News

Machine learning helps design new materials

Researchers at Tampere University of Technology and Aalto University taught machine learning algorithms to predict how materials stretch. This new application of machine learning opens new opportunities in physics and possible applications can be found in the design of new optimal materials.
Machine Learning algorithm prediciting stress v strain

Most regular objects tend to stretch ‘evenly’, that is: scientists can predict how much force is required to make a material stretch by a certain distance. Recent experiments have shown that these predictions don’t hold up at the micrometre scale. The stretching of microscopic crystals happens in discrete bursts with a very wide size distribution. Since the bursts occur sporadically, seemingly identical micro-scale samples can stretch in very different ways. This variability of the strength characteristics of the samples poses a challenge for the development of novel materials with desired properties. In their article Machine learning plastic deformation of crystals published in Nature Communications, the researchers use machine learning to predict the characteristics of individual samples.

'The machine learning algorithms succeeded in measuring how predictable the stretch process of small crystalline samples is. This would have been practically impossible with traditional means, but machine learning enables the discovery of new and interesting results,' explains Associate Professor Lasse Laurson from the Laboratory of Physics at Tampere University of Technology.

The irreversible plastic deformation of crystalline substances occurs when crystallographic defects, called dislocations, move from one location in the crystal to another. Crystalline materials, such as metals or ice almost always contain networks of dislocations, with each crystal containing its own network.  

The researchers trained machine learning algorithms to recognise the connection between an object’s microscopic structure and the amount of force required to stretch a sample. The study revealed, amongst other things, that the predictability of the amount of force required changes on the stretching of the sample: At first, it becomes harder to predict the force required as the stretch grows, which depends mostly on the stretch bursts’ sporadic nature. Surprisingly, however, predictability improves as the stretch continues to grow. Size also affects predictability: it is easier to predict the deformation process of larger crystals than smaller ones.

'As the stretch grows, the number of bursts reduces, consequently improving predictability. This is promising in terms of predicting the yield of individual samples, which is a key objective in material physics,' says Henri Salmenjoki, doctoral candidate at the Department of Applied Physics at Aalto University. 

'Our research indicates that machine learning can be used to predict very complex and non-linear physical processes. In addition to the development of optimal materials, possible applications can be found in the prediction of dynamics of many other complex systems,' Laurson explains.

Professor Mikko Alava from Aalto University was also involved in the recently published study. The study received funding from the Academy of Finland.

Read more about the study in the Nature Communications publication.

  • Published:
  • Updated:
Share
URL copied!

Read more news

Tuoleja ravintolatilassa, taustalla asiakaspalvelutilanne
Press releases Published:

New technologies can help people make sustainable dietary decisions

Blockchain-backed app provides information about food impacts and combined customer choice
An illustration with a graph on the left and a molecular structure inset in a cube on the right. Each curve on the graph is a different colour, and each is connected by a line to an inset circle with a specific molecular feature corresponding to that curve. Above the cube with the molecular structure is a squigly arrow coming in, labelled "hv", and a straight arrow going out, labelled "e-". The entire figure (graph and inset cube) is labelled "XPS".
Press releases Published:

Machine learning gives material science researchers a peek at the answer key

A model trained to predict spectroscopic profiles helps to decipher the structure of materials
A schematic showing two circular light waves coming from the left, passing through a square representing the modulator, and emerging as a single linear light beam.
Press releases Published:

The handedness of light holds the key to better optical control

A new optical modulator could boost the performance of optical technologies in domains from communication to computing
Lauri Parkkonen and the family cat, Roosa. Photo: Lauri Parkkonen, Aalto, University.
Press releases Published:

New imaging technique to find out what happens in the brains of cats and dogs

A brain imaging device based on quantum optical sensors could also be used to study the brains of human babies