Back to Table of contents

Primeur weekly 2017-10-02

Special

2017 - Another year on the Road to Exascale: HPC applications towards exascale ...

Focus

CEA, ETP4HPC and European Commission working hard together to deliver commercial exascale by 2023 ...

Exascale supercomputing

Cartography of the cosmos ...

Quantum computing

A quantum computer to tackle fundamental science problems ...

Quantum communications bend to our needs ...

With new Microsoft breakthroughs, general purpose quantum computing moves closer to reality ...

Focus on Europe

SHAPE Sixth Call for Applications now open ...

EPCC to announce best use of ARCHER competition winners ...

Middleware

Bright Computing announces integration with IBM Power systems ...

US-based CryoEM company, SingleParticle.com, partners with Bright ...

Hardware

Cray takes aim at fast-growing HPC storage market with completion of strategic transaction of Seagate's ClusterStor storage business ...

Penguin Computing announces NVIDIA Tesla V100-based servers to drive Deep Learning and Artificial Intelligence ...

Penguin Computing announces Altus servers with AMD EPYC 7000 series high performance processors ...

Supermicro introduces broadest portfolio of GPU optimized systems for NVIDIA Tesla V100 GPUs ...

New type of supercomputer could be based on 'magic dust' combination of light and matter ...

Applications

Antonio Peña is the IEEE-CS TCHPC 2017 Award Winner for Excellence for Early Career Researchers in HPC ...

University of Texas at El Paso researchers use supercomputers to understand the fundamentals of artificial photosynthesis ...

Turbocharging engine design ...

The sublime challenge of jet noise ...

Mapping black hole collisions gives astronomers - and hitchhikers - a new guide ...

George Washington-led consortium and FDA release new specifications to advance genomic data analysis ...

Artificial intelligence for obtaining chemical fingerprints ...

IBM Research and UC San Diego collaborate to advance the use of Artificial Intelligence for Healthy Living ...

Dresden researchers have pioneered a brain-network bio-inspired algorithm to predict new therapeutic targets of approved drugs ...

The Cloud

IBM unveils a new high-powered analytics system for fast access to data science ...

HPE chooses Mellanox Spectrum to power StoreFabric M-series switches ...

Artificial intelligence for obtaining chemical fingerprints


The scientists have found a way to accelerate chemical simulations using artificial intelligence. Credit: Philipp Marquetand.
26 Sep 2017 Vienna - Drastic advances in research of artificial intelligence have led to a wide range of fascinating developments in this area over the last decade. Autonomously driven cars, but also everyday applications such as search engines and spam filters illustrate the versatility of methods from the field of artificial intelligence.

Infrared spectroscopy is one of the most valuable experimental methods to gain insight into the world of molecules. Infrared spectra are chemical fingerprints that provide information on the composition and properties of substances and materials. In many cases, these spectra are very complex - a detailed analysis makes computer-aided simulations indispensable. While quantum chemical calculations in principle enable extremely precise prediction of infrared spectra, their applicability in practice is made difficult by the high computational effort associated with them. For this reason, reliable infrared spectra can only be calculated for relatively small chemical systems.

An international group of researchers led by Philipp Marquetand from the Faculty of Chemistry at the University of Vienna has now found a way to accelerate these simulations using artificial intelligence. For this purpose, so-called artificial neural networks are used, mathematical models of the human brain. These are able to learn the complex quantum mechanical relationships that are necessary for the modelling of infrared spectra by using only a few examples. In this way, the scientists can carry out simulations within a few minutes, which would otherwise take thousands of years even with modern supercomputers - without sacrificing reliability. "We can now finally simulate chemical problems that could not be overcome with the simulation techniques used up to now", stated Michael Gastegger, the first author of the study.

Based on the results of this study, the researchers are confident that their method of spectra prediction will be widely used in the analysis of experimental infrared spectra in the future.

The paper titled " Machine learning molecular dynamics for the simulation of infrared spectra " is authored by Michael Gastegger, Jörg Behler, and Philipp Marquetand. It has appeared inChemical Science.

Source: University of Vienna

Back to Table of contents

Primeur weekly 2017-10-02

Special

2017 - Another year on the Road to Exascale: HPC applications towards exascale ...

Focus

CEA, ETP4HPC and European Commission working hard together to deliver commercial exascale by 2023 ...

Exascale supercomputing

Cartography of the cosmos ...

Quantum computing

A quantum computer to tackle fundamental science problems ...

Quantum communications bend to our needs ...

With new Microsoft breakthroughs, general purpose quantum computing moves closer to reality ...

Focus on Europe

SHAPE Sixth Call for Applications now open ...

EPCC to announce best use of ARCHER competition winners ...

Middleware

Bright Computing announces integration with IBM Power systems ...

US-based CryoEM company, SingleParticle.com, partners with Bright ...

Hardware

Cray takes aim at fast-growing HPC storage market with completion of strategic transaction of Seagate's ClusterStor storage business ...

Penguin Computing announces NVIDIA Tesla V100-based servers to drive Deep Learning and Artificial Intelligence ...

Penguin Computing announces Altus servers with AMD EPYC 7000 series high performance processors ...

Supermicro introduces broadest portfolio of GPU optimized systems for NVIDIA Tesla V100 GPUs ...

New type of supercomputer could be based on 'magic dust' combination of light and matter ...

Applications

Antonio Peña is the IEEE-CS TCHPC 2017 Award Winner for Excellence for Early Career Researchers in HPC ...

University of Texas at El Paso researchers use supercomputers to understand the fundamentals of artificial photosynthesis ...

Turbocharging engine design ...

The sublime challenge of jet noise ...

Mapping black hole collisions gives astronomers - and hitchhikers - a new guide ...

George Washington-led consortium and FDA release new specifications to advance genomic data analysis ...

Artificial intelligence for obtaining chemical fingerprints ...

IBM Research and UC San Diego collaborate to advance the use of Artificial Intelligence for Healthy Living ...

Dresden researchers have pioneered a brain-network bio-inspired algorithm to predict new therapeutic targets of approved drugs ...

The Cloud

IBM unveils a new high-powered analytics system for fast access to data science ...

HPE chooses Mellanox Spectrum to power StoreFabric M-series switches ...