International Journal of

Advances in Scientific Research and Engineering (ijasre) E-ISSN : 2454-8006

DOI: 10.31695/IJASRE.2021.34057 Volume 7, Issue 8

August - 2021

Artificial Intelligence in Materials Science

Matthew N. O. Sadiku, Guddi K. Suman, and Sarhan M. Musa

Roy G. Perry College of Engineering

Prairie View A&M University

Prairie View, TX 77446

_______________________________________________________________________________________________
ABSTRACT
Artificial intelligence (AI) is changing the way we discover new materials. The emergence of AI brings a
new dawn to the development of material science. It enables material researchers to harness the power of
machine learning and artificial intelligence to develop a system that autonomously discovers new materials.
AI is also helping materials scientists and engineers to revolutionize the way of understanding and
discovering materials used in applications ranging from aerospace engineering to soft robotic prosthetics.
This paper provides an introduction to the uses of AI in materials science.
Key Words: Artificial Intelligence, Machine Learning, Materials, Research.

1. INTRODUCTION
Materials have been key to the growth, prosperity, security, and life quality of humans. Material science
mainly aims at exploring the relationship between materials structure, process, properties, and application.
Over the past few years, materials science has undergone a rapid transformation facilitated by the pervasive
data revolution. Traditional materials science research is a time-consuming, human-centered process that
takes a certain kind of individual with the knowledge, patience, and understanding to design, conduct,
analyze, and interpret experimental data.
Materials scientists are often seeking for materials that have superior properties. They characterize and
measure the properties of materials using three major tools: analytical, experimental, and computer
simulation [1]. Scientific discovery evolves from the “experimental” through the “analytical” and
“computational.” Experiments have traditionally been used to play a key role in characterizing or designing
new materials. Simulation is essentially computational modeling. A combination of experimentation and
computer simulations has contributed towards exploring materials design more economically [2]. It has
allowed researchers to cut substantially the time and cost of materials design.
One of the most exciting tools that have entered the material science toolbox is artificial intelligence.
The emergence of artificial intelligence (AI) brings a new dawn to the development of material science. The
main purpose of AI is to aid human capabilities and help us make advanced decisions with far-reaching
consequences. There has been an ever-increasing application of machine learning (ML) and artificial
intelligence (AI) techniques by materials researchers.

www.ijasre.net Page 77
Licensed Under Creative Commons Attribution CC BY-NC
International Journal of Advances in Scientific Research and Engineering (ijasre), Vol 7 (8), August -2021

2. REVIEW ON ARTIFICIAL INTELLIGENCE

Artificial intelligence (AI) refers to computer systems that mimic human cognitive functions. It is a field
of computer science that deals with intelligent machines. AI has a long history that is actively and constantly
changing and growing. The term “artificial intelligence” was first used at a Dartmouth College
conference in 1956. The main goal of AI is to enable machines to perform complex tasks that typically
require human intelligence [3, 4]. In simple terms, AI attempts to clone human behavior. An important
feature of AI technology is that it can be added to existing technologies. AI is now one of the most
important global issues of the 21st century. It is poised to disrupt our world and change processes and
developments in science, engineering, education, business, entertainment, and agriculture.
The concept of AI is an umbrella term that encompasses many different technologies. AI is not a
single technology but a collection of techniques that enables computer systems to perform tasks that would
otherwise require human intelligence [5]. The major disciplines in AI include:
 Expert systems
 Fuzzy logic
 Neural networks
 Machine learning (ML)
 Deep learning
 Natural Language Processors (NLP)
 Robots
These AI tools are illustrated in Figure 1. Each AI tool has its own advantages. Using a combination of
these models rather than a single model is recommended. AI systems are designed to make decisions using
real-time data. They have the ability to learn and adapt as they make decisions.
AI has benefited many areas such as chemistry and medicine, where routine diagnoses can be initiated
by AI-aided computers. It embraces a wide range of disciplines such as computer science, engineering,
machine learning, chemistry, biology, physics, astronomy, medicine, neuroscience, social sciences, and the
military. Today, AI algorithms are integrated into our daily lives in several forms, such as personal
assistants, automated mass transportation, aviation, computer gaming, facial recognition at passport control,
voice recognition on virtual assistants, driverless cars, companion robots, wearables, etc. [6]. AI algorithms
are increasingly used to open up new horizons for scientists and engineers.

