Chinese Peril

AI CAN HELP HUNT DOWN MISSILE SITES IN CHINA
By Jeremy Hsu

A surface-to-air missile is seen through a doorway in Zhuhai, China.

INTELLIGENCE AGENCIES HAVE a limited number of trained human analysts looking for undeclared nuclear facilities, or secret military sites, hidden among terabytes of satellite images. 

But the same sort of deep learning artificial intelligence that enables Google and Facebook to automatically filter images of human faces and cats could also prove invaluable in the world of spy versus spy. 

An early example: US researchers have trained deep learning algorithms to identify Chinese surface-to-air missile sites—hundreds of times faster than their human counterparts.
The deep learning algorithms proved capable of helping people with no prior imagery analysis experience find surface-to-air missile sites scattered across nearly 90,000 square kilometers of southeastern China. 

Such AI based on neural networks—layers of artificial neuron capable of filtering and learning from huge amounts of data—matched the overall 90 percent accuracy of expert human imagery analysts in locating the missile sites. 

Perhaps even more impressively, the deep learning software helped humans reduce the time needed to eyeball potential missile sites from 60 hours to just 42 minutes.
"The algorithms were used to find the locations where they said there is a high confidence of a missile site, and then humans reviewed the results for accuracy and figured out how much time the algorithms saved," says Curt Davis, a professor of electrical engineering and computer science, and director of the Center for Geospatial Intelligence, at the University of Missouri. 

"To my knowledge that’s never been studied before: How much time did you save, and how does that ultimately impact the human performance?"
The University of Missouri study, published on October 6 in the Journal of Applied Remote Sensing, comes at a time when satellite imagery analysts are figuratively drowning in a deluge of big data. DigitalGlobe, a leading commercial satellite imagery company, generates about 70 terabytes of raw satellite imagery each day, never mind all the imagery data coming from other commercial satellites and government spy satellites.
Davis and his colleagues showed how off-the-shelf deep learning models—heavily trained and modified for satellite imagery analysis—could identify objects of potentially great interest to intelligence agencies and national security experts. 

The deep learning models, including GoogleNet and Microsoft Research's ResNet, were initially created to detect and classify objects in traditional photo and video imagery. 

Davis and his colleagues adapted such models to the challenges and limitations of interpreting satellite imagery, such as training some deep learning models to interpret both color and black-and-white imagery, in case only black-and-white images of SAM sites were available.
They did so with satellite imagery representing a huge swath of Chinese territory, not that much smaller than the entire country of North Korea.
And in fact, analysts rely extensively on satellite imagery to keep track of how North Korea's weapons programs evolve. 

Human analysts have already likely identified most, if not all, existing SAM sites within the relatively small country. 

But similar deep learning tools could help automatically flag new SAM sites that appear in North Korea or other countries. 

Knowing the location of existing and new SAM sites can sometimes lead analysts to other locations of interest, because countries often place SAM sites in specific areas to defend valuable nearby assets from air attack.
The latest study also illustrates the challenges of applying deep learning AI to satellite imagery analysis. 

One major problem is the relative lack of large training datasets that include the hand-labeled examples needed to train deep learning algorithms to accurately identify features in satellite imagery. The University of Missouri team combined public data on the worldwide locations of about 2,200 SAM sites with DigitalGlobe satellite imagery to create their training data, and then tested four deep learning models to find the best-performing one.
The researchers ended up with only about 90 positively identified Chinese SAM site examples to train their AI. 

Such a puny training dataset might normally fail to yield accurate deep learning results. 

To get around that problem, Davis and his colleagues transformed the 90-odd training samples into about 893,000 training samples by shifting the original images slightly in different directions.
The impressive deep learning performance in the study likely benefited from SAM sites being fairly large, and having distinctive patterns when viewed from above in satellite images. 

Davis cautioned that deep learning algorithms face a much greater challenge when trying to analyze smaller objects such as mobile missile launchers, radar antennas, mobile radar systems, and military vehicles, because the available satellite imagery data will have fewer pixels to work with in extracting identifying features.
"It is an open question in our mind how well convolutional neural networks will work on smaller scale objects like this, especially when tested against large area datasets like we did with the China study," Davis says.
Even imperfect AI tools could prove incredibly helpful for intelligence gathering. 

For example, the International Atomic Energy Agency has the unenviable task of monitoring all declared nuclear facilities and also searching for undeclared facilities among nearly 200 countries. 

