Classification of Oxide Compounds through Data‐Mining Density of States Spectra

Broderick, Scott; Aourag, H.; Rajan, Krishna

doi:10.1111/j.1551-2916.2011.04476.x

Cited by 31 publications

(19 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A larger-scale version of DOS classification was performed by Isayev et al, 70 who grouped together structures in the AFLOWlib 39 database through the use of a "D-fingerprint" to encode DOS information (similar to the encoding used by Broderick et al 84 described previously). Rather than assessing similarity in the space of principal components, the distance between these D-fingerprint vectors was computed directly and used to construct force-directed graphs that placed materials with similar DOS together.…”

Section: Clusteringmentioning

confidence: 99%

“…Often, only a few principal components are needed to explain most of the data variance, allowing clustering to be performed in a small number of dimensions (e.g., 2 or 3) and subsequently visualized. One example of such a clustering analysis is the classification of oxide DOS spectra performed by Broderick et al 84 In this study, DFT-based DOS data for 13 compounds were normalized and aligned such that each DOS was parametrized as a 1000 element vector relating energies to number of states. A principal components analysis was then applied to determine which parts of the DOS explained the greatest difference between materials; i.e., the first principle component, which is itself a 1000-element vector resembling a DOS, was highly related to the average difference in the DOS spectrum between monoclinic and cubic/tetragonal structures.…”

Section: Clusteringmentioning

confidence: 99%

See 1 more Smart Citation

New opportunities for materials informatics: Resources and data mining techniques for uncovering hidden relationships

et al. 2016

View full text Add to dashboard Cite

Data mining has revolutionized sectors as diverse as pharmaceutical drug discovery, finance, medicine, and marketing, and has the potential to similarly advance materials science. In this paper, we describe advances in simulation-based materials databases, open-source software tools, and machine learning algorithms that are converging to create new opportunities for materials informatics. We discuss the data mining techniques of exploratory data analysis, clustering, linear models, kernel ridge regression, tree-based regression, and recommendation engines. We present these techniques in the context of several materials application areas, including compound prediction, Li-ion battery design, piezoelectric materials, photocatalysts, and thermoelectric materials. Finally, we demonstrate how new data and tools are making it easier and more accessible than ever to perform data mining through a new analysis that learns trends in the valence and conduction band character of compounds in the Materials Project database using data on over 2500 compounds.Materials science has traditionally been driven by scientific intuition followed by experimental study. In recent years, theory and computation have provided a secondary avenue for materials property prediction and design. Several successful examples of materials designed in a computer and then realized in the laboratory 1 have now established such methods as a new route for materials discovery and optimization. As computational methods approach maturity, new and complementary techniques based on statistical analysis and machine learning are poised to revolutionize materials science.While the modern use of the term materials informatics dates back only a decade ago, 2 the use of an informatics approach to chemistry and materials science is as old as the periodic table. When Mendeleev grouped together elements by their properties, the electron was yet to be discovered, and the principles of electron configuration and quantum mechanics that underpin chemistry were still many decades away. However, Mendeleev's approach not only resulted in a useful classification but could also make predictions: missing positions in the periodic table indicated potential new elements that were later confirmed experimentally. Mendeleev was also able to spot inaccuracies in atomic weight data of the time. Today, the search for patterns in data remains the goal of materials informatics, although the tools have evolved considerably since Mendeleev's work.While materials informatics methods are still in their infancy compared to other fields, advancements in materials databases and software in the last decade are rapidly gaining ground. In this paper, we discuss recent developments of materials informatics, concentrating specifically on connecting a material's crystal structure and its composition to its properties (and ignoring, for instance, microstructure and processing). First, we provide a brief history of classic studies based on mining crystallographic databases. Next, we describe the recent...

