arXiv subjects

Kamal Choudhary

Publications and source records attributed to Kamal Choudhary.

At least 55 records · Page 3Linked to original sources

arXiv2023

On the redundancy in large material datasets: efficient and robust learning with less data

Extensive efforts to gather materials data have largely overlooked potential data redundancy. In this study, we present evidence of a significant degree of redundancy across multiple large datasets for various material properties, by revealing that up to 95 % of data can be safely removed from machine learning training with little impact on in-distribution prediction performance. The redundant data is related to over-represented material types and does not mitigate the severe performance degradation on out-of-distribution samples. In addition, we show that uncertainty-based active learning algorithms can construct much smaller but equally informative datasets. We discuss the effectiveness of informative data in improving prediction performance and robustness and provide insights into efficient data acquisition and machine learning training. This work challenges the "bigger is better" mentality and calls for attention to the information richness of materials data rather than a narrow emphasis on data volume.

cond-mat.mtrl-sci↗

arXiv2023

Interpretable Ensemble Learning for Materials Property Prediction with Classical Interatomic Potentials: Carbon as an Example

Machine learning (ML) is widely used to explore crystal materials and predict their properties. However, the training is time-consuming for deep-learning models, and the regression process is a black box that is hard to interpret. Also, the preprocess to transfer a crystal structure into the input of ML, called descriptor, needs to be designed carefully. To efficiently predict important properties of materials, we propose an approach based on ensemble learning consisting of regression trees to predict formation energy and elastic constants based on small-size datasets of carbon allotropes as an example. Without using any descriptor, the inputs are the properties calculated by molecular dynamics with 9 different classical interatomic potentials. Overall, the results from ensemble learning are more accurate than those from classical interatomic potentials, and ensemble learning can capture the relatively accurate properties from the 9 classical potentials as criteria for predicting the final properties.

cond-mat.mtrl-sci↗

arXiv2023

14 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathon

Large-language models (LLMs) such as GPT-4 caught the interest of many scientists. Recent studies suggested that these models could be useful in chemistry and materials science. To explore these possibilities, we organized a hackathon. This article chronicles the projects built as part of this hackathon. Participants employed LLMs for various applications, including predicting properties of molecules and materials, designing novel interfaces for tools, extracting knowledge from unstructured data, and developing new educational applications. The diverse topics and the fact that working prototypes could be generated in less than two days highlight that LLMs will profoundly impact the future of our fields. The rich collection of ideas and projects also indicates that the applications of LLMs are not limited to materials science and chemistry but offer potential benefits to a wide range of scientific disciplines.

cond-mat.mtrl-sci↗

arXiv2023

Fast and Accurate Prediction of Material Properties with Three-Body Tight-Binding Model for the Periodic Table

Parameterized tight-binding models fit to first principles calculations can provide an efficient and accurate quantum mechanical method for predicting properties of molecules and solids. However, well-tested parameter sets are generally only available for a limited number of atom combinations, making routine use of this method difficult. Furthermore, most previous models consider only simple two-body interactions, which limits accuracy. To tackle these challenges, we develop a density functional theory database of nearly one million materials, which we use to fit a universal set of tight-binding parameters for 65 elements and their binary combinations. We include both two-body and three-body effective interaction terms in our model, plus self-consistent charge transfer, enabling our model to work for metallic, covalent, and ionic bonds with the same parameter set. To ensure predictive power, we adopt a learning framework where we repeatedly test the model on new low energy crystal structures and then add them to the fitting dataset, iterating until predictions improve. We distribute the materials database and tools developed in this work publicly.

cond-mat.mtrl-sci↗

arXiv2023

High-Throughput DFT-Based Discovery of Next Generation Two-Dimensional (2D) Superconductors

High-throughput density functional theory (DFT) calculations allow for a systematic search for conventional superconductors. With the recent interest in two-dimensional (2D) superconductors, we used a high-throughput workflow to screen over 1,000 2D materials in the JARVIS-DFT database and performed electron-phonon coupling calculations, using the McMillan-Allen-Dynes formula to calculate the superconducting transition temperature ($T_c$) for 165 of them. Of these 165 materials, we identify 34 dynamically stable structures with transition temperatures above 5 K, including materials such as W$_2$N$_3$, NbO$_2$, ZrBrO, TiClO, NaSn$_2$S$_4$, Mg$_2$B$_4$C$_2$ and the previously unreported Mg$_2$B$_4$N$_2$ ($T_c$ = 21.8 K). Finally, we performed experiments to determine the $T_c$ of selected layered superconductors (2H-NbSe$_2$, 2H-NbS$_2$, ZrSiS, FeSe) and discuss the measured results within the context of our DFT results. We aim that the outcome of this workflow can guide future computational and experimental studies of new and emerging 2D superconductors by providing a roadmap of high-throughput DFT data.

