Materials discovery and design using machine learning

By Yue Liu, Tianlu Zhao, Wangwei Ju, S. Shi 施. 2017

1,161 citations recorded by the source corpus.

Abstract The screening of novel materials with good performance and the modelling of quantitative structure-activity relationships (QSARs), among other issues, are hot topics in the field of materials science. Traditional experiments and computational modelling often consume tremendous time and resources and are limited by their experimental conditions and theoretical foundations. Thus, it is imperative to develop a new method of accelerating the discovery and design process for novel materials. Recently, materials discovery and design using machine learning have been receiving increasing attention and have achieved great improvements in both time efficiency and prediction accuracy. In this review, we first outline the typical mode of and basic procedures for applying machine learning in materials science, and we classify and compare the main algorithms. Then, the current research status is reviewed with regard to applications of machine learning in material property prediction, in new materials discovery and for other purposes. Finally, we discuss problems related to machine learning in materials science, propose possible solutions, and forecast potential directions of future research. By directly combining computational studies with experiments, we hope to provide insight into the parameters that affect the properties of materials, thereby enabling more efficient and target-oriented research on materials discovery and design.

Subfields: Materials Chemistry, Mechanical Engineering

How researchers see this paper

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

In Materials Chemistry

In Mechanical Engineering

Citations in the corpus

Generative Counterfactual Introspection for Explainable Deep Learning (2019, background): “Knowing causal reasoning behind a prediction is vital in fields such as drug or material discovery [8] where the aim is to map a known value from the output (i.”
Machine learning: Accelerating materials development for energy storage and conversion (2020, methodology): “To construct a supercell model for composites, the lattice mismatch related to lattice parameters of all the constituents, has great influence on the product.(27) ML methods such as SVR, ANN, and linear regression (LR) have been used to predict lattice parameters for crystal materials.”
Recent advances in hot tearing during casting of aluminium alloys (2020, background): “Note that no single algorithm is appropriate for all situations, and selecting a suitable algorithm is essential to achieve a high prediction accuracy [187,188].”
Tackling Climate Change with Machine Learning (2019, background): “1) to accelerate the materials discovery process [75, 80, 81, 426] to maximize sorbent reusability and CO2 uptake while minimizing the heat required for CO2 release.”
Benchmarking materials property prediction methods: the Matbench test set and Automatminer reference algorithm (2020, background): “Similar multi-layer feature reduction was previously shown by Liu et al.15 to significantly improve ML performance across materials prediction tasks; the exact sequence of dimensionality reduction algorithms is determined by the pipeline preset or by the user.”
Opportunities and Challenges for Machine Learning in Materials Science (2020, methodology): “…Science Audus and de Pablo 2017 185 Polymer Informatics: Opportunities and Challenges Voyles 2017 73 Informatics and data science in materials microscopy Liu et al. 2017 170 Materials discovery and design using machine learning Ramprasad et al. 2017 186 Machine Learning and Materials Informatics:…”
The 2021 flexible and printed electronics roadmap (2021, background): “A less traditional approach to optimize printing parameters and ink properties could bemachine learning, which is taking root in other areas of materials science [104].”
Artificial Intelligence in Advanced Manufacturing: Current Status and Future Outlook (2020, neutral): “For example, the properties of materials, such as hardness, melting point, and molecular atomization energy, can be classi ﬁ ed and described at either the macroscopic or microscopic level [150].”
Physical metallurgy-guided machine learning and artificial intelligent design of ultrahigh-strength stainless steel (2019, background): “stainless steels with excellent properties were successfully developed via systematic experiments, the experimental trial and error approach is considered inefficient, limiting its capacity to explore unknown domains [7,8].”
A review of the application of machine learning in water quality evaluation (2022, methodology): “In machine learning, a branch of arti ﬁ cial intelligence, algorithms are used to analyze data and attempt to mine potential patterns in the data to predict new information [7,8].”