Prediction Of Material Properties Research Articles

Discovery of Novel Materials Through Machine Learning.

Experimental exploration of new materials relies heavily on a laborious trial-and-error approach. In addition to substantial time and resource requirements, traditional experiments and computational modelling are typically limited in finding target materials within the enormous chemical space. Therefore, creating innovative techniques to expedite material discovery becomes essential. Recently, machine learning has emerged as a valuable tool for material discovery, garnering significant attention due to its remarkable advancements in prediction accuracy and time efficiency. This rapidly developing computational technique accelerates the search and optimization process and enables the prediction of material properties at a minimal computational cost, thereby facilitating the discovery of novel materials. We provide a comprehensive overview of recent studies on discovering new materials by predicting materials and their properties using machine learning techniques. Beginning with an introduction of the fundamental principles of machine learning methods, we subsequently examine the current research landscape on the applications of machine learning in predicting material properties that lead to the discovery of novel materials. Finally, we discuss challenges in employing machine learning within materials science, propose potential solutions, and outline future research directions.

Introducing a new correlation functional in density functional theory

The correlation functional holds significance in density functional theory as it addresses electron–electron interactions beyond the mean-field approximation, enhancing the accuracy of total energy calculations, electronic excitations, and the prediction of materials properties. There are several expressions to describe this energy, and each of them has a unique set of errors in calculating particular properties of materials. This work offers a new correlation functional by employing the density's dependence on ionization energy. We theoretically derived this functional and combined it with the previously reported ionization energy dependent exchange functional to investigate its effect on the total energy, bond energy, dipole moment, and zero-point energy of 62 molecules. The comparison of this new functional in respect to existing widely used correlation models including QMC, PBE, B3LYP and Chachiyo models shows how well it works in producing accurate results with minimal mean absolute error.

Machine learning accelerated the prediction of mechanical properties of copper modified by TMDs based on molecular dynamics simulation

Abstract In this study, we constructed a dataset of elastic modulus and ultimate stress for copper material enhanced by Transition Metal Dichalcogenides (TMDs) through Molecular Dynamics (MD) simulations. Subsequently, leveraging chemical insights, we selected appropriate descriptors and established machine learning prediction models for elastic modulus and ultimate stress, respectively. Finally, the performance of the machine learning models was evaluated using a test set. The results demonstrate excellent performance of the machine learning models in predicting material properties. This work presents a novel approach for efficient material screening, demonstrating the synergy between MD simulations and machine learning in advancing materials research and intelligent material selection platforms.

Differential impedance analysis — Extensions and applications in machine learning

The technique of differential impedance analysis (DIA) has shown promising results in identifying appropriate model orders when applied to electrochemical impedance spectroscopy (EIS) measurements of a given medium. However, even with this method it remains challenging to reliably deduce general material properties of the medium from impedance data alone. Here, we discuss a number of possible extensions and modifications of the technique and, in particular, an extension of the process from mere model order identification to a complete modelling approach. In addition, the combination of DIA and machine learning methods to predict material properties is explored. Our results were validated with impedance measurements between 20Hz and 1MHz of moulding sand containing varying amounts of quartz and chromite sand as well as bentonite and carbon.

Rewc-GNN Algorithm for the Property Prediction of Large-Scale Crystals.

The space group of a crystal describes the symmetry and periodic arrangement of its structure. As the fundamental element in the structure, it plays a vital role in determining the physical and chemical properties of crystals. The investigation of crystal space group information allows for the prediction of material properties, thereby providing guidance for material design and synthesis to enhance their performance or functionality. Currently prevalent first-principles-based computational methods exhibit good accuracy, but they rely heavily on computing resources, greatly limiting the efficiency of material screening. In this paper, our study is oriented toward the prediction the spatial group of crystals, and an algorithm named Rewc, based on graph neural networks (GNNs) is proposed. This algorithm encodes all atoms and the interactions between atoms in the crystal as features by combining Floyd algorithm and k-hop message passing and employs multilayer convolutional networks to extract connections between k layers. This allows for the automatic learning of more representative atomic vector representations through iterations of feature information for each atom and its neighbors. Experimental results demonstrate that the Rewc framework exhibits reliable accuracy and good generalization capabilities in predicting the crystal structure compared to previous GNN methods.

