arXiv subjects

Kamal Choudhary

Publications and source records attributed to Kamal Choudhary.

At least 73 records · Page 4Linked to original sources

arXiv2021

Recent Advances and Applications of Deep Learning Methods in Materials Science

Deep learning (DL) is one of the fastest growing topics in materials data science, with rapidly emerging applications spanning atomistic, image-based, spectral, and textual data modalities. DL allows analysis of unstructured data and automated identification of features. Recent development of large materials databases has fueled the application of DL methods in atomistic prediction in particular. In contrast, advances in image and spectral data have largely leveraged synthetic data enabled by high quality forward models as well as by generative unsupervised DL methods. In this article, we present a high-level overview of deep-learning methods followed by a detailed discussion of recent developments of deep learning in atomistic simulation, materials imaging, spectral analysis, and natural language processing. For each modality we discuss applications involving both theoretical and experimental data, typical modeling approaches with their strengths and limitations, and relevant publicly available software and datasets. We conclude the review with a discussion of recent cross-cutting work related to uncertainty quantification in this field and a brief perspective on limitations, challenges, and potential growth areas for DL methods in materials science. The application of DL methods in materials science presents an exciting avenue for future materials discovery and design.

cond-mat.mtrl-sci↗

arXiv2021

OPTIMADE, an API for exchanging materials data

The Open Databases Integration for Materials Design (OPTIMADE) consortium has designed a universal application programming interface (API) to make materials databases accessible and interoperable. We outline the first stable release of the specification, v1.0, which is already supported by many leading databases and several software packages. We illustrate the advantages of the OPTIMADE API through worked examples on each of the public materials databases that support the full API specification.

cond-mat.mtrl-sci↗

arXiv2021

Uncertainty Prediction for Machine Learning Models of Material Properties

Uncertainty quantification in Artificial Intelligence (AI)-based predictions of material properties is of immense importance for the success and reliability of AI applications in material science. While confidence intervals are commonly reported for machine learning (ML) models, prediction intervals, i.e., the evaluation of the uncertainty on each prediction, are seldomly available. In this work we compare 3 different approaches to obtain such individual uncertainty, testing them on 12 ML-physical properties. Specifically, we investigated using the Quantile loss function, machine learning the prediction intervals directly and using Gaussian Processes. We identify each approachs advantages and disadvantages and end up slightly favoring the modeling of the individual uncertainties directly, as it is the easiest to fit and, in most cases, minimizes over-and under-estimation of the predicted errors. All data for training and testing were taken from the publicly available JARVIS-DFT database, and the codes developed for computing the prediction intervals are available through JARVIS-Tools.

cs.LG↗

arXiv2021

The Joint Automated Repository for Various Integrated Simulations (JARVIS) for data-driven materials design

The Joint Automated Repository for Various Integrated Simulations (JARVIS) is an integrated infrastructure to accelerate materials discovery and design using density functional theory (DFT), classical force-fields (FF), and machine learning (ML) techniques. JARVIS is motivated by the Materials Genome Initiative (MGI) principles of developing open-access databases and tools to reduce the cost and development time of materials discovery, optimization, and deployment. The major features of JARVIS are: JARVIS-DFT, JARVIS-FF, JARVIS-ML, and JARVIS-Tools. To date, JARVIS consists of 40,000 materials and 1 million calculated properties in JARVIS-DFT, 1,500 materials and 110 force-fields in JARVIS-FF, and 25 ML models for material-property predictions in JARVIS-ML, all of which are continuously expanding. JARVIS-Tools provides scripts and workflows for running and analyzing various simulations. We compare our computational data to experiments or high-fidelity computational methods wherever applicable to evaluate error/uncertainty in predictions. In addition to the existing workflows, the infrastructure can support a wide variety of other technologically important applications as part of the data-driven materials design paradigm. The JARVIS datasets and tools are publicly available at the website: https://jarvis.nist.gov .

