Satellite Revolution Empowered by Cloud Watches for Dangerous Weather

On Sept. 28, 2022, Hurricane Ian made landfall in southwest Florida. One of the strongest storms to ever strike the Sunshine State, the Category 4 hurricane battered the Gulf Coast with catastrophic winds of 150 miles per hour and a storm surge that was up to 12 feet deep in some places. It claimed more than 100 lives and caused at least $63 billion worth of damage.

It’s a harsh reminder that natural disasters are becoming more frequent and dangerous. In the last 50 years, the number of extreme weather incidents has increased five-fold, killing more than 45,000 people per year while costing individuals, businesses and governments trillions of dollars.

Unfortunately, governments don’t have crystal balls with which to predict storms or magic wands with which to prevent them. They do, however, have satellites.

Over the past decade, the space sector has experienced massive growth in investment activity, according to research firm McKinsey. Between 2012 and 2021, total annual investment grew to more than $10 billion, from $300 million. The number of satellites are expected to grow by 1,000%+ this decade, with a wide-ranging impact on everything from predicting pandemics and saving the planet, according to the business and tech news site The Hustle.

Improvements in rocket launch technologies, satellite design and data analysis have led to an explosion in high-resolution satellite imagery that can deliver new information for improving life on Earth. This investment and innovation are redefining what it means to have “flying eyes in the sky.” The first Earth observation satellite, Landsat 1, which was launched by NASA in 1972, weighed 1800kg and was roughly the size of a garbage truck, according to The Hustle. Today’s so-called ‘smallsats’ weigh as little as 12kg and are about the size of a shoebox.

The proliferation of satellites is bringing complex challenges, including privacy rights, space waste and atmosphere congestion to name a few. However, with satellite technologies more accessible and readily available than ever before, many startups and established companies are rushing to find ways for satellites to bring new valuable services to life.

The Eye of the Storm

Although they’re one of the most robust tools available for surveying and analyzing changes on Earth, satellites were useless during storms until the advent of synthetic aperture radar (SAR), which uses radio waves instead of conventional cameras to “see” through clouds, giving scientists, governments and first responders a clear view from space on even the stormiest days. By viewing what previously was hidden behind an impenetrable wall of clouds and fog, they can track deadly weather events and respond to them more quickly, saving money and precious lives in the process.

“With SAR, we can capture data in hazardous situations, bad weather or climate conditions so that we are able to get information on a disaster area,” said Dr. Vijayan Asari, director of the Vision Lab at the University of Dayton, which analyzes SAR data.

Unlike optical cameras, synthetic aperture radar works by shooting microwave signals of various wavelengths toward a target zone. Spaceborne sensors receive these signals as they bounce off the Earth’s surface. Called backscatter, this reflection varies from object to object, which means analysts can distinguish not only a tree from a building but also freshwater from saltwater.

“It can penetrate any kind of obstacle,” Asari continued. “Lighting isn’t a problem. Haze isn’t a problem. Fog isn’t a problem. Clouds aren’t a problem.”

When livelihoods and lives are at stake, nothing is more essential than real-time data. Because it penetrates clouds, SAR provides exactly that, functioning day or night so satellites can observe Earth in any weather and at any time.

That’s vital to helping first responders evacuate victims during floods, to helping governments allocate money and manpower to the neediest disaster locations, and to helping scientists track and predict storm risks.

“A picture may be worth a thousand words, but that’s true only if you can get a shot in the first place,” author Sarah Scoles explained in an article for Wired magazine. 

“Clouds cover, on average, about two-thirds of Earth. And at any given time, roughly half of the planet is dark … In either of those conditions, traditional satellite imagery is not worth many words at all.”

SAR’s unique characteristics have made satellites invaluable not only for monitoring extreme weather, but also for tracking Russian troop movements in Ukraine, for capturing pirates off the coast of Indonesia and for monitoring dams in countries that depend on hydropower.