Deep learning tools could help the IAEA and other independent organizations use satellite imagery to monitor development of nuclear power and related weapons of mass destruction, says Melissa Hanham, a senior research associate in the East Asia Nonproliferation Program at the Middlebury Institute of International Studies at Monterey, Calif.
"We're in a world where there is just so much data that the best way to approach it is to do a good job on a lot of it rather than a perfect job on a small bit of it," Hanham says. 

"I'm looking forward to automating all the tedious and redundant parts of my job."

Sina Delenda Est

Satellite images reveal Chinese expansion in South China Sea

By: Barbara Opall-Rome

TEL AVIV, Israel — Imagery captured Monday from an ImageSat International (ISI) Eros B satellite indicates Chinese preparations for new land-based missile installations on an increasingly strategic island base in the South China Sea.
The high-resolution imagery, shown here for the first time, reveals recent changes in the layout of the People’s Liberation Army’s Yulin Naval Base at the tip of Hainan Island in the disputed Scarborough Shoal.
In less than two months, the PLA deployed multiple missile launchers on the western side of the base, deployments that ISI imagery analyst Amit Gur has concluded are anti-ship missiles.
“The direction in which the launchers are facing leads us to believe these are shore-to-ship missiles,” Gur told Defense News.

He said that similar systems had shown up in satellite data about two years ago, but had been removed in recent months to accommodate infrastructure upgrades at the site.
ISI's imagery from March 15 shows an empty plateau, but by May 8 the firm’s Eros B captured a clear image of newly paved infrastructure and multiple launch sites.
“They must have concluded renovation work, as the systems are clearly visible,” Gur said.
“We just don’t know if they are new systems, or a [redeployment] of the ones that were stored during the renovation.”
Perhaps even more interesting, according to ISI, is progress taking place on Yulin’s eastern side. “We’re seeing the building of infrastructure that wasn’t there before and what looks like preparations for shore-to-ship missiles, just like on the western side,” company spokesman Gil Or said.

Photo Credit: ImageSat International

Gur noted that expansion of the Yulin base fortifies Beijing’s strategic triangle of forward bases with which to quickly project its power well beyond neighboring Vietnam and the Philippines.

Chinese Aggressions

China can deploy warplanes on artificial islands any time: Think tank

Reuters

Missile destroyer Changsha returns to a port in Sanya City, south China's Hainan Province, March 7, 2017, after a high sea drill that passed through the South China Sea.

China appears to have largely completed major construction of military infrastructure on artificial islands it has built in the South China Sea and can now deploy combat planes and other military hardware there at any time, a U.S. think tank said on Monday.
The Asia Maritime Transparency Initiative (AMTI), part of Washington's Center for Strategic and International Studies, said the work on Fiery Cross, Subi and Mischief Reefs in the Spratly Islands included naval, air, radar and defensive facilities.
The think tank cited satellite images taken this month, which its director, Greg Poling, said showed new radar antennas on Fiery Cross and Subi.
"So look for deployments in the near future," he said.
China has denied U.S. charges that it is militarizing the South China Sea, although last week Li Keqiang said defense equipment had been placed on islands in the disputed waterway to maintain "freedom of navigation."
AMTI said China's three air bases in the Spratlys and another on Woody Island in the Paracel chain further north would allow its military aircraft to operate over nearly the entire South China Sea, a key global trade route that Beijing claims most of.
Several neighboring states have competing claims in the sea, which is widely seen as a potential regional flashpoint.
The think tank said advanced surveillance and early-warning radar facilities at Fiery Cross, Subi, and Cuarteron Reefs, as well as Woody Island, and smaller facilities elsewhere gave it similar radar coverage.
It said China had installed HQ-9 surface-to-air missiles at Woody Island more than a year ago and had deployed anti-ship cruise missiles there on at least one occasion.
It had also constructed hardened shelters with retractable roofs for mobile missile launchers at Fiery Cross, Subi and Mischief and enough hangars at Fiery Cross for 24 combat aircraft and three larger planes, including bombers.
U.S. officials told Reuters last month that China had finished building almost two dozen structures on Subi, Mischief and Fiery Cross that appeared designed to house long-range surface-to-air missiles.
In his Senate confirmation hearing in January, new U.S. Secretary of State Rex Tillerson said China should be denied access to islands it had built up in the South China Sea.
He subsequently softened his language, saying that in the event of an unspecified "contingency," the United States and its allies "must be capable of limiting China's access to and use of" those islands to pose a threat.
In recent years, the United States has conducted a series of what it calls freedom-of-navigation operations in the South China Sea, raising tensions with Beijing.