cond-mat.supr-con↗

arXiv2023

Systematic DFT+U and Quantum Monte Carlo benchmark of magnetic two-dimensional (2D) CrX$_3$ (X = I, Br, Cl, F)

The search for two-dimensional (2D) magnetic materials has attracted a great deal of attention because of the experimental synthesis of 2D CrI$_3$, which has a measured Curie temperature of 45 K. Often times, these monolayers have a higher degree of electron correlation and require more sophisticated methods beyond density functional theory (DFT). Diffusion Monte Carlo (DMC) is a correlated electronic structure method that has been demonstrated successful for calculating the electronic and magnetic properties of a wide variety of 2D and bulk systems, since it has a weaker dependence on the Hubbard parameter (U) and density functional. In this study we designed a workflow that combines DFT+U and DMC in order to treat 2D correlated magnetic systems. We chose monolayer CrX$_3$ (X = I, Br, Cl, F), with a stronger focus on CrI$_3$ and CrBr$_3$, as a case study due to the fact that they have been experimentally realized and have a finite critical temperature. With this DFT+U and DMC workflow and the analytical method of Torelli and Olsen, we estimated an upper bound of 43.56 K for the T$_c$ of CrI$_3$ and 20.78 K for the T$_c$ of CrBr$_3$, in addition to analyzing the spin densities and magnetic properties with DMC and DFT+U. We expect that running this workflow for a well-known material class will aid in the future discovery and characterization of lesser known and more complex correlated 2D magnetic materials.

cond-mat.str-el↗

arXiv2022

AtomVision: A machine vision library for atomistic images

Computer vision techniques have immense potential for materials design applications. In this work, we introduce an integrated and general-purpose AtomVision library that can be used to generate, curate scanning tunneling microscopy (STM) and scanning transmission electron microscopy (STEM) datasets and apply machine learning techniques. To demonstrate the applicability of this library, we 1) generate and curate an atomistic image dataset of about 10000 materials, 2) develop and compare convolutional and graph neural network models to classify the Bravais lattices, 3) develop fully convolutional neural network using U-Net architecture to pixelwise classify atom vs background, 4) use generative adversarial network for super-resolution, 5) curate a natural language processing based image dataset using open-access arXiv dataset, and 6) integrate the computational framework with experimental microscopy tools. AtomVision library is available at https://github.com/usnistgov/atomvision.

cond-mat.mtrl-sci↗

arXiv2022

A critical examination of robustness and generalizability of machine learning prediction of materials properties

Recent advances in machine learning (ML) methods have led to substantial improvement in materials property prediction against community benchmarks, but an excellent benchmark score may not imply good generalization of performance. Here we show that ML models trained on the Materials Project 2018 (MP18) dataset can have severely degraded prediction performance on new compounds in the Materials Project 2021 (MP21) dataset. We document performance degradation in graph neural networks and traditional descriptor-based ML models for both quantitative and qualitative predictions. We find the source of the predictive degradation is due to the distribution shift between the MP18 and MP21 versions. This is revealed by the uniform manifold approximation and projection (UMAP) of the feature space. We then show that the performance degradation issue can be foreseen using a few simple tools. Firstly, the UMAP can be used to investigate the connectivity and relative proximity of the training and test data within feature space. Secondly, the disagreement between multiple ML models on the test data can illuminate out-of-distribution samples. We demonstrate that the simple yet efficient UMAP-guided and query-by-committee acquisition strategies can greatly improve prediction accuracy through adding only 1~\% of the test data. We believe this work provides valuable insights for building materials databases and ML models that enable better prediction robustness and generalizability.

cond-mat.mtrl-sci↗

arXiv2022

Designing High-Tc Superconductors with BCS-inspired Screening, Density Functional Theory and Deep-learning

We develop a multi-step workflow for the discovery of conventional superconductors, starting with a Bardeen Cooper Schrieffer inspired pre-screening of 1736 materials with high Debye temperature and electronic density of states. Next, we perform electron-phonon coupling calculations for 1058 of them to establish a large and systematic database of BCS superconducting properties. Using the McMillan-Allen-Dynes formula, we identify 105 dynamically stable materials with transition temperatures, Tc>5 K. Additionally, we analyze trends in our dataset and individual materials including MoN, VC, VTe, KB6, Ru3NbC, V3Pt, ScN, LaN2, RuO2, and TaC. We demonstrate that deep-learning(DL) models can predict superconductor properties faster than direct first principles computations. Notably, we find that by predicting the Eliashberg function as an intermediate quantity, we can improve model performance versus a direct DL prediction of Tc. We apply the trained models on the crystallographic open database and pre-screen candidates for further DFT calculations.

