Aspia Space joins the ranks of companies and space agencies involved in remote sensing, tracking the physical properties of things on the ground using sensors on satellites. Most Earth observation satellites, like NASA’s long-running Landsat program, use sensors for optical imagery — essentially photos taken from space. But at any given time, most of the earth is covered in clouds, smoke, and air pollution, which can block these sensors and lead to large data gaps. Radar has the advantage of being able to penetrate clouds, so it can provide a clear picture at all times – even in perpetually overcast parts of the Irish countryside.
In radar satellite imagery, radio waves and microwaves are sent, reflected from the earth’s surface, and their echoes are captured. You can see landmarks in a radar image, but the images are difficult to interpret without expertise. That’s why Aspia uses ClearSky to convert them into optical images. Resolution is also important, so Aspia and others typically use “synthetic aperture radar” or SAR, which simulates the effect of a longer antenna and produces higher-resolution images.
Several companies in the commercial space industry have adopted SAR in recent years, including California-based companies Capella Space and Umbra Space, and Finnish company Iceye. While Aspia focuses on analyzing data from space agency orbiters, these companies own their own satellites and sell or license their radar data to others. For example, Capella recently announced one Analytics Partnership Program so other companies can design their own algorithms using Capella’s radar images, says Adam Thomas, the company’s director of business development.
Comparing high-resolution radar images of the same area to spot precise changes, such as damaged or healthy plants, is “the real superpower for SAR,” says Todd Master, Umbra’s chief operating officer. (His company is particularly interested in a similar application: flood tracking.)
Until a few years ago, SAR data were mostly only available to the military and secret services. But now that customers have access to radar data from private companies like Umbra, they will find more potential uses for it, particularly in the area of analytics. “That will be unlocked in the next decade,” says Master.
Aspia is now working to integrate generative AI into ClearSky to forecast future crop growth and droughts. “Essentially, ClearSky uses the same principles as GPT,” says Geach. Just as large language models like ChatGPT and Bard, which have ingested vast amounts of text from the Internet, can predict a likely word sequence, ClearSky takes satellite imagery of a given area and predicts a sequence of images that will follow. “The model predicts the most likely next sequence: what does tomorrow look like?” he says.