Nav: Home

Machine learning method accurately predicts metallic defects

February 03, 2017

For the first time, researchers at the Lawrence Berkeley National Laboratory (Berkeley Lab) have built and trained machine learning algorithms to predict defect behavior in certain intermetallic compounds with high accuracy. This method will accelerate research of new advanced alloys and lightweight new materials for applications spanning automotive to aerospace and much more.

Their results were published in the December 2016 issue of Nature Computational Materials.

Materials are never chemically pure and structurally flawless. They almost always contain defects, which play an important role in dictating properties. These defects may appear as vacancies, which are essentially 'holes' in the substance's crystal structure, or antisite defects, which are essentially atoms placed on the wrong crystal site. Understanding of such point defects is crucial for scientists designing materials because they can have a dramatic effect on long-time structural stability and strength.

Traditionally, researchers have used a computational quantum mechanical method known as density functional calculations to predict what kinds of defects can be formed in a given structure and how they affect the material's properties. Although effective, this approach is very computationally expensive to execute for point defects limiting the scope of such investigations.

"Density functional calculations work well if you are modeling one small unit, but if you want to make your modeling cell bigger the computational power required to do this increases substantially," says Bharat Medasani, a former Berkeley Lab postdoc and lead author of the npj paper. "And because it is computationally expensive to model defects in a single material, doing this kind of brute force modeling for tens of thousands of materials is not feasible."

To overcome these computing challenges, Medasani and his colleagues developed and trained machine learning algorithms to predict point defects in intermetallic compounds, focusing on the widely observed B2 crystal structure. Initially, they selected a sample of 100 of these compounds from the Materials Project Database and ran density functional calculations on supercomputers at the National Energy Research Scientific Computing Center (NERSC), a DOE Office of Science User Facility at Berkeley Lab, to identify their defects.

Because they had a small data sample to work from, Medasani and his team used a forest approach called gradient boosting to develop their machine learning method to a high accuracy. In this approach additional machine learning models were built successively and combined with prior models to minimize the difference between the models predictions and the results from density functional calculations. The researchers repeated the process until they achieved a high level of accuracy in their predictions.

"This work is essentially a proof of concept. It shows that we can run density functional calculations for a few hundred materials, then train machine learning algorithms to accurately predict point defects for a much larger group of materials," says Medasani, who is now a postdoctoral researcher at the Pacific Northwest National Laboratory.

"The benefit of this work is now we have a computationally inexpensive machine learning approach that can quickly and accurately predict point defects in new intermetallic materials " says Andrew Canning, a Berkeley Lab Computational Scientist and co-author on the npj paper. "We no longer have to run very costly first principle calculations to identify defect properties for every new metallic compound."

"This tool enables us to predict metallic defects faster and robustly, which will in turn accelerate materials design," says Kristin Persson, a Berkeley Lab Scientist and Director of the Materials Project, an initiative aimed at drastically reducing the time needed to invent new materials by providing open web-based access to computed information on known and predicted materials. As an extension of this work an open source Python toolkit for modeling point defects in semiconductors and insulators (PyCDT) has been developed.
In addition to Medasani, Canning and Persson, other authors on the Nature Computational Materials paper include: Hong Ding, Wei Chen, Mark Asta and Maciej Haranczyk (Berkeley Lab); and Anthony Gamst (University of California, San Diego). Additionally, Danny Broberg (University of California, Berkeley), Geoffroy Hautier (University Catholique de Louvain, Belgium) and Nils Zimmermann (Berkeley Lab) were involved in the development of the PyCDT software.

The research was supported by the Department of Energy's Office of Science.

DOE/Lawrence Berkeley National Laboratory

Related Crystal Structure Articles:

DIY crystal-makers get refurbished online cookbook
In response to popular demand, materials scientists at Duke University have resurrected an online cookbook of crystalline structures that started when the World Wide Web was Netscape Navigator and HTML 1.0.
Dawn of organic single crystal electronics
Researchers at the Institute for Molecular Science, National Institutes of Natural Sciences (Japan) have developed a method for high performance doping of organic single crystal.
Crystallization made crystal clear
Researchers at the Weizmann Institute of Science have, for the first time, directly observed the process of crystallization on the molecular level, validating some recent theories about crystallization, as well as showing that if one knows how the crystal starts growing, one can predict the end structure.
Mapping the effects of crystal defects
MIT research offers insights into how crystal dislocations -- a common type of defect in materials -- can affect electrical and heat transport through crystals, at a microscopic, quantum mechanical level.
Scientists create new form of matter, a time crystal
Scientists are reporting in the journal Nature on the creation of a phase of matter, dubbed a time crystal, in which atoms move in a pattern that repeats in time rather than in space.
Most complex nanoparticle crystal ever made by design
The most complex crystal designed and built from nanoparticles has been reported by researchers at Northwestern University and the University of Michigan.
In-cell molecular sieve from protein crystal
Scientists at Tokyo Institute of Technology, RIKEN, and Kyoto Institute of Technology have applied rational crystal design to create protein crystals with extended porous network to accumulate exogenous molecules inside living cells.
Novel liquid crystal could triple sharpness of today's televisions
An international team of researchers has developed a new blue-phase liquid crystal that could enable televisions, computer screens and other displays that pack more pixels into the same space while also reducing the power needed to run the device.
Researcher's discovery of new crystal structure holds promise for optoelectronic devices
A Florida State University professor has observed a never-been-seen crystal structure that holds promise for optoelectronic devices.
Einstein in an iron crystal
Angle-resolved photoemission spectroscopy has enabled scientists from Forschungszentrum J├╝lich and LMU Munich to directly visualize the formation of shifts in the band structure (band gaps) of a sample of prototypical magnetic material as a response to the change in direction of a magnetic field.

Related Crystal Structure Reading:

Best Science Podcasts 2019

We have hand picked the best science podcasts for 2019. Sit back and enjoy new science podcasts updated daily from your favorite science news services and scientists.
Now Playing: TED Radio Hour

Failure can feel lonely and final. But can we learn from failure, even reframe it, to feel more like a temporary setback? This hour, TED speakers on changing a crushing defeat into a stepping stone. Guests include entrepreneur Leticia Gasca, psychology professor Alison Ledgerwood, astronomer Phil Plait, former professional athlete Charly Haversat, and UPS training manager Jon Bowers.
Now Playing: Science for the People

#524 The Human Network
What does a network of humans look like and how does it work? How does information spread? How do decisions and opinions spread? What gets distorted as it moves through the network and why? This week we dig into the ins and outs of human networks with Matthew Jackson, Professor of Economics at Stanford University and author of the book "The Human Network: How Your Social Position Determines Your Power, Beliefs, and Behaviours".