We're Getting A Lot Better at Looking for Habitable Planets

Good news! If recent events inspire you to look for a way off this planet, we just got a lot better at hunting for another habitable space rock. As researchers are finally starting to directly observe the stars we know have planetary systems, it’s now possible to accurately gauge if their planets' orbits are not too far, but not too close to their stellar parent.

In a study published in Astrophysical Journal, Stephen Kane, associate professor of astronomy at San Francisco State University, focused on the red dwarf star Wolf 1061, located only 14 light-years from Earth. He and his researchers have been able to accumulate enough information to determine the star’s precise habitable zone—that is, the area around a star that harbours conditions conducive for life. What’s even more exciting is that the study confirms suspicions that the second planet in the system is found on the inside edge of this region.

“We understand planets only as well as we understand the star,” Stephen Kane told Motherboard over the phone. Wolf 1061 is a faint star of the M dwarf family. That means that—despite its proximity to our solar system—it’s still very hard to observe and get exact details about it. Kane and his team have measured the luminosity and temperature of Wolf 1061 and also determined the detailed orbits of the star’s three planets. With this data, they can say for sure that Wolf 1061c, the system’s second planet from the star, is situated where scientists believe liquid water could exist on the planet’s surface if there was enough atmosphere to sustain it.

Before now, Wolf 1061’s properties were only approximated through stellar modelling, a process in which a star’s type is used to extrapolate additional data.

“Unfortunately, stellar models do not always give an accurate picture of what these small stars are really like and getting direct measurements has been extraordinarily useful for being able to characterized the system and the planets that are in it,” Kane said.

What we don’t know are the conditions of Wolf 1061c’s atmosphere, or if it even has one. Kane expects that could change with the launch and deployment of space-based telescopes like 2018’s James Webb Space Telescope. Because Wolf 1061 is so close, telescopes would have a good chance of producing a distinguishable image of the planet without it being blotted out by its main star.

Does this mean we should we point our generation sleeper ships at Wolf 1061c? Doubtful. What Kane and his team found is a planetary system with wildly changing Milankovitch cycles. The Milankovitch cycle is how much a planet’s movement through space (like it’s tilt or orbit) affects its climate. Kane explains that the gravity of the other planets in the system influence the orbit of Wolf 1061c to such a degree that its climate could drastically transform over the course of centuries, as opposed to Earth's climate, which changes over tens of thousands of years.

Kane believes we still have a lot to study in our own system before we look outside. There’s still the question of what type of planets develop in habitable zones. Are more planets like Earth, with its temperate atmosphere, or like Venus, wrapped in a completely opaque haze that produces a runaway greenhouse effect?

Kane explained that the early history of Earth and Venus were likely very similar and we need to figure out how they ended up two very distinct planets. “They probably had the same composition in their atmosphere. Now they're completely different, so they diverged dramatically from each other at some point in the past.”

Wolf 1061 is just the first observations of what will be a great hunt, the eventual conclusion of which could be finding a second Earth. Next on Kane’s list is the Proxima Centauri planet Proxima b, which is actually the closest exoplanet to Earth at a mere 4.22 light-years away. It will take time, but with everything happening on this world, I’m glad we’re sorting it out.

from We're Getting A Lot Better at Looking for Habitable Planets

Seven Policy Explanations Were Quietly Dropped From Trump Team Website

With less than a week until the inauguration of President-elect Donald Trump, it sometimes feels like what’s going to happen after January 19 is becoming less and less clear.

The billionaire’s ascension has been characterized as a gaslighting of the American electorate due to Trump’s habit of confidently declaring inaccurate statements as fact. (After finally conceding that Barack Obama was in fact born in the US, after falsely implying otherwise for years, Trump wrongly claimed that Hillary Clinton started the rumour. And that’s just one example.)

It doesn’t help that some of the information relating to the Trump administration’s transition plans and policies seems to have disappeared from the internet.

GreatAgain.gov is a website created to inform the American populace about the efforts of the incoming transition team. Originally, the website included 12 policy statements filed under a drop-down menu titled “Making America Great Again.”