Rational Design of Deep Learning Networks Based on a Fusion Strategy for Improved Material Property Predictions.

The success of machine learning in predicting material properties is largely dependent on the design of the model. However, the current designs of deep learning models in materials science have the following prominent problems. First, the model design lacks a rational guidance strategy and heavily relies on a large amount of trial and error. Second, numerous deep learning models are utilized across various fields, each with its own advantages and disadvantages. Therefore, it is important to incorporate a fusion strategy to fully leverage them and further expand the design strategies of the models. To address these problems, we analyze that the main reason is the lack of a new feedback method rich in physical insights. In this study, we developed a feedback method called the Chemical Environment Clustering Vector (CECV) of compounds at different thresholds, which is rich in physical insights. Based on CECV, we rationally designed the Long Short-Term Memory and Gated Recurrent Unit fused with Deep Convolutional Neural Network (L-G-DCNN) to explore the field of structure-agnostic material property predictions. L-G-DCNN accurately captures the interactions between elements in compounds, enabling more accurate and efficient predictions of the material properties. Our results demonstrate that the performance of the L-G-DCNN surpasses the current state-of-the-art structure-agnostic models across 28 benchmark data sets, exhibiting superior sample efficiency and faster convergence speed. By employing different visualization methods, we demonstrate that the fusion strategy based on CECV significantly enhances the comprehension of the L-G-DCNN model design and provides a fresh perspective for researchers in the field of materials informatics.

Ab initio framework for deciphering trade-off relationships in multi-component alloys

While first-principles methods have been successfully applied to characterize individual properties of multi-principal element alloys (MPEA), their use in searching for optimal trade-offs between competing properties is hampered by high computational demands. In this work, we present a framework to explore Pareto-optimal compositions by integrating advanced ab initio-based techniques into a Bayesian multi-objective optimization workflow, complemented by a simple analytical model providing straightforward analysis of trends. We benchmark the framework by applying it to solid solution strengthening and ductility of refractory MPEAs, with the parameters of the strengthening and ductility models being efficiently computed using a combination of the coherent-potential approximation method, accounting for finite-temperature effects, and actively-learned moment-tensor potentials parameterized with ab initio data. Properties obtained from ab initio calculations are subsequently used to extend predictions of all relevant material properties to a large class of refractory alloys with the help of the analytical model validated by the data and relying on a few element-specific parameters and universal functions that describe bonding between elements. Our findings offer crucial insights into the traditional strength-vs-ductility dilemma of refractory MPEAs. The proposed framework is versatile and can be extended to other materials and properties of interest, enabling a predictive and tractable high-throughput screening of Pareto-optimal MPEAs over the entire composition space.

Structure-based out-of-distribution (OOD) materials property prediction: a benchmark study

In real-world materials research, machine learning (ML) models are usually expected to predict and discover novel exceptional materials that deviate from the known materials. It is thus a pressing question to provide an objective evaluation of ML model performances in property prediction of out-of-distribution (OOD) materials that are different from the training set. Traditional performance evaluation of materials property prediction models through the random splitting of the dataset frequently results in artificially high-performance assessments due to the inherent redundancy of typical material datasets. Here we present a comprehensive benchmark study of structure-based graph neural networks (GNNs) for extrapolative OOD materials property prediction. We formulate five different categories of OOD ML problems for three benchmark datasets from the MatBench study. Our extensive experiments show that current state-of-the-art GNN algorithms significantly underperform for the OOD property prediction tasks on average compared to their baselines in the MatBench study, demonstrating a crucial generalization gap in realistic material prediction tasks. We further examine the latent physical spaces of these GNN models and identify the sources of CGCNN, ALIGNN, and DeeperGATGNN’s significantly more robust OOD performance than those of the current best models in the MatBench study (coGN and coNGN) as a case study for the perovskites dataset, and provide insights to improve their performance.

