The stories on artificial intelligence’s improving ability to predict extreme weather often begin with powerful hurricanes. As Scientific American detailed this year, when Hurricane Lee was moving through the Atlantic Ocean last September, scientists using traditional weather models got a clear idea of where the hurricane would go just six days ahead of its Canadian landfall. Nine days before landfall, an experimental A.I. modeling system called GraphCast predicted that outcome. As William J. Broad recently wrote in the New York Times, when Hurricane Beryl blew through the Caribbean early this July, a European weather agency predicted that the storm would most likely hit Mexico, though other landfalls were possible. On the same day as the European weather agency prediction, A.I. software predicted landfall in Texas, and four days later that is where the hurricane hit.

So A.I. has predicted the correct paths for certain storms earlier than other methods. But before we examine the significance of such accomplishments, it helps to have some history about how more traditional weather forecasting and A.I. work.

For decades we have gotten our forecasts thanks to numerical weather prediction. Satellites, weather stations and buoys collect data—like temperature, humidity and other variables—that is fed into giant supercomputers. The supercomputers generate a grid of cubes representing the Earth’s atmosphere and employ physics to see how the cubes interact with each other. “You can’t just simulate the physics of the atmosphere directly, because the atmosphere is too complex,” says computer scientist and meteorologist Amy McGovern, of the University of Oklahoma. “You’re trying to simulate what’s happening in one little area of it, and then you try to figure out how it’s interacting with the other areas.”

In short, the models are simulations of the atmosphere that use the current weather to predict atmospheric conditions in the future. But these models may need to run on giant supercomputers for hours—making quadrillions of calculations—before they can generate a prediction. Then the predictions go to a meteorologist who refines the forecast for a specific area.

While the American Meteorological Society began promoting and advancing artificial intelligence in the 1980s, its use has really moved forward in the past two decades or so in three main ways. First, for over 20 years, forecasters have done something called post-processing, where they take numerical weather models that are wrong and use A.I. methods to improve the predictions. Secondly, in the last roughly ten years or so, experts developed hybrid models—where bits of A.I. were plugged into numerical weather prediction models to speed them up.

Those methods using A.I. still incorporate physics, but the third big revolution in A.I. that has gained momentum in the last few years uses data-driven models that don’t incorporate physics at all. A.I. models trained on roughly 40 years of freely available weather data use the same collected weather data that is fed into supercomputers and create forecasts. But rather than having to make quadrillions of calculations to come up with a forecast, they simply look for patterns in data. For this reason, A.I. models can run on modest computers, even regular laptops, and spit out forecasts in seconds. And since the runs take hardly any time, A.I. can generate thousands of forecasts in the time it takes a numerical weather model to make one, allowing meteorologists to see a wider range of possible outcomes.

But just how much can meteorologists trust those fast new A.I. forecasts of extreme weather?

McGovern, who leads the NSF A.I. Institute for Research on Trustworthy A.I. in Weather, Climate and Coastal Oceanography (AI2ES) at the University of Oklahoma, is the perfect person to ask. She has been studying A.I. and weather prediction for twenty years.

Growing up, McGovern was inspired by Sally Ride, the first American woman to rocket into space, and wanted to be an astronaut. As she got older, she became interested in earth science—and also in ways to make computers smarter in a way that helped people. She earned her bachelor’s at Carnegie Mellon University and her PhD at the University of Massachusetts Amherst in 2002—both in computer science. When the University of Oklahoma offered her a job to focus on A.I. and weather beginning in 2005, she jumped at the opportunity. Because even though she wanted to leave Earth, she’s always been interested in earth science—and the job would allow her to fulfill her goal of using computers to help people. “Weather is an application where we can actually save lives and save property,” she says. “And I was like, ‘This is a perfect match.’”

To find out what she’s learned in the past two decades about the promise of A.I. to forecast extreme weather, we asked her a few questions.

How will A.I. change or improve forecasting extreme weather events like tornadoes or hailstorms or hurricanes?

