This story is featured in the Asia Research News 2025 magazine. Book space in the next issue now.
Get the news in your inbox
Polymers such as polypropylene are found in everything, from computers to cars. Because of their ubiquity, it is vital to know how each newly developed polymer will perform under different conditions.
Predicting the mechanical properties of new polymers, such as their tensile strength or flexibility, usually involves putting them through destructive and costly physical tests. Now, scientists from Japan’s National Institute for Materials Science (NIMS) have shown how machine learning can determine what to expect from a new polymer. Their study was published in the journal Science and Technology of Advanced Materials.
“Machine learning can be applied to data from existing materials to predict the properties of unknown materials,” study authors Ryo Tamura, Kenji Nagata, and Takashi Nakanishi explain. “However, to achieve accurate predictions, it’s essential to use descriptors that correctly represent the features of these materials.”
Polymers have a complex structure that is further altered during the process of molding them into the shape of the end product. Therefore, it was important for the team to adequately capture the details of the polymers’ structure with X-ray diffraction and to ensure that the machine learning algorithm could identify the most important descriptors in that data.
To that end, they analysed two datasets. The first dataset was X-ray diffraction data from 15 types of polymers subjected to a range of temperatures, and the second was data from polymers with elastomers. The mechanical properties analysed included stiffness, elasticity, the temperature at which the material starts to deform, and how much it would stretch before breaking.
The team found that the machine learning analysis accurately linked features in the X-ray diffraction imagery with specific material properties of the polymers, with some easy to predict and some more challenging.
“We believe our study will offer a non-destructive alternative to conventional polymer testing methods, and it can also be used to understand properties of other materials, both inorganic and organic,” the NIMS researchers say.
Further information
Dr Takashi Nakanishi
[email protected]
National Institute for Materials Science (NIMS)
Dr Kenji Nagata
[email protected]
National Institute for Materials Science (NIMS)
Dr Ryo Tamura
[email protected]
National Institute for Materials Science (NIMS)
STAM Inquiries
[email protected]
