In 2017, for example. intense flooding flooded the city of Impfondo in the Democratic Republic of Congo, but its remote location made it difficult to send aid and determine people’s needs. In collaboration with the Congolese government and humanitarian groups, the Cloud to Streets platform has since shortened flood detection times from weeks to days and provided information on where to safely move refugees.
To begin with, Cloud to Street’s customers were governments, their disaster weapons and organizations like the World Bank, which helped them figure out who to move and where, and provided them with evidence that they could use to lobby for additional emergency aid. Today, Cloud to Street also works on several business activities and helps insurance companies leverage their risk and payout calculations. Either way, Schwarz says, they will need SAR. “It’s very clear that radar really has a conspicuous advantage, which is hard to overcome, which would always be necessary – and that is when it is flooded, it is often cloudy and rainy,” she says. “That’s right, the big advantage of that.”
Development of algorithms that can parse SAR data, however, it is harder than whipping up those who can parse images.
In part, it is an artifact of the limitations of the human brain. Some data processing algorithms are modeled on how our brains analyze visual information. But we do not perceive anything as SAR data. “It’s harder than dealing with optical data because we do not see in radar,” said Vijayan Asari, director of the Vision Lab at the University of Dayton, which has a SAR image analysis arm. “We do not look in microwaves.”
(The group, which collaborates with the Air Force Research Lab, among other things, is working on using SAR to detect and predict glacier activities – another environmental application for this data. Glaciers are typically in dark, cloudy parts of the planet. In addition to looking through darkness, the SAR can also penetrate the top of the ice and reveal the flow dynamics of glaciers as they melt and move. .)
Even Umbra’s COO initially found it difficult to grow SAR. “My first exposure to it was in terms of U.S. classified capabilities,” says Master, a former program manager at Darpa, the defense department’s high-risk, perhaps-rewarded research agency. “I think I kind of got into it with an attitude that’s like, ‘SAR is weird, it probably won’t tell you anything.'” After all, as he puts it, “our brain is tuned to our sensors.” (He means eyeballs.) But, he continues, you can think of the SAR as being like a “flashlight” that lights up what your eyeballs cannot see by itself.
SAR also has an advantage over high-definition visual satellites: Radar satellites are inexpensive and (relatively) easy to make. They do not require a clean room or giant, precise mirrors. “The problem with optical is that resolution controls the day,” says Master, which means that the sharper an optical image is, the more useful it is. “Resolution is driven by large glasses,” he says. “And large glasses are expensive.”
Umbra’s business model is similarly streamlined: it simply sells data to groups like Cloud to Street instead of analyzing it. Morrison believes it is better to leave it to the specialists. Take Black, says Morrison. “She wakes up in the morning, and from the moment she’s awake to the moment her head hits the pillow, she’s thinking of flooding,” he says. Meanwhile, he rarely dreams of rising water. (“I have a satellite to operate,” he says.)
But he hopes that once SAR data is readily and relatively cheaply available, more people may wonder how it can help their own research or business – whether it involves deforestation, carbon credits, forest fires, oil shipments, military movements , leaky pipes or aging roofs. “There are a million of these little niches,” Morrison says. And some of these niches could prevent both life and livelihood from going underwater.