The tornadoes and the hailstorms are something I’ve studied a lot of, and I think A.I. is getting used more in the post-processing sense still. Right now, the average warning time on a tornado is 15 minutes. If you could get that warning time up to 30 or 45 minutes [using A.I.] and you could improve the spatial resolution so that there’s a warning zone, but I’m going to make it as narrow as possible so I know that this is exactly where the tornado is coming, I think you can improve saving lives and property. We’ve definitely got some promising results with A.I. that can do that for both tornadoes and hail.

Another one related to that will be convective initiation, which is the start of the thunderstorms. Convective initiation matters for turbulence forecasting for airplanes. They have onboard radar, but it’s not giving them a great view. But if they knew where a storm was about to form, they could avoid flying over an area, and that could help with turbulence.

Hurricanes are a larger-scale event, so they’re a little bit easier to forecast. And these new systems are starting to predict where the hurricanes are going and when they’re going to develop. Those can’t really do tornadoes right now because they’re too small-scale. I think those systems show some promise of being able to give us more days in advance than the current systems.

Are there things A.I. can do right now better than numerical weather prediction can do?

I had two students both working on similar ideas, one on the convective initiation and one on hail. They were ingesting in real time the observations that had happened in the last 30 minutes and then giving you a forecast in about 30 seconds. That’s pretty cool. And it’s something that A.I. can do that numerical weather prediction just isn’t going to be able to do, because we don’t have computers capable of doing that.

Is there a risk that A.I. might miss outlier events related to climate change because it’s learning from events that have already happened?

Apparently, yeah, because it doesn’t have the laws of physics. Everything is changing so much, then it’s going to be hard for it to predict. I mean, how do you predict a flooding event that you’ve never seen? If you have some physics in there, you can at least give yourself some confidence in it. I mean, it’s hard for numerical weather prediction events to predict events they’ve never seen either, but they can.

One of the things I’ve seen you say before is that you want to create A.I. that is trustworthy. Can you explain what you mean by that?

That’s what my NSF A.I. Institute focuses on. You saw our long name, NSF A.I. Institute for Trustworthy A.I. in Weather, Climate and Coastal Oceanography. We focus on understanding what it means to trust an A.I. model and what it means for the forecasters to trust it or distrust it. Many weather situations are life-and-death situations where you’re trying to decide what you’re doing about evacuating or calling a warning or something like that. A trustworthy model is one that you trust to give you proper input for making that decision.

It isn’t one that, in our case, that’s going to replace the humans. It’s providing input to those human forecasters, but they trust what it’s giving them.

And are we there yet with A.I.?

There are some forecasts that are in operation inside NOAA [the National Oceanic and Atmospheric Administration], and so those are clearly trustworthy. Are we there with everything? No.

You mentioned NOAA. Who else is already using A.I. to forecast extreme weather events?

Private industry is using A.I., too. Not all of them are going to tell you about what they’re doing. Some of the smaller companies are just flat-out telling you they’re using A.I., but they don’t tell you much about it. Caveat to all of that, I am advising in a private industry company that’s a startup right now, so I know what they’re doing. I know it’s happening. Not as many people are talking about the inside methods yet.

And the Europeans, are they using A.I.?

They have a model called AIFS, which is the A.I. version of their IFS, Integrated Forecasting System. The AIFS is a model comparable to the Google model and the NVIDIA model and all these others, and I think it’s going to long-term be able to give you some nice hurricane warnings, except for they call them tropical cyclones in Europe. And heat waves.

When people get information from the A.I. models, are they using it in combination with information from the numerical weather models?

Yes. It’s not being used by itself right now.

You’re working with certain institutions and colleges on a certificate for A.I. Can you just tell me a little bit about what that is and what you hope to accomplish with it?