New satellite images show inside China’s ghost cities

By Gus Lubin

China still has a startling number of vacant real-estate developments, judging from new satellite analysis by DigitalGlobe and Business Insider.

Chinese ghost cities have made headlines for nearly a decade, with huge new real-estate developments sitting mostly empty for years. 

Some see them as a sign China is heading for a real-estate crash. 

Others see them as just the typical style of urban expansion for a giant state-run economy.
While some ghost cities are reportedly filling in, the problem isn’t going away. 

A recent Baidu study of phone data gave clear evidence of 50 cities with areas of high vacancy. 

And just this fall China's richest man called Chinese real estate "the biggest bubble in history."
We looked inside some ghost cities with the latest in satellite technology, including time-lapse images, to show what’s making progress and what isn’t. 

See the highlights below.
Chenggong District, Kunming, Yunnan Province,  was labeled a ghost city back in 2012, with reports of 100,000 vacant apartments. 

Five years later, the city still looks very empty — yet skyscrapers are still being built.

Chenggong has big plans, evident in an extensive road grid. 

But the roads are still mostly empty, and many city blocks are still farmland.

A closer look at some of Chenggong’s mostly vacant skyscrapers. 

Note the paved road that transitions to dirt as it moves to the left.

Chenggong, like other ambitious Chinese developments, has dramatic architecture — in this case surrounded by farmland.

Chenggong has several big new university campuses. 

This has sat mostly empty and unfinished for a while, according to DigitalGlobe.

Erenhot is a notorious ghost city in Inner Mongolia. 

Check out our time lapse of one development there: just dirt in 2013 …

... streets full of McMansions in 2015 …

... still-empty streets full of McMansions in 2017.

Ordos, another notorious ghost city in Inner Mongolia, is reportedly adding people but still has lots of unsold housing and unfinished construction. 

This beautiful stadium, for instance, has been sitting unfinished for a long time, according to DigitalGlobe.

Another cool building in Ordos sits dormant, no longer under construction and not in use, according to DigitalGlobe.

Dongsheng District (named by Baidu as a partial ghost city), Ordos City, has large developments like this one sitting dormant. 

The skyscrapers are apparently finished, but the construction equipment is gone, so it appears that work has stopped on the site, DigitalGlobe says.

This development in Dongsheng is up and running but appears to have very few residents.

Ghost city or future city? 

The giant Meixi Lake development, Hunan, looks eerie today, with skyscrapers going up by the dozens and not a lot of residents. 

Then again, prices are still rising in the area, and, according to DigitalGlobe, construction is still going rapidly.

Once called a ghost city, Zhengdong New Area, Henan is reportedly doing quite well. 

Still, the city is building new skyscrapers by the dozens.

Another shot of Zhengdong. 

Will people move in? 

Time will tell.

Sina Delenda Est

China installs weapons systems on artificial islands
By David Brunnstrom | WASHINGTON

A satellite image shows what CSIS Asia Maritime Transparency Initiative says appears to be anti-aircraft guns and what are likely to be close-in weapons systems (CIWS) on the artificial island Subi Reef in the South China Sea in this image released on December 13, 2016.

A satellite image shows what CSIS Asia Maritime Transparency Initiative says appears to be anti-aircraft guns and what are likely to be close-in weapons systems (CIWS) on the artificial island Fiery Cross Reef in the South China Sea in this image released on December 13, 2016.

A satellite image shows what CSIS Asia Maritime Transparency Initiative says appears to be anti-aircraft guns and what are likely to be close-in weapons systems (CIWS) on the artificial island Johnson Reef in the South China Sea in this image released on December 13, 2016.

A satellite image shows what CSIS Asia Maritime Transparency Initiative says appears to be anti-aircraft guns and what are likely to be close-in weapons systems (CIWS) on the artificial island Hughes Reef in the South China Sea in this image released on December 13, 2016.

China appears to have installed weapons, including anti-aircraft and anti-missile systems, on all seven of the artificial islands it has built in the South China Sea, a U.S. think tank reported on Wednesday, citing new satellite imagery.
The Asia Maritime Transparency Initiative (AMTI) at the Center for Strategic and International Studies said its findings come despite statements by the Chinese leadership that Beijing has no intention to militarize the islands in the strategic trade route, where territory is claimed by several countries.
AMTI said it had been tracking construction of hexagonal structures on Fiery Cross, Mischief and Subi reefs in the Spratly Islands since June and July. 

