Data-driven Materials Design Research Articles

NJmat: Data-Driven Machine Learning Interface to Accelerate Material Design.

Machine learning techniques have significantly transformed the way materials scientists conduct research. However, the widespread deployment of machine learning software in daily experimental and simulation research for materials and chemical design has been limited. This is partly due to the substantial time investment and learning curve associated with mastering the necessary codes and computational environments. In this paper, we introduce a user-friendly, data-driven machine learning interface featuring multiple "button-clicking" functionalities to streamline the design of materials and chemicals. This interface automates the processes of transforming materials and molecules, performing feature selection, constructing machine learning models, making virtual predictions, and visualizing results. Such automation accelerates materials prediction and analysis in the inverse design process, aligning with the time criteria outlined by the Materials Genome Initiative. With simple button clicks, researchers can build machine learning models and predict new materials once they have gathered experimental or simulation data. Beyond the ease of use, NJmat offers three additional features for data-driven materials design: (1) automatic feature generation for both inorganic materials (from chemical formulas) and organic molecules (from SMILES), (2) automatic generation of Shapley plots, and (3) automatic construction of "white-box" genetic models and decision trees to provide scientific insights. We present case studies on surface design for halide perovskite materials encompassing both inorganic and organic species. These case studies illustrate general machine learning models for virtual predictions as well as the automatic featurization and Shapley/genetic model construction capabilities. We anticipate that this software tool will expedite materials and molecular design within the scope of the Materials Genome Initiative, particularly benefiting experimentalists.

AFLOW-CCE for the thermodynamics of ionic materials.

Accurate thermodynamic stability predictions enable data-driven computational materials design. Standard density functional theory (DFT) approximations have limited accuracy with average errors of a few hundred meV/atom for ionic materials, such as oxides and nitrides. Thus, insightful correction schemes as given by the coordination corrected enthalpies (CCE) method, based on an intuitive parametrization of DFT errors with respect to coordination numbers and cation oxidation states, present a simple, yet accurate solution to enable materials stability assessments. Here, we illustrate the computational capabilities of our AFLOW-CCE software by utilizing our previous results for oxides and introducing new results for nitrides. The implementation reduces the deviations between theory and experiment to the order of the room temperature thermal energy scale, i.e., ∼25 meV/atom. The automated corrections for both materials classes are freely available within the AFLOW ecosystem via the AFLOW-CCE module, requiring only structural inputs.

Future Aspects of Data-Driven Materials Design Using both Simulation and AI

Future Aspects of Data-Driven Materials Design Using both Simulation and AI

(Invited) Data-Driven Design for Energy Materials

Fueled by our abilities to compute materials properties and characteristics orders of magnitude faster than they can be measured and recent advancements in harnessing literature data, we are entering the era of the fourth paradigm of science: data-driven materials design. The Materials Project uses supercomputing together with state-of-the-art quantum mechanical theory to compute the properties of inorganic materials, design novel materials and offer the data for free to the community together with online analysis and design algorithms. Specifically relevant to the Energy Materials Network effort, the Project produces and disseminates materials properties relevant for a broad range of energy materials, interfacial reaction predictions, and Pourbaix diagrams to assess corrosion. We will in this talk survey the existing capabilities, current and ongoing developments and highlight design of novel materials for photocatalysis; from ab initio prediction to synthesis and characterization. Specifically, we identify bottlenecks in the design process and our efforts to accelerate it. Finally, we recognize that the highest impact from the Materials Project comes from its rapidly growing user community, currently counting over 400,000 registered users, and their use of our resources.