3. A.I. IN MATERIALS SCIENCE

Modern civilization heavily depends on technology. Materials have always been technology enablers,
and currently, there are many key technology areas that await materials discovery and processing solutions.
Addressing these opportunities will drive and propel the required developments. Today, we can harness the
power of digital technologies to accelerate the discovery of new materials by marrying AI and materials
science. The marriage of artificial intelligence and materials science represents one of the examples of the
fourth industrial revolution. Computational materials science has made significant progress since the
concept of materials science in the 1950s.
Traditionally, materials scientists have been using a conventional experimental process to identify and
discover new composite materials from scratch. They design a new material, make it, and then test it, but
this approach is time-consuming and subject to error. The development of new materials is painfully slow.
www.ijasre.net Page 78

DOI: 10.31695/IJASRE.2021.34057
International Journal of Advances in Scientific Research and Engineering (ijasre), Vol 7 (8), August -2021

AI, when applied to material science, offers the possibility of speeding up the materials-discovery
process. Figure 2 illustrates the application of AI in material science [7]. Machine learning, a branch of AI,
gives us a tool to search a large amount of space in little time. It often requires input on what to look for,
where to look, and data that the machine can learn from.

4. APPLICATIONS
There are various applications of AI and ML in materials science. Current applications of AI in materials
science focus more on solving engineering and design problems than on directly deriving fundamental
scientific insight from data. A FAIR treatment encompasses the four principles: findability, accessibility,
interoperability, and repurposability. The FAIR principles can guide the materials science and engineering
community in developing infrastructure suited to collaboration [8].
Some companies are capitalizing on using AI to develop advanced materials.
Citrine Informatics has developed AI software to narrow the choice of materials to test for a given
application. Zymergenis combines AI and automation in biology and materials science to improve industrial
microbes.

5. BENEFITS
We are currently experiencing an explosion of works that develop and apply AI to materials. Advances
in AI for materials research are as important as ever for accelerating innovation in materials. Artificial
intelligence can help us more efficiently and effectively practice scientific inquiry. It could help promote the
development of material science and accelerate the invention of new materials. Through the use of ML, AI
could outperform many material scientists and make a more efficient prediction of new materials. AI is
employed in modern materials research to develop new technologies. AI could reduce the time needed to
develop a new material to one-two years from the current 10-20 years [9].

6. CHALLENGES
AI and machine learning face some challenges and limitations machine in their application to materials
science. To expand the application of AI methods and realize the full potential of AI, the materials
community must develop AI systems that can represent, evaluate, and perform inference about physical
mechanisms underlying observational data. Current applications of AI in materials science largely ignore the
uncertainty of the raw data used to train models [10].
One of the most significant concerns about deep learning in the scientific community right now is
regarding the accuracies of the results. In particular, there is no consensus on what is the minimum amount
of data required for a given property prediction.
For sure, AI will not completely replace human at the work of material research but will serve as a
powerful tool to accelerate the progress of materials discovery. Material researchers will need to learn to
master AI tools to decrease the trial error times, solve more difficult material problems [11].

www.ijasre.net Page 79

DOI: 10.31695/IJASRE.2021.34057
International Journal of Advances in Scientific Research and Engineering (ijasre), Vol 7 (8), August -2021

