For example, in 2017, strong flood The town of Impfondo in the Democratic Republic of Congo is flooded, but its remoteness makes it difficult to provide aid and identify people’s needs. Working with the Congolese government and humanitarian organizations, Cloud to Street’s platform reduced flood detection times from weeks to days and provided information on where refugees could be safely housed.
Initially, Cloud to Street clients were governments, their disaster departments, and organizations like the World Bank, helping them identify who and where to relocate and providing them with evidence they could use to lobby for additional relief funds. Today, Cloud to Street is also working on more corporate pursuits, helping insurers mine their risk and payment calculations. Either way, they need SAR, Schwarz said. “It’s clear that radar does have an insurmountable salient advantage that’s always necessary — and it’s usually cloudy and rainy during floods,” she said. “That’s its huge advantage, very direct.”
develop algorithms However, interpreting SAR data is more difficult than making data that can interpret pictures.
In part, this is a product of the limitations of the human brain. Some styles of data processing algorithms are modeled on how our brains analyze visual information. But we don’t perceive anything like SAR data. “It’s harder than processing optical data, because we can’t see it on radar,” said Vijayan Asari, director of the University of Dayton’s Vision Lab, which has a SAR image analysis unit. “We don’t see it in the microwave.”
(The group, in collaboration with the Air Force Research Laboratory and other organizations, is working on using SAR to detect and predict the activity of glaciers—another environmental application of this data. Glaciers are typically located on dark, cloudy parts of the planet. In addition to seeing through Haze, SAR can also penetrate the top of ice, revealing flow dynamics as glaciers melt and move. As an academic community, the lab may need to use data collected by Umbra or competitors, as well as information from public satellites such as Sentinel.)
Even Umbra’s COO struggled to understand SAR at first. “My first exposure to it was about U.S. classified capabilities,” said Master, a former program manager at Darpa, a high-stakes, potentially rewarding research facility for the U.S. Department of Defense. “I think I went into it with an attitude, like, ‘SAR is weird, it probably won’t tell you anything.'” After all, as he puts it, “our brains have adapted to our sensors. (He meant eyeballs.) But, he goes on, you can think of SAR as a “flashlight” that illuminates things your eyeballs can’t identify on their own.
SAR also has advantages over high-definition vision satellites: Radar satellites are cheap and (relatively) easy to manufacture. They don’t require clean rooms or huge, precise mirrors. “The problem with optics is that resolution makes the day,” Master said, meaning the sharper the optical image, the more useful it is. “The resolution is driven by large glass,” he said. “And big glass is expensive.”
Umbra’s business model is similarly streamlined: it just sells data to groups like Cloud to Street instead of analyzing it. Morrison thinks it’s best left to the experts. Take Schwartz, Morrison said. “She woke up in the morning and from the moment she woke up and hit her head on the pillow, she was thinking about the flood,” he said. At the same time, he rarely dreams of rising waters. (“I have a satellite to operate,” he said.)
But he hopes that once SAR data is readily available and relatively cheap, more people may wonder how it can help their own research or business — whether it involves tracking deforestation, carbon credits, wildfires, oil shipments, military operations, spills The pipes or the aging roof. “There are a million of these little niches,” Morrison said. Some of these niches can prevent life and livelihoods from sinking underwater.