Discovering the next generation of batteries with some help from AI
Designing the best molecular building blocks for battery components is like trying to create a recipe for a new kind of cake, when you have billions of potential ingredients. The challenge involves determining which ingredients work best together — or, more simply, produce an edible (or, in the case of batteries, a safe) product. But even with state-of-the-art supercomputers, scientists cannot precisely model the chemical characteristics of every molecule that could prove to be the basis of a next-generation battery material.
Instead, researchers at the U.S. Department of Energy’s (DOE) Argonne National Laboratory have turned to the power of machine learning and artificial intelligence to dramatically accelerate the process of battery discovery.
As described in two new papers, Argonne researchers first created a highly accurate database of roughly 133,000 small organic molecules that could form the basis of battery electrolytes. To do so, they used a computationally intensive model called G4MP2. This collection of molecules, however, represented only a small subset of 166 billion larger molecules that scientists wanted to probe for electrolyte candidates.
“If we are going to use a molecule for energy storage applications, we need to know properties like its stability, and we can use this machine learning to predict properties of bigger molecules more accurately.” — Argonne chemist Rajeev Assary
Because using G4MP2 to resolve each of the 166 billion molecules would have required an impossible amount of computing time and power, the research team used a machine learning algorithm to relate the precisely known structures from the smaller data set to much more coarsely modeled structures from the larger data set.
“When it comes to determining how these molecules work, there are big tradeoffs between accuracy and the time it takes to compute a result,” said Ian Foster, Argonne Data Science and Learning division director and author of one of the papers. ?“We believe that machine learning represents a way to get a molecular picture that is nearly as precise at a fraction of the computational cost.”
To provide a basis for the machine learning model, Foster and his colleagues used a less computationally taxing modeling framework based on density functional theory, a quantum mechanical modeling framework used to calculate electronic structure in large systems. Density functional theory provides a good approximation of molecular properties, but is less accurate than G4MP2.
Refining the algorithm to better ascertain information about the broader class of organic molecules involved comparing the atomic positions of the molecules computed with the highly accurate G4MP2 versus those analyzed using only density functional theory. By using G4MP2 as a gold standard, the researchers could train the density functional theory model to incorporate a correction factor, improving its accuracy while keeping computational costs down.
“The machine learning algorithm gives us a way to look at the relationship between the atoms in a large molecule and their neighbors, to see how they bond and interact, and look for similarities between those molecules and others we know quite well,” said Argonne computational scientist Logan Ward, an author of one of the studies. ?“This will help us to make predictions about the energies of these larger molecules or the differences between the low- and high-accuracy calculations.”
“This whole project is designed to give us the biggest picture possible of battery electrolyte candidates,” added Argonne chemist Rajeev Assary, an author of both studies. ?“If we are going to use a molecule for energy storage applications, we need to know properties like its stability, and we can use this machine learning to predict properties of bigger molecules more accurately.”
Learn more: Building a better battery with machine learning
The Latest Google Headlines on:
Next generation battery
The Latest Bing News on:
Next generation battery
- LiDAR-based autonomous driving tech will come standard on next generation Volvoson May 7, 2020 at 11:25 pm
Volvo has taken a further step towards autonomous driving and safety by confirming the fitment of LiDAR technology in its next generation of vehicles from 2022. Developed in partnership with ...
- Ensure EV and Industrial-System Safety with Next-Gen Fuse Technologyon May 7, 2020 at 8:17 am
The latest in energy-storage systems demand high-performance safety components and sophisticated circuit-protection solutions that can provide the critical levels of protection to ensure both safety ...
- Ring Announces Next-Generation Affordable Ring Video Doorbellon May 6, 2020 at 7:29 am
Ring today announced they have updated their original video doorbell, improving features, security and the overall value of the product.
- Microsoft’s next-gen Surface products are hereon May 6, 2020 at 6:06 am
But I vowed that I would get one at some point after I got a real job, and in November 2017, I pre-ordered a Surface Book 2. Even though the Surface Book 2 still holds its weight (it’s the laptop I’m ...
- Large & Advanced Battery Technologies and Markets, 2018-2024 - ResearchAndMarkets.comon May 6, 2020 at 4:52 am
The "Large and Advanced Battery Technology and Markets" report has been added to ResearchAndMarkets.com's offering.
