Collection 

Machine learning for materials characterisation

Submission status
Closed
Submission deadline

In the last decade we have achieved significant advances in machine learning techniques, which have been widely exploited in a number of applications including biomedical, data and image processing, and materials science. In these applications it’s particularly valuable to be able to process large amounts of data and images in a standardised method, and using machine learning techniques to achieve this can dramatically reduce the drain on resources – e.g. time, computing power, expert man-hours.

In materials science, and in particular when applied to X-ray and neutron scattering techniques, machine learning has been beneficial in discovery, optimisation, and characterisation of new materials. Scattering simulations that are traditionally performed using Monte Carlo techniques (which are time and processing heavy), can be much improved through the use of well-validated machine learning techniques.

This Collection reports the latest advances in machine learning techniques for materials.

Neural network 3D

Editors