arXiv subjects

Rama K. Vasudevan

Publications and source records attributed to Rama K. Vasudevan.

At least 55 records · Page 3Linked to original sources

arXiv2020

Deep Bayesian Local Crystallography

The advent of high-resolution electron and scanning probe microscopy imaging has opened the floodgates for acquiring atomically resolved images of bulk materials, 2D materials, and surfaces. This plethora of data contains an immense volume of information on materials structures, structural distortions, and physical functionalities. Harnessing this knowledge regarding local physical phenomena necessitates the development of the mathematical frameworks for extraction of relevant information. However, the analysis of atomically resolved images is often based on the adaptation of concepts from macroscopic physics, notably translational and point group symmetries and symmetry lowering phenomena. Here, we explore the bottom-up definition of structural units and symmetry in atomically resolved data using a Bayesian framework. We demonstrate the need for a Bayesian definition of symmetry using a simple toy model and demonstrate how this definition can be extended to the experimental data using deep learning networks in a Bayesian setting, namely rotationally invariant variational autoencoders.

physics.comp-ph↗

arXiv2020

Guided search for desired functional responses via Bayesian optimization of generative model: Hysteresis loop shape engineering in ferroelectrics

Advances in predictive modeling across multiple disciplines have yielded generative models capable of high veracity in predicting macroscopic functional responses of materials. Correspondingly, of interest is the inverse problem of finding the model parameter that will yield desired macroscopic responses, such as stress-strain curves, ferroelectric hysteresis loops, etc. Here we suggest and implement a Gaussian Process based methods that allow to effectively sample the degenerate parameter space of a complex non-local model to output regions of parameter space which yield desired functionalities. We discuss the specific adaptation of the acquisition function and sampling function to make the process efficient and balance the efficient exploration of parameter space for multiple possible minima and exploitation to densely sample the regions of interest where target behaviors are optimized. This approach is illustrated via the hysteresis loop engineering in ferroelectric materials, but can be adapted to other functionalities and generative models. The code is open-sourced and available at [github.com/ramav87/Ferrosim].

cond-mat.dis-nn↗

arXiv2020

Super-resolution and signal separation in contact Kelvin probe force microscopy of electrochemically active ferroelectric materials

Imaging mechanisms in contact Kelvin Probe Force Microscopy (cKPFM) are explored via information theory-based methods. Gaussian Processes are used to achieve super-resolution in the cKPFM signal, effectively extrapolating across the spatial and parameter space. Tensor matrix factorization is applied to reduce the multidimensional signal to the tensor convolution of the scalar functions that show clear trending behavior with the imaging parameters. These methods establish a workflow for the analysis of the multidimensional data sets, that can then be related to the relevant physical mechanisms. We also provide an interactive Google Colab notebook (http://bit.ly/39kMtuR) that goes through all the analysis discussed in the paper.

physics.app-ph↗

arXiv2020

Exploration of lattice Hamiltonians for functional and structural discovery via Gaussian Process-based Exploration-Exploitation

Statistical physics models ranging from simple lattice to complex quantum Hamiltonians are one of the mainstays of modern physics, that have allowed both decades of scientific discovery and provided a universal framework to understand a broad range of phenomena from alloying to frustrated and phase-separated materials to quantum systems. Traditionally, exploration of the phase diagrams corresponding to multidimensional parameter spaces of Hamiltonians was performed using a combination of basic physical principles, analytical approximations, and extensive numerical modeling. However, exploration of complex multidimensional parameter spaces is subject to the classic dimensionality problem, and the behaviors of interest concentrated on low dimensional manifolds can remain undiscovered. Here, we demonstrate that a combination of exploration and exploration-exploitation with Gaussian process modeling and Bayesian optimization allows effective exploration of the parameter space for lattice Hamiltonians, and effectively maps the regions at which specific macroscopic functionalities or local structures are maximized. We argue that this approach is general and can be further extended well beyond the lattice Hamiltonians to effectively explore parameter space of more complex off-lattice and dynamic models.