show abstract

Section: Clusteringmentioning

confidence: 99%

Section: Clusteringmentioning

confidence: 99%

New opportunities for materials informatics: Resources and data mining techniques for uncovering hidden relationships

et al. 2016

View full text Add to dashboard Cite

show abstract

“…Even today, with the tremendous advancements in high-throughput electronic structure calculations, these design rules are guideposts in the interpretation of what, from a data science perspective, is a classification problem. Examples include the classical Hume-Rothery rules for substitutional alloys and the Philips-Van Vechten rules for classifying compounds on the basis of their ionicity (4,(39)(40)(41)(42)(43). Such design rules, although useful for retrospectively creating groupings among chemistry-structure relationships, have had a lesser impact on structure-property prediction.…”

Section: Applicationsmentioning

confidence: 97%

Materials Informatics: The Materials “Gene” and Big Data

Rajan

2015

Annu. Rev. Mater. Res.

Self Cite

255

150

View full text Add to dashboard Cite

Materials informatics provides the foundations for a new paradigm of materials discovery. It shifts our emphasis from one of solely searching among large volumes of data that may be generated by experiment or computation to one of targeted materials discovery via high-throughput identification of the key factors (i.e., "genes") and via showing how these factors can be quantitatively integrated by statistical learning methods into design rules (i.e., "gene sequencing") governing targeted materials functionality. However, a critical challenge in discovering these materials genes is the difficulty in unraveling the complexity of the data associated with numerous factors including noise, uncertainty, and the complex diversity of data that one needs to consider (i.e., Big Data). In this article, we explore one aspect of materials informatics, namely how one can efficiently explore for new knowledge in regimes of structure-property space, especially when no reasonable selection pathways based on theory or clear trends in observations exist among an almost infinite set of possibilities. 153 Annu. Rev. Mater. Res. 2015.45:153-169. Downloaded from www.annualreviews.org Access provided by Yale University -Law Library on 07/04/15. For personal use only.

show abstract

“…PCA operates by defining a linear combination of the descriptors that captures the most independent information in the dataset. [59][60][61] In this way, by ordering the new axes in terms of the corresponding information, the data may be described in fewer dimensions with a minimum loss of information. The relationships uncovered and the corresponding visualizations become more robust and interpretable.…”

Section: Trends Of Phase Stabilitymentioning

confidence: 99%

Computational discovery of stableM2AXphases

et al. 2016

Self Cite

View full text Add to dashboard Cite

The family of layered Mn+1AXn compounds provides a large class of materials with applications ranging from magnets, to high-temperature coatings, to nuclear cladding. In this work, we employ a density-functional theory based discovery approach to identify a large number of thermodynamically stable Mn+1AXn compounds, where n = 1, M = Sc, Ti, V, Cr, Zr, Nb, Mo, Hf, Ta; A = Al, Si, P, S, Ga, Ge, As, Cd, In, Sn, Tl, Pb; and X = C, N. We calculate the formation energy for 216 pure M2AX compounds and 10,314 solid solutions, (MM )2(AA )(XX ), relative to their competing phases. We find that the 49 experimentally known M2AX phases exhibit formation energies less than 30 meV/atom. Among the 10,530 compositions considered, 3,140 exhibit formation energies below 30 meV/atom, most of which have yet to be experimentally synthesized. A significant subset of 301 compositions exhibits strong exothermic stability in excess of 100 meV/atom, indicating favorable synthesis conditions. We identify empirical design rules for stable M2AX compounds. Among the metastable M2AX compounds are two Cr-based compounds with ferromagnetic ordering and expected Curie temperatures around 75K. These results can serve as a map for the experimental design and synthesis of previously unknown M2AX compounds.

show abstract

Classification of Oxide Compounds through Data‐Mining Density of States Spectra

Cited by 31 publications

References 18 publications

New opportunities for materials informatics: Resources and data mining techniques for uncovering hidden relationships

New opportunities for materials informatics: Resources and data mining techniques for uncovering hidden relationships

Materials Informatics: The Materials “Gene” and Big Data

Computational discovery of stableM2AXphases

Contact Info

Product

Resources

About