cond-mat.supr-con↗

arXiv2022

Unified Graph Neural Network Force-field for the Periodic Table

Classical force fields (FF) based on machine learning (ML) methods show great potential for large scale simulations of materials. MLFFs have hitherto largely been designed and fitted for specific systems and are not usually transferable to chemistries beyond the specific training set. We develop a unified atomisitic line graph neural network-based FF (ALIGNN-FF) that can model both structurally and chemically diverse materials with any combination of 89 elements from the periodic table. To train the ALIGNN-FF model, we use the JARVIS-DFT dataset which contains around 75000 materials and 4 million energy-force entries, out of which 307113 are used in the training. We demonstrate the applicability of this method for fast optimization of atomic structures in the crystallography open database and by predicting accurate crystal structures using genetic algorithm for alloys.

cond-mat.mtrl-sci↗

arXiv2022

Efficient Computational Design of 2D van der Waals Heterostructures: Band-Alignment, Lattice-Mismatch, Web-app Generation and Machine-learning

We develop a computational database, web-apps, and machine-learning (ML) models to accelerate the design and discovery of two-dimensional (2D)-heterostructures. Using density functional theory (DFT) based lattice-parameters and electronic band-energies for 674 non-metallic exfoliable 2D-materials, we generate 226,779 possible heterostructures. We classify these heterostructures into type-I, II and III systems according to Andersons rule, which is based on the relative band-alignments of the non-interacting monolayers. We find that type-II is the most common and the type-III the least common heterostructure type. We subsequently analyze the chemical trends for each heterostructure type in terms of the periodic table of constituent elements. The band alignment data can be also used for identifying photocatalysts and high-work function 2D-metals for contacts. We validate our results by comparing them to experimental data as well as hybrid-functional predictions. Additionally, we carry out DFT calculations of a few selected systems (MoS2/WSe2, MoS2/h-BN, MoSe2/CrI3), to compare the band-alignment description with the predictions from Andersons rule. We develop web-apps to enable users to virtually create combinations of 2D materials and predict their properties. Additionally, we use ML tools to predict band-alignment information for 2D materials. The web-apps, tools and associated data will be distributed through JARVIS-Heterostructure website (https://jarvis.nist.gov/jarvish/). Our analysis, results and the developed web-apps can be applied to the screening and design applications, such as finding novel photocatalysts, photodetectors, and high-work function (WF) 2D-metal contacts.

cond-mat.mtrl-sci↗

arXiv2022

Reproducible Sorbent Materials Foundry for Carbon Capture at Scale

We envision an autonomous sorbent materials foundry (SMF) for rapidly evaluating materials for direct air capture of carbon dioxide (CO2), specifically targeting novel metal organic framework materials. Our proposed SMF is hierarchical, simultaneously addressing the most critical gaps in the inter-related space of sorbent material synthesis, processing, properties, and performance. The ability to collect these critical data streams in an agile, coordinated, and automated fashion will enable efficient end-to-end sorbent materials design through machine learning driven research framework.

cond-mat.mtrl-sci↗

arXiv2022

Rapid Prediction of Phonon Structure and Properties using an Atomistic Line Graph Neural Network (ALIGNN)

The phonon density-of-states (DOS) summarizes the lattice vibrational modes supported by a structure, and gives access to rich information about the material's stability, thermodynamic constants, and thermal transport coefficients. Here, we present an atomistic line graph neural network (ALIGNN) model for the prediction of the phonon density of states and the derived thermal and thermodynamic properties. The model is trained on a database of over 14,000 phonon spectra included in the JARVIS-DFT (Joint Automated Repository for Various Integrated Simulations: Density Functional Theory) database. The model predictions are shown to capture the spectral features of the phonon density-of-states, effectively categorize dynamical stability, and lead to accurate predictions of DOS-derived thermal and thermodynamic properties, including heat capacity $C_{\mathrm{V}}$, vibrational entropy $S_{\mathrm{vib}}$, and the isotopic phonon scattering rate $τ^{-1}_{\mathrm{i}}$. The DOS-mediated ALIGNN model provides superior predictions when compared to a direct deep-learning prediction of these material properties as well as predictions based on analytic simplifications of the phonon DOS, including the Debye or Born-von Karman models. Finally, the ALIGNN model is used to predict the phonon spectra and properties for about 40,000 additional materials listed in the JARVIS-DFT database, which are validated as far as possible against other open-sourced high-throughput DFT phonon databases.

cond-mat.mtrl-sci↗

arXiv2022

A Deep-learning Model for Fast Prediction of Vacancy Formation in Diverse Materials

