Connect with us


New computer vision method speeds up screening of electronic materials | MIT News

New computer vision method speeds up screening of electronic materials | MIT News


To improve the performance of solar cells, transistors, LEDs and batteries, we will need better electronic materials made from new compositions that have yet to be discovered.

To speed up the search for advanced functional materials, scientists are using AI tools to identify promising materials from hundreds of millions of chemical compositions. In parallel, engineers are building machines that can print hundreds of material samples at a time, based on their chemical compositions tagged by AI search algorithms.

However, until now there has been no equally rapid way to confirm whether printed materials actually perform as expected, and this final step in materials characterization has been a major bottleneck in the advanced materials screening pipeline.

Now, a new computer vision technique developed by MIT engineers greatly speeds up the characterization of newly synthesized electronic materials. The technique automatically analyzes images of printed semiconductor samples to rapidly estimate two important electronic properties of each sample: its band gap (a measure of electron activation energy) and its stability (a measure of lifetime).

This new technique accurately characterizes electronic materials 85 times faster than standard benchmark methods.

The researchers intend to use this technique to accelerate the search for promising solar cell materials and also plan to incorporate it into a fully automated materials screening system.

Ultimately, MIT graduate student Younis Aysi says, they envision incorporating this technology into the autonomous labs of the future. The entire system would allow them to give a materials problem to a computer, have it predict potential compounds, and then run the process of making and characterizing the predicted materials 24/7 until they arrive at a desired solution.

The applications of these technologies range from improved solar energy to transparent electronics and transistors, adds MIT graduate student Alexander (Aleks) Siemenn. The scope of how semiconductor materials can benefit society is truly broad.

Aysi and Seemen detail their new technology in a study published today in Nature Communications. MIT co-authors include graduate student Fan Shen, postdoctoral researcher Basita Das, mechanical engineering professor Tonio Buonassisi, as well as former visiting professor Hamide Kavak of Çukurova University and visiting postdoctoral researcher Armi Tiihonen of Aalto University.

The power of optics

Once a new electronic material is synthesized, its properties are typically evaluated by domain experts who look at one sample at a time using a benchtop tool called UV-Vis, which scans different colors of light to determine where the semiconductor begins to absorb more strongly. This manual process is precise but time-consuming. Domain experts typically evaluate about 20 material samples per hour, a very slow pace compared to some printing tools that can print 10,000 different material combinations per hour.

The manual characterization process is very slow, Buonassisi said, and although it provides a high degree of confidence in the results, it cannot keep up with the speed at which material can currently be placed on a substrate.

To speed up the characterization process and eliminate one of the biggest bottlenecks in materials screening, Buonassisi and his colleagues turned to computer vision, a field that applies computer algorithms to quickly and automatically analyze optical features in images.

Optical characterization methods are powerful, Buonassisi points out: They can provide information very quickly, and images across many pixels and wavelengths have a richness that humans can't process but that computer machine learning programs can.

The team realized that if they captured the information in enough detail and interpreted it correctly, certain electronic properties, namely band gap and stability, could be inferred based on visual information alone.

With that goal in mind, the researchers developed two new computer vision algorithms to automatically interpret images of electronic materials: one to estimate the band gap and the other to determine their stability.

The first algorithm is designed to process visual data from highly detailed hyperspectral imagery.

“A standard camera image has three channels – red, green and blue (RBG) – but a hyperspectral image has 300 channels,” explains Seemen. “The algorithm takes that data, converts it and calculates the band gap, and this process happens extremely fast.”

The second algorithm analyzes standard RGB images and assesses the stability of materials based on the visual change in the material's color over time.

“We found that the color change could be a good indicator of the degradation rate of the material systems we study,” Aisi says.

Material Composition

The research team applied two new algorithms to characterize the band gap and stability of about 70 printed semiconductor samples. They used a robotic printer to arrange the samples on a single slide, like cookies on a baking sheet. Each arrangement used a slightly different combination of semiconductor materials. In this case, the team printed different ratios of perovskites, a type of material that shows promise as a promising candidate for solar cells but is also known to degrade rapidly.

People are trying to change the composition by adding a little bit of this, a little bit of that. [perovskites] This will make it more stable and performant, Buonassisi says.

