Disorder identification in hysteresis data: recognition analysis of the random-bond-random-field Ising model

Autonomous scanning probe microscopy with hypothesis learning: Exploring the physics of domain switching in ferroelectric materials

Using hypothesis-learning-driven automated scanning probe microscopy (SPM), we explore the bias-induced transformations that underpin the functionality of broad classes of devices and materials from batteries and memristors to ferroelectrics and antiferroelectrics. Optimization and design of these materials require probing the mechanisms of these transformations on the nanometer scale as a function of a broad range of control parameters, leading to experimentally intractable scenarios. Meanwhile, often these behaviors are understood within potentially competing theoretical hypotheses. Here, we develop a hypothesis list covering possible limiting scenarios for domain growth in ferroelectric materials, including thermodynamic, domain-wall pinning, and screening limited. The hypothesis-driven SPM autonomously identifies the mechanisms of bias-induced domain switching, and the results indicate that domain growth is ruled by kinetic control. We note that the hypothesis learning can be broadly used in other automated experiment settings.

Hierarchical Materials from High Information Content Macromolecular Building Blocks: Construction, Dynamic Interventions, and Prediction

Hierarchical materials that exhibit order over multiple length scales are ubiquitous in nature. Because hierarchy gives rise to unique properties and functions, many have sought inspiration from nature when designing and fabricating hierarchical matter. More and more, however, nature's own high-information content building blocks, proteins, peptides, and peptidomimetics, are being coopted to build hierarchy because the information that determines structure, function, and interfacial interactions can be readily encoded in these versatile macromolecules. Here, we take stock of recent progress in the rational design and characterization of hierarchical materials produced from high-information content blocks with a focus on stimuli-responsive and "smart" architectures. We also review advances in the use of computational simulations and data-driven predictions to shed light on how the side chain chemistry and conformational flexibility of macromolecular blocks drive the emergence of order and the acquisition of hierarchy and also on how ionic, solvent, and surface effects influence the outcomes of assembly. Continued progress in the above areas will ultimately usher in an era where an understanding of designed interactions, surface effects, and solution conditions can be harnessed to achieve predictive materials synthesis across scale and drive emergent phenomena in the self-assembly and reconfiguration of high-information content building blocks.

Extensive deep neural networks for transferring small scale learning to large scale systems

We present a physically-motivated topology of a deep neural network that can efficiently infer extensive parameters (such as energy, entropy, or number of particles) of arbitrarily large systems, doing so with scaling. We use a form of domain decomposition for training and inference, where each sub-domain (tile) is comprised of a non-overlapping focus region surrounded by an overlapping context region. The size of these regions is motivated by the physical interaction length scales of the problem. We demonstrate the application of EDNNs to three physical systems: the Ising model and two hexagonal/graphene-like datasets. In the latter, an EDNN was able to make total energy predictions of a 60 atoms system, with comparable accuracy to density functional theory (DFT), in 57 milliseconds. Additionally EDNNs are well suited for massively parallel evaluation, as no communication is necessary during neural network evaluation. We demonstrate that EDNNs can be used to make an energy prediction of a two-dimensional 35.2 million atom system, over 1.0 μm² of material, at an accuracy comparable to DFT, in under 25 minutes. Such a system exists on a length scale visible with optical microscopy and larger than some living organisms.

Materials Science in the AI age: high-throughput library generation, machine learning and a pathway from correlations to the underpinning physics

The use of advanced data analytics and applications of statistical and machine learning approaches ('AI') to materials science is experiencing explosive growth recently. In this prospective, we review recent work focusing on generation and application of libraries from both experiment and theoretical tools, across length scales. The available library data both enables classical correlative machine learning, and also opens the pathway for exploration of underlying causative physical behaviors. We highlight the key advances facilitated by this approach, and illustrate how modeling, macroscopic experiments and atomic-scale imaging can be combined to dramatically accelerate understanding and development of new material systems via a statistical physics framework. These developments point towards a data driven future wherein knowledge can be aggregated and used collectively, accelerating the advancement of materials science.

Deep neural networks for direct, featureless learning through observation: The case of two-dimensional spin models

We demonstrate the capability of a convolutional deep neural network in predicting the nearest-neighbor energy of the 4×4 Ising model. Using its success at this task, we motivate the study of the larger 8×8 Ising model, showing that the deep neural network can learn the nearest-neighbor Ising Hamiltonian after only seeing a vanishingly small fraction of configuration space. Additionally, we show that the neural network has learned both the energy and magnetization operators with sufficient accuracy to replicate the low-temperature Ising phase transition. We then demonstrate the ability of the neural network to learn other spin models, teaching the convolutional deep neural network to accurately predict the long-range interaction of a screened Coulomb Hamiltonian, a sinusoidally attenuated screened Coulomb Hamiltonian, and a modified Potts model Hamiltonian. In the case of the long-range interaction, we demonstrate the ability of the neural network to recover the phase transition with equivalent accuracy to the numerically exact method. Furthermore, in the case of the long-range interaction, the benefits of the neural network become apparent; it is able to make predictions with a high degree of accuracy, and do so 1600 times faster than a CUDA-optimized exact calculation. Additionally, we demonstrate how the neural network succeeds at these tasks by looking at the weights learned in a simplified demonstration.