cond-mat.mtrl-sci↗

arXiv2021

Quantum Computation for Predicting Electron and Phonon Properties of Solids

Quantum chemistry is one of the most promising near-term applications of quantum computers. Quantum algorithms such as variational quantum eigen solver (VQE) and variational quantum deflation (VQD) algorithms have been mainly applied for molecular systems and there is a need to implement such methods for periodic solids. Using Wannier tight-binding Hamiltonian (WTBH) approaches, we demonstrate the application of VQE and VQD to accurately predict both electronic and phonon bandstructure properties of several elemental as well as multi-component solid-state materials. We apply VQE-VQD calculations for 307 spin-orbit coupling based electronic WTBHs and 933 finite-difference based phonon WTBHs. Also, we discuss a workflow for using VQD with lattice Greens function that can be used for solving dynamical mean-field theory problems. The WTBH model solvers can be used for testing other quantum algorithms and models also.

cond-mat.mtrl-sci↗

arXiv2021

Machine learning approaches for feature engineering of the crystal structure: Application to the prediction of the formation energy of cubic compounds

In this study, we present a novel approach along with the needed computational strategies for efficient and scalable feature engineering of the crystal structure in compounds of different chemical compositions. This approach utilizes a versatile and extensible framework for the quantification of a three-dimensional (3-D) voxelized crystal structure in the form of 2-point spatial correlations of multiple atomic attributes and performs principal component analysis to extract the low-dimensional features that could be used to build surrogate models for material properties of interest. An application of the proposed feature engineering framework is demonstrated on a case study involving the prediction of the formation energies of crystalline compounds using two vastly different surrogate model building strategies - local Gaussian process regression and neural networks. Specifically, it is shown that the top 25 features (i.e., principal component scores) identified by the proposed framework serve as good regressors for the formation energy of the crystalline substance for both model building strategies.

cond-mat.mtrl-sci↗

arXiv2021

High-throughput search for magnetic topological materials using spin-orbit spillage, machine-learning and experiments

Magnetic topological insulators and semi-metals have a variety of properties that make them attractive for applications including spintronics and quantum computation, but very few high-quality candidate materials are known. In this work, we use systematic high-throughput density functional theory calculations to identify magnetic topological materials from 40000 three-dimensional materials in the JARVIS-DFT database (https://jarvis.nist.gov/jarvisdft). First, we screen materials with net magnetic moment > 0.5 μB and spin-orbit spillage > 0.25, resulting in 25 insulating and 564 metallic candidates. The spillage acts as a signature of spin-orbit induced band-inversion. Then, we carry out calculations of Wannier charge centers, Chern numbers, anomalous Hall conductivities, surface bandstructures, and Fermi-surfaces to determine interesting topological characteristics of the screened compounds. We also train machine learning models for predicting the spillage, bandgaps, and magnetic moments of new compounds, to further accelerate the screening process. We experimentally synthesize and characterize a few candidate materials to support our theoretical predictions.

cond-mat.mtrl-sci↗

arXiv2020

Predicting Anomalous Quantum Confinement Effect in van der Waals Materials

Materials with van der Waals-bonding are known to exhibit quantum confinement effect, in which the electronic bandgap of the three-dimensional (3D) realization of a material is lower than that of its two-dimensional (2D) counterpart. However, the possibility of an anomalous quantum confinement effect (AQCE) exists, where the bandgap trend is reversed. In this work, we computationally identify materials for which such AQCE occurs. Using density functional theory (DFT), we compute ~1000 OptB88vdW (semi-local functional), ~50 HSE06 and ~50 PBE0 (hybrid functional) bandgaps for bulk and their corresponding monolayers in the JARVIS-DFT database. OptB88vdW identifies 65 AQCE materials, but the hybrid functionals only confirm such finding in 14 cases. Some of the AQCE systems identified through HSE06 and PBE0 are: hydroxides or oxide hydroxide compounds (AlOH2, Mg(OH)2, Mg2H2O3, Ni(OH)2, SrH2O3) as well as Sb-halogen-chalcogenide compounds (SbSBr, SbSeI) and alkali-chalcogenides (RbLiS and RbLiSe). A detailed electronic structure analysis, based on band-structure and projected density of states, shows AQCE is often characterized by lowering of the conduction band in the monolayer and corresponding changes in the pz electronic orbital contribution, with z being the non-periodic direction in the 2D case. We believe our computational results would spur the effort to validate the results experimentally and will have impact on bandgap engineering applications based on low-dimensional materials.