China has already built military length airstrips on these islands.
"It now seems that these structures are an evolution of point-defense fortifications already constructed at China’s smaller facilities on Gaven, Hughes, Johnson, and Cuarteron reefs," it said citing images taken in November and made available to Reuters.
"This model has gone through another evolution at (the) much-larger bases on Fiery Cross, Subi and Mischief reefs."
Satellite images of Hughes and Gaven reefs showed what appeared to be anti-aircraft guns and what were likely to be close-in weapons systems (CIWS) to protect against cruise missile strikes, it said.
Images from Fiery Cross Reef showed towers that likely contained targeting radar, it said.
AMTI said covers had been installed on the towers at Fiery Cross, but the size of platforms on these and the covers suggested they concealed defense systems similar to those at the smaller reefs.
"These gun and probable CIWS emplacements show that Beijing is serious about defense of its artificial islands in case of an armed contingency in the South China Sea," it said.
"Among other things, they would be the last line of defense against cruise missiles launched by the United States or others against these soon-to-be-operational air bases."

PHILIPPINES CONCERNED
Philippine Foreign Affairs spokesperson Charles Jose told Reuters they were still verifying the report.
"But if report is true, then it is a cause for serious concern because it tends to raise tension and undermine peace and stability in the region," Jose said.
Vietnam's foreign ministry did not immediately respond to requests for comment.
AMTI director Greg Poling said AMTI had spent months trying to figure out what the purposes of the structures was.
"This is the first time that we're confident in saying they are anti-aircraft and CIWS emplacements. We did not know that they had systems this big and this advanced there," he told Reuters.
"This is militarization. The Chinese can argue that it's only for defensive purposes, but if you are building giant anti-aircraft gun and CIWS emplacements, it means that you are prepping for a future conflict.
"They keep saying they are not militarizing, but they could deploy fighter jets and surface-to-air missiles tomorrow if they wanted to," he said. 

"Now they have all the infrastructure in place for these interlocking rings of defense and power projection."

The report said the installations would likely back up a defensive umbrella provided by a future deployment of mobile surface-to-air missile (SAM) platforms like the HQ-9 system deployed to Woody Island in the Paracel Islands, farther to the north in the South China Sea.
It forecast that such a deployment could happen "at any time," noting a recent Fox News report that components for SAM systems have been spotted at the southeastern Chinese port of Jieyang, possibly destined for the South China Sea.
Singapore-based South China Sea expert Ian Storey said he believed the move would help ready the facilities for the probable next step of China flying jet fighters and military transport planes to its new runways.
“From the outset it’s been quite obvious that the artificial islands were designed to serve as military outposts in the South China Sea,” said Storey, of the ISEAS Yusof Ishak Institute.
“Even while tensions are at a relatively low ebb, I think we can expect to see military flights to the Spratlys in the coming months – including the first jet fighters,” Storey said.
China has said military construction on the islands will be limited to necessary defensive requirements.
The United States has criticized what it called China's militarization of its maritime outposts and stressed the need for freedom of navigation by conducting periodic air and naval patrols near them that have angered Beijing.
U.S. President Donald Trump, who takes office on Jan. 20, has also criticized Chinese behavior in the South China Sea while signaling he may adopt a tougher approach to China's assertive behavior in the region than Barack Obama.
The State Department said it would not comment on intelligence matters, but spokesman John Kirby added: "We consistently call on China as well as other claimants to commit to peacefully managing and resolving disputes, to refrain from further land reclamation and construction of new facilities and the militarization of disputed features."

You Can Strike Oil In China: Four Reasons The Satellite Market Is Taking Off

By Michael Kanellos

China has more oil than people thought.
Orbital Insight, a Palo Alto-based startup hoping to capitalize on the growing interest in mining satellite imagery, undertook an interesting assignment: it captured, and then analyzed, satellite images regarding the world’s 20,000+ oil storage depots to try to determine the real-time supply of oil.
How? 

It focused on the shadows being cast on the inside of the world’s 20,000+ oil storage tanks. 

Oil storage tanks have floating ceilings: a short shadow indicated a well-stocked silo while a long one indicated potential shortages. 

And while doing their shadow analysis, Orbital discovered a funny thing. 