The research team printed perovskite samples of 70 different compositions onto a single slide and then scanned the slide with a hyperspectral camera. They then applied an algorithm to visually segment the image and automatically separate the samples from the background. They then ran a new band gap algorithm on the separated samples to automatically calculate the band gaps of all samples. The entire band gap extraction process took approximately six minutes.

According to Seemen, it would typically take a domain expert several days to manually characterize the same number of samples.

To test stability, the team placed the same slides in chambers with varying environmental conditions, including humidity, temperature, and exposure to light. Using a standard RGB camera, the team took images of the samples every 30 seconds over a two-hour period. They then applied a second algorithm to the images of each sample over time to estimate the extent to which each droplet changed color, or degraded, under the various environmental conditions. Ultimately, the algorithm produced a stability index — a measure of each sample's durability.

To confirm, the team compared their results to manual measurements of the same droplets performed by experts in the field. Compared to the experts' benchmark estimates, the team's bandgap and stability results were 85 times faster, with 98.5 percent and 96.9 percent accuracy, respectively.

“We were constantly amazed by how these algorithms not only speeded up characterization, but also gave us accurate results,” says Seemen. “We envision incorporating this into the current automated materials pipeline that we're developing in the lab, so that we can use machine learning to guide us to where we want to discover these new materials, print them, and actually characterize them, all at a very fast rate, in a fully automated fashion.”

This research was supported by First Solar.




The mention sources can contact us to remove/changing this article

What Are The Main Benefits Of Comparing Car Insurance Quotes Online

LOS ANGELES, CA / ACCESSWIRE / June 24, 2020, / Compare-autoinsurance.Org has launched a new blog post that presents the main benefits of comparing multiple car insurance quotes. For more info and free online quotes, please visit https://compare-autoinsurance.Org/the-advantages-of-comparing-prices-with-car-insurance-quotes-online/ The modern society has numerous technological advantages. One important advantage is the speed at which information is sent and received. With the help of the internet, the shopping habits of many persons have drastically changed. The car insurance industry hasn't remained untouched by these changes. On the internet, drivers can compare insurance prices and find out which sellers have the best offers. View photos The advantages of comparing online car insurance quotes are the following: Online quotes can be obtained from anywhere and at any time. Unlike physical insurance agencies, websites don't have a specific schedule and they are available at any time. Drivers that have busy working schedules, can compare quotes from anywhere and at any time, even at midnight. Multiple choices. Almost all insurance providers, no matter if they are well-known brands or just local insurers, have an online presence. Online quotes will allow policyholders the chance to discover multiple insurance companies and check their prices. Drivers are no longer required to get quotes from just a few known insurance companies. Also, local and regional insurers can provide lower insurance rates for the same services. Accurate insurance estimates. Online quotes can only be accurate if the customers provide accurate and real info about their car models and driving history. Lying about past driving incidents can make the price estimates to be lower, but when dealing with an insurance company lying to them is useless. Usually, insurance companies will do research about a potential customer before granting him coverage. Online quotes can be sorted easily. Although drivers are recommended to not choose a policy just based on its price, drivers can easily sort quotes by insurance price. Using brokerage websites will allow drivers to get quotes from multiple insurers, thus making the comparison faster and easier. For additional info, money-saving tips, and free car insurance quotes, visit https://compare-autoinsurance.Org/ Compare-autoinsurance.Org is an online provider of life, home, health, and auto insurance quotes. This website is unique because it does not simply stick to one kind of insurance provider, but brings the clients the best deals from many different online insurance carriers. In this way, clients have access to offers from multiple carriers all in one place: this website. On this site, customers have access to quotes for insurance plans from various agencies, such as local or nationwide agencies, brand names insurance companies, etc. "Online quotes can easily help drivers obtain better car insurance deals. All they have to do is to complete an online form with accurate and real info, then compare prices", said Russell Rabichev, Marketing Director of Internet Marketing Company. CONTACT: Company Name: Internet Marketing CompanyPerson for contact Name: Gurgu CPhone Number: (818) 359-3898Email: [email protected]: https://compare-autoinsurance.Org/ SOURCE: Compare-autoinsurance.Org View source version on accesswire.Com:https://www.Accesswire.Com/595055/What-Are-The-Main-Benefits-Of-Comparing-Car-Insurance-Quotes-Online View photos


to request, modification Contact us at Here or [email protected]