Adaptive Strategies for Materials Design using Uncertainties

被引：173

作者：

Balachandran, Prasanna V. ^{[1
]}

Xue, Dezhen ^{[1
,2
]}

Theiler, James ^{[3
]}

Hogden, John ^{[4
]}

Lookman, Turab ^{[1
]}

机构：

[1] Los Alamos Natl Lab, Div Theoret, Los Alamos, NM 87545 USA

[2] Xi An Jiao Tong Univ, State Key Lab Mech Behav Mat, Xian 710049, Peoples R China

[3] Los Alamos Natl Lab, Intelligence & Space Res, POB 1663, Los Alamos, NM 87545 USA

[4] Los Alamos Natl Lab, Comp & Computat Sci, POB 1663, Los Alamos, NM 87545 USA

来源：

SCIENTIFIC REPORTS | 2016年 / 6卷

关键词：

CLASSIFICATION; OPTIMIZATION; INFORMATICS; PREDICTION; GENE;

D O I：

10.1038/srep19660

中图分类号：

O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

We compare several adaptive design strategies using a data set of 223 M(2)AX 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.

引用

页数：9

共 35 条

[21] A predictive machine learning approach for microstructure optimization and materials design [J].

Liu, Ruoqian ;

Kumar, Abhishek ;

Chen, Zhengzhang ;

Agrawal, Ankit ;

Sundararaghavan, Veera ;

Choudhary, Alok .

SCIENTIFIC REPORTS, 2015, 5

[22] On outliers and activity cliffs - Why QSAR often disappoints [J].

Maggiora, Gerald M. .

JOURNAL OF CHEMICAL INFORMATION AND MODELING, 2006, 46 (04) :1535-1535

[23] Combinatorial screening for new materials in unconstrained composition space with machine learning [J].

Meredig, B. ;

Agrawal, A. ;

Kirklin, S. ;

Saal, J. E. ;

Doak, J. W. ;

Thompson, A. ;

Zhang, K. ;

Choudhary, A. ;

Wolverton, C. .

PHYSICAL REVIEW B, 2014, 89 (09)

[24]

Mueller T, 2016, REV COMP CH, V29, P186

[25]

Pedregosa F, 2011, J MACH LEARN RES, V12, P2825

[26] Accelerating materials property predictions using machine learning [J].

Pilania, Ghanshyam ;

Wang, Chenchen ;

Jiang, Xun ;

Rajasekaran, Sanguthevar ;

Ramprasad, Ramamurthy .

SCIENTIFIC REPORTS, 2013, 3

[27]

Powell Warren B, 2012, Optimal learning, V841

[28] Materials Informatics: The Materials "Gene" and Big Data [J].

Rajan, Krishna .

ANNUAL REVIEW OF MATERIALS RESEARCH, VOL 45, 2015, 45 :153-169

[29] Data mining for materials: Computational experiments with AB compounds [J].

Saad, Yousef ;

Gao, Da ;

Thanh Ngo ;

Bobbitt, Scotty ;

Chelikowsky, James R. ;

Andreoni, Wanda .

PHYSICAL REVIEW B, 2012, 85 (10)

[30] Materials Design and Discovery with High-Throughput Density Functional Theory: The Open Quantum Materials Database (OQMD) [J].

Saal, James E. ;

Kirklin, Scott ;

Aykol, Muratahan ;

Meredig, Bryce ;

Wolverton, C. .

JOM, 2013, 65 (11) :1501-1509

← 1 2 3 4 →