cond-mat.mtrl-sci↗

arXiv2020

Application of variational policy gradient to atomic-scale materials synthesis

Atomic-scale materials synthesis via layer deposition techniques present a unique opportunity to control material structures and yield systems that display unique functional properties that cannot be stabilized using traditional bulk synthetic routes. However, the deposition process itself presents a large, multidimensional space that is traditionally optimized via intuition and trial and error, slowing down progress. Here, we present an application of deep reinforcement learning to a simulated materials synthesis problem, utilizing the Stein variational policy gradient (SVPG) approach to train multiple agents to optimize a stochastic policy to yield desired functional properties. Our contributions are (1) A fully open source simulation environment for layered materials synthesis problems, utilizing a kinetic Monte-Carlo engine and implemented in the OpenAI Gym framework, (2) Extension of the Stein variational policy gradient approach to deal with both image and tabular input, and (3) Developing a parallel (synchronous) implementation of SVPG using Horovod, distributing multiple agents across GPUs and individual simulation environments on CPUs. We demonstrate the utility of this approach in optimizing for a material surface characteristic, surface roughness, and explore the strategies used by the agents as compared with a traditional actor-critic (A2C) baseline. Further, we find that SVPG stabilizes the training process over traditional A2C. Such trained agents can be useful to a variety of atomic-scale deposition techniques, including pulsed laser deposition and molecular beam epitaxy, if the implementation challenges are addressed.

physics.comp-ph↗

arXiv2020

Investigating phase transitions from local crystallographic analysis based on machine learning of atomic environments

Traditionally, phase transitions are explored using a combination of macroscopic functional characterization and scattering techniques, providing insight into average properties and symmetries of the lattice but local atomic level mechanisms during phase transitions generally remain unknown. Here we explore the mechanisms of a phase transition between the trigonal prismatic and distorted octahedral phases of layered chalogenides in the MoS2 ReS2 system from the observations of local degrees of freedom, namely atomic positions by Scanning Transmission Electron Microscopy (STEM). We employ local crystallographic analysis based on machine learning of atomic environments to build a picture of the transition from the atomic level up and determine local and global variables controlling the local symmetry breaking. In particular, we argue that the dependence of the average symmetry breaking distortion amplitude on global and local concentration can be used to separate local chemical and global electronic effects on transition. This approach allows exploring atomic mechanisms beyond the traditional macroscopic descriptions, utilizing the imaging of compositional fluctuations in solids to explore phase transitions over a range of realized and observed local stoichiometries and atomic configurations.

cond-mat.mtrl-sci↗

arXiv2020

Gaussian process analysis of Electron Energy Loss Spectroscopy (EELS) data: parallel reconstruction and kernel control

Advances in hyperspectral imaging modes including electron energy loss spectroscopy (EELS) in scanning transmission electron microscopy (STEM) bring forth the challenges of exploratory and subsequently physics-based analysis of multidimensional data sets. The (by now common) multivariate unsupervised linear unmixing methods and their nonlinear analogs generally explore similarities in the energy dimension but ignore correlations in the spatial domain. At the same time, Gaussian process (GP) methods that explicitly incorporate spatial correlations in the form of kernel functions tend to be extremely computationally intensive, while the use of inducing point-based sparse methods often leads to reconstruction artefacts. Here, we suggest and implement a parallel GP method operating on the full spatial domain and reduced representations in the energy domain. In this parallel GP, the information between the components is shared via a common spatial kernel structure while allowing for variability in the relative noise magnitude or image morphology. We explore the role of common spatial structures and kernel constraints on the quality of the reconstruction and suggest an approach for estimating these factors from the experimental data. Application of this method to an example EELS dataset demonstrates that spatial information contained in higher-order components can be reconstructed and spatially localized. This approach can be further applied to other hyperspectral and multimodal imaging modes. The notebooks developed in this manuscript are freely available as part of a GPim package (https://github.com/ziatdinovmax/GPim).

