“It’s been around a long time, actually,” muses Senior Scientist, Dr. Jennifer Francis. “It’s gotten more sophisticated, sure, and a lot of the applications are new. But the concept of artificial intelligence is not.”
Dr. Francis has been working with it for almost two decades, in fact. Although, back when she started working with a research tool called “neural networks,” they were less widely known in climate science and weren’t generally referred to as artificial intelligence.
But recently, AI seems to have come suddenly out of the woodwork, infusing nearly every field of research, analysis, and communication. Climate science is no exception. From mapping thawing Arctic tundra, to tracking atmospheric variation, and even transcribing audio interviews into text for use in this story, AI in varying forms is woven into the framework of how Woodwell Climate creates new knowledge.
AI helps climate scientists track trends and patterns
The umbrella term of artificial intelligence encompasses a diverse set of tools that can be trained to do tasks as diverse as imitating human language (à la ChatGPT), playing chess, categorizing images, solving puzzles, and even restoring damaged ancient texts.
Dr. Francis uses AI to study variations in atmospheric conditions, most recently weather whiplash events— when one stable weather pattern suddenly snaps to a very different one (think months-long drought in the west disrupted by torrential rain). Her particular method is called self-organizing maps which, as the name suggests, automatically generates a matrix of maps showing atmospheric data organized so Dr. Francis can detect these sudden snapping patterns.
“This method is perfect for what we’re looking for because it removes the human biases. We can feed it daily maps of, say, what the jetstream looks like, and then the neural network finds characteristic patterns and tells us exactly which days the atmosphere is similar to each pattern. There are no assumptions,” says Dr. Francis.
This aptitude for pattern recognition is a core function of many types of neural networks. In the Arctic program, AI is used to churn through thousands of satellite images to detect patterns that indicate specific features in the landscape using a technique originally honed for use in the medical industry to read CT scan images.
Data science specialist, Dr. Yili Yang, uses AI models trained to identify features called retrogressive thaw slumps (RTS) in permafrost-rich regions of the Arctic. Thaw slumps form in response to subsiding permafrost and can be indicators of greater thawing on the landscape, but they are hard to identify in images.
“Finding one RTS is like finding a single building in a city,” Dr. Yang says. It’s time consuming, and it really helps if you already know what you’re looking for. Their trained neural network can pick the features out of high-resolution satellite imagery with fairly high accuracy.
Research Assistant Andrew Mullen uses a similar tool to find and map millions of small water bodies across the Arctic. A neural network generated a dataset of these lakes and ponds so that Mullen and other researchers could track seasonal changes in their area.
And there are opportunities to use AI not just for the data creation side of research, but trend analysis as well. Associate Scientist Dr. Anna Liljedahl leads the Permafrost Discovery Gateway project which used neural networks to create a pan-Arctic map of ice wedge polygons—another feature that indicates ice-rich permafrost in the ground below and, if altered over time, could suggest permafrost thaw.
“Our future goals for the Gateway would utilize new AI models to identify trends or patterns or relationships between ice wedge polygons and elevation, soil or climate data,” says Dr. Liljedahl.
How do neural networks work?
The projects above are examples of neural-network-based AI. But how do they actually work?
The comparison to human brains is apt. The networks are composed of interconnected, mathematical components called “neurons.” Also like a brain, the system is a web of billions upon billions of these neurons. Each neuron carries a fragment of information into the next, and the way those neurons are organized determines the kind of tasks the model can be trained to do.
“How AI models are built is based on a really simple structure—but a ton of these really simple structures stacked on top of each other. This makes them complex and highly capable of accomplishing different tasks,” says Mullen.
In order to accomplish these highly specific tasks, the model has to be trained. Training involves feeding the AI input data, and then telling it what the correct output should look like. The process is called supervised learning, and it’s functionally similar to teaching a student by showing it the correct answers to the quiz ahead of time, then testing them, and repeating this cycle over and over until they can reliably ace each test.
In the case of Dr. Yang’s work, the model was trained using input satellite images of the Arctic tundra with known retrogressive thaw slump features. The model outputs possible thaw slumps which are then compared to the RTS labels hand-drawn by Research Assistant Tiffany Windholz. It then assesses the similarity between the prediction and the true slump, and automatically adjusts its billions of neurons to improve the similarity. Do this a thousand times and the internal structure of the AI starts to learn what to look for in an image. Sharp change in elevation? Destroyed vegetation and no pond? Right geometry? That’s a potential thaw slump.
Just as it would be impossible to pull out any single neuron from a human brain and determine its function, the complexity of a neural network makes the internal workings of AI difficult to detail—Mullen calls it a “black box”—but with a large enough training set you can refine the output without ever having to worry about the internal workings of the machine.
Speeding up and scaling up
Despite its reputation in pop culture, and the uncannily human way these algorithms can learn, AI models are not replacing human researchers. In their present form, neural networks aren’t capable of constructing novel ideas from the information they receive—a defining characteristic of human intelligence. The information that comes out of them is limited by the information they were trained on, in both scope and accuracy.
But once a model is trained with enough accurate data, it can perform in seconds a task that might take a human half an hour. Multiply that across a dataset of 10,000 individual images and it can condense months of image processing into a few hours. And that’s where neural networks become crucial for climate research.
“They’re able to do that tedious, somewhat simple work really fast,” Mullen says. “Which allows us to do more science and focus on the bigger picture.”
Dr. Francis adds, “they can also elucidate patterns and connections that humans can’t see by gazing at thousands of maps or images.”
Another superpower of these AI models is their capability for generalization. Train a model to recognize ponds or ice wedges or thaw slumps with enough representative images and you can use it to identify the water bodies across the Arctic—even in places that would be hard to reach for field data collection.
All these qualities dramatically speed up the pace of research, which is critical as the pace of climate change itself accelerates. The faster scientists can analyze and understand changes in our environment, the better we’ll be able to predict, adapt to, and maybe lessen the impacts to come.
‘Never occurred before’: How the Arctic is sizzling Texas
The oppressive heat wave roasting Texas and Mexico is rekindling a scientific debate about the effects that Arctic climate change might have on weather patterns around the world.
Many experts say that rapid warming in the Arctic — where temperatures are rising four times faster than the global average — may cause an increase in these kinds of long-lasting extreme weather events.
Canada’s wildfire season is off to an ‘unprecedented’ start. Here’s what it could mean for the US
Raging wildfires in Canada have already scorched about 15 times the normal burned area for this time of the year: nearly 11 million acres — more than double the size of New Jersey — with more than 2 million acres concentrated in Quebec alone.
Canada’s fire season is only just beginning, and officials there warned this week it would continue to be severe through the summer. If it follows the pattern of a normal year, it will peak in the hotter months of July and August.
But this is anything but a normal year.
How Arctic ice melt raises the risk of far-away wildfires
The thawing of the polar region from climate change helps produce conditions that make distant forests more likely to burn.
As millions of people in New York and other major North American cities choke on acrid smoke, they could point their accusatory fingers farther North than the wildfires ravaging Quebec — all the way to the global Arctic.
Canada’s fire season has barely started and it’s already on track to break records. So far, NOAA has documented more than 2,000 wildfires that have resulted in the forced evacuation of over 