Recent progress in the JARVIS infrastructure for next-generation data-driven materials design

The joint automated repository for various integrated simulations (JARVIS) infrastructure at the National Institute of Standards and Technology is a large-scale collection of curated datasets and tools with more than 80 000 materials and millions of properties. JARVIS uses a combination of electronic structure, artificial intelligence, advanced computation, and experimental methods to accelerate materials design. Here, we report some of the new features that were recently included in the infrastructure, such as (1) doubling the number of materials in the database since its first release, (2) including more accurate electronic structure methods such as quantum Monte Carlo, (3) including graph neural network-based materials design, (4) development of unified force-field, (5) development of a universal tight-binding model, (6) addition of computer-vision tools for advanced microscopy applications, (7) development of a natural language processing tool for text-generation and analysis, (8) debuting a large-scale benchmarking endeavor, (9) including quantum computing algorithms for solids, (10) integrating several experimental datasets, and (11) staging several community engagement and outreach events. New classes of materials, properties, and workflows added to the database include superconductors, two-dimensional (2D) magnets, magnetic topological materials, metal-organic frameworks, defects, and interface systems. The rich and reliable datasets, tools, documentation, and tutorials make JARVIS a unique platform for modern materials design. JARVIS ensures the openness of data and tools to enhance reproducibility and transparency and to promote a healthy and collaborative scientific environment.

High-throughput solubility determination for data-driven materials design and discovery in redox flow battery research

High-throughput solubility determination for data-driven materials design and discovery in redox flow battery research

Rapid design of top-performing metal-organic frameworks with qualitative representations of building blocks

Data-driven materials design often encounters challenges where systems possess qualitative (categorical) information. Specifically, representing Metal-organic frameworks (MOFs) through different building blocks poses a challenge for designers to incorporate qualitative information into design optimization, and leads to a combinatorial challenge, with large number of MOFs that could be explored. In this work, we integrated Latent Variable Gaussian Process (LVGP) and Multi-Objective Batch-Bayesian Optimization (MOBBO) to identify top-performing MOFs adaptively, autonomously, and efficiently. We showcased that our method (i) requires no specific physical descriptors and only uses building blocks that construct the MOFs for global optimization through qualitative representations, (ii) is application and property independent, and (iii) provides an interpretable model of building blocks with physical justification. By searching only ~1% of the design space, LVGP-MOBBO identified all MOFs on the Pareto front and 97% of the 50 top-performing designs for the CO2 working capacity and CO2/N2 selectivity properties.

A Bi-Gradient Dielectric Polymer/High-Κ Nanoparticle/Molecular Semiconductor Ternary Composite for High-Temperature Capacitive Energy Storage.

Attaining compact energy storage under extreme temperature conditions is of paramount importance in the development of advanced dielectric materials. The polymer composite approach has proved effective towards this goal, and addressing the correlation between filler distribution and electrical properties is foremost in designing composite dielectrics, especially in multifiller systems. Here, the design of a bi-gradient polymer composite dielectric using an integrated framework based on the phase field model is reported. This framework can predict the charge-inhibiting behavior of composite dielectrics, which is a key factor impacting the high-temperature capacitive performance but unfortunately is ignored in conventional phase field models. It is found that due to the traps provided by the functional organic fillers, more carriers are trapped near the electrodes and weaken the electric field, thus significantly suppressing the breakdown initialization process. An interpenetrating gradient structure is designed rationally and synthesized experimentally, which exhibits concurrent high energy density (5.51 J cm-3 ) and high charge-discharge efficiency (90%) up to 200 °C. This work provides a strategy to predict the high-temperature energy storage performance of polymer composites containing charge-inhibiting components and helps broaden the scope of data-driven materials design based on phase-field modeling.

EwaldSolidSolution: A High-Throughput Application to Quickly Sample Stable Site Arrangements for Ionic Solid Solutions.

Data-driven materials design of ionic solid solutions often requires sampling (meta)stable site arrangements among the massive number of possibilities, which has been hampered by the lack of relevant methods. Herein, we develop a quick high-throughput sampling application for site arrangements of ionic solid solutions. Given the Ewald Coulombic energies for an initial site arrangement, EwaldSolidSolution updates the modified parts of the energy with varying sites only, which can be exhaustively estimated by using massively parallel processing. Given two representative examples of solid electrolytes, Li10GeP2S12 and Na3Zr2Si2PO12, EwaldSolidSolution successfully calculates the Ewald Coulombic energies of 211,266,225 (235,702,467) site arrangements for Li10GeP2S12 (Na3Zr2Si2PO12) with 216 (160) ion sites per unit cell in 1223.2 (1187.9) seconds: 0.0057898 (0.0050397) milliseconds per site arrangement. The computational cost is enormously saved in comparison with an existing application, which estimates the energy of a site arrangement on the second timescale. The positive correlations between the Ewald Coulombic energies and those estimated by density functional theory calculations show that (meta)stable samples are easily revealed by our computationally inexpensive algorithm. We also reveal that the different-valence nearest-neighbor pairs are distinctively formed in the low-energy site arrangements. EwaldSolidSolution will boost the materials design of ionic solid solutions by attracting broad interest.