That’s part of AI2ES’s work, which is our NSF A.I. Institute. The certificate is being developed by Del Mar College, a Hispanic-serving, minority-serving college down in South Texas. They’re in Corpus Christi. They’ve prototyped it. They’ve had a bunch of students who’ve already graduated with it. We’re trying to reach a different audience and trying to get A.I. to more people, get more people involved in A.I. By working with a Hispanic-serving, minority-serving institution, we’re reaching a different audience than we get at our typical universities—and trying to help diversify the field of A.I. and A.I. for weather.

And I also read that you’re doing work with K-12 students in A.I.

That’s also being led by Del Mar. They’re amazing. They have an outreach that they do for K-12 students to teach them just about coding in general, and then to teach them some basic A.I. concepts. I went down and saw their camp one year. They’re doing a great job. They’re teaching kids how to fly drones and teaching them how to program the drones, how to program their little robots to run around and do different tasks, and just getting the kids excited about the things they can do with A.I.

Do you think A.I. forecasting will ever replace human meteorologists?

Well, “ever” is a long time to predict. How about the next five to ten years?

All right. That sounds good.

In the next five to ten years, we still need human meteorologists, because we still need that human expertise on top of things. Their physics-based knowledge is still really important. I get asked a lot: Are you developing things to replace the meteorologists? No. We’re developing things to give them more options so that they can focus on turning the forecasts into actionable information for people to make better decisions. Humans are a lot better at that than A.I. is right now.

This interview has been edited for length and clarity.

Full image credit: Illustration by Emily Lankiewicz / ABI imagery from NOAA’s GOES-16 Satellite – AWS S3 Explorer / NASA / Matthew Dominick

In recent years, the Arctic has become a magnet for climate change anxiety, with scientists nervously monitoring the Greenland ice sheet for signs of melting and fretting over rampant environmental degradation. It wasn’t always that way.

At the height of the Cold War in the 1950s, as the fear of nuclear Armageddon hung over American and Soviet citizens, ­idealistic scientists and engineers saw the vast Arctic region as a place of unlimited potential for creating a bold new future. Greenland emerged as the most tantalizing proving ground for their research.

Scientists and engineers working for and with the U.S. military cooked up a rash of audacious cold-region projects—some innovative, many spitballed and most quickly abandoned. They were the stuff of science fiction: disposing of nuclear waste by letting it melt through the ice; moving people, supplies and missiles below the ice using subways, some perhaps atomic-powered; testing hovercraft to zip over impassable crevasses; making furniture from a frozen mix of ice and soil; and even building a nuclear-powered city under the ice sheet.

Today, many of their ideas, and the fever dreams that spawned them, survive only in the yellowed pages and covers of magazines like Real (billed as “the exciting magazine for men”) and dozens of obscure Army technical reports.

---

Karl and Bernhard Philberth, both physicists and ordained priests, thought Greenland’s ice sheet the perfect repository for nuclear waste. Not all the waste—first they’d reprocess spent reactor fuel so that the long-lived nuclides would be recycled. The remaining, mostly short-lived radionuclides would be fused into glass or ceramic and surrounded by a few inches of lead for transport. They imagined several million radioactive medicine balls about 16 inches in diameter scattered over a small area of the ice sheet (about 300 square miles) far from the coast.

Because the balls were so radioactive, and thus warm, they would melt their way into the ice, each with the energy of a bit less than two dozen 100-watt incandescent light bulbs—a reasonable leap from Karl Philberth’s expertise designing heated ice drills that worked by melting their way through glaciers. The hope was that by the time the ice carrying the balls emerged at the coast thousands or tens of thousands of years later, the radioactivity would have decayed away. One of the physicists later reported that the idea was shown to him by God, in a vision.

Of course, the plan had plenty of unknowns and led to heated discussion at scientific meetings when it was presented—what, for example, would happen if the balls got crushed or caught up in flows of meltwater near the base of the ice sheet? And would the radioactive balls warm the ice so much that the ice flowed faster at the base, speeding the balls’ trip to the coast?