“Announcing important policy then erasing it is very problematic"

After a full redesign of the site on December 12, 2016, that menu was nowhere to be found. Only five of the 12 statements were implemented in the new design, and they’re buried on the bottom of the front page. The other seven appeared to be deleted and are no longer accessible.

This is according to Russ Kick, who curates a website devoted to making sure erased government information stays accessible. Kick used the Internet Archive’s Wayback Machine, which archives web pages for posterity, to make his discovery.

The website’s initial 12 different sections went into detail about a battery of Trump’s policies, according to Kick’s blog post and confirmed by the Wayback Machine, a tool to check archived versions of web pages.

Only the details of the defense, energy, healthcare, constitutional rights, and transportation policies survived the deletions, it shows. Pages that outlined details about immigration, Trump’s tax and trade reform plans, education changes, and how he plans to unravel 20,000 regulations from the Obama administration and the Dodd-Frank financial rules, appear to have been deleted.

These are a cross-section of some of the more controversial of Trump’s plans.

Transition team spokesperson Jessica Ditto, when reached by Motherboard for comment on Wednesday, denied that policy pages had been deleted.

“The policy pages are still on GreatAgain.gov. Please correct any misreporting you may have done on this matter,” said Ditto in an email. She did not reply to repeated follow-up emails asking her to clarify her statement.

All seven deleted policy pages are screenshotted and saved on Kick’s blog.

Read More: Here’s 520 Hours of Trump Interviews So You Can Fact-Check the President

The Memory Hole 2, which was relaunched in June 2016 after being hacked and shut down in 2009, is named for one of the censorship mechanisms in George Orwell’s dystopian novel Nineteen Eighty-Four. The memory hole was a chute that led to an incinerator, where embarrassing and troublesome documents were disposed of.

Kick’s blog keeps track of those sorts of documents from the various levels of the US government. In the blog’s original run, Kick chronicled the removed web documents of the George W. Bush administration.

“Announcing important policy then erasing it is very problematic, in a totally different league than deleting a tweet about [Vice President-elect Mike] Pence getting lectured at Hamilton,” Kick told Motherboard over email.

The Memory Hole 2 isn’t the only place tracking Trump’s online deletions. Politwoops, for example, tracks deleted tweets from elected officials, including Trump. Scientists are working furiously to archive research that could be removed from the web under his administration, as Motherboard’s Jason Koebler previously reported.

The incoming president’s penchant for deleting information has been highlighted before. In November, he was criticized for taking down the plans to ban Muslims from immigrating to the US. That info was restored after public outcry.

Get six of our favorite Motherboard stories every day by signing up for our newsletter.

from Seven Policy Explanations Were Quietly Dropped From Trump Team Website

Bacteria Use Electrical Zaps to Recruit Others to Their Slime Colonies

Image: lmnop88a/Flickr

Bacterial colonies have the ability to communicate with each other over relatively long distances via a series of electrical zaps—and can actually use these signals to recruit other bugs to their massive slime “cities,” San Diego researchers say.

Figuring out how these tiny creatures exchange information could be key in understanding our own microbiomes, and give us new ways to deal with the impending antibiotic resistance crisis. Beyond that, it’s another interesting window into bacterial life.

In a similar fashion to neurons, colonies called “biofilms” use potassium ion channels to regulate social interactions between bacteria in these massive groupings, and those nearby. This includes resolving conflicts, as this same team of researchers has previously shown.

Biofilms form when microorganisms collect on a surface, like a scummy rock or the bathtub you keep meaning to clean. They can be gatherings of one or more species of bacteria or other microbes, and are generally referred to even by researchers by their colloquial name: slime.

Video: Suel Lab @ UCSD/Youtube

“They live in dense cities just like we do,” Gürol Süel, Associate Director of the San Diego Center for Systems Biology, and lead author of the new paper, published Thursday in Cell, told Motherboard during a telephone interview. “The environment is basically other bacteria and they're very densely packed in these biofilms.”

Read More: I Skipped Showering for Two Weeks and Bathed in Bacteria Instead

Süel’s previous work was to determine how these collections of creatures—which can have populations numbering in the millions—cooperate to collect food and make sure that creatures on the inside of the biofilm don’t end up starving, if the guys at the edge eat up all the nutrients available.