China had 2,000 more coastal tanks than people thought, said Orbital’s Shwetank Kumar at the Center for Effective Global Action in Berkeley, California this week.
The hunt may not be over either: South American nations regularly do not report their oil inventories either, he added.
So what do you need to know?

It’s a Huge Opportunity
The global satellite market is growing at 19.54%, according to some estimates. 

Venture capitalists invested $1.8 billion in space startups in 2015.
But more importantly, a growing raft of companies want to couple their data with imagery. 

I attended the conference to speak about the epidemic of water leakage—over 30% of the water in many areas of the world drips away before it gets to your tap. 

Satellite imagery can be matched with pressure data to pinpoint leaks. 

Farming and health care companies are mining data. 

Even stock traders are getting into the act.
The world takes an estimated 1 trillion images a year: it’s only going to expand.
Hello from Beijing: an image from Orbital insight

It’s Multifaceted
Like other digital imaging markets, there are a number of entry points and companies are carving out areas of specialization. 

Orbital’s stock-in-trade, for instance, revolves around blending satellite data with other streams like commodity prices or poverty index. 

The satellite images aren’t the end goal: they become a source of data for macroeconomic analysis.
Planet, meanwhile, is putting up an armada of Dove CubeSats – or very small, but capable —satellites for capturing images of life on earth. (I wrote about CubeSats back in 2005 when it was a research project so it’s gratifying to see it come to fruition.) 

Planet’s goal is to use “space to help life on earth,” said Planet’s Tara O’Shea. 

The satellites capture images at three to five meters of earth space per pixel. 

That’s fine enough to capture the progress of road building in India or the Amazon and far greater than the 30 meters per pixel resolution of Landsat. 

At the same time, it’s not deep enough to pinpoint faces, license plates or personal information. 

In Palawan, an island in the Philippines, the company is helping map the 50% of roads that wouldn’t ordinarily show up on maps.
To avoid the cost creep that can impact companies developing hardware, Planet tries to develop and launch quickly. 

It has developed 13 different versions of its satellite in 3 years and a new vehicle gets launched every three to four months. 

By contrast, it typically takes three years to launch a conventional satellite.
A Dove Cubesat from Planet.com

It has 70 satellites in orbit today and should have 100 by the end of the year. 

That will give the company the capability to take a new, comprehensive image of the earth every day.
By contrast, you have DigitalGlobe, a publicly-held company that recently bought the Radiant Group for $140 million. 

It specializes in super-high resolution photos. 

A traditional Landsat image might take up half a gigabyte, said Shay Har-Noy. 

An image from Planet might come to 16GB. 

One of DigitalGlobe’s images can weigh in at a hefty 941GB: more data, more insight. 

The company takes on projects like mapping Australia to help map out water and agricultural issues.

It’s Not Just About Hardware
Software is where you will see most of the startup activity, says Ruchit G Garg, a Microsoft alum who has founded Harvesting, which uses satellite imagery to optimize harvests. 

The data will help farmers, but mostly it’s for banks and insurance companies. 

Ideally, better data will lower the barriers to credit, he says. (SlantRange is taking a similar tack with drones.).
Likewise, Facebook is using satellite data as part of its plan to bring Internet access to emerging nations and rural communities. 

1.6 billion people worldwide live outside the reach of mobile networks, said Andreas Gros of the Facebook Connectivity Lab. 

99% of the world, however, lives within 80 kilometers of a city with a population of 10,000 or more. 

The idea is to leverage that as much as possible.
Combining imagery with census data is giving the company greater insight into population density and settlement patterns. 

So far, Facebook has scanned 27 million square kilometers and amassed 500TB of data. 

It can analyze some countries for density in population density eight hours.

It’s Not Just About Space
If there’s one meme that kept getting past around at the event, it was “ground truth,” i.e., information from people on the ground that confirms or expands satellite data.
Prabal Dutta at the University of Michigan is overseeing a project to pinpoint grid outages by using cell phones as sensors. 

73.8% of Kenyans, after all, have cell phones.
Traffic? 

70% of the traffic in Kenya comes from Matatus, or drivers for hire, said UC Berkeley’s David Schonholzer. 

Three million people use this precursor of Uber on a daily basis. 

His department is integrating sensors to monitor drivers—how fast they accelerate, whether the go off-road, how many sudden stops or sharp turns they take—to improve road safety. 

If you tried to analyze grid or road traffic with imagery alone, you’d only get a partial answer.