7. CONCLUSION
Artificial intelligence is a branch of computer science with the ambitious goal of studying and designing
intelligent systems. It has raised the expectation that AI can revolutionize scientific discovery in general and
materials science specifically. AI is also impacting materials science by employing machine learning
algorithms to automate specific research tasks. The scientific community is currently exploring the use of AI
for scientific discovery, among other things [12].
There is a critical need for workforce development to ensure that AI techniques are introduced into the
materials science workflow. It is therefore expedient to educate the next generation workforce to be
conversant in AI techniques. Materials science curricula need urgent restructuring to produce a competitive
next-generation workforce. More information on the uses of AI in material science can be found in the
books in [13, 14] and related journal: Materials Letters.
REFERENCES
[1] M. N. O. Sadiku, Computational Electromagnetics with MATLAB. Boca Raton: CRC Press, 4th ed., 2019, p. 1.
[2] R. Batra, “Accurate machine learning in materials science facilitated by using diverse data sources,” Nature, January
2021, pp. 524-525.
[3] M. N. O. Sadiku, "Artificial intelligence", IEEE Potentials, May 1989, pp. 35-39.
[4] S. Greengard, “What is artificial intelligence?” May 2019,
https://www.datamation.com/artificial-intelligence/what-is-artificial-intelligence.html
[5] https://in.pinterest.com/pin/828662400161409072/
[6] Y. Mintz and R. Brodie, “Introduction to artificial intelligence in medicine,” Minimally Invasive Therapy & Allied
Technologies, vol. 28, no. 2, 2019, pp. 73-81
[7] M. Todorovic, “Artificial intelligence for materials research,”
https://mycourses.aalto.fi/course/view.php?id=15280
[8] B. L. DeCost, et al., “Scientific AI in materials science: A path to a sustainable and scalable paradigm,” Machine
Learning: Science and Technology, vol. 1, no. 3, July 2020.
[9] M. Annunziata, “Mind over matter: Artificial intelligence can slash the time needed to develop new materials,”
December 2018,
https://www.forbes.com/sites/marcoannunziata/2018/12/03/mind-over-matter-artificial-intelligence-and-materials-
science/?sh=3b088153e9db
[10] J. Schmidt et al., “Recent advances and applications of machine learning in solid-state materials science,” npj
Computational Materials, vol. 5, no. 83, 2019.
[11] W. Sha, et al., “Artificial intelligence to power the future of materials science and engineering,” Advanced Intelligent
System, February 2020
[12] C. P. Gomes, B. Selman, and J. M. Gregoire, “Artificial intelligence for materials discovery,” MRS Bulletin, vol. 44,
2019, pp. 538–544.
[13] Y. Cheng, T. Wang and G. Zhang (eds.), Artificial Intelligence for Materials Science. Springer 2021.
[14] R. J. Harrison and L. D. Roth eds. , Artificial Intelligence Applications in Materials Science: roceedings.
Tms, 1987

ABOUT THE AUTHORS

Matthew N.O. Sadiku is a professor emeritus in the Department of Electrical and Computer Engineering at Prairie
View A&M University, Prairie View, Texas. He is the author of several books and papers. His areas of research
interest include computational electromagnetics and computer networks. He is a fellow of IEEE.
Guddi K. Suman is currently working towards a Ph.D. in Electrical and Computer Engineering at Prairie View A&M
University, Prairie View, TX. Her areas of research interest include space radiation effects on electronics,
nanomaterials, characterization of nanomaterials and semiconductors, thin film nanofabrication, nanosensors, and AI
in material science. Currently, she worked as an intern at Pacific Northwest National Laboratory, Richland, WA in
2021. She is a member of IEEE.
Sarhan M. Musa is a professor in the Department of Electrical and Computer Engineering at Prairie View A&M
University, Texas. He has been the director of Prairie View Networking Academy, Texas, since 2004. He is an LTD
Sprint and Boeing Welliver Fellow. His areas of research interest include computational electromagnetics and
computer networks.

www.ijasre.net Page 80

DOI: 10.31695/IJASRE.2021.34057
International Journal of Advances in Scientific Research and Engineering (ijasre), Vol 7 (8), August -2021

Figure 1 Different branches of artificial intelligence.

Figure 2 Artificial intelligence for material science [7].

www.ijasre.net Page 81

DOI: 10.31695/IJASRE.2021.34057