Designing of potential polymer donors with lower reorganization energy and chemical space exploration in search of materials for efficient organic solar cells

Machine learning with fascinating material predicting capabilities has emerged as a growing throughput artificial intelligence technology to accelerate the design, screening and prediction of material properties. In this study, chemical descriptors are employed to train machine learning (ML) models for the designing of potential polymer donor materials aimed at enhancing the efficiency of organic solar cells (OSCs). To achieve this, ten ML models are evaluated. Among all, the random forest regressor model has shown better predictive ability. In addition, to quantify the importance of features, the numerical scores of the significance of the features are determined through Feature importance analysis. Moreover, 10k new polymers are generated employing the python-based method and their reorganization energies are further predicted using a pre-trained ML model. The assemblage of polymers is done on the basis of the reorganization energy, those with lower reorganization energy being preferred. Furthermore, the synthetic accessibility and thus the structural diversity among the chosen polymers donors are examined, revealing a structural difference among the chosen polymers. This work paves a way for the designing and screening of efficient semiconductors with low reorganization energy to increase the efficiency of OSCs.

AtomGPT: Atomistic Generative Pretrained Transformer for Forward and Inverse Materials Design.

Large language models (LLMs) such as generative pretrained transformers (GPTs) have shown potential for various commercial applications, but their applicability for materials design remains underexplored. In this Letter, AtomGPT is introduced as a model specifically developed for materials design based on transformer architectures, demonstrating capabilities for both atomistic property prediction and structure generation. This study shows that a combination of chemical and structural text descriptions can efficiently predict material properties with accuracy comparable to graph neural network models, including formation energies, electronic bandgaps from two different methods, and superconducting transition temperatures. Furthermore, AtomGPT can generate atomic structures for tasks such as designing new superconductors, with the predictions validated through density functional theory calculations. This work paves the way for leveraging LLMs in forward and inverse materials design, offering an efficient approach to the discovery and optimization of materials.

Chemistry and Local Environment Adaptive Representation graphs as material descriptors

Accelerating materials design and property prediction via supervised learning involves manually generating feature vectors or performing complicated atom coordinates transformation, which restricts the model to a limited set of crystal structures or makes it challenging to provide chemical insights. In this work, we devised a unique low-dimensional featurization technique known as "Chemistry and Local Environment Adaptive Representation" (CLEAR) graphs to automatically learn the properties of materials through the chemistry of the atom connections. CLEAR is an adaptive featurization method that integrates the chemistry of atoms with their atomic environment using Voronoi nearest neighbours (NN). In addition, integrating the CLEAR descriptors with explainable machine learning models unravels its potential to obtain numerous scientific insights. We applied this approach to study the stability of compositional and configurational diverse high entropy alloys (HEAs). The proposed framework provides a universal low-dimensional representation with chemistry-informed local environment descriptors, which outperforms the prediction of phases and formation energies in HEAs.

Optimizing High-Entropy Alloys using Deep Neural Networks

Exceptional mechanical properties of multi-principal element alloys have been typically achieved through manual trial-and-error approaches. The advances in artificial neural networks (ANN) have recently allowed for the development of predictive alloy design ANN models that take into account a large variety of prior experimental findings. However, when mechanical performance is considered, prior processing protocols (e.g. annealing, cold working) are almost impossible to track across different research groups and material classes. In this work, we propose to reverse the use of the yield stress point, setting it as an explicit input (instead of predictive output) parameter that is then used for the quantification of the material state, towards predicting material properties, such as the Ultimate Tensile Strength (UTS). This novel approach specifically addresses the challenge of predicting and improving ductility, a common issue in existing methods focused on yield stress, hardness, and phases. By combining available, validated databases of eleven elements and 734 total materials, we develop an ANN that receives as input the compositions out of 11 possible elements and the "observed" yield stress. Then, we utilize this model to perform predictions for 5-element concentrated alloys with exceptional UTS. We show that this ANN modeling strategy leads to exceptional confidence scores, and then, we use this ANN model for the design of HEAs, which we further discuss.