The paper describes a newly discovered mechanism where bacteria use the same communication channels to reach out and tell free-floating organisms that there’s safe haven where they can live and eat nearby.

What makes it even more striking is it doesn’t matter what kind of bacteria is on the receiving end of the message. “We show that this recruitment is not species-specific, but it's species independent in the sense that it works also for very different species,” said Süel.

Electrical messages sent by biofilms (in green, at left) recruit new members (in red, at right) to the microbial community. Image: Suel Lab/UC San Diego

Many biologists now theorize that the three pounds of gut bacteria that live inside of us play a huge part in a number of bodily functions—including our mental faculties. Imagine if this new discovery could be used as an interface for us to control our internal ecosystems, a possibility raised by Süel and others.

“In the future it might be possible to sort of use some kind of electrical-based biomedical approach to control the behavior of bacterial communities that might be relevant for human health,” said Süel.

This results could also open up new fronts in the war against antibiotic resistance, as biofilms are very difficult to kill.

“Just discovering that these bacteria can communicate electrically to coordinate not only their behavior within biofilm,” said Süel. “But now we're showing it also affects the behavior of bacteria at a distance. What else can it do?”

Get six of our favorite Motherboard stories every day by signing up for our newsletter.

from Bacteria Use Electrical Zaps to Recruit Others to Their Slime Colonies

This Ice Cream Cone Shaped Creature Finally Has a Home on the Tree of Life

Soft tissues. Image: Royal Ontario Museum

A 20-year-old University of Toronto undergraduate student didn’t expect to get the chance to solve a paleontological mystery this early in his career, yet his name is on a new paper describing where an ancient cone-shaped, not-quite-but-sorta-mollusc-like creature fits into the phylogenetic tree of life—the classification system that connects every plant and animal that has existed on Earth.

If you live in an area that was once underwater, it’s not hard to find the fossils of hyoliths. These long-extinct invertebrates sported a distinct conical shell, giving them the appearance of an inverted ice cream cone. They were some of the first creatures known to form mineralized external skeletons, too.

Joseph Moysiuk showing matching halves a fossil slab while in Kootenay National Park on a Royal Ontario Museum field expedition in 2014. Image: Joseph Moysiuk

They were very common during the Cambrian period, about 540 million years ago, when they first appear on the fossil record. Long thought to be related to squids and snails, it was hard for paleontologists to figure out where these small sea-creatures fit on the tree of life, exactly, because there’s nothing like hyoliths alive today. That correct classification is what paleontology student Joe Moysiuk has published in Nature, along with his co-authors.

“Hyoliths went extinct millions of years before the first dinosaurs appeared. It can be tough to get one’s head around the age of these fossils,” Moysiuk told Motherboard over email.

Read More: This 22-Year-Old Found Four New Planets, Including a ‘Warm Neptune’

The break came when they analysed a specimen from the Burgess Shale in the Rocky Mountains of British Columbia. The fieldwork team, led by study co-author Jean-Bernard Caron, senior curator of invertebrate palaeontology at the Royal Ontario Museum, was able to investigate fossils with soft-tissue still visible. After looking at over 1500 samples, the answer came from the way that the creatures fed themselves. The hyolith “feeding structure,” Moysiuk explained, displays a “row of flexible tentacles extending away from the mouth,” which it probably used to sweep food into its mouth.

This illustration shows the hyolith Haplophrentis extending the tentacles of its feeding organ (lophophore) from between its shells. The paired spines, or ‘helens’, are rotated downwards to prop the animal up off the ocean floor. Image: Danielle Dufault

Those features identified hyoliths as a kind of brachiopod, or shellfish with symmetrical shells. Brachiopods have valves above and below their shells to open and close for feeding or protection. This makes them similar to, but still distinct from, molluscs. Molluscs have valves on the left and right of their bodies.

“Only one group of living animals has a comparable feeding structure (called a lophophore) enclosed by a pair of shells,” said Moysiuk.