cond-mat.mtrl-sci↗

arXiv2020

Database of Wannier Tight-binding Hamiltonians using High-throughput Density Functional Theory

We develop a computational workflow for high-throughput Wannierization of density functional theory (DFT) based electronic band structure calculations. We apply this workflow to 1771 materials, and we create a database with the resulting Wannier-function based tight binding Hamiltonians (WTBH). We evaluate the accuracy of the WTBHs by comparing the Wannier band structures to directly calculated DFT band structures on both the set of k-points used in the Wannierization as well as independent k-points from high symmetry lines. Accurate WTBH can be used for the calculation of many materials properties, and we include a few example applications. We also develop a web-app that can be used to predict electronic properties on-the-fly using WTBH from our database. The tools to generate the Hamiltonian and the database of the WTB parameters will be made publicly available through the websites https://github.com/usnistgov/jarvis and https://www.ctcms.nist.gov/jarviswtb.

cond-mat.mtrl-sci↗

arXiv2020

Density Functional Theory based Electric Field Gradient Database

The deviation of the electron density around the nuclei from spherical symmetry determines the electric field gradient (EFG), which can be measured by various types of spectroscopy. Nuclear Quadrupole Resonance (NQR) is particularly sensitive to the EFG. The EFGs, and by implication NQR frequencies, vary dramatically across materials. Consequently, searching for NQR spectral lines in previously uninvestigated materials represents a major challenge. Calculated EFGs can significantly aid at the search inception. To facilitate this task, we have applied high-throughput density functional theory calculations to predict EFGs for 15187 materials in the JARVIS-DFT database. This database, which will include EFG as a standard entry, is continuously increasing. Given the large scope of the database, it is impractical to verify each calculation. However, we assess accuracy by singling out cases for which reliable experimental information is readily available and compare them to the calculations. We further present a statistical analysis of the results. The database and tools associated with our work are made publicly available by JARVIS-DFT ( https://www.ctcms.nist.gov/~knc6/JVASP.html ) and NIST-JARVIS API ( http://jarvis.nist.gov ).

cond-mat.mtrl-sci↗

arXiv2020

High-throughput Density Functional Perturbation Theory and Machine Learning Predictions of Infrared, Piezoelectric and Dielectric Responses

Many technological applications depend on the response of materials to electric fields, but available databases of such responses are limited. Here, we explore the infrared, piezoelectric and dielectric properties of inorganic materials by combining high-throughput density functional perturbation theory and machine learning approaches. We compute Γ-point phonons, infrared intensities, Born-effective charges, piezoelectric, and dielectric tensors for 5015 non-metallic materials in the JARVIS-DFT database. We find 3230 and 1943 materials with at least one far and mid-infrared mode, respectively. We identify 577 high-piezoelectric materials, using a threshold of 0.5 C/m2. Using a threshold of 20, we find 593 potential high-dielectric materials. Importantly, we analyze the chemistry, symmetry, dimensionality, and geometry of the materials to find features that help explain variations in our datasets. Finally, we develop high-accuracy regression models for the highest infrared frequency and maximum Born-effective charges, and classification models for maximum piezoelectric and average dielectric tensors to accelerate discovery.

cond-mat.mtrl-sci↗

arXiv2020

Computational Search for Magnetic and Non-magnetic 2D Topological Materials using Unified Spin-orbit Spillage Screening

