microscopy ^*