A Well-Oiled Machine

SAR does not generate normal imagery. Instead, it returns raw data that on its own is unintelligible to the human eye. That means analysts must employ algorithms and machine learning to make sense of it.  

“We use machine learning to train the system to distinguish objects,” Asari said. 

“We extract all of the features automatically like a human being does. A human is not looking at the edges, gradient and texture – they just identify an object. Machine learning automatically does the same things as a human by perceiving and identifying objects.”

When the data is quickly interpreted and synthesized, government agencies like the Federal Emergency Management Agency (FEMA) can extract from it actionable insights that impact integral, minute-by-minute decision making.

Along with sensors in the sky, that takes “enormous amounts of computing power” on the ground, according to Asari. 

“We have lots of data and algorithms that need to be tested and evaluated,” he continued. “You might not have the facility at your lab or research center to execute all of these things simultaneously, but you need to have more high-end computing power for the huge amount of data and complex algorithms.”

Enter cloud computing platforms, which make time-sensitive data usable when it’s needed most.

“Satellite imagery is everywhere … The data behind that imagery is nothing like a screenshot, though. It’s comprised of tiny packets of data, digitally manipulated to resemble the surface of the Earth, a swirling storm system or a map of urban growth,” host John Hult explained in an August 2021 episode of Eyes on Earth, a podcast from the U.S. Geological Survey’s (USGS) Earth Resources Observation and Science (EROS) Center.

According to Hult, a single satellite picture of 115 square miles can consume over 2 gigabytes of storage, which is larger than some feature-length films. 

“These are huge files,” Hult said. 

“It takes a lot of computing horsepower to download and analyze large satellite datasets, particularly when the goal is to answer questions about change over time. That’s one of the reasons why remote sensing scientists are increasingly turning to cloud computing, which allows users with cloud accounts to analyze, visualize and interpret satellite data without downloading it and storing it locally.”

Being able to process large datasets without local infrastructure means scientists and first responders can understand and react to data quickly, collaboratively and at scale, which can yield new life- and property-saving insights.

“Another benefit is being able to combine data that was really never able to be combined when we were working from local machines because of the restrictions of resources,” Aaron Friesz, science coordination lead for EROS’s Land Processes Distributed Active Archive Center (LP DAAC), told Hult. 

“With that data in the cloud, you can start combining data and start gaining new insights that were not achievable when we were working from local machines.”

Wave of the Future

As the planet continues to warm, storms will increase in intensity and frequency, according to USGS, which has many tools in its toolbox – of which SAR is only one.

For example, take USGS’s and NASA’s Landsat 9 satellite, which launched in 2021. Although it’s not equipped with SAR, it features two other advanced instruments with which to monitor natural and human-induced changes to Earth’s surface: the Operational Land Imager 2 (OLI-2), which captures observations of the Earth’s surface in visible, near-infrared and shortwave-infrared bands, and the Thermal Infrared Sensor 2 (TIRS-2), which measures heat emitted from the Earth’s surface.

“Landsat tells us about the Earth’s vegetation, land use, coastlines and surface water, just to name a few,” said Karen St. Germain, head of NASA’s Earth Science Division, according to Space.com. 

“When combined with other Earth science missions, that can tell us what is happening and also why.”

Still, SAR provides timely and life-saving information where previous technology could not.

“We need these kinds of sensors for applications irrespective of any weather and lighting conditions,” Asari said.

“This technology is growing exponentially. There will be a future where a human being isn’t able to reach a location, but we are able to send in a remote-sensing platform … to collect and process the data and make appropriate decisions.”

For communities in the eye of an impending storm, that capability could be the difference between life and death.

Chase Guttman is a technology writer. He’s also an award-winning travel photographer, Emmy-winning drone cinematographer, author, lecturer and instructor. His book, The Handbook of Drone Photography, was one of the first written on the topic and received critical acclaim. Find him at chaseguttman.com or @chaseguttman. 

© 2022 Nutanix, Inc. All rights reserved. For additional legal information, please go here.