The program that catapulted Moysiuk into his own research paper is known as the Research Opportunity Program at the University of Toronto. Started in 2000, it was a way for second-year undergraduate students to make connections with the research community at the school. It lets students get a feel for what it’s like to work with faculty members and get their hands dirty in research projects.

“While not all of them get the opportunity to publish in a prestigious journal like Nature, many students in the program say the experience is transformative for them,” said Pamela Klassen, vice-dean of undergraduate education in the Faculty of Arts & Science.

With our newfound understanding of where these invertebrates sit phylogenetically, we can put to rest a mystery that has stumped researchers, and connect hyoliths to some of the most plentiful creatures that inhabited ancient oceans. Though brachiopods are way less abundant today, they were key filter-feeders and reef builders in the Paleozoic Era.

“Our findings allow us to finally place a sizeable branch in the tree of life and add to our understanding of the earliest evolution of brachiopods, which went on to become a diverse group of animals,” said Moysiuk.

Get six of our favorite Motherboard stories every day by signing up for our newsletter.

from This Ice Cream Cone Shaped Creature Finally Has a Home on the Tree of Life

Geoengineering Schemes Could Block View of the Night Sky, Astronomers Warn

Beyond just reducing our carbon emissions, some people have suggested that to combat climate change, we could pump small particles into the atmosphere to reflect more sunlight away from Earth, thereby cooling the planet. But this could seriously mess with humanity’s ability to see the stars, astronomers warned on Wednesday at the 229th American Astronomical Society Meeting in Grapevine, Texas.

They were on a panel discussing some of the possible benefits and drawbacks of geoengineering—schemes to modify the Earth’s climate system on a massive scale.

This year’s AAS meeting, which runs through this week, is hosting about 2,400 scientists. Between presentations on black holes and alien planets, a panel that included astrobiologist David Grinspoon and Mel Ulmer, director of astrophysics at Northwestern University, discussed the potential planet-wide climate project.

Motherboard caught the chat as it was being livestreamed on Facebook.

There are many ideas floating around about how we could deliberately tinker with Earth’s climate, from launching big reflective mirrors into space, to creating algae blooms to photosynthesize the excess CO2. One of the most prominent ideas is to release gases like sulfur dioxide into the stratosphere—the outer edge of the earth’s atmosphere—to increase albedo. This would reflect more of the sun’s energy back into space. (The same mechanism causes worldwide cooling after major volcanic eruptions.)

The panelists’ discussion showed that scientists are taking these ideas seriously. And they agreed there may be some potential to use them in the short–term to protect our overheating world.

Read More: We Can’t Count on Geoengineering to Save Us From Climate Change, Scientists Warn

The question that hit closest to home was inspired by a recent poster from Charlie Zender, professor of Earth System Science at the University of California, Irvine. Zender predicts that humanity’s ability to see the stars from the ground would be immediately impaired by any plans to increase the albedo of the atmosphere.

According to him, urban skies could get as much as 25 percent brighter, making it harder to see the stars. That’s a problem for astronomers, but not only them: animals like bats and turtles are already being negatively affected by our current levels of light pollution, which is thought to be bad for human health, too, as Zender notes.

But panelists said the small cost of fewer stars twinkling in the night sky wouldn’t necessarily be a deal breaker if such schemes could actually save the planet. “Fixing global warming is more important than astronomy,” said Grinspoon.

Beyond all the unanswered questions about geoengineering—not to mention how technologically far-out many of these ideas still are—such solutions are still only theoretical stop gaps to the larger issue of ceasing CO2 emissions, panelists recognized.

“If we’re going to do this,” said panelist Tom Ackerman, Professor of Atmospheric Sciences at the University of Washington, “we’re going to have an argument about what planet do we want to have, and who gets to decide.”

Get six of our favorite Motherboard stories every day by signing up for our newsletter.

from Geoengineering Schemes Could Block View of the Night Sky, Astronomers Warn

How Pipelines Carrying Bitumen From The Oilsands Could Threaten Sea Life

In 2017, construction is set to begin on Kinder Morgan’s Trans Mountain pipeline expansion, which will carry bitumen from the Alberta oilsands to the BC coast. It’s shaping up to be a big year for pipeline projects, with fossil fuel-friendly Donald Trump coming into the White House (he’s said he’d like to revive Keystone XL) and two projects, including Kinder Morgan, going ahead in Canada after receiving Prime Minister Justin Trudeau’s recent approval.