The presence of point defects such as vacancies plays an important role in material design. Here, we demonstrate that a graph neural network (GNN) model trained only on perfect materials can also be used to predict vacancy formation energies ($E_{vac}$) of defect structures without the need for additional training data. Such GNN-based predictions are considerably faster than density functional theory (DFT) calculations with reasonable accuracy and show the potential that GNNs are able to capture a functional form for energy predictions. To test this strategy, we developed a DFT dataset of 508 $E_{vac}$ consisting of 3D elemental solids, alloys, oxides, nitrides, and 2D monolayer materials. We analyzed and discussed the applicability of such direct and fast predictions. We applied the model to predict 192494 $E_{vac}$ for 55723 materials in the JARVIS-DFT database.

cond-mat.mtrl-sci↗

arXiv2022

Atomistic Line Graph Neural Network for Improved Materials Property Predictions

Graph neural networks (GNN) have been shown to provide substantial performance improvements for atomistic material representation and modeling compared with descriptor-based machine learning models. While most existing GNN models for atomistic predictions are based on atomic distance information, they do not explicitly incorporate bond angles, which are critical for distinguishing many atomic structures. Furthermore, many material properties are known to be sensitive to slight changes in bond angles. We present an Atomistic Line Graph Neural Network (ALIGNN), a GNN architecture that performs message passing on both the interatomic bond graph and its line graph corresponding to bond angles. We demonstrate that angle information can be explicitly and efficiently included, leading to improved performance on multiple atomistic prediction tasks. We ALIGNN models for predicting 52 solid-state and molecular properties available in the JARVIS-DFT, Materials project, and QM9 databases. ALIGNN can outperform some previously reported GNN models on atomistic prediction tasks by up to 85% in accuracy with better or comparable model training speed.

cond-mat.mtrl-sci↗

arXiv2022

Prediction of the electron density of states for crystalline compounds with Atomistic Line Graph Neural Networks (ALIGNN)

Machine learning (ML) based models have greatly enhanced the traditional materials discovery and design pipeline. Specifically, in recent years, surrogate ML models for material property prediction have demonstrated success in predicting discrete scalar-valued target properties to within reasonable accuracy of their DFT-computed values. However, accurate prediction of spectral targets such as the electron Density of States (DOS) poses a much more challenging problem due to the complexity of the target, and the limited amount of available training data. In this study, we present an extension of the recently developed Atomistic Line Graph Neural Network (ALIGNN) to accurately predict DOS of a large set of material unit cell structures, trained to the publicly available JARVIS-DFT dataset. Furthermore, we evaluate two methods of representation of the target quantity - a direct discretized spectrum, and a compressed low-dimensional representation obtained using an autoencoder. Through this work, we demonstrate the utility of graph-based featurization and modeling methods in the prediction of complex targets that depend on both chemistry and directional characteristics of material structures.

cond-mat.mtrl-sci↗

arXiv2021

Graph Neural Network Predictions of Metal Organic Framework CO2 Adsorption Properties

The increasing CO2 level is a critical concern and suitable materials are needed to capture such gases from the environment. While experimental and conventional computational methods are useful in finding such materials, they are usually slow and there is a need to expedite such processes. We use Atomistic Line Graph Neural Network (ALIGNN) method to predict CO2 adsorption in metal organic frameworks (MOF), which are known for their high functional tunability. We train ALIGNN models for hypothetical MOF (hMOF) database with 137953 MOFs with grand canonical Monte Carlo (GCMC) based CO2 adsorption isotherms. We develop high accuracy and fast models for pre-screening applications. We apply the trained model on CoREMOF database and computationally rank them for experimental synthesis. In addition to the CO2 adsorption isotherm, we also train models for electronic bandgaps, surface area, void fraction, lowest cavity diameter, and pore limiting diameter, and illustrate the strength and limitation of such graph neural network models. For a few candidate MOFs we carry out GCMC calculations to evaluate the deep-learning (DL) predictions.

cond-mat.mtrl-sci↗

arXiv2021

Predicting Lattice Phonon Vibrational Frequencies Using Deep Graph Neural Networks

Lattice vibration frequencies are related to many important materials properties such as thermal and electrical conductivity as well as superconductivity. However, computational calculation of vibration frequencies using density functional theory (DFT) methods is too computationally demanding for a large number of samples in materials screening. Here we propose a deep graph neural network-based algorithm for predicting crystal vibration frequencies from crystal structures with high accuracy. Our algorithm addresses the variable dimension of vibration frequency spectrum using the zero padding scheme. Benchmark studies on two data sets with 15,000 and 35,552 samples show that the aggregated $R^2$ scores of the prediction reaches 0.554 and 0.724 respectively. Our work demonstrates the capability of deep graph neural networks to learn to predict phonon spectrum properties of crystal structures in addition to phonon density of states (DOS) and electronic DOS in which the output dimension is constant.

cond-mat.mtrl-sci↗