Logistical challenges, scientific doubt and politics sunk the project. Producing millions of radioactive glass balls wasn’t yet practical, and the Danes, who at the time controlled Greenland, were never keen on allowing nuclear waste disposal on what they saw as their island. Some skeptics even worried about climate change melting the ice. Nonetheless, the Philberths made visits to the ice sheet and published peer-reviewed scientific papers about their waste dream.

---

Arctic military imagination predates the Cold War. In 1943, that imagination spawned the Kee Bird—a mythical creature. An early description appears in a poem by Aviation Cadet Warren M. Kniskern published in the Army’s weekly magazine for enlisted men, Yank. The bird taunts men across the Arctic with its call: “Kee-Kee-Keerist, but it’s cold!” Its name was widely applied. Best-known was a B-29 bomber named Kee Bird that took off from Alaska with a heading toward the North Pole, but then got badly lost and put down on a frozen Greenland lake in 1947 as it ran out of fuel. An ambitious plan to fly the nearly pristine plane off the ice in the mid-1990s was thwarted by fire. But the Kee Bird lineage was by no means extinct.

In 1959, the Detroit Free Press, under the headline “The Crazy, Mixed-Up Keebird Can’t Fly,” reported that the Army was testing a new over-snow vehicle. This Keebird was not a flying machine but rather a snowmobile/tractor/airplane chimera that would cut travel time across the ice sheet by a factor of ten or more. Unlike similar but utilitarian contraptions of the 1930s, developed in the central plains of North America and Russia and equipped with short skis, boxy bodies and propellors that pushed them along, this new single-propped version was built for sheer speed.

The prototype hit 40 miles per hour at the Army’s testing facility in Houghton, Michigan, thanks to the “almost friction-proof” Teflon coating on its around 25-foot-long skis and a 300-horsepower airplane engine that spun the propellor. The goal was for the machine to hit 70 miles per hour, but after several failed tests, and a few technical publications, it warranted only the one syndicated newspaper article written by Jean Hanmer Pearson, who was a military pilot in World War II before she became a journalist and one of the first women to set foot on the South Pole. The Soviet version, known as an “airsleigh”, was short, stout and armed with weapons for Arctic combat. There’s no record the Army’s Keebird carrying weapons.

In 1964, the Army tested a distant relative of the Keebird in Greenland. The Carabao, which floated over the ground and over water or snow on a cushion of air, was developed by Bell Aerosystems Company and had been previously tested in tropical locales, including southern Florida. It carried two men and 1,000 pounds of cargo, and had a top speed of 100 miles per hour. The air cushion vehicle skimmed over crevasses but was grounded by even moderate winds, an all-too-common occurrence on the ice sheet.

Another problem: The craft went uphill fine, but going downhill was another matter, because it had no brakes. Unsurprisingly, the Carabao—its namesake a Philippine water buffalo—proved to be unsuited for ice travel despite the claim that: “All this is no mere pipe-dream following an overdose of science fiction. The acknowledged experts are thinking hard about the future use of hovercraft in polar travel.” Despite all the hard thinking, hovercraft have yet to catch on and are still rarely used for Arctic travel and research.

---

In 1956, Colliers, a weekly magazine once read by millions of Americans, published an article titled “Subways Under the Icecap.” It was a sensationalized report of Army activities in Greenland and opened with a photograph of an enlisted soldier holding a pick. Behind him, a 250-foot tunnel, mostly excavated by hand and lit only by lanterns, probed the Greenland ice sheet. Colliers included a simple map and a stylistic cut-away showing an imaginary rail line slicing across northwestern Greenland. But the Army’s ice tunnels ended only about a thousand feet from where they started—doomed by the fragility of their icy walls, which crept inward up to several feet each year, closing the tunnels like a healing wound. The subway never happened.

That didn’t stop the Army from proposing Project Iceworm—a top-secret plan that might represent peak weirdness. A network of tunnels would crisscross northern Greenland over an area about the size of Alabama. Hundreds of missiles, topped with nuclear warheads, would roll through the tunnels on trains, pop up at firing points and, if needed, respond to Soviet aggression by many annihilating many Eastern Bloc targets. Greenland was much closer to Europe than North America, allowing a prompt strategic response, and the snow provided cover and blast protection. Iceworm would be a giant under-snow shell game of sorts, which the Army would power using portable nuclear reactors.