The potential impact of this type of extraction on coastal environments is sorely understudied. Although plenty of research has been done on the impacts of conventional oil spills in coastal environments, the effects of bitumen carried from the oilsands are virtually unknown, according to a new study in the journal Frontiers in Ecology and the Environment.

”Why is there so little research on the biological effects of bitumen?”

“When we look at [impacts] that are really specific to this particular industry—the oil sands—we know virtually nothing,” said lead author Stephanie Green, a postdoctoral fellow at Stanford University’s Center for Ocean Solutions, in a phone interview.

The oilsands are typically thought of as an “inland industry,” she continued, but there are potentially serious “unrealized impacts for the oceans.” And with pipelines carrying this stuff directly through coastal environments, we shouldn't ignore them.

Bitumen is a mined slurry of crude oil, sand, and clay, but also includes diluting materials to make it flow efficiently through pipelines. Scientists don’t know a whole lot about the impact of these dilutents, partly because manufacturers aren’t required to fully report their chemical makeup, according to the researchers.

“This is something that we're trying to get a handle on,” Green said. ”Why is there so little research on the biological effects of bitumen?”

Read More: The United States of Climate Change Denial

This study was a synthesis of more than 9,000 papers that have examined the consequences of oil sands development. It found that, while individual problems like ocean acidification or the impact on wildlife were taken into account, the cumulative effects of more than one of these issues occurring at once haven’t been examined in any detail.

Green found 15 potential stressors that could arise during the movement of bitumen to the coast

Green found 15 potential stressors that could arise during the movement of bitumen to the West Coast and beyond, from the impacts of higher amounts of sea traffic, to the possible movement of non-native species along the proposed pipeline route.

“Biologists are particularly worried about the amount of noise pollution in the water that really disrupts things like feeding and the production and behavior of a whole range of marine species,” said Green. For example, scientists and conservationists have expressed worry that the Kinder Morgan pipeline could drive an endangered population of orcas off the BC coast to extinction.

Trudeau and his current US counterpart, Barack Obama, seem to acknowledge that continued resource extraction will put marine environments under threat. The two recently announced partial bans on drilling for oil in the Arctic, and Trudeau’s government unveiled a marine protection plan earlier this year. Even so, Trudeau has said he’s ready to play ball with Trump on Keystone XL.

Green thinks that more research on the impacts of oilsands development on marine environments is critical—before development plans are made. “Ideally you would have a good understanding of risks to weigh into your decision-making process,” she said.

Get six of our favorite Motherboard stories every day by signing up for our newsletter.

from How Pipelines Carrying Bitumen From The Oilsands Could Threaten Sea Life

Controversial Keystone XL Pipeline Comes Back to Life With News of Trump Win

News of Donald Trump’s win on Tuesday night brought plenty of reactions—from elation to despair—but for TransCanada, a Calgary-based pipeline builder, it was a signal to get moving. Under President Barack Obama, the majorly controversial Keystone XL pipeline project, which would will carry up to 830,000 barrels of crude oil per day, was killed.

But Trump has indicated he might bring it back to life, as long as he gets a “better deal” and more profit for the US as a result. TransCanada has said it’s still committed to the project, and plans to engage with the President-elect.

A former US Department of Energy staffer told the CBC that the Keystone XL pipeline, representing the northern connection of Alberta’s tar sands moving crude oil to the refineries along the Texas gulf coast, could be approved within days of Trump’s inauguration.

Keystone XL protest at the White House in 2011. Image: tarsandsaction/Flickr

A number of Canadians would welcome Keystone XL’s approval, as it would bolster a flagging Albertan economy. When the deal died in 2015, Prime Minister Justin Trudeau called himself “disappointed,” and Conservatives are saying they’ll push him to get it going now that they've got a possible ally on this project in Washington.