Two-dimensional topological materials (TMs) have a variety of properties that make them attractive for applications including spintronics and quantum computation. However, there are only a few such experimentally known materials. To help discover new 2D TMs, we develop a unified and computationally inexpensive approach to identify magnetic and non-magnetic 2D TMs, including gapped and semi-metallic topological classifications, in a high-throughput way using density functional theory-based spin-orbit spillage, Wannier-interpolation, and related techniques. We first compute the spin-orbit spillage for the ~1000 2D materials in the JARVIS-DFT dataset (https://www.ctcms.nist.gov/~knc6/JVASP.html ), resulting in 122 materials with high-spillage values. Then, we use Wannier-interpolation to carry-out Z2, Chern-number, anomalous Hall conductivity, Curie temperature, and edge state calculations to further support the predictions. We identify various topologically non-trivial classes such as quantum spin-hall insulators (QSHI), quantum anomalous-hall insulators (QAHI), and semimetals. For a few predicted materials, we run G0W0+SOC and DFT+U calculations. We find that as we introduce many-body effects, only a few materials retain non-trivial band-topology, suggesting the importance of high-level DFT methods in predicting 2D topological materials. However, as an initial step, the automated spillage screening and Wannier-approach provide useful predictions for finding new topological materials and to narrow down candidates for experimental synthesis and characterization.

cond-mat.mtrl-sci↗

arXiv2020

Data-driven Discovery of 3D and 2D Thermoelectric Materials

In this work, we first perform a systematic search for high-efficiency three-dimensional (3D) and two-dimensional (2D) thermoelectric materials by combining semiclassical transport techniques with density functional theory (DFT) calculations and then train machine-learning models on the thermoelectric data. Out of 36000 three-dimensional and 900 two-dimensional materials currently in the publicly available JARVIS-DFT database, we identify 2932 3D and 148 2D promising thermoelectric materials using a multi-steps screening procedure, where specific thresholds are chosen for key quantities like bandgaps, Seebeck coefficients and power factors. We compute the Seebeck coefficients for all the materials currently in the database and validate our calculations by comparing our results, for a subset of materials, to experimental and existing computational datasets. We also investigate the effect of chemical, structural, crystallographic and dimensionality trends on thermoelectric performance. We predict several classes of efficient 3D and 2D materials such as Ba(MgX)2 (X=P,As,Bi), X2YZ6 (X=K,Rb, Y=Pd,Pt, Z=Cl,Br), K2PtX2(X=S,Se), NbCu3X4 (X=S,Se,Te), Sr2XYO6 (X=Ta, Zn, Y=Ga, Mo), TaCu3X4 (X=S, Se,Te), and XYN (X=Ti, Zr, Y=Cl, Br). Finally, as high-throughput DFT is computationally expensive, we train machine learning models using gradient boosting decision trees (GBDT) and classical force-field inspired descriptors (CFID) for n-and p-type Seebeck coefficients and power factors, to quickly pre-screen materials for guiding the next set of DFT calculations. The dataset and tools are made publicly available at the websites: https://www.ctcms.nist.gov/~knc6/JVASP.html , https://www.ctcms.nist.gov/jarvisml/ and https://jarvis.nist.gov/ .

cond-mat.mtrl-sci↗

arXiv2019

Density Functional Theory and Deep-learning to Accelerate Data Analytics in Scanning Tunneling Microscopy

We introduce the first systematic database of scanning tunneling microscope (STM) images obtained using density functional theory (DFT) for two-dimensional (2D) materials, calculated using the Tersoff-Hamann method. It currently contains data for 716 exfoliable 2D materials. Examples of the five possible Bravais lattice types for 2D materials and their Fourier-transforms are discussed. All the computational STM images generated in this work will be made available on the JARVIS-DFT website (https://www.ctcms.nist.gov/~knc6/JVASP.html). We find excellent qualitative agreement between the computational and experimental STM images for selected materials. As a first example application of this database, we train a convolution neural network (CNN) model to identify Bravais lattices from the STM images. We believe the model can aid high-throughput experimental data analysis. These computational STM images can directly aid the identification of phases, analyzing defects and lattice-distortions in experimental STM images, as well as be incorporated in the autonomous experiment workflows.

cond-mat.mtrl-sci↗

arXiv2019

Discovering Inorganic Electrides from an Automated Computational Screening

Electrides, with their excess electrons distributed in crystal cavities playing the role of anions, exhibit a variety of unique properties which make these materials desirable for many applications in catalysis, nonlinear optics and electron emission. While the first electride was discovered almost four decades ago, only few electride materials are known today, which limits our fundamental understanding as well as the practical use of these exotic materials. In this work, we propose an automated computational screening scheme to search for interstitial electrons and quantify their distributions inside the crystal cavities and energy space. Applying this scheme to all candidate materials in the Inorganic Crystal Structure Database (ICSD), we report the identification of 167 potential electride materials. This work significantly increases the current library of electride materials, which enables an in-depth investigation of their chemistry-structure-property relations and opens new avenues for future electride design.