physics.comp-ph↗

arXiv2020

Off-the-shelf deep learning is not enough: parsimony, Bayes and causality

Deep neural networks ("deep learning") have emerged as a technology of choice to tackle problems in natural language processing, computer vision, speech recognition and gameplay, and in just a few years has led to superhuman level performance and ushered in a new wave of "AI." Buoyed by these successes, researchers in the physical sciences have made steady progress in incorporating deep learning into their respective domains. However, such adoption brings substantial challenges that need to be recognized and confronted. Here, we discuss both opportunities and roadblocks to implementation of deep learning within materials science, focusing on the relationship between correlative nature of machine learning and causal hypothesis driven nature of physical sciences. We argue that deep learning and AI are now well positioned to revolutionize fields where causal links are known, as is the case for applications in theory. When confounding factors are frozen or change only weakly, this leaves open the pathway for effective deep learning solutions in experimental domains. Similarly, these methods offer a pathway towards understanding the physics of real-world systems, either via deriving reduced representations, deducing algorithmic complexity, or recovering generative physical models. However, extending deep learning and "AI" for models with unclear causal relationship can produce misleading and potentially incorrect results. Here, we argue the broad adoption of Bayesian methods incorporating prior knowledge, development of DL solutions with incorporated physical constraints, and ultimately adoption of causal models, offers a path forward for fundamental and applied research. Most notably, while these advances can change the way science is carried out in ways we cannot imagine, machine learning is not going to substitute science any time soon.

physics.comp-ph↗

arXiv2020

Fast Scanning Probe Microscopy via Machine Learning: Non-rectangular scans with compressed sensing and Gaussian process optimization

Fast scanning probe microscopy enabled via machine learning allows for a broad range of nanoscale, temporally resolved physics to be uncovered. However, such examples for functional imaging are few in number. Here, using piezoresponse force microscopy (PFM) as a model application, we demonstrate a factor of 5.8 improvement in imaging rate using a combination of sparse spiral scanning with compressive sensing and Gaussian processing reconstruction. It is found that even extremely sparse scans offer strong reconstructions with less than 6 % error for Gaussian processing reconstructions. Further, we analyze the error associated with each reconstructive technique per reconstruction iteration finding the error is similar past approximately 15 iterations, while at initial iterations Gaussian processing outperforms compressive sensing. This study highlights the capabilities of reconstruction techniques when applied to sparse data, particularly sparse spiral PFM scans, with broad applications in scanning probe and electron microscopies.

cond-mat.mtrl-sci↗

arXiv2020

Deep learning of interface structures from the 4D STEM data: cation intermixing vs. roughening

Interface structures in complex oxides remain one of the active areas of condensed matter physics research, largely enabled by recent advances in scanning transmission electron microscopy (STEM). Yet the nature of the STEM contrast in which the structure is projected along the given direction precludes separation of possible structural models. Here, we utilize deep convolutional neural networks (DCNN) trained on simulated 4D scanning transmission electron microscopy (STEM) datasets to predict structural descriptors of interfaces. We focus on the widely studied interface between LaAlO3 and SrTiO3, using dynamical diffraction theory and leveraging high performance computing to simulate thousands of possible 4D STEM datasets to train the DCNN to learn properties of the underlying structures on which the simulations are based. We validate the DCNN on simulated data and show that it is possible (with >95% accuracy) to identify a physically rough from a chemically diffuse interface and achieve 85% accuracy in determination of buried step positions within the interface. The method shown here is general and can be applied for any inverse imaging problem where forward models are present.

cond-mat.mes-hall↗

arXiv2020

Bayesian inference in band excitation Scanning Probe Microscopy for optimal dynamic model selection in imaging

The universal tendency in scanning probe microscopy (SPM) over the last two decades is to transition from simple 2D imaging to complex detection and spectroscopic imaging modes. The emergence of complex SPM engines brings forth the challenge of reliable data interpretation, i.e. conversion from detected signal to descriptors specific to tip-surface interactions and subsequently to materials properties. Here, we implemented a Bayesian inference approach for the analysis of the image formation mechanisms in band excitation (BE) SPM. Compared to the point estimates in classical functional fit approaches, Bayesian inference allows for the incorporation of extant knowledge of materials and probe behavior in the form of corresponding prior distribution and return the information on the material functionality in the form of readily interpretable posterior distributions. We note that in application of Bayesian methods, special care should be made for proper setting on the problem as model selection vs. establishing practical parameter equivalence. We further explore the non-linear mechanical behaviors at topological defects in a classical ferroelectric material, PbTiO3. We observe the non-trivial evolution of Duffing resonance frequency and the nonlinearity of the sample surface, suggesting the presence of the hidden elements of domain structure. These observations suggest that the spectrum of anomalous behaviors at the ferroelectric domain walls can be significantly broader than previously believed and can extend to non-conventional mechanical properties in addition to static and microwave conductance.