Modeling Charged Defects Using the Defect Energy Formalism With a Charge Sublattice Within a CALPHAD Framework

AbstractThe non‐stoichiometry of material compounds significantly influences their functional properties. In semiconductors, point defects determine whether a material is n‐type or p‐type and the concentration of charge carriers. Even in structural alloys and ion conductors used in batteries and fuel cells, non‐stoichiometry and dilute defects play an integral role in their function. The design of metal alloys has advanced rapidly with the aid of thermodynamic modeling using calculation of phase diagrams (CALPHAD) to predict the phases produced during different processing conditions. While thermodynamic modeling has been done previously by fitting experimental data, the advent of first‐principle techniques has enabled the computational prediction of material properties. The defect energy formalism (DEF) is described for modeling charged and uncharged defects in compounds, showing that it accurately predicts non‐stoichiometry using density functional theory (DFT), without fitting experiments. The model reproduces the expected defect and free‐charge carrier concentrations using the statistical mechanics approach commonly used in most DFT defect studies. Finally, the model is used to accurately predict the single‐phase region of PbTe with no fitting to measured defect concentrations. This method can revolutionize materials development of insulators, semiconductors, and even metals by allowing rapid DFT calculations to replace laborious experiments when dilute defects are involved.

From density functional theory to machine learning predictive models for electrical properties of spinel oxides.

This work focuses on predicting and characterizing the electronic conductivity of spinel oxides, which are promising materials for energy storage devices and for the oxygen evolution and oxygen reduction reactions due to their attractive properties and abundance of transition metals that can act as active sites for catalysis. To this end, a new database was developed from first principles, including band structure and conductivity properties of spinel oxides, and machine learning algorithms were trained on this database to predict electronic conductivity and band gaps based solely on the compositions. The models developed in this study are scaled from the quantum level up to a continuum conductivity model. The relatively small database used in this study allowed for accurate predictions of band gap and conductivity. By altering the composition of spinel oxides, the model was able to predict high conductivity for spinels with high nickel content and to match experimental trends for manganese cobalt spinels. The ability to predict material properties is especially important in energy conversion devices such as batteries and supercapacitors where redox reactions take place.

Metals strengthen with increasing temperature at extreme strain rates

The strength of materials depends on the rate at which they are tested, as defects, for example dislocations, that move in response to applied strains have intrinsic kinetic limitations1–4. As the deformation strain rate increases, more strengthening mechanisms become active and increase the strength4–7. However, the regime in which this transition happens has been difficult to access with traditional micromechanical strength measurements. Here, with microballistic impact testing at strain rates greater than 106 s−1, and without shock conflation, we show that the strength of copper increases by about 30% for a 157 °C increase in temperature, an effect also observed in pure titanium and gold. This effect is counterintuitive, as almost all materials soften when heated under normal conditions. This anomalous thermal strengthening across several pure metals is the result of a change in the controlling deformation mechanism from thermally activated strengthening to ballistic transport of dislocations, which experience drag through phonon interactions1,8–10. These results point to a pathway to better model and predict materials properties under various extreme strain rate conditions, from high-speed manufacturing operations11 to hypersonic transport12.

Plantar pressure distribution using personalised 3D printed lattice insoles with distributed stiffness

This work presents a proof-of-concept study on the use of additive manufacturing for developing customised lattice topology insoles, with the aim of redistributing plantar pressures. Four cubic lattice structures were applied to five sections of the moulded insole contours, which were based in 3D foot scans using Ansys material designer to predict material properties. The variation of the elastic modulus across the sections was controlled via the lattice cell structure volume ratio. The insole lattice structures were made from elastic photosensitive liquid resin resulting in flexible parts. A commercially available shoe was used to compare pressure distribution between the original and customised insole. Plantar pressure distribution and peak pressures were measured during standing, walking, and running. Pressure redistribution varied between insole conditions. During standing, the customised insole reduced peak pressure at the left heel, while the right foot experienced increased peak pressure compared to the control insole. Substantial peak pressure reduction was observed on the left foot during walking and running whilst the reduction was much less for the right foot. The study highlights the potential of additive manufacturing for cost-effective, accurate, and personalized insole production, offering material control and pressure redistribution benefits for various applications like injury prevention and rehabilitation.