On Twitter, Canada’s former Conservative PM, Stephen Harper, issued a call to get moving on the pipeline and a congratulations to Trump.

Congratulations to Donald Trump on his impressive victory. Canada/US partnership is strong. There is much to do, incl moving ahead with KXL.
— Stephen Harper (@stephenharper) November 9, 2016

TransCanada fought a seven-year battle with the Obama administration to get the project built, and came up against strong environmental opposition, which culminated in a presidential veto in November 2015. Opponents in the US have attention to the impact the pipeline would have on an aquifer that fed major urban centres, threats to indigenous sites, and even the route it takes through a newly active seismic zone. (The proposed route was moved several times as a result of protesters’ efforts.)

Read More: How We Plan to Cover the Environment In a Trump Presidency

Canadian critics, meanwhile, cite a lack of economic benefit to the country, and the support it would give one of the dirtiest sources of energy in North America—the oil sands.

The new President-elect, who has previously stated that climate change is a hoax perpetuated by the Chinese and has been extremely critical of regulations in place to protect the environment, doesn’t seem to have such qualms.

Although Trudeau has yet to comment on what he’ll do about Keystone XL with Trump in the White House, his track record so far indicates he might be amenable to its development. The Pacific NorthWest LNG project was approved earlier this year despite harsh criticism from environmentalists and indigenous groups, and the Kinder Morgan’s TransMountain pipeline just took a step closer after a key condition was met.

Both projects are on Canada's Pacific coast, which has been reeling from environmental accidents, although Trudeau just pledged $1.5 billion over five years for marine protection in the area.

It’s still impossible to say exactly what will happen with Keystone XL, or any other pipeline. Trump has said that ultimately, he would prefer to drill oil from American sources.

Get six of our favorite Motherboard stories every day by signing up for our newsletter.

from Controversial Keystone XL Pipeline Comes Back to Life With News of Trump Win

Tesla’s Clever Plan To Push Self-Driving Cars Into the Mainstream

All new Tesla drivers are being signed up for one big beta test of autonomous cars. On Wednesday, the automaker announced that every vehicle it produces will come equipped with self-driving technology. Many believe that self-driving cars are still a long way off, and that they need to be implemented with caution—especially after a fatal autonomous vehicle accident involving a Tesla this summer.

But the beauty here is that Tesla's self-driving technology won’t be deployed before it’s ready, and instead will be tested and improved with human drivers.

The computer will run in “shadow mode,” which means the Tesla will track every decision or action taken by the driver, and compare it to what the computer would have done in the same situation. In this way, the computer will learn safe driving habits from the human behind the wheel, who’ll act sort of like a driving instructor.

With enough of this practice, Musk thinks the system can go from being twice as good as the average human driver, to ten times as safe.

Video: Tesla

The next Tesla drivers will actually be losing some features that they’ve had with current iterations of autopilot: the lane-changing and car-spacing abilities will disappear for a time. The company aims to upgrade its autopilot to become a level 5 autonomous driving system, which means that no input is required from the human in the vehicle to get from place A to place B. It’s still being debated exactly what a true level 5 system entails, but Google says that a level 5 system makes the steering wheel and pedals obsolete.

Read More: The Head of CMU's Robotics Lab Says Self-Driving Cars Are ‘Not Even Close’

Tesla’s technology uses an array of sensors throughout the car’s body that will give it a 360-degree view. The car’s new eyes include eight high-definition video cameras, 12 ultrasonic detectors, and a radar system that will not impact its shape or external design. An Nvidia GPU that makes trillions of calculations a second will be the brains of the operation.

Musk announced that, in 2017, the technology will be used to drive someone cross-country—from downtown Los Angeles to New York City—without even needing the human to charge the vehicle.

Charging prototype finding its way to Model S. Video: Tesla/YouTube

Fully autonomous, self-driving cars might still be a long way off. Jalopnik rightly points out that the video published to demo the new technology takes place in the perfect driving environment, and not the messy reality in which most of us live.

But Musk’s move to lay the groundwork for the future of driving will put Tesla ahead. The point of these new features is not to have self driving cars today, but implement the machine learning that will bring safer autonomous vehicles.