- Jaguar's next-generation XJ will be electric, but it won't bend design ruleson May 4, 2020 at 5:17 pm
It will ditch gasoline-powered six- and eight-cylinder engines in favor of electric power, the British company confirmed, but that's not an excuse to completely change its proportions. It will still ...
- New Opel Mokka Teased With Electric Version, Minor Name Changeon April 22, 2020 at 2:20 am
lectric, naturally: new Mokka available as battery electric vehicle from start ... the further developed Opel design philosophy. The next-generation Mokka combines German engineering with a ...
- New iPhone SE vs iPhone 11 vs iPhone XR: which is better?on April 17, 2020 at 3:25 am
There are a couple of other subtle differences to be aware of: the iPhone SE and iPhone 11 support Wi-Fi 6, the next generation of Wi-Fi designed ... won't be shocked to hear that it has the smaller ...
- Legion 7i laptop heads Lenovo's 2020 gaming machineson April 16, 2020 at 9:08 am
Leading the charge is the 7i, with a 240-Hz display, TrueStrike keyboard, long battery life and next-gen cooling technology. Lenovo describes its new Legion army as being stylish on the outside ...
- Porsche doesn't see Tesla as a rival, R&D boss explainson April 16, 2020 at 6:34 am
Porsche plans to focus on making battery cells smaller ... and the automaker has said the next-generation version will be electric only. However, Porsche is expected to continue selling the ...
The Latest Google Headlines on:
The Latest Bing News on:
- Scientists map tiny twists in “magic-angle” grapheneon May 10, 2020 at 3:34 am
Made of a single layer of carbon atoms linked in a hexagonal honeycomb pattern, graphene’s structure is simple and seemingly delicate. Since its discovery in 2004, scientists have found that graphene ...
- Battery Co. Hit With Discovery Sanctions In $100M IP Fighton May 8, 2020 at 5:35 pm
An Illinois federal judge on Friday imposed sanctions on stored energy solutions company LiiON LLC for discovery violations and other issues in a $100 million trade secrets fight against former ...
- Harvey Weinstein Denied Privilege Shield In Trafficking Suiton May 8, 2020 at 3:56 pm
A Manhattan federal judge on Friday swatted aside Harvey Weinstein's attempt to withhold documents in a sex trafficking lawsuit, ruling that the Hollywood-mogul-turned-imprisoned-rapist had lost his ...
- Researchers map tiny twists in magic-angle grapheneon May 8, 2020 at 5:54 am
Made of a single layer of carbon atoms linked in a hexagonal honeycomb pattern, graphene's structure is simple and seemingly delicate. Since its discovery in 2004, scientists have found that graphene ...
- Tiny Twists Mapped in “Magic-Angle” Graphene Could Enable Quantum Computing Deviceson May 8, 2020 at 4:43 am
Results could help designers engineer high-temperature superconductors and quantum computing devices. Made of a single layer of carbon atoms linked in a hexagonal honeycomb pattern, graphene’s ...
- Did Infamously Awful Greenhorn Kelly Collins From 'Deadliest Catch' End up in Jail?on May 5, 2020 at 1:48 pm
What happened to Kelly Collins from 'Deadliest Catch'? The greenhorn traded a hostile work environment for a prison cell.
- NFC Forum Approves Global Wireless Charging Specificationon May 5, 2020 at 7:04 am
The NFC Forum, the global standards and advocacy association for Near Field Communication (NFC) technology, announced today that its Board of Directors approved and adopted the Wireless Charging ...
- Hitting the Books: Without glass, we'd have never discovered the electronon May 2, 2020 at 8:40 am
Inside the glass, the cathode rays sprayed out in many directions like water out of a hose and were focused into a narrow stream, with two slits that acted like a nozzle. That beam then hit the ...
- Fort Smith man charged with domestic battery after assaulting woman, causing miscarriageon May 1, 2020 at 3:11 pm
A man from Fort Smith has been charged with domestic battery after assaulting a pregnant woman, which resulted in a miscarriage. Ricardo Blair has been charged with ...
- ‘Superfast’ new manufacturing method could mean breakthrough in battery technology, scientists sayon May 1, 2020 at 7:29 am
Reinvention’ of ceramics firing process could be used by artificial intelligence to create new materials with wide range of possible applications ...