How Chemical Composition Alone Can Predict Vibrational Free Energies and Entropies of Solids

Legrain, Fleur; Carrete, Jesús; Roekeghem, Ambroise van; Curtarolo, Stefano; Mingo, Natalio

doi:10.1021/acs.chemmater.7b00789

Cited by 125 publications

(111 citation statements)

References 58 publications

Supporting

Mentioning

108

Contrasting

Order By: Relevance

“…A recent work reported the identification of lattice symmetries by representing crystals via diffraction image calculations, which then serve to construct a deep learning neural network model for classification [418]. Not only to structural properties, recently the vibrational free energies and entropies of compounds were studied by ML models and achieved good accuracy with only chemical compositions [419]. Even further, ML was used to predict interatomic force constants, which can then be used to obtain vibrational properties of metastable structures, good indicators of finite temperature stability [420].…”

Section: Discovery Energies and Stabilitymentioning

confidence: 99%

From DFT to machine learning: recent approaches to materials science–a review

et al. 2019

View full text Add to dashboard Cite

Recent advances in experimental and computational methods are increasing the quantity and complexity of generated data. This massive amount of raw data needs to be stored and interpreted in order to advance the materials science field. Identifying correlations and patterns from large amounts of complex data is being performed by machine learning algorithms for decades. Recently, the materials science community started to invest in these methodologies to extract knowledge and insights from the accumulated data. This review follows a logical sequence starting from density functional theory as the representative instance of electronic structure methods, to the subsequent high-throughput approach, used to generate large amounts of data. Ultimately, data-driven strategies which include data mining, screening, and machine learning techniques, employ the data generated. We show how these approaches to modern computational materials science are being used to uncover complexities and design novel materials with enhanced properties. Finally, we point to the present research problems, challenges, and potential future perspectives of this new exciting field. characterized by its diverse and huge volume, usually ranging from terabytes to petabytes of data, being created in or near real-time. Such data is found either structured and unstructured in nature, and is exhaustive, usually aiming to capture entire populations in a scalable manner [7]. Simple tasks represent challenges in this scale: capture, curation, storage, search, sharing, analysis, and visualization of the data cannot be accomplished without the proper tools. Thus, it can be effectively summarized by the popular 'five V's': volume, velocity, variety, veracity, and value, shown in figure 3(right). A related sixth V is visualization, although not exclusive to Big Data, which requires different techniques to handle data with various characteristics.Striving to tackle the challenges imposed by Big Data, the field of Data Science has arisen. It is largely interdisciplinary being a combination of mathematics and statistics, computer science and programming, and domain knowledge for problem definition and solving, as shown in figure 3(left). Its objective is, roughly speaking, to deal with the whole process of data production, cleaning, preparation, and finally, analysis. Data science encompasses areas such as Big Data, which deals with large volumes of data, and data mining, which relates to analysis processes to discover patterns and extract knowledge from data, part of the so-called Knowledge Discovery in Databases (KDD).The analysis process within Data Science is challenging, as the techniques are very different from traditional static and rigid datasets, generated and analyzed under a predetermined hypothesis. The distinction from traditional data is based on the larger abundance, exhaustivity, and variety of Big Data. It is also much more dynamic, messy and uncertain, being highly relational [7]. Recently, the possibility of overcoming such a challenge slowly sta...

show abstract

Section: Discovery Energies and Stabilitymentioning

confidence: 99%

From DFT to machine learning: recent approaches to materials science–a review

et al. 2019

View full text Add to dashboard Cite

show abstract

“…1,2 One common task in materials informatics is the use of machine learning (ML) for the prediction of materials properties. Examples of recent models built with ML include steel fatigue strength, 3 small molecule properties calculated from density functional theory, 4 thermodynamic stability, 5 Gibbs free energies, 6 band gaps of inorganic compounds, 7 alloy formation enthalpies, 8 and grain boundary energies. 9 Across all of these applications, a training database of simulated or experimentally-measured materials properties serves as input to a ML algorithm that predictively maps features (i.e., materials descriptors) to target materials properties.…”

Section: Materials Informatics (Mi)mentioning

confidence: 99%

Can machine learning identify the next high-temperature superconductor? Examining extrapolation performance for materials discovery

Meredig

Antono

Church

et al. 2018

Mol. Syst. Des. Eng.

