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.

Refractory high-entropy alloys (RHEAs) show significant elevated-temperature yield strengths and have potential to use as high-performance materials in gas turbine engines. Exploring the vast RHEA compositional space experimentally is challenging, and a small fraction of this space has been explored to date. This work demonstrates the development of a state-of-the-art machine learning framework coupled with optimization methods to intelligently explore the vast compositional space and drive the search in a direction that improves high-temperature yield strengths. Our yield strength model is shown to have a significantly improved predictive accuracy relative to the state-of-the-art approach, and also provides inherent uncertainty quantification through the use of repeatedk-fold cross-validation. Upon developing and validating a robust yield strength prediction model, the coupled framework is used to discover RHEAs with superior high temperature yield strength. We have shown that RHEA compositions can be customized to have maximum yield strength at a specific temperature.

This paper develops a statistical learning approach to identify potentially new high-temperature ferroelectric piezoelectric perovskite compounds. Unlike most computational studies on crystal chemistry, where the starting point is some form of electronic structure calculation, we use a data-driven approach to initiate our search. This is accomplished by identifying patterns of behaviour between discrete scalar descriptors associated with crystal and electronic structure and the reported Curie temperature ( T _C ) of known compounds; extracting design rules that govern critical structure–property relationships; and discovering in a quantitative fashion the exact role of these materials descriptors. Our approach applies linear manifold methods for data dimensionality reduction to discover the dominant descriptors governing structure–property correlations (the ‘genes’) and Shannon entropy metrics coupled to recursive partitioning methods to quantitatively assess the specific combination of descriptors that govern the link between crystal chemistry and T _C (their ‘sequencing’). We use this information to develop predictive models that can suggest new structure/chemistries and/or properties. In this manner, BiTmO ₃ –PbTiO ₃ and BiLuO ₃ –PbTiO ₃ are predicted to have a T _C of 730 ^° C and 705 ^° C, respectively. A quantitative structure–property relationship model similar to those used in biology and drug discovery not only predicts our new chemistries but also validates published reports.

This paper describes a database framework that enables one to rapidly explore systematics in structure-function relationships associated with new and emerging PFAS chemistries. The data framework maps high dimensional information associated with the SMILES approach of encoding molecular structure with functionality data including bioactivity and physicochemical property. This ‘PFAS-Map’ is a 3-dimensional unsupervised visualization tool that can automatically classify new PFAS chemistries based on current PFAS classification criteria. We provide examples on how the PFAS-Map can be utilized, including the prediction and estimation of yet unmeasured fundamental physical properties of PFAS chemistries, uncovering hierarchical characteristics in existing classification schemes, and the fusion of data from diverse sources.

In engineering design, we are constantly faced with the need to describe the behavior of complex engineered systems for which there is no closed‐form solution. There is rarely a single multiscale theory or experiment that can meaningfully and accurately capture such information primarily due to the inherently multivariate nature of the variables influencing materials behavior. Seeking structure‐property relationships is an accepted paradigm in materials science, yet these relationships are often not linear, and so the challenge is to seek patterns among multiple length and time scales. In this paper, we present two separate but complementary examples of addressing the issue of high‐dimensional data in materials science in the spirit of the intellectual focus of this new journal. The first example uses principal component analysis and the second example uses statistical analysis coupled to dimensional analysis. Copyright © 2009 Wiley Periodicals, Inc., A Wiley Company