Prediction model of band gap for inorganic compounds by combination of density functional theory calculations and machine learning techniques

Lee, Joohwi; Seko, Akira; Shitara, Kazuki; Nakayama, Keiichi I.; Tanaka, Isao

doi:10.1103/physrevb.93.115104

Cited by 309 publications

(254 citation statements)

References 46 publications

Supporting

Mentioning

249

Contrasting

Unclassified

Order By: Relevance

“…Several successful examples have already been reported for organic chemistry reactions, including those that involve homogeneous catalysts . However, the applicability of ML predictions for heterogeneous catalysis have been limited mainly to computationally determined values such as band gaps, d‐band centers, and adsorption energies . For the practical use of ML for discovering new solid catalytic materials, not only first‐principles calculated values but also experimental values for specific catalytic reactions are needed, especially in heterogeneous catalysis because an adequate theoretical model for heterogeneous catalysis is not available.…”

Section: Introductionmentioning

confidence: 99%

Statistical Analysis and Discovery of Heterogeneous Catalysts Based on Machine Learning from Diverse Published Data

et al. 2019

View full text Add to dashboard Cite

The literature provides insights for catalyst design and discovery. Effective analysis of reported data using machine learning (ML) methods offers the ability to gain valuable information. However, utilizing the literature in this way has obstacles such as lack of compositional overlaps, bias from prior published data, and low sample counts for many elements. The present study describes an ML approach that considers elemental features as input representations instead of inputting catalyst compositions directly. This ML method has the potential for catalyst discovery, including catalytic reactions with limited catalyst composition overlap in the available data. Oxidative coupling of methane (OCM), water gas shift (WGS), and CO oxidation reactions were chosen to confirm the effectiveness of the proposed method by analysis using several state‐of‐the‐art ML methods. Among the ML methods tested, gradient boosting regression with XGBoost (XGB) provided the best results, and prediction accuracy was improved by the proposed approach for all three reaction types. In addition, a quantitative value of “feature importance score” was calculated to evaluate the most influential input variables on catalyst performance. Finally, catalyst optimization was explored using ML as a “surrogate” model, and the top 20 promising candidate catalysts were identified for the OCM reaction based on the optimization. The advantages of ML in catalysis analysis as well as the difficulties and limitations originating from the complexity of heterogeneous catalysis were explored.

show abstract

Section: Introductionmentioning

confidence: 99%

Statistical Analysis and Discovery of Heterogeneous Catalysts Based on Machine Learning from Diverse Published Data

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Examples can be found in the literature (e.g., Refs. [1][2][3][4]). Other candidates are simply a binary digit representing the presence of each element in a compound ( Fig.…”

Section: Compound Descriptorsmentioning

confidence: 99%

Descriptors for Machine Learning of Materials Data

2018

Self Cite

View full text Add to dashboard Cite

Descriptors, which are representations of compounds, play an essential role in machine learning of materials data. Although many representations of elements and structures of compounds are known, these representations are difficult to use as descriptors in their unchanged forms. This chapter shows how compounds in a dataset can be represented as descriptors and applied to machine-learning models for materials datasets.Keywords Machine-learning interatomic potential ⋅ Lattice thermal conductivity ⋅ Recommender system ⋅ Gaussian process ⋅ Bayesian optimization IntroductionRecent developments of data-centric approaches should accelerate the progress in materials science dramatically. Thanks to the recent advances in computational power and techniques, the results from numerous density functional theory (DFT) calculations with predictive performances have been stored as databases. A combination of such databases and an efficient machine-learning approach should realize prediction and classification models of target physical properties. Consequently, machine-learning techniques are becoming ubiquitous. They are used to explore materials and structures from a huge number of candidates and to extract meaningful information and patterns from existing data.A key factor in controlling the performance of a machine-learning approach is how compounds are represented in a data set. Representations of compounds are called "descriptors" or "features". To perform machine-learning modeling, available descriptors must be determined according to the evaluation cost of the target property

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.

212

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

Prediction model of band gap for inorganic compounds by combination of density functional theory calculations and machine learning techniques

Abstract: Machine learning techniques are applied to make prediction models of the G 0 W 0 band-gaps for 156 AX binary compounds using Kohn-Sham band-gaps and other fundamental information of constituent elements and crystal structure as predictors. Ordinary least square regression (

Cited by 309 publications

References 46 publications

Statistical Analysis and Discovery of Heterogeneous Catalysts Based on Machine Learning from Diverse Published Data

Statistical Analysis and Discovery of Heterogeneous Catalysts Based on Machine Learning from Diverse Published Data

Descriptors for Machine Learning of Materials Data

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

Contact Info

Product

Resources

About