193

180

View full text Add to dashboard Cite

Traditional machine learning (ML) metrics overestimate model performance for materials discovery. We introduce (1) leave-onecluster-out cross-validation (LOCO CV) and (2) a simple nearestneighbor benchmark to show that model performance in discovery applications strongly depends on the problem, data sampling, and extrapolation. Our results suggest that ML-guided iterative experimentation may outperform standard high-throughput screening for discovering breakthrough materials like high-T c superconductors with ML.Materials informatics (MI), or the application of data-driven algorithms to materials problems, has grown quickly as a field in recent years. 9 Across all of these applications, a training database of simulated or experimentally-measured materials properties serves as input to a ML algorithm that predictively maps features (i.e., materials descriptors) to target materials properties. Ideally, the result of training such models would be the experimental realization of new materials with promising properties. The MI community has produced several such success stories, including thermoelectric compounds, 10,11 shapememory alloys, 12 superalloys, 13 and 3d-printable high-strength aluminum alloys. 14 However, in many cases, a model is itself the output of a study, and the question becomes: to what extent could the model be used to drive materials discovery? Typically, the performance of ML models of materials properties is quantified via cross-validation (CV). CV can be performed either in a single division of the available data into a training set (to build the model) and a test set (to evaluate its performance), or as an ensemble process known as k-fold CV wherein the data are partitioned into k nonoverlapping subsets of nearly equal size (folds) and model performance is averaged across each combination of k-1 training folds and one test fold. Leave-one-out crossvalidation (LOOCV) is the limit where k is the number of total examples in the dataset. Table 1 summarizes some examples of model performance statistics as reported in the aforementioned studies (some studies involved testing multiple algorithms across multiple properties).In Table 1, the reported model performance is uniformly excellent across all studies. A tempting conclusion is that any of these models could be used for one-shot high-throughput screening of large numbers of materials for desired properties. However, as we discuss below, traditional CV has critical shortcomings in terms of quantifying ML model performance for materials discovery. Issues with traditional crossvalidation for materials discoveryMany ML benchmark problems consist of data classification into discrete bins, i.e., pattern matching. For example, the Design, System, ApplicationMachine learning (ML) has become a widely-adopted predictive tool for materials design and discovery. Random k-fold cross-validation (CV), the traditional gold-standard approach for evaluating the quality of ML models, is fundamentally mismatched to the nature of materials discovery, and leads to ...

show abstract

“…The use of machine learning and data analytics to accelerate materials design and discovery through descriptor-based property prediction is becoming a standard approach in materials science, [17][18][19][20][21][22][23][24] however, these techniques have not previously been used to predict the Gibbs energies of inorganic crystalline solids.…”

Section: Introductionmentioning

confidence: 99%

Physical descriptor for the Gibbs energy of inorganic crystalline solids and temperature-dependent materials chemistry

et al. 2018

View full text Add to dashboard Cite

The Gibbs energy, G, determines the equilibrium conditions of chemical reactions and materials stability. Despite this fundamental and ubiquitous role, G has been tabulated for only a small fraction of known inorganic compounds, impeding a comprehensive perspective on the effects of temperature and composition on materials stability and synthesizability. Here, we use the SISSO (sure independence screening and sparsifying operator) approach to identify a simple and accurate descriptor to predict G for stoichiometric inorganic compounds with ~50 meV atom−1 (~1 kcal mol−1) resolution, and with minimal computational cost, for temperatures ranging from 300–1800 K. We then apply this descriptor to ~30,000 known materials curated from the Inorganic Crystal Structure Database (ICSD). Using the resulting predicted thermochemical data, we generate thousands of temperature-dependent phase diagrams to provide insights into the effects of temperature and composition on materials synthesizability and stability and to establish the temperature-dependent scale of metastability for inorganic compounds.

show abstract

How Chemical Composition Alone Can Predict Vibrational Free Energies and Entropies of Solids

Cited by 125 publications

References 58 publications

From DFT to machine learning: recent approaches to materials science–a review

From DFT to machine learning: recent approaches to materials science–a review

Can machine learning identify the next high-temperature superconductor? Examining extrapolation performance for materials discovery

Physical descriptor for the Gibbs energy of inorganic crystalline solids and temperature-dependent materials chemistry

Contact Info

Product

Resources

About