MIT devises method to accelerate electronic materials screening

The new computer vision technique characterises a material’s electronic properties 85 times faster than conventional procedures, according to Massachusetts Institute of Technology (MIT) engineers.

MIT graduate students Eunice Aissi (left) and Alexander Siemenn have developed a technique designed to automatically analyze visual features in printed samples (pictured) and swiftly determine key properties of new semiconducting materials. Picture: Bryce Vickmark.

MIT said a new computer vision technique has been developed by its engineers to “significantly speed up” the characterization of newly synthesized electronic materials. Two computer vision algorithms have been produced to automatically interpret images of electronic materials: one to estimate band gap (a measure of electron activation energy) and the other to determine stability (a measure of longevity). This method automatically analyzes images of printed semiconducting samples and estimates these two key electronic properties for each sample.

The first algorithm is designed to process visual data from highly detailed, hyperspectral images. MIT graduate student Alexander (Aleks) Siemenn explained: “Instead of a standard camera image with three channels — red, green, and blue (RBG) — the hyperspectral image has 300 channels. The algorithm takes that data, transforms it, and computes a band gap. We run that process extremely fast.”

The second algorithm analyzes standard RGB images and assesses a material’s stability based on visual changes in the material’s colour over time. MIT graduate student Eunice Aissi commented: “We found that colour change can be a good proxy for degradation rate in the material system we are studying.”

Researchers intend to use the method to speed up the search for promising solar cell materials. They also plan to incorporate the technique into a fully automated materials screening system.

“Ultimately, we envision fitting this technique into an autonomous lab of the future,” stated Aissi. “The system would allow us to give a computer a materials problem, have it predict potential compounds, and then run 24-7 making and characterizing those predicted materials until it arrives at the desired solution.”

Siemenn added: “The application for these techniques ranges from improving solar energy to transparent electronics and transistors. It really spans the full gamut of where semiconductor materials can benefit society.”

Aissi and Siemenn detail the new technique in a study appearing in Nature Communications. Their MIT co-authors include graduate student Fang Sheng, postdoc Basita Das, and professor of mechanical engineering Tonio Buonassisi, along with former visiting professor Hamide Kavak of Cukurova University and visiting postdoc Armi Tiihonen of Aalto University.