Alloys innovation through machine learning: a statistical literature review

ABSTRACT

This review systematically analyzes over 200 publications to explore the growing role of data-driven methods and their potential benefits in accelerating alloy development. The review presents a comprehensive overview of different aspects of alloy innovation by machine learning and other computational approaches used in recent years. These methods harness the power of advanced simulation techniques and data analytics to expedite materials’ discovery, predict properties, and optimize performance. Through analysis, significant trends and disparities within the data discerned, while highlighting previously overlooked research gaps, thus underscoring areas that require further exploration. Machine Learning techniques are widely applied across various alloys, with a pronounced emphasis on steel and High Entropy Alloys. Notably, researchers primarily investigate the physical, mechanical, and catalytic properties of materials. In terms of methodology, while 68% of the examined papers rely on a single machine learning model, the remainder employ a range of 2 to 12 models, with Neural Network being the most prevalent choice. However, a notable concern arises as 53% of these papers do not share their dataset, and a staggering 81% do not provide access to their code. Paramount importance of adopting a systematic approach when scrutinizing machine learning methodologies is underscored. Analysis shows lack of consistency and diversity in the methods employed by researchers in the field of alloy development, highlighting the potential for improvement through standardization. The critical analysis of the literature not only reveals prevailing trends and patterns but also shines a light on the inherent limitations within the traditional trial-and-error paradigm.

GRAPHICAL ABSTRACT

IMPACT STATEMENT

Through statistical analysis of 200+ papers, this research identifies trends, patterns and gaps to highlight areas for further exploration in using machine learning for alloy development.

KEYWORDS:

• Alloy development
• machine learning
• data-driven research
• materials informatics
• materials genome initiative
• materials databases

Acknowledgements

We acknowledge Dr Taylor D.Sparks from The University of Utah for many useful discussions.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Authorship contribution statement

Alireza Valizadeh: Investigation, Data curation, Conceptualization, Methodology, Writing – original draft, Visualization, Writing – review & editing. Ryoji Sahara: Conceptualization, Writing – review & editing. Maaouia Souissi: Investigation, Conceptualization, Methodology, Writing – original draft, Supervision, Project administration, Writing – review & editing.

Additional information

Notes on contributors

Alireza Valizadeh

Alireza Valizadeh, is a distinguished scientist in materials informatics, and specializes in energy materials. With a Ph.D. from Brunel University London, he currently researches at NEX Power Ltd, utilizing AI and machine learning for materials development. Focused on the energy sector, his goal is to innovate sustainable energy solutions. In 2018, he was awarded the Frank Fitzgerald medal by the Institute of Materials, Mines and Minerals for his extensive work in the iron and steel industry. Through his pursuit of scientific excellence, Alireza shapes a sustainable energy landscape for societal and environmental benefits.

Ryoji Sahara

Ryoji Sahara, graduated in Materials Science from Tohoku University, Japan, in 2000. He worked as an assistant professor at the Institute for Materials Research (IMR) and later joined the National Institute for Materials Science (NIMS) as a principal researcher in 2003. At NIMS, he supervised postdoctoral researchers, leading projects on carbide formation in heat-resistant creep steels, oxidation of titanium alloys, and materials design using machine learning. He collaborates with researchers from Saveetha University, TU-Deft, and Ohio State University. As chairman and member of ACCMS, he contributes to computational materials science. With 60+ publications, he currently leads the Computational Structural Materials Group at NIMS’s Research Center for Structural Materials.

Maaouia Souissi

Maaouia Souissi, graduated from the National School of Engineering of Sfax in 2005 and worked as a research assistant in Tunisia until 2007. He obtained his Ph.D. in Materials Science from Tohoku University, Japan, in 2011. Following that, he conducted postdoctoral research at Osaka Prefecture University for five years, focusing on defect modeling in steels using density functional theory. In 2016, he joined NIMS, Japan, investigating structural materials modeling for high-strength heat-resistant applications. Later, he joined Brunel University London as a research fellow, collaborating with Constellium partnership on aluminum alloy development for aerospace and automotive purposes. He has over 15 years of research experience, contributed to prestigious journals, and actively participated in international conferences.