Center-environment deep transfer machine learning across crystal structures: from spinel oxides to perovskite oxides

In data-driven materials design where the target materials have limited data, the transfer machine learning from large known source materials, becomes a demanding strategy especially across different crystal structures. In this work, we proposed a deep transfer learning approach to predict thermodynamically stable perovskite oxides based on a large computational dataset of spinel oxides. The deep neural network (DNN) source domain model with “Center-Environment” (CE) features was first developed using the formation energy of 5329 spinel oxide structures and then was fine-tuned by learning a small dataset of 855 perovskite oxide structures, leading to a transfer learning model with good transferability in the target domain of perovskite oxides. Based on the transferred model, we further predicted the formation energy of potential 5329 perovskite structures with combination of 73 elements. Combining the criteria of formation energy and structure factors including tolerance factor (0.7 < t ≤ 1.1) and octahedron factor (0.45 < μ < 0.7), we predicted 1314 thermodynamically stable perovskite oxides, among which 144 oxides were reported to be synthesized experimentally, 10 oxides were predicted computationally by other literatures, 301 oxides were recorded in the Materials Project database, and 859 oxides have been first reported. Combing with the structure-informed features the transfer machine learning approach in this work takes the advantage of existing data to predict new structures at a lower cost, providing an effective acceleration strategy for the expensive high-throughput computational screening in materials design. The predicted stable novel perovskite oxides serve as a rich platform for exploring potential renewable energy and electronic materials applications.

An automatic descriptors recognizer customized for materials science literature

Materials science literature contains domain knowledge about numerous descriptors, which play a critical role in data-driven materials design. However, automatically extracting descriptors from literature remains challenging. Here, we develop an automatic descriptors recognizer based on natural language processing (NLP) to mine latent descriptors, which consists of a conditional data augmentation model incorporating materials domain knowledge (cDA-DK), coarse- and fine-grained descriptors subrecognizers (CGDR and FGDR). cDA-DK conducts augmenting training data of text mining model, which can significantly reduce the cost of manually labeling and enhance the robustness of its model. On this basis, CGDR recognizes coarse-grained descriptor entities automatically, and FGDR performs screening of fine-grained descriptors related to specific materials design. Following this, the activation energy of NASICON-type solid electrolytes, which is influenced by complicated descriptors, is taken as an example to demonstrate the potential utility of our recognizer. CGDR extracts 106896 descriptor entities from 1808 relevant articles with an accuracy (F1) of 0.87. Furthermore, with features from 408 descriptors screened by FGDR, six activation energy prediction models are constructed to perform experiments, achieving an optimal prediction performance (R2) of 0.96. This work provides important insight towards the understanding of structure-activity relationships, thus promoting materials design and discovery.

Automated pipeline for superalloy data by text mining

Data provides a foundation for machine learning, which has accelerated data-driven materials design. The scientific literature contains a large amount of high-quality, reliable data, and automatically extracting data from the literature continues to be a challenge. We propose a natural language processing pipeline to capture both chemical composition and property data that allows analysis and prediction of superalloys. Within 3 h, 2531 records with both composition and property are extracted from 14,425 articles, covering γ′ solvus temperature, density, solidus, and liquidus temperatures. A data-driven model for γ′ solvus temperature is built to predict unexplored Co-based superalloys with high γ′ solvus temperatures within a relative error of 0.81%. We test the predictions via synthesis and characterization of three alloys. A web-based toolkit as an online open-source platform is provided and expected to serve as the basis for a general method to search for targeted materials using data extracted from the literature.

