image: Jesús Sánchez Juárez, a doctoral student in Jaime Cardenas’ laboratory, has facilitated the detection of monolayers — two-dimensional materials less than 1 / 100,000 the width of a human hair — that are highly sought after for electronics, the photonics. , and optoelectronic devices for their unique properties. Sánchez Juárez combined an economical microscope with a slow 5X lens and a low-cost camera, shown at the far right, with a neural network of artificial intelligence, to detect and process monolayer images, as shown in green on your computer screen. see more
Credit: Photo by J. Adam Fenster / University of Rochester
One of the most tedious and daunting tasks of undergraduate assistants in university research laboratories is to look at samples of material through hours and hours through a microscope, trying to find monolayers.
These two-dimensional materials (less than 1 / 100,000 the width of a human hair) are highly sought after for use in electronics, photonics, and optoelectronic devices because of their unique properties.
“Research labs are hiring armies of undergraduate students to do nothing more than look for monolayers,” says Jaime Cardenas, an assistant professor of optics at the University of Rochester. “It’s very tedious, and if you get tired, you may miss some of the monolayers or you may start making misidentifications.”
Even after all this work, labs have to review materials with a face Raman spectroscopy or atomic force microscopy.
Jesús Sánchez Juárez, a doctoral student at Cardenas Lab, has greatly facilitated the lives of undergraduate students, their research laboratories and companies that find similar difficulties in detecting monolayer.
The innovative technology, an automated scanning device described in Optical Materials Express, can detect monolayers with 99.9 percent accuracy, surpassing any other method to date.
At a fraction of the cost. In much less time. With easily accessible materials.
“One of the main goals was to develop a system with a very small budget so that students and labs could replicate these methodologies without having to invest thousands and thousands of dollars just to buy the necessary equipment,” says Sánchez Juárez, lead author of the paper.
For example, the device you created can be replicated with an economical microscope with a 5X lens and a low-cost OEM (original equipment manufacturer) camera.
“We’re very excited,” Cardenas says. “Jesus did several new and different things here, applying artificial intelligence in a new way to solve a major problem in the use of 2D materials.”
Many laboratories have attempted to eliminate the need to scan expensive human backup characterization tests by training an artificial intelligence (AI) neural network to scan monolayers. Most labs that have tested this approach try to build a network from scratch, which takes a significant amount of time, Cardenas says.
Instead, Sánchez Juárez started with a publicly available neural network called AlexNet that is already trained to recognize objects.
He then developed a new process that inverts the images of the materials so that everything that was bright in the original image looks black, and vice versa. Inverted images are executed using additional processing steps. At the moment, the images “do not look good to the human eye,” says Cárdenas, “but it is easier for a computer to separate the monolayers from the substrates on which they are deposited.”
Conclusion: Compared to these tedious and tedious scanning hours by undergraduate students, Sánchez Juárez’s system can process 100 images covering samples measuring 1 centimeter x 1 centimeter in nine minutes with an accuracy of almost 100 %.
“Our demonstration paves the way for the automated production of monolayer materials for use in research and industrial environments by greatly reducing processing time,” writes Sánchez Juárez in the document. Applications include 2D materials suitable for photodetectors, excitonic light emitting devices (LEDs), lasers, optical spin valley current generation, single photon emission, and modulators.
Additional co-authors include Marissa Granados Baez, a PhD student at the Cardenas Lab, and Alberto A. Aguilar-Lasserre, a professor at the Orizaba Institute of Technology.
magazine
Express optical materials
Research method
Experimental study
Research topic
Not applicable
Article title
Automated system for the detection of 2D materials through image processing and deep learning
Date of publication of the article
April 6, 2022
IOC statement
The authors declare no conflict of interest.
Disclaimer: AAAS and EurekAlert! is not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or by the use of any information through the EurekAlert system.