Accelerated search for materials with targeted properties by adaptive design

By D. Xue, P. Balachandran, J. Hogden, James Theiler, D. Xue, Turab Lookman. 2016

748 citations recorded by the source corpus.

Finding new materials with targeted properties has traditionally been guided by intuition, and trial and error. With increasing chemical complexity, the combinatorial possibilities are too large for an Edisonian approach to be practical. Here we show how an adaptive design strategy, tightly coupled with experiments, can accelerate the discovery process by sequentially identifying the next experiments or calculations, to effectively navigate the complex search space. Our strategy uses inference and global optimization to balance the trade-off between exploitation and exploration of the search space. We demonstrate this by finding very low thermal hysteresis (ΔT) NiTi-based shape memory alloys, with Ti50.0Ni46.7Cu0.8Fe2.3Pd0.2 possessing the smallest ΔT (1.84 K). We synthesize and characterize 36 predicted compositions (9 feedback loops) from a potential space of ∼800,000 compositions. Of these, 14 had smaller ΔT than any of the 22 in the original data set. Design of materials with targeted properties requires innovative approaches to guide researchers through complex search space. Here, the authors report an adaptive design strategy, using inference and global optimization methods, which can find shape memory alloys with very low thermal hysteresis.

Subfields: Biomaterials, Materials Chemistry

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomaterials

In Materials Chemistry

Citations in the corpus

Machine Learning and Materials Informatics: Recent Applications and Prospects (2017, methodology): “Some of the ﬁrst examples of using adaptive design for targeted materials discovery include identiﬁcation of shape memory alloys with low thermal hysteresis [46] and accelerated search for BaTiO 3 -based piezoelectrics with optimized morphotropic phase boundary [47].”
Tree-structured Parzen estimator: Understanding its algorithm components and their roles for better empirical performance (2023, background): “…upsurge, reflecting the rapid advancement of various research fields such as drug discovery (Schneider et al., 2020), material discovery (Xue et al., 2016; Li et al., 2017a; Vahid et al., 2018), financial applications (Gonzalvez et al., 2019), and hyperparameter optimization (HPO) of…”
Bayesian Optimization for Adaptive Experimental Design: A Review (2020, methodology): “In [23], Bayesian optimisation is applied in combinationwith a density functional theory (DFT) based computational tool to design low thermal hysteresis NiTi-based shape memory alloys.”
Materials informatics (2018, methodology): “Xue et al. (2016) developed an adaptive design approach, as schematically shown in Fig.”
Emerging materials intelligence ecosystems propelled by machine learning (2020, methodology): “These methods are collectively classified as Bayesian optimization or active learning, and are increasingly becoming a vital part of the materials science ML portfolio to plan experiments 23,24 .”
Physical metallurgy-guided machine learning and artificial intelligent design of ultrahigh-strength stainless steel (2019, methodology): “Due to its generally good performance, the RBF kernel has also been widely used in the prediction and design of material properties in several previous studies [36,42].”
Stable Bayesian optimization (2018, background): “For example, in alloy design [23], one of the main goals is to find the mixing proportion of a set of elements with the highest value of a physical property (e.”