cond-mat.mtrl-sci↗

arXiv2019

Accelerated Discovery of Efficient Solar-cell Materials using Quantum and Machine-learning Methods

Solar-energy plays an important role in solving serious environmental problems and meeting high-energy demand. However, the lack of suitable materials hinders further progress of this technology. Here, we present the largest inorganic solar-cell material search to date using density functional theory (DFT) and machine-learning approaches. We calculated the spectroscopic limited maximum efficiency (SLME) using Tran-Blaha modified Becke-Johnson potential for 5097 non-metallic materials and identified 1997 candidates with an SLME higher than 10%, including 934 candidates with suitable convex-hull stability and effective carrier mass. Screening for 2D-layered cases, we found 58 potential materials and performed G0W0 calculations on a subset to estimate the prediction-uncertainty. As the above DFT methods are still computationally expensive, we developed a high accuracy machine learning model to pre-screen efficient materials and applied it to over a million materials. Our results provide a general framework and universal strategy for the design of high-efficiency solar cell materials. The data and tools are publicly distributed at: https://www.ctcms.nist.gov/~knc6/JVASP.html, https://www.ctcms.nist.gov/jarvisml/, https://jarvis.nist.gov/ and https://github.com/usnistgov/jarvis .

cond-mat.mtrl-sci↗

arXiv2019

High-throughput Discovery of Topologically Non-trivial Materials using Spin-orbit Spillage

We present a novel methodology to identify topologically non-trivial materials based on band inversion induced by spin-orbit coupling (SOC) effect. Specifically, we compare the density functional theory (DFT) based wavefunctions with and without spin-orbit coupling and compute the spin-orbit-spillage as a measure of band-inversion. Due to its ease of calculation, without any need for symmetry analysis or dense k-point interpolation, the spillage is an excellent tool for identifying topologically non-trivial materials. Out of 30000 materials available in the JARVIS-DFT database, we applied this methodology to more than 4835 non-magnetic materials consisting of heavy atoms and low bandgaps. We found 1868 candidate materials with high-spillage (using 0.5 as a threshold). We validated our methodology by carrying out conventional Wannier-interpolation calculations for 289 candidate materials. We demonstrate that in addition to Z2 topological insulators, this screening method successfully identified many semimetals and topological crystalline insulators. Importantly, our approach is applicable to the investigation of disordered or distorted as well as magnetic materials, because it is not based on symmetry considerations. We discuss some individual example materials, as well as trends throughout our dataset, which is available at the websites: https://www.ctcms.nist.gov/~knc6/JVASP.html and https://jarvis.nist.gov/.

cond-mat.mtrl-sci↗

arXiv2019

Convergence and machine learning predictions of Monkhorst-Pack k-points and plane-wave cut-off in high-throughput DFT calculations

In this work, we developed an automatic convergence procedure for k-points and plane wave cut-off in density functional (DFT) calculations and applied it to more than 30000 materials. The computational framework for automatic convergence can take a user-defined input as a convergence criterion. For k-points, we converged energy per cell (EPC) to 0.001 eV/cell tolerance and compared the results with those obtained using an energy per atom (EPA) convergence criteria of 0.001 eV/atom. From the analysis of our results, we could relate k-point density and plane wave cut-off to material parameters such as density, the slope of bands, number of band-crossings, the maximum plane-wave cut-off used in pseudopotential generation, crystal systems, and the number of unique species in materials. We also identified some material species that would require more careful convergence than others. Moreover, we statistically investigated the dependence of k-points and cutoff on exchange-correlation functionals. We utilized all this data to train machine learning models to predict the k-point line density and plane-wave cut-off for generalized materials. This would provide users with a good starting point towards converged DFT calculations. The code used, and the converged data are available on the following websites: https://jarvis.nist.gov/, and https://github.com/usnistgov/jarvis .

cond-mat.mtrl-sci↗