Adaptive Strategies for Materials Design using Uncertainties

We compare several adaptive design strategies using a data set of 223 M2AX family of compounds for which the elastic properties [bulk (B), shear (G), and Young’s (E) modulus] have been computed using density functional theory. The design strategies are decomposed into an iterative loop with two main steps: machine learning is used to train a regressor that predicts elastic properties in terms of elementary orbital radii of the individual components of the materials; and a selector uses these predictions and their uncertainties to choose the next material to investigate. The ultimate goal is to obtain a material with desired elastic properties in as few iterations as possible. We examine how the choice of data set size, regressor and selector impact the design. We find that selectors that use information about the prediction uncertainty outperform those that don’t. Our work is a step in illustrating how adaptive design tools can guide the search for new materials with desired properties.

[1]  Donald R. Jones,et al.  Efficient Global Optimization of Expensive Black-Box Functions , 1998, J. Glob. Optim..

[2]  D. Cromer,et al.  Orbital Radii of Atoms and Ions , 1965 .

[3]  Alok Choudhary,et al.  Combinatorial screening for new materials in unconstrained composition space with machine learning , 2014 .

[4]  Somnath Datta,et al.  Informatics-aided bandgap engineering for solar materials , 2014 .

[5]  Kristin A. Persson,et al.  Commentary: The Materials Project: A materials genome approach to accelerating materials innovation , 2013 .

[6]  Andy J. Keane,et al.  Recent advances in surrogate-based optimization , 2009 .

[7]  Amin Zollanvari,et al.  The Illusion of Distribution-Free Small-Sample Classification in Genomics , 2011, Current genomics.

[8]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[9]  Gerald M. Maggiora,et al.  On Outliers and Activity Cliffs-Why QSAR Often Disappoints , 2006, J. Chem. Inf. Model..

[10]  Warren B. Powell,et al.  Optimal Learning: Powell/Optimal , 2012 .

[11]  D R McKenzie,et al.  A comprehensive survey of M2AX phase elastic properties , 2009, Journal of physics. Condensed matter : an Institute of Physics journal.

[12]  R. Ramprasad,et al.  Machine Learning in Materials Science , 2016 .

[13]  Michel W. Barsoum,et al.  Elastic and Mechanical Properties of the MAX Phases , 2011 .

[14]  Zoubin Ghahramani,et al.  Probabilistic machine learning and artificial intelligence , 2015, Nature.

[15]  Ridwan Sakidja,et al.  A genomic approach to the stability, elastic, and electronic properties of the MAX phases , 2014 .

[16]  Yousef Saad,et al.  Data mining for materials: Computational experiments with AB compounds , 2012 .

[17]  Tim Mueller,et al.  Machine Learning in Materials Science , 2016 .

[18]  Alok Choudhary,et al.  A predictive machine learning approach for microstructure optimization and materials design , 2015, Scientific Reports.

[19]  Warren B. Powell,et al.  The Knowledge-Gradient Policy for Correlated Normal Beliefs , 2009, INFORMS J. Comput..

[20]  H. K. D. H. Bhadeshia,et al.  Neural Networks in Materials Science , 1999 .

[21]  Krishna Rajan,et al.  Identifying the ‘inorganic gene’ for high-temperature piezoelectric perovskites through statistical learning , 2011, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[22]  Felix A Faber,et al.  Crystal structure representations for machine learning models of formation energies , 2015, 1503.07406.

[23]  Sergei V. Kalinin,et al.  Big-deep-smart data in imaging for guiding materials design. , 2015, Nature materials.

[24]  Travis E. Jones,et al.  Extreme Poisson's ratios and their electronic origin in B2 CsCl-type AB intermetallic compounds , 2012 .

[25]  G. Schneider,et al.  Voyages to the (un)known: adaptive design of bioactive compounds. , 2009, Trends in biotechnology.

[26]  Muratahan Aykol,et al.  Materials Design and Discovery with High-Throughput Density Functional Theory: The Open Quantum Materials Database (OQMD) , 2013 .

[27]  Sanguthevar Rajasekaran,et al.  Accelerating materials property predictions using machine learning , 2013, Scientific Reports.

[28]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[29]  Krishna Rajan,et al.  Materials Informatics: The Materials ``Gene'' and Big Data , 2015 .

[30]  Min Ji,et al.  Influence of the electronic structure on the ductile behavior of B2 CsCl-type AB intermetallics , 2009 .

[31]  Surya R. Kalidindi,et al.  Materials Data Science: Current Status and Future Outlook , 2015 .

[32]  Liping Yu,et al.  Prediction and accelerated laboratory discovery of previously unknown 18-electron ABX compounds. , 2014, Nature chemistry.

[33]  Atsuto Seko,et al.  Machine learning with systematic density-functional theory calculations: Application to melting temperatures of single- and binary-component solids , 2013, 1310.1546.

[34]  M Eberhart.  Charge-density-shear-moduli relationships in aluminum-lithium alloys. , 2001, Physical review letters.

[35]  Marco Buongiorno Nardelli,et al.  The high-throughput highway to computational materials design. , 2013, Nature materials.

[36]  James Theiler,et al.  Materials Prediction via Classification Learning , 2015, Scientific Reports.