Except it wasn’t a game. The Army hired the Spur and Siding Constructors Company of Detroit to scope out and price the rail project. A 1965 report, complete with maps of stations and sidings where trains would sit when not in use, concluded that contractors could build a railroad stretching 22 miles over land and 138 miles inside the ice sheet for a mere $47 million (or roughly $470 million today). The company suggested studying nuclear-powered locomotives because they reduced the risk of heat from diesel engines melting the frozen tunnels. Never mind that no one had ever built a nuclear locomotive or run rails through tunnels crossing constantly shifting crevasses.

But in the end, Iceworm amounted only to a single railcar, 1,300 feet of track and an abandoned military truck on railroad wheels.

---

The split personality of Arctic permafrost frustrated Army engineers. When frozen in the winter, it was stable but difficult to excavate. But in the summer, under the warmth of 24-hour sunshine, the top foot or two of soil melted, creating an impassable quagmire for people and vehicles. When the permafrost under airstrips melted, the pavement buckled, and the resulting potholes could damage landing gear. The military responded by painting Arctic runways white to reflect the constant summer sunshine and keep the underlying permafrost cool—a potentially good idea grounded in physics that was stymied by the fact that the paint reduced the braking ability of planes.

The military engineers, ever optimistic, put a more positive spin on permafrost. Trying to use native materials in the Arctic, where transportation costs were exceptionally high, they made a synthetic version of permafrost that they nicknamed permacrete—a mash-up of the words permafrost and concrete. First, they mixed the optimal amount of water and dry soil. Then, after allowing the mix to freeze solid in molds, they made beams, bricks, tunnel linings and even a chair. But permacrete never caught on as a building material, likely because one warm day was all it would take to turn even the most robust construction project into a puddle of mud.

---

The Army’s most ambitious Arctic dream actually came true. In 1959, engineers began building Camp Century, known by many as the City Under the Ice. A 138-mile ice road led to the camp that was about 100 miles inland from the edge of the ice sheet. Almost a vertical mile of ice separated the camp from the rock and soil below.

Camp Century contained several dozen massive trenches, one more than a thousand feet long, all carved into the ice sheet by giant snowplows and then covered with metal arches and more snow. Inside were heated bunkrooms for several hundred men, a mess hall and a portable nuclear power plant. The first of its kind, the reactor provided unlimited hot showers and plenty of electrical power.

The camp was ephemeral. In less than a decade, flowing ice crushed Century—but not before scientists and engineers drilled the first deep ice core that eventually penetrated the full thickness of Greenland’s ice sheet. In 1966, the last season the Army occupied Camp Century, drillers recovered more than 11 feet of frozen soil from beneath the ice—another first.

Little studied, the Camp Century soil vanished in the early 1990s, but it was rediscovered by Danish scientists in the late 2010s, safely frozen in Copenhagen. Samples revealed that the soil contained abundant plant and insect fossils, unambiguous evidence that large parts of Greenland were free of ice some 400,000 years ago, when the Earth was about the same temperature as today but had almost 30 percent less carbon dioxide in the atmosphere.

In the half century or so since the demise of Camp Century, global warming has begun melting large amounts of Greenland’s ice. The past ten years are the warmest on record, and the ice sheet is shrinking a bit more every year. That’s science, not fiction, and a world away from the heady optimism of the Cold War dreamers who once envisioned a future embedded in ice.

Paul Bierman is a geoscientist who teaches at the University of Vermont. He is the author, most recently, of When the Ice Is Gone: What a Greenland Ice Core Reveals About Earth’s Tumultuous History and Perilous Future, a study of Greenland, the Cold War, and the collection and analysis of the world’s first deep ice core. Bierman’s research in Greenland is supported by the U.S. National Science Foundation.

This article was originally published on Undark. Read the original article.