Collecting driving data through advanced sensors is a critical step towards the use of tech by the masses.

Get six of our favorite Motherboard stories every day by signing up for our newsletter.

from Tesla’s Clever Plan To Push Self-Driving Cars Into the Mainstream

Watson Made a Movie Trailer, Paving the Way for Police-Worn Body Cameras

Morgan is a horror movie about an artificial child that quickly runs out of control and causes much death and destruction. With that outcome, producers at Fox nonetheless thought it might be a good idea to get a real artificial intelligence involved in preparing it for release (the movie came out on Friday). So they asked a research team at IBM to leverage their multitasking AI, Watson, to pick the scenes for a movie trailer.

Watson did so with gusto, astounding even the developers of the learning software. This could open doors to other uses of video processing, and take the work out of sorting through large amounts of video data, including what’s generated by police-worn body cameras.

As for the trailer, “this was very much an experimental investigation. We didn't know a priori how this was going to turn out,” said John Smith, lead of the IBM research team in Yorktown Heights, New York, in phone call. “It was the first time we went into a very specific genre, like horror. In the end, it was quite surprising and we were very pleased with what we learned from this.”

Morgan. IBM Creates First Movie Trailer By AI. Video: 20th Century Fox/YouTube

The team used systems that they had already developed, known as the visual recognition services part of the IBM Watson Developer Cloud, which allows companies tap into the abilities of this particular AI. Watson already understood how to process video footage, and can interpret emotional content. All the team needed to do was teach Watson about the horror genre, specifically.

After feeding the AI roughly 100 horror movies from various eras (including the 1976 classic The Omen), it didn’t take much for the software to begin picking out patterns.

Read More: Yahoo! Made an AI That Automatically Turns Videos Into Fire GIFs

“The approach that we took here was very much machine learning, deep learning statistical analysis,” said Smith. The AI was trained on a series of inputs (horror movies) to learn to recognize features. Watson could then label emotions that were present in a scene, without human intervention.

The AI can successfully tell what’s in a scene because emotions can be quantified in two dimensions: arousal and valence. Each emotion falls on a Cartesian plane where valence is measured as negative or positive. The second axis, arousal, is the level of agitation: Is the emotion soothing or exciting?

“For example, ‘joy’ can be considered high arousal and high valence, ‘sad’ is low arousal and low valence, ‘fear’ his high arousal and low valence,” Smith elaborated in a follow-up email. “When applied to a new movie, the computer sees patterns in this arousal vs. valence space along with the extracted visual object and place categories, which allows it to pick the statistically dominant scenes.”

The statistical and graphical analysis the system ran on the Morgan film. Image: IBM

Researchers initially tried to get Watson to recognize tropes of the genre: classic scenes of a mysterious figure hiding from the character who’s on the phone, for example, or the car that won’t start. But what the AI picked up on was emotional content, like fear and tenderness.

“When we looked at the patterns of those emotional-type signals in trailers,” said Smith, “we could actually see that they were dominating.”

They ran the entirety of Morgan through this processing. Watson chose ten scenes to send to the human editor, who eventually cut the trailer together.

“In the end, [the editor] used nine out of the ten [clips] and did some very nice work.” The editor fine-tuned the boundaries of the clip, inserted transitions and added the music score, according to Smith. “So, that was a completely human process,” he said.

This research takes us further down the road to autonomous vehicles understanding their surroundings, or possibly allowing for detailed analysis of an athlete’s ability.

With advances in video processing, the tech is also applicable to large collections of video footage, like police-worn body cameras. A current problem with the use of these cameras is the gargantuan task of sorting through hours of mundane video. When I brought up that connection, Smith told me that IBM is in the midst of working on a solution to that problem, too.

“A lot of the same components and tools that we used here for Morgan, we’re also applying to body-worn cameras for law enforcement. It’s a big area, 12 million police officers worldwide, and many of them will be wearing body-worn cameras. That’s a huge amount of video, so we’re already going down that path,” he said.

from Watson Made a Movie Trailer, Paving the Way for Police-Worn Body Cameras