A metadata schema for lattice thermal conductivity from first-principles calculations

Materials genome engineering databases represent fundamental infrastructures for data-driven materials design, in which the data resources should satisfy the FAIR (Findable, Accessible, Interoperable and Reusable) principles. However, a variety of challenges, such as data standardization, veracity and longevity, still impede the progress of data-driven materials science, including both high-throughput experiments and simulations. In this work, we propose a metadata schema for lattice thermal conductivity from first-principles calculations. The calculation workflow for lattice thermal conductivity includes structural optimization and the calculation of interatomic force constants and lattice thermal conductivity. The data generated during the calculation process corresponds to the virtual sample information, virtual source data and processed data, respectively, as specified in the General rule for materials genome engineering data of the Chinese Society for Testing and Materials. Following this general rule, the metadata structure and schema for each action are systematically defined and all metadata elements can be collected completely. Although this metadata schema is specific to lattice thermal conductivity calculations, it provides general rules and insights for other computational materials data in materials genome engineering.

Data-driven thermoelectric modeling: Current challenges and prospects

Recent advancements in computing technologies coupled with the need to make sense of large amounts of raw data have renewed much interest in data-driven materials design and discovery. Traditional materials science research relies heavily on experimental data to gauge the properties of materials. However, this paradigm is purely based on trial and error and ongoing research can take decades to discover new materials. Data-driven modeling tools such as machine learning and its proven libraries can help speed up the materials’ discovery process through the implementation of powerful algorithms on readily available material datasets mined from the ever-increasing private- and government-funded material databases. In this Perspective, we applied various machine learning models on tens of hundreds of thermoelectric compounds obtained from density functional theory calculation results. In our preliminary analysis, we made use of pymatgen and the powerful materials science library matminer to add and explore key material features that have the propensity to accurately predict our achievable target output. We evaluated the accuracy and performance of our models with the coefficient of determination (R2), the root mean square error, and K-fold cross-validation metrics and identified the most important descriptors for our materials. Finally, we reviewed the current state-of-the-art in data-driven thermoelectric materials’ design and discovery, its current challenges, and prospects.

An adaptive multi-temperature isokinetic method for the RVE generation of particle reinforced heterogeneous materials, Part II: Numerical assessment and statistical analysis

This contribution presents the application of a new computational generation method for high-fidelity representative volume elements (RVEs) composed of particle-reinforced materials coined AMINO (Adaptive Multi-temperature Isokinetic Method). The theoretical formulation and the computational framework of the method are described in Part I. Here, the focus is placed on the generation of a large set of RVEs for two and three-dimensional cases, covering a broad range of particles and volume fractions following specific statistical distributions, highlighting AMINO’s efficiency, robustness, and flexibility. Detailed statistical analysis and quantitative comparisons with real micrographs demonstrate that AMINO can generate high-fidelity computational microstructures that closely resemble experimental observations. The geometrical interpretation of the so-called Minkowski structure metrics is further explored, and these are shown to be suitable tools to characterize particle-reinforced materials’ microstructures. Therefore, AMINO fulfills the requirements to be integrated into the recent paradigm of data-driven materials design based on multi-scale modeling.

Learning interpretable descriptors for the fatigue strength of steels

While the new paradigm of data-driven materials science has proven efficient in accelerated materials discovery, one challenge is whether the data-driven methods could deliver interpretable models that provide scientific insights in addition to accuracy. In this work, with the example of data-driven materials design for high-strength steels, we compared the efficiency of the recent Sure Independence Screening and Sparsifying Operator (SISSO) with several other conventional machine learning methods, Support Vector Regression (SVR), Decision Tree (DTe), and Gradient Boost Decision Tree (GBDT). The results show that SISSO gives interpretable and simple descriptors, while the accuracy is comparable to that of the relatively “black-box” model from SVR, GBDT, and DTe. The best SISSO descriptor was found to be scientifically consistent with that in previous studies. In addition, we show that combining with particle swarm optimization, the simple and explicit expression of the descriptor also bears advantages in reverse materials design, which is a general way for machine learning to not only predict but also tell what is the next possible action to be done.

