Back to Table of contents

Primeur weekly 2017-02-06

Focus

Photon and Neutron Community ready to act as a go-between for the e-Infrastructures and user communities ...

Bridging socio-cultural distance in science through technical community-engaging mechanisms ...

Exascale supercomputing

How to improve data management in the supercomputers of the future ...

Crowd computing

Your computer can help scientists search for new childhood cancer treatments ...

Quantum computing

Quantum phase transition observed for the first time ...

Quantum matter: Shaken, but not stirred ...

First ever blueprint unveiled to construct a large scale quantum computer ...

Focus on Europe

PRACE opens Tier-1 for Tier-0 service ...

Middleware

New version of Univa Unisight 4.1 provides comprehensive tool to support IT purchasing decisions ...

Czech TV speeds broadcast and production delivery with DDN's fully integrated MEDIAScaler platform ...

Optimized compiler yields more-efficient parallel programmes ...

Hardware

Three magnetic states for each hole: researchers investigate the potential of metal grids for electronic components ...

Making the switch to polarization diversity ...

SDSC's 'Comet' supercomputer surpasses '10,000 users' milestone ...

New Cheyenne supercomputer triples scientific capability with greater efficiency ...

GBP 3.2 million for Midlands-based high performance computing centre ...

Applications

Machine learning accurately predicts metallic defects ...

Jupiter Medical Center implements revolutionary Watson for Oncology to help oncologists make data-driven cancer treatment decisions ...

University of Delaware's Anderson Janotti receives NSF Career Award to model defects in complex materials ...

Supercomputing and experiment combine for first look at magnetism of real nanoparticle ...

Researchers flip script for Li-Ion electrolytes to simulate better batteries ...

Huawei and SURFsara join forces for ICT innovation in Smart Healthcare and Smart Energy ...

The shape of melting in two dimensions: University of Michigan team uses Titan to explore fundamental phase transitions ...

Nature Geoscience highlights CALIOPE's ability to "provide decision makers with the information they need to take preventive action" on air quality ...

Magnetic recording with light and no heat on garnet ...

Breaking the jargon barrier ...

Carnegie Mellon Artificial Intelligence beats top poker pros ...

Preventing blood clots with a new metric for heart function: Simulations on Stampede supercomputer reveal better way of predicting future clots in the left ventricle ...

Berkeley Lab resources used to model superluminous supernova in 2D for first time ...

The Cloud

Utilities regulators see value in the Cloud and Cloud technology investments as critical to utilities' success ...

Machine learning accurately predicts metallic defects


Dominant defect type predictions from r-MART model for 946 B2-type intermetallics. Colours indicates the relationship between prediction and calculations as shown in the legend.
3 Feb 2017 Berkeley - For the first time, researchers at the Lawrence Berkeley National Laboratory have built and trained machine learning algorithms to predict defect behaviour 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 modelling cell bigger the computational power required to do this increases substantially", stated Bharat Medasani, a former Berkeley Lab postdoc and lead author of the 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, Bharat 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, Bharat 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", stated Bharat 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", stated 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", stated 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 Bharat Medasani, Andrew Canning and Kristin Persson, other authors on theNature Computational Materialspaper 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.
Source: National Energy Research Scientific Computing Center - NERSC

Back to Table of contents

Primeur weekly 2017-02-06

Focus

Photon and Neutron Community ready to act as a go-between for the e-Infrastructures and user communities ...

Bridging socio-cultural distance in science through technical community-engaging mechanisms ...

Exascale supercomputing

How to improve data management in the supercomputers of the future ...

Crowd computing

Your computer can help scientists search for new childhood cancer treatments ...

Quantum computing

Quantum phase transition observed for the first time ...

Quantum matter: Shaken, but not stirred ...

First ever blueprint unveiled to construct a large scale quantum computer ...

Focus on Europe

PRACE opens Tier-1 for Tier-0 service ...

Middleware

New version of Univa Unisight 4.1 provides comprehensive tool to support IT purchasing decisions ...

Czech TV speeds broadcast and production delivery with DDN's fully integrated MEDIAScaler platform ...

Optimized compiler yields more-efficient parallel programmes ...

Hardware

Three magnetic states for each hole: researchers investigate the potential of metal grids for electronic components ...

Making the switch to polarization diversity ...

SDSC's 'Comet' supercomputer surpasses '10,000 users' milestone ...

New Cheyenne supercomputer triples scientific capability with greater efficiency ...

GBP 3.2 million for Midlands-based high performance computing centre ...

Applications

Machine learning accurately predicts metallic defects ...

Jupiter Medical Center implements revolutionary Watson for Oncology to help oncologists make data-driven cancer treatment decisions ...

University of Delaware's Anderson Janotti receives NSF Career Award to model defects in complex materials ...

Supercomputing and experiment combine for first look at magnetism of real nanoparticle ...

Researchers flip script for Li-Ion electrolytes to simulate better batteries ...

Huawei and SURFsara join forces for ICT innovation in Smart Healthcare and Smart Energy ...

The shape of melting in two dimensions: University of Michigan team uses Titan to explore fundamental phase transitions ...

Nature Geoscience highlights CALIOPE's ability to "provide decision makers with the information they need to take preventive action" on air quality ...

Magnetic recording with light and no heat on garnet ...

Breaking the jargon barrier ...

Carnegie Mellon Artificial Intelligence beats top poker pros ...

Preventing blood clots with a new metric for heart function: Simulations on Stampede supercomputer reveal better way of predicting future clots in the left ventricle ...

Berkeley Lab resources used to model superluminous supernova in 2D for first time ...

The Cloud

Utilities regulators see value in the Cloud and Cloud technology investments as critical to utilities' success ...