q&more
My watch list
my.chemie.de  
Login  

News

Artificial intelligence identifies optimal material formula

One algorithm replaces countless time-consuming experiments

© Lars Banko

A look into the sputtering system where nanostructured layers are generated.

30-Mar-2020: Nanostructured layers boast countless potential properties – but how can the most suitable one be identified without any long-term experiments? A team from the Materials Discovery Department at Ruhr-Universität Bochum (RUB) has ventured a shortcut: using a machine learning algorithm, the researchers were able to reliably predict the properties of such a layer.

Porous or dense, columns or fibres

During the manufacture of thin films, numerous control variables determine the condition of the surface and, consequently, its properties. Relevant factors include the composition of the layer as well as process conditions during its formation, such as temperature. All these elements put together result in the creation of either a porous or a dense layer during the coating process, with atoms combining to form columns or fibres. “In order to find the optimal parameters for an application, it used to be necessary to conduct countless experiments under different conditions and with different compositions; this is an incredibly complex process,“ explains Professor Alfred Ludwig, Head of the Materials Discovery and Interfaces Team.

Findings yielded by such experiments are so-called structure zone diagrams, from which the surface of a certain composition resulting from certain process parameters can be read. “Experienced researchers can subsequently use such a diagram to identify the most suitable location for an application and derive the parameters necessary for producing the suitable layer,” points out Ludwig. “The entire process requires an enormous effort and is highly time consuming.”

Algorithm predicts surface

Striving to find a shortcut towards the optimal material, the team took advantage of artificial intelligence, more precisely machine learning. To this end, PhD researcher Lars Banko, together with colleagues from the Interdisciplinary Centre for Advanced Materials Simulation at RUB, Icams for short, modified a so-called generative model. He then trained this algorithm to generate images of the surface of a thoroughly researched model layer of aluminium, chromium and nitrogen using specific process parameters, in order to predict what the layer would look like under the respective conditions.

“We fed the algorithm with a sufficient amount of experimental data in order to train it, but not with all known data,” stresses Lars Banko. Thus, the researchers were able to compare the results of the calculations with those of the experiments and analyse how reliable its prediction was. The results were conclusive: “We combined five parameters and were able to look in five directions simultaneously using the algorithm – without having to conduct any experiments at all,” outlines Alfred Ludwig. “We have thus shown that machine learning methods can be transferred to materials research and can help to develop new materials for specific purposes.”

Original publication:
Lars Banko, Yury Lysogorskiy, Dario Grochla, Dennis Naujoks, Ralf Drautz, Alfred Ludwig; "Predicting structure zone diagrams for thin film synthesis by generative machine learning"; Communications Materials; 2020

Facts, background information, dossiers

  • materials science
  • machine-learning
  • artificial intelligence
  • prediction models

More about Ruhr-Universität Bochum

  • News

    Immunoprotein impairs Sars-Cov-2

    A protein produced by the human immune system can strongly inhibit corona viruses, including Sars-Cov-2, the pathogen causing Covid-19. An international team from Germany, Switzerland and the USA successfully showed that the LY6E-Protein prevents coronaviruses from causing an infection. “Th ... more

    Water molecules are gold for nanocatalysis

    Nanocatalysts made of gold nanoparticles dispersed on metal oxides are very promising for the industrial, selective oxidation of compounds, including alcohols, into valuable chemicals. They show high catalytic activity, particularly in aqueous solution. A team of researchers from Ruhr-Unive ... more

    Wrapping up hydrophobic hydration

    In water, hydrophobic molecules are surrounded by a two different water populations: the inner shell forms a two-dimensional network of water molecules. The next layer is formed by a second water population that is almost bulk like but forms slightly stronger hydrogen bonds to the bulk wate ... more

  • q&more articles

    Light plus current: The formula for researching what happens to individual nanoparticles

    A combination of dark-field microscopy and electrochemistry can make individual nanoparticles in a liquid medium visible. The technique is suited to determine the activity of catalysts during their use. more

    Vibrational spectroscopy - Label-free imaging

    Spectroscopic methods are now granting us deep insights into biological systems at previously unattainable spatial and temporal resolutions. Complementing the already well-established fluorescence spectroscopy, the major potential of label-free vibrational spectroscopy has become clear in r ... more

  • Authors

    Kevin Wonner

    Kevin Wonner, born in 1995, studied chemistry with the focus on electrochemical nanoparticle characterization at the Ruhr University Bochum. He started his PhD in 2018 at the chair of Analytical Chemistry II of Professor Dr. Kristina Tschulik and is supported by the graduate school 2376. Hi ... more

    Mathies V. Evers

    Mathies Evers, born in 1989, studied chemistry at the Ruhr University Bochum, where he researched the synthesis of atom-precise molecular clusters. After his master's degree he started his doctoral thesis at the Chair of Analytical Chemistry II of Professor Dr. Kristina Tschulik and is supp ... more

    Prof. Dr. Kristina Tschulik

    Kristina Tschulik received her doctorate from TU Dresden in 2012 and worked as a postdoctoral fellow at the Leibniz Institute for Solid State and Materials Research Dresden and at the University of Oxford. Afterwards she established the working group for “Electrochemistry and Nanoscale Mate ... more

q&more – the networking platform for quality excellence in lab and process

The q&more concept is to increase the visibility of recent research and innovative solutions, and support the exchange of knowledge. In the broad spectrum of subjects covered, the focus is on achieving maximum quality in highly innovative sectors. As a modern knowledge platform, q&more offers market participants one-of-a-kind networking opportunities. Cutting-edge research is presented by authors of international repute. Attractively presented in a high-quality context, and published in German and English, the original articles introduce new concepts and highlight unconventional solution strategies.

> more about q&more

q&more is supported by:

 

Your browser is not current. Microsoft Internet Explorer 6.0 does not support some functions on Chemie.DE