Vancouver, British Columbia-based Metaspectral, a software company offering deep learning and hyperspectral imagery technologies, has raised $4.7 million in seed funding from Soma Capital, Acequia Capital, the government of Canada and multiple angel investors, including Jude Gomila and Alan Rutledge. Metaspectral says it plans to use the seed funding to scale its team to support the development and refinement of its Fusion technology platform, which it says is set to launch this year.
According to Metaspectral, Fusion deploys deep-learning models that analyze hyperspectral imagery in real-time. Metaspectral says hyperspectral images contain information from across the electromagnetic spectrum, making it possible to identify the chemical composition and other invisible properties of materials with computer vision.
“The platform can visually detect defects on a manufacturing line, classify plastic polymers, quantify greenhouse gas levels on the Earth’s surface and has countless other applications,” says Francis Doumet, Metaspectral CEO and co-founder. “We have spent the last three years developing this technology, and it is already being used in the aerospace, defense, agriculture, manufacturing and other significant industries.”
Doumet says hyperspectral data analysis can identify the chemical properties of objects, adding that this information can be used to sort and recycle materials more effectively. “It works by shining a light on an object and analyzing the reflected light,” he says. “In the case of plastic recycling, hyperspectral data analysis can be used to identify the type of plastic at the polymer level. This matters because different types of plastic require different recycling processes. Using this technology, it is possible to quickly and accurately sort plastics for recycling. … There is another method that we see used in production today uses the shape of the objects to attempt to determine the materials, which results in up to 30 percent error/contamination rates. Fusion offers a new alternative that can work rapidly and accurately.”
Aneel Ranadive, managing director and founder of Soma Capital, says Soma decided to support Metaspectral’s Fusion platform because it believes that Metaspectral “is perfectly positioned to service the diverse needs of both enterprise and government clients to inform better, more immediate decision-making.”
According to Metaspectral, its technology is planned for deployment on the International Space Station to demonstrate real-time compression, streaming and analysis of hyperspectral data from Low Earth Orbit. Other Metaspectral clients include the Canadian Space Agency, Defence Research and Development Canada and a large Canadian recycler. Metaspectral says it could not disclose the name of the large recycler.
Migel Tissera, co-founder and chief technology officer at Metaspectral, says the Fusion platform is “an easy-to-use, all-in-one platform” that can be used to create artificial intelligence models for any desired purpose.
He says, “Currently, the platform is configured to identify specific plastics for recycling, but it can be easily adapted to any other kind of recycling. This could include building materials after a demolition, automotive parts, thin plastics like chip bags and black material. Because this kind of analysis can provide much more accurate information about the composition of materials, the resulting postconsumer recycled materials can be of much higher purity and quality. There is a growing demand in the market for recycled plastic, and increased purity means that these materials can fetch a higher price in the market.”