Mechanical and thermodynamic data-driven design of Al-Co-Cr-Fe-Ni multi-principal element alloys

Data-driven materials design is a modern approach, which is particularly desired for complex systems, such as the multi-principal element alloy (MPEA), also known as the high entropy alloy (HEA). The concept of MPEA/HEA brings tremendous opportunities of alloy design for superior mechanical properties, for instance, seeking for the ultimate goal of balanced strength and elongation in structural materials applications. Herein, we took the Al-Co-Cr-Fe-Ni quinary alloys as a model system to examine the semi-empirical method of alloy design based on empirical equations and high-throughput CALculation of PHAse Diagram (CALPHAD) modeling. The hardness, yield strength, ultimate tensile strength, and elongation of the as-cast Al-Co-Cr-Fe-Ni MPEA in the literatures were fit with the phase volume fraction of the fcc, bcc, and B2 phases. 10,000 CALPHAD solidification modeling based on the Scheil model were performed. Two alloys, Al14Co24Cr22Fe21Ni19 (A1) and Al16Co23Cr17Fe19Ni25 (A2), were cast and characterized with an X-ray diffractometer, a scanning electron microscope, a differential scanning calorimeter, hardness tests, and tensile tests. The semi-empirical method of combining empirical fitting of mechanical data in the literatures and thermodynamic calculation showed qualitatively agreements between experiments and predictions. While the CALPHAD modeling successfully interpreted the formation of phases and microstructures, the accuracy of empirical predictions can be further improved when more data are accessible for alloy and MPEA design under the guidance of calculations.

SuperMat: construction of a linked annotated dataset from superconductors-related publications

A growing number of papers are published in the area of superconducting materials science. However, novel text and data mining (TDM) processes are still needed to efficiently access and exploit this accumulated knowledge, paving the way towards data-driven materials design. Herein, we present SuperMat (Superconductor Materials), an annotated corpus of linked data derived from scientific publications on superconductors, which comprises 142 articles, 16052 entities, and 1398 links that are characterised into six categories: the names, classes, and properties of materials; links to their respective superconducting critical temperature (Tc); and parametric conditions such as applied pressure or measurement methods. The construction of SuperMat resulted from a fruitful collaboration between computer scientists and material scientists, and its high quality is ensured through validation by domain experts. The quality of the annotation guidelines was ensured by satisfactory Inter Annotator Agreement (IAA) between the annotators and the domain experts. SuperMat includes the dataset, annotation guidelines, and annotation support tools that use automatic suggestions to help minimise human errors.

Center-Environment Feature Model for Machine Learning Study of Spinel Oxides Based on First-Principles Computations

Spinel oxides have attracted extensive attention due to their unique physical, chemical, optical, and electronic properties with their applications in lithium batteries, photocatalysts, and ferroelectricity. Owing to a large number of possible cation substitutions, many novel potential oxides are yet to be discovered with interesting properties. Inspired by the data-driven materials design approach, in this work, we developed machine learning (ML) models based on the first-principles computational data to investigate the energy and structure properties of normal cubic spinel oxides. The density functional theory (DFT) calculations were first carried out for 5329 spinel oxides with cubic AB2O4 structures where A and B sites were substituted with 73 elements, respectively. We predicted 451 new spinel oxides more stable than all the studied known experimental structures worth for further experimental investigation. We found the “good” A/B elements stabilizing spinel oxides include II–IV group elements and rare-earth elements in the periodic table. Furthermore, we proposed a new "Center-Environment" (CE) model to construct features containing both the composition and structure information as inputs to machine learning algorithms. Based on the DFT data, we developed ML models using a support vector regression algorithm to predict accurately and efficiently the formation energies, lattice parameters, and band gaps of spinel oxides. The composition design principles proposed in this work prompt the experimental discovery of new spinel oxides and the CE feature model can be generally applied in the data-driven materials design by ML methods.

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, ≈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.