Uncertainty quantification in multivariable regression for material property prediction with Bayesian neural networks

With the increased use of data-driven approaches and machine learning-based methods in material science, the importance of reliable uncertainty quantification (UQ) of the predicted variables for informed decision-making cannot be overstated. UQ in material property prediction poses unique challenges, including multi-scale and multi-physics nature of materials, intricate interactions between numerous factors, limited availability of large curated datasets, etc. In this work, we introduce a physics-informed Bayesian Neural Networks (BNNs) approach for UQ, which integrates knowledge from governing laws in materials to guide the models toward physically consistent predictions. To evaluate the approach, we present case studies for predicting the creep rupture life of steel alloys. Experimental validation with three datasets of creep tests demonstrates that this method produces point predictions and uncertainty estimations that are competitive or exceed the performance of conventional UQ methods such as Gaussian Process Regression. Additionally, we evaluate the suitability of employing UQ in an active learning scenario and report competitive performance. The most promising framework for creep life prediction is BNNs based on Markov Chain Monte Carlo approximation of the posterior distribution of network parameters, as it provided more reliable results in comparison to BNNs based on variational inference approximation or related NNs with probabilistic outputs.

Material Property Prediction Using Machine Learning

The ability to accurately predict the properties of materials is crucial for numerous applications across various industries, including materials science, engineering, and manufacturing. With the advent of machine learning (ML) techniques, researchers have gained powerful tools to model and predict material properties based on their composition, structure, and processing conditions. This review paper provides a comprehensive overview of material property prediction using machine learning. It covers the historical development, available ML models, recent trends, and prospects in this rapidly evolving domain.

JARVIS-Leaderboard: a large scale benchmark of materials design methods

Lack of rigorous reproducibility and validation are significant hurdles for scientific development across many fields. Materials science, in particular, encompasses a variety of experimental and theoretical approaches that require careful benchmarking. Leaderboard efforts have been developed previously to mitigate these issues. However, a comprehensive comparison and benchmarking on an integrated platform with multiple data modalities with perfect and defect materials data is still lacking. This work introduces JARVIS-Leaderboard, an open-source and community-driven platform that facilitates benchmarking and enhances reproducibility. The platform allows users to set up benchmarks with custom tasks and enables contributions in the form of dataset, code, and meta-data submissions. We cover the following materials design categories: Artificial Intelligence (AI), Electronic Structure (ES), Force-fields (FF), Quantum Computation (QC), and Experiments (EXP). For AI, we cover several types of input data, including atomic structures, atomistic images, spectra, and text. For ES, we consider multiple ES approaches, software packages, pseudopotentials, materials, and properties, comparing results to experiment. For FF, we compare multiple approaches for material property predictions. For QC, we benchmark Hamiltonian simulations using various quantum algorithms and circuits. Finally, for experiments, we use the inter-laboratory approach to establish benchmarks. There are 1281 contributions to 274 benchmarks using 152 methods with more than 8 million data points, and the leaderboard is continuously expanding. The JARVIS-Leaderboard is available at the website: https://pages.nist.gov/jarvis_leaderboard/

Accelerating material property prediction using generically complete isometry invariants

Periodic material or crystal property prediction using machine learning has grown popular in recent years as it provides a computationally efficient replacement for classical simulation methods. A crucial first step for any of these algorithms is the representation used for a periodic crystal. While similar objects like molecules and proteins have a finite number of atoms and their representation can be built based upon a finite point cloud interpretation, periodic crystals are unbounded in size, making their representation more challenging. In the present work, we adapt the Pointwise Distance Distribution (PDD), a continuous and generically complete isometry invariant for periodic point sets, as a representation for our learning algorithm. The PDD distinguished all (more than 660 thousand) periodic crystals in the Cambridge Structural Database as purely periodic sets of points without atomic types. We develop a transformer model with a modified self-attention mechanism that combines PDD with compositional information via a spatial encoding method. This model is tested on the crystals of the Materials Project and Jarvis-DFT databases and shown to produce accuracy on par with state-of-the-art methods while being several times faster in both training and prediction time.