Neural networks carry out chemical simulations in record time
Researchers at the Universities of Vienna and Göttingen have succeeded in developing a method for predicting molecular infrared spectra based on artificial intelligence. These chemical “fingerprints” could only be simulated by common prediction techniques for small molecules in high quality. With the help of the new technology, which is based on neuronal networks similar to the human brain and is therefore capable of learning, the team led by Philipp Marquetand from the Faculty of Chemistry at the University of Vienna was able to carry out simulations that were previously not possible. The potential of this new strategy has now been published in the current issue of the journal “Chemical Science”.
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,” says 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 Latest on: Chemical fingerprints
- ALMA Detects Salts around Young Star on February 18, 2019 at 3:26 am
Astronomers using the Atacama Large Millimeter/submillimeter Array (ALMA) have detected the chemical fingerprints of sodium chloride (NaCl), potassium chloride (KCl), and their 37 Cl and 41 K isotopol... […]
- Tainted water: the scientists tracing thousands of fluorinated chemicals in our environment on February 6, 2019 at 3:23 am
“These chemicals are changing all the time,” she says ... It’s easy to spot known PFASs, such as PFOS and PFOA, because their characteristic fingerprints are already known. But for fragments with unfa... […]
- How Does Fingerprint Drug Testing Work? on February 5, 2019 at 6:20 pm
Fingerprint drug tests analyse the sweat left behind in the ... Opiates such as heroin produce the major metabolite 6-acetylmorphine, which is the main chemical found in sweat to evidence opioid use. ... […]
- High-Precision Chemical Fingerprint Allows Unambiguous Identification on January 29, 2019 at 4:00 pm
EQ BOKU at the University of Natural Resources and Life Sciences, Vienna uses high-tech approach to classification of 42 wines Numerous components of 42 different wines have been analysed using state- ... […]
- High-precision chemical fingerprint allows unambiguous identification on January 29, 2019 at 6:39 am
Components of 42 wines have been analysed using state-of-the-art equipment for the first time. The data generated will provide an extremely accurate basis for definitively characterising wine varietie... […]
- Icy moons, galaxy clusters, and distant worlds among selected targets for James Webb Space Telescope on July 22, 2018 at 6:25 am
to searching for chemical fingerprints of life on Enceladus, Europa, and exoplanets like TRAPPIST-1e, Webb will be looking at some incredible things in our universe,” said Eric Smith, James Webb Space ... […]
- Scientists develop the smallest, cheapest electronic nose for search and rescue on May 17, 2018 at 12:00 am
The nose is an array of sensors to detect various substances which, when found together, would provide the crucial "chemical fingerprint" showing the presence of human life. The array builds on the te... […]
- Revealing Individual Lifestyles through Mass Spectrometry Imaging of Chemical Compounds in Fingerprints on March 25, 2018 at 5:00 pm
Fingerprints, specifically the ridge details within the print, have long been used in forensic investigations for individual identification. Beyond the ridge detail, fingerprints contain useful chemic... […]
- Combining Microbial and Chemical Fingerprints for Forensics Applications on March 15, 2018 at 7:28 am
Researchers at the UC San Diego School of Medicine and Center for Microbiome Innovation have for the first time combined technologies that detect the presence of microbes and chemicals to identify “wh... […]
- Forensic chemical analysis of wood could stop illegal logging on June 2, 2017 at 6:10 am
Now, researchers in Oregon, USA, have developed a technique that uses the chemical fingerprint of a wood sample to pinpoint its origin to a smaller area than ever before. Endangered species or populat... […]
via Google News and Bing News