For most of human history, the discovery of new materials has been a crapshoot. But now, UConn researchers have systematized the search with machine learning that can scan millions of theoretical compounds for qualities that would make better solar cells, fibers, and computer chips.
The search for new materials may never be the same.
No one knows why an early metallurgist decided to smelt a hunk of tin into some copper, but the resulting bronze alloy was harder and more durable than any material previously known. Most materials experimentation over the ensuing 7,000 years has been similarly random, guided largely by philosophy and chemical intuition.
But in a world that contains at least 95 stable elements – the basic building blocks of matter – the number of possible combinations is enormous, and experimentation is an awfully inefficient way to find what you’re looking for.
Enter UConn materials scientist Ramamurthy ‘Rampi’ Ramprasad. Instead of randomly mixing chemicals to see what they do, Ramprasad designs them rationally, using machine learning to figure out which atomic configurations make a polymer a good electrical conductor or insulator.
A polymer is a large molecule made of many repeating building blocks. Polymers are very common in both living and man-made materials. Probably the most familiar example is plastics, and the wide variation in plastics – which can be hard, soft, stretchy, brittle, spongy, clear, opaque or translucent – gives an inkling of how diverse polymers in general can be.
Polymers can also have diverse electronic properties. For example, they can be very good insulators – preventing electrons, and thus electric current, from traveling through them – or good conductors, allowing electricity to pass through them freely. And what controls all these properties is mainly how the atoms in the polymer connect to each other. But until recently, no one had systematically related properties to atomic configurations.
So Ramprasad and his colleagues decided to do just that. First, they would analyze known polymers, using laborious but accurate quantum mechanics-based calculations to figure out which arrangements of atoms confer which properties, and quantify those atomic-level relationships via a string of numbers that fingerprint each polymer. Once they had those, they could have a computer search through any number of theoretical polymers to figure out which ones might have which properties. Then anyone looking for a polymer with a certain property could quickly scan the list and decide which theoretical polymers might be worth trying.
Many polymers are made of building blocks containing just a few atoms. For instance, polyurea, a common plastic, has as the basic structure a repeating sequence of nitrogen (N), hydrogen (H) and oxygen (O): NH-O-NH-O. Most polymers look like that, made of carbon (C), H, N and O, with a few other elements thrown in occasionally.
For their project, Ramprasad’s group looked at polymers made of just seven building blocks: CH2, C6H4, CO, O, NH, CS, and C4H2S (the S is sulfur). These are found in common plastics such as polyethylene, polyesters, and polyureas. An enormous variety of polymers could theoretically be constructed using just these building blocks; Ramprasad’s group decided at first to analyze just 283, each composed of a repeated four-block unit.
They started from basic quantum mechanics, and calculated the three-dimensional atomic and electronic structures of each of those 283 four-block polymers. This is not trivial: calculating the position of every electron and atom in a molecule with more than two atoms takes a powerful computer a significant chunk of time, which is why they did it for only 283 molecules.
Learn more: Building a better mouse trap, from the atoms up
The Latest on: Machine learning
No news articles
via Google News
The Latest on: Machine learning
- A machine learning project that will use Natural Language Processing (NLP) to classify who says a line of dialogueon January 21, 2021 at 2:44 am
A machine learning project that will use Natural Language Processing (NLP) to classify who says a line of dialogue - prestondunton/marvel-dialogue-nlp ...
- 4Paradigm Defends its Championship in China’s Machine Learning Platform Market in the 1st Half of 2020, According to IDCon January 20, 2021 at 9:53 pm
Paradigm stays on a leadership position from 2018 to the first half of 2020. IDC, a premier global provider of market intelligence, has recently published China AI Software and A ...
- Skyrim modders have a new machine learning tool that turns text to realistic NPC speechon January 20, 2021 at 2:06 pm
VASynth creator Dan Ruta used NPC voices from various Bethesda video games to train the tool's machine learning AI models. He published multiple flavors of the ...
- Understanding machine learning will go a long way toward higher adoption for SMBson January 20, 2021 at 11:56 am
Expert says larger companies are more willing to spend money for top talent to achieve machine learning, whereas smaller companies aren't able to do so. Pre-configured solutions can help.
- Machine Learning Market Global Industry Trends, Share, Size and Forecast Reporton January 20, 2021 at 6:21 am
Machine Learning Market Opportunities, Size, Share, Emerging Trends, Technological Innovation and Forecasts "The report on the global machine learning market provides qualitative and quantitative ...
- Machine learning could cut delays from traffic lightson January 20, 2021 at 6:20 am
Researchers have designed a new system that uses machine learning to improve the flow of vehicles at traffic lights.
- Splice Machine Launches the Splice Machine Feature Store Platform to Simplify Feature Engineering and Democratize Machine Learningon January 19, 2021 at 10:08 pm
Splice Machine, the only scale-out SQL database with built-in machine learning, today announced it has launched the Splice Machine Feature Store Platform. The Platform will help more companies ...
- Researchers build models using machine learning technique to enhance predictions of COVID-19 outcomeson January 19, 2021 at 2:39 pm
Mount Sinai researchers have published one of the first studies using a machine learning technique called 'federated learning' to examine electronic health records to better predict how COVID-19 ...
- Machine Learning Finds More Gravitational Lenses Than All Astronomers Combinedon January 17, 2021 at 11:00 pm
The lensing effect stretches, distorts, and magnifies the background galaxy, as well as creating multiple images of it. One of Einstein’s most revolutionary predictions is that mass bends light.
- Get the machine learning for beginners overview bundle for under $20on January 17, 2021 at 9:00 pm
If you want your chance to fill one of these roles, then you need to get familiar with machine learning. There's no better place to start on that task than the Machine Learning for Beginners Overview ...
via Bing News