Deep data analysis via physically constrained linear unmixing: universal framework, domain examples, and a community-wide platform

Many spectral responses in materials science, physics, and chemistry experiments can be characterized as resulting from the superposition of a number of more basic individual spectra. In this context, unmixing is defined as the problem of determining the individual spectra, given measurements of multiple spectra that are spatially resolved across samples, as well as the determination of the corresponding abundance maps indicating the local weighting of each individual spectrum. Matrix factorization is a popular linear unmixing technique that considers that the mixture model between the individual spectra and the spatial maps is linear. Here, we present a tutorial paper targeted at domain scientists to introduce linear unmixing techniques, to facilitate greater understanding of spectroscopic imaging data. We detail a matrix factorization framework that can incorporate different domain information through various parameters of the matrix factorization method. We demonstrate many domain-specific examples to explain the expressivity of the matrix factorization framework and show how the appropriate use of domain-specific constraints such as non-negativity and sum-to-one abundance result in physically meaningful spectral decompositions that are more readily interpretable. Our aim is not only to explain the off-the-shelf available tools, but to add additional constraints when ready-made algorithms are unavailable for the task. All examples use the scalable open source implementation from https://github.com/ramkikannan/nmflibrary that can run from small laptops to supercomputers, creating a user-wide platform for rapid dissemination and adoption across scientific disciplines.

Unsupervised learning of phase transitions: From principal component analysis to variational autoencoders

We examine unsupervised machine learning techniques to learn features that best describe configurations of the two-dimensional Ising model and the three-dimensional XY model. The methods range from principal component analysis over manifold and clustering methods to artificial neural-network-based variational autoencoders. They are applied to Monte Carlo-sampled configurations and have, a priori, no knowledge about the Hamiltonian or the order parameter. We find that the most promising algorithms are principal component analysis and variational autoencoders. Their predicted latent parameters correspond to the known order parameters. The latent representations of the models in question are clustered, which makes it possible to identify phases without prior knowledge of their existence. Furthermore, we find that the reconstruction loss function can be used as a universal identifier for phase transitions.

Big, Deep, and Smart Data in Scanning Probe Microscopy

Scanning probe microscopy (SPM) techniques have opened the door to nanoscience and nanotechnology by enabling imaging and manipulation of the structure and functionality of matter at nanometer and atomic scales. Here, we analyze the scientific discovery process in SPM by following the information flow from the tip-surface junction, to knowledge adoption by the wider scientific community. We further discuss the challenges and opportunities offered by merging SPM with advanced data mining, visual analytics, and knowledge discovery technologies.

Big data and deep data in scanning and electron microscopies: deriving functionality from multidimensional data sets

The development of electron and scanning probe microscopies in the second half of the twentieth century has produced spectacular images of the internal structure and composition of matter with nanometer, molecular, and atomic resolution. Largely, this progress was enabled by computer-assisted methods of microscope operation, data acquisition, and analysis. Advances in imaging technology in the beginning of the twenty-first century have opened the proverbial floodgates on the availability of high-veracity information on structure and functionality. From the hardware perspective, high-resolution imaging methods now routinely resolve atomic positions with approximately picometer precision, allowing for quantitative measurements of individual bond lengths and angles. Similarly, functional imaging often leads to multidimensional data sets containing partial or full information on properties of interest, acquired as a function of multiple parameters (time, temperature, or other external stimuli). Here, we review several recent applications of the big and deep data analysis methods to visualize, compress, and translate this multidimensional structural and functional data into physically and chemically relevant information.

Microstructure identification via detrended fluctuation analysis of ultrasound signals

We describe an algorithm for simulating ultrasound propagation in random one-dimensional media, mimicking different microstructures by choosing physical properties such as domain sizes and mass densities from probability distributions. By combining a detrended fluctuation analysis (DFA) of the simulated ultrasound signals with tools from the pattern-recognition literature, we build a Gaussian classifier which is able to associate each ultrasound signal with its corresponding microstructure with a very high success rate. Furthermore, we also show that DFA data can be used to train a multilayer perceptron which estimates numerical values of physical properties associated with distinct microstructures.