
Schematic diagram of machine learning for materials discovery. Credit: Chiho Kim, Ramprasad Lab, UConn
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
via Google News
The Latest on: Machine learning
- Deno 1.8 preps for GPU-accelerated machine learningon March 3, 2021 at 3:17 pm
WebGPU API for GPU rendering and computation is supported in the latest upgrade to the JavaScript/TypeScript runtime.
- Streamlining data science with open source: Data version control and continuous machine learningon March 3, 2021 at 6:42 am
Can an open source-based workflow leveraging version control and continuous integration and deployment help streamline machine learning, like it did for software development?
- Machine Learning Reveals Traits of High Mental Health Utilizerson March 2, 2021 at 9:30 pm
Machine learning tools analyzed EHR data and identified characteristics of high utilizers for mental health services.
- How the use of machine learning can help Netflix streaming qualityon March 2, 2021 at 9:16 pm
Here's how Netflix uses machine learning to provide an enjoyable and smooth streaming experience to its users.
- Microsoft launches Azure Arc machine learning and container serviceson March 2, 2021 at 2:00 pm
Microsoft unveiled two new Azure Arc services aimed at data scientists and enterprises with containerized workloads.
- An open-source machine learning framework to carry out systematic reviewson March 2, 2021 at 9:44 am
When scientists carry out research on a given topic, they often start by reviewing previous study findings. Conducting systematic literature reviews or meta-analyses can be very challenging and time ...
- Machine Learning Can Help The Insurance Industry Throughout The Process Lifecycleon March 2, 2021 at 8:58 am
Not all insurance is alike. Life insurance and automobile insurance are not (as far as I know) the same thing. There are many similar processes, but data and numerous flows can be different. Machine ...
- Microsoft’s Azure Arc multi-cloud platform now supports machine learning workloadson March 2, 2021 at 6:01 am
With Azure Arc, Microsoft offers a service that allows its customers to run Azure in any Kubernetes environment, no matter where that container cluster is hosted. From Day One, Arc supported a wide ...
- Machine learning-based prediction model using clinico-pathologic factors for papillary thyroid carcinoma recurrence | Scientific Reportson March 2, 2021 at 2:59 am
The performance of five machine learning models related to recurrence prediction was compared based on accuracy. The Decision Tree model showed the best accuracy at 95%, and the lightGBM and stacking ...
- Way beyond AlphaZero: Berkeley and Google work shows robotics may be the deepest machine learning of allon March 1, 2021 at 7:42 pm
With no well-specified rewards and state transitions that take place in a myriad of ways, training a robot via reinforcement learning represents perhaps the most complex arena for machine learning.
via Bing News