physics.comp-ph↗

arXiv2020

Reconstruction of the lattice Hamiltonian models from the observations of microscopic degrees of freedom in the presence of competing interactions

The emergence of scanning probe and electron beam imaging techniques have allowed quantitative studies of atomic structure and minute details of electronic and vibrational structure on the level of individual atomic units. These microscopic descriptors in turn can be associated with the local symmetry breaking phenomena, representing stochastic manifestation of underpinning generative physical model. Here, we explore the reconstruction of exchange integrals in the Hamiltonian for the lattice model with two competing interactions from the observations of the microscopic degrees of freedom and establish the uncertainties and reliability of such analysis in a broad parameter-temperature space. As an ancillary task, we develop a machine learning approach based on histogram clustering to predict phase diagrams efficiently using a reduced descriptor space. We further demonstrate that reconstruction is possible well above the phase transition and in the regions of the parameter space when the macroscopic ground state of the system is poorly defined due to frustrated interactions. This suggests that this approach can be applied to the traditionally complex problems of condensed matter physics such as ferroelectric relaxors and morphotropic phase boundary systems, spin and cluster glasses, quantum systems once the local descriptors linked to the relevant physical behaviors are known.

cond-mat.stat-mech↗

arXiv2020

Dynamic manipulation in piezoresponse force microscopy: creating non-equilibrium phases with large electromechanical response

Domains walls and topological defects in ferroelectric materials have emerged as a powerful new paradigm for functional electronic devices including memory and logic. Similarly, wall interactions and dynamics underpin a broad range of mesoscale phenomena ranging from giant electromechanical responses to memory effects. Exploring the functionalities of individual domain walls, their interactions, and controlled modifications of the domain structures is crucial for applications and fundamental physical studies. However, the dynamic nature of these features severely limits studies of their local physics since application of local biases or pressures in piezoresponse force microscopy induce wall displacement as a primary response. Here, we introduce a fundamentally new approach for the control and modification of domain structures based on automated experimentation whereby real space image-based feedback is used to control the tip bias during ferroelectric switching, allowing for modification routes conditioned on domain states under the tip. This automated experiment approach is demonstrated for the exploration of domain wall dynamics and creation of metastable phases with large electromechanical response.

cond-mat.mes-hall↗

arXiv2019

Imaging Mechanism for Hyperspectral Scanning Probe Microscopy via Gaussian Process Modelling

We investigate the ability to reconstruct and derive spatial structure from sparsely sampled 3D piezoresponse force microcopy data, captured using the band-excitation (BE) technique, via Gaussian Process (GP) methods. Even for weakly informative priors, GP methods allow unambiguous determination of the characteristic length scales of the imaging process both in spatial and frequency domains. We further show that BE data set tends to be oversampled, with ~30% of the original data set sufficient for high-quality reconstruction, potentially enabling the faster BE imaging. Finally, we discuss how the GP can be used for automated experimentation in SPM, by combining GP regression with non-rectangular scans. The full code for GP regression applied to hyperspectral data is available at https://git.io/JePGr.

physics.comp-ph↗

arXiv2019

Inversion of lattice models from the observations of microscopic degrees of freedom: parameter estimation with uncertainty quantification

Experimental advances in condensed matter physics and material science have enabled ready access to atomic-resolution images, with resolution of modern tools often sufficient to extract minute details of symmetry-breaking distortions such as polarization, octahedra tilts, or other structure-coupled order parameters. The patterns of observed distortions in turn contain the information on microscopic driving forces defining the development of materials microstructure and associated thermodynamics. However, the analysis of underpinning physical models from experimentally observed microscopic degrees of freedom remains a largely unresolved issue. Here, we explore such an approach using the paradigmatic Ising model on a square lattice. We show that the microscopic parameters of the Ising model both for ferromagnetic and antiferromagnetic case can be extracted from the spin configurations for temperatures an order of magnitude higher than the phase transition and perform uncertainty analysis for such reconstructions. This suggests that microscopic observations of materials with sufficiently high precision can provide information on generative physics at temperatures well above corresponding phase transition, opening new horizons for scientific exploration via high-resolution imaging.

cond-mat.stat-mech↗

arXiv2019

Order and randomness in dopant distributions: exploring the thermodynamics of solid solutions from atomically resolved imaging

Exploration of structure-property relationships as a function of dopant concentration is commonly based on mean field theories for solid solutions. However, such theories that work well for semiconductors tend to fail in materials with strong correlations, either in electronic behavior or chemical segregation. In these cases, the details of atomic arrangements are generally not explored and analyzed. The knowledge of the generative physics and chemistry of the material can obviate this problem, since defect configuration libraries as stochastic representation of atomic level structures can be generated, or parameters of mesoscopic thermodynamic models can be derived. To obtain such information for improved predictions, we use data from atomically resolved microscopic images that visualize complex structural correlations within the system and translate them into statistical mechanical models of structure formation. Given the significant uncertainties about the microscopic aspects of the material's processing history along with the limited number of available images, we combine model optimization techniques with the principles of statistical hypothesis testing. We demonstrate the approach on data from a series of atomically-resolved scanning transmission electron microscopy images of Mo$_x$Re$_{1-x}$S$_2$ at varying ratios of Mo/Re stoichiometries, for which we propose an effective interaction model that is then used to generate atomic configurations and make testable predictions at a range of concentrations and formation temperatures.

cond-mat.mtrl-sci↗

arXiv2019

USID and Pycroscopy -- Open frameworks for storing and analyzing spectroscopic and imaging data

Materials science is undergoing profound changes due to advances in characterization instrumentation that have resulted in an explosion of data in terms of volume, velocity, variety and complexity. Harnessing these data for scientific research requires an evolution of the associated computing and data infrastructure, bridging scientific instrumentation with super- and cloud- computing. Here, we describe Universal Spectroscopy and Imaging Data (USID), a data model capable of representing data from most common instruments, modalities, dimensionalities, and sizes. We pair this schema with the hierarchical data file format (HDF5) to maximize compatibility, exchangeability, traceability, and reproducibility. We discuss a family of community-driven, open-source, and free python software packages for storing, processing and visualizing data. The first is pyUSID which provides the tools to read and write USID HDF5 files in addition to a scalable framework for parallelizing data analysis. The second is Pycroscopy, which provides algorithms for scientific analysis of nanoscale imaging and spectroscopy modalities and is built on top of pyUSID and USID. The instrument-agnostic nature of USID facilitates the development of analysis code independent of instrumentation and task in Pycroscopy which in turn can bring scientific communities together and break down barriers in the age of open-science. The interested reader is encouraged to be a part of this ongoing community-driven effort to collectively accelerate materials research and discovery through the realms of big data.

physics.data-an↗

arXiv2019

Building and exploring libraries of atomic defects in graphene: scanning transmission electron and scanning tunneling microscopy study

Population and distribution of defects is one of the primary parameters controlling materials functionality, are often non-ergodic and strongly dependent on synthesis history, and are rarely amenable to direct theoretical prediction. Here, dynamic electron beam-induced transformations in Si deposited on a graphene monolayer are used to create libraries of the possible Si and carbon vacancy defects. Automated image analysis and recognition based on deep learning networks is developed to identify and enumerate the defects, creating a library of (meta) stable defect configurations. The electronic properties of the sample surface are further explored by atomically resolved scanning tunneling microscopy (STM). Density functional theory is used to estimate the STM signatures of the classified defects from the created library, allowing for the identification of several defect types across the imaging platforms. This approach allows automatic creation of defect libraries in solids, exploring the metastable configurations always present in real materials, and correlative studies with other atomically-resolved techniques, providing comprehensive insight into defect functionalities. Such libraries will be of critical importance in automated AI-assisted workflows for materials prediction and atom-by atom manipulation via electron beams and scanning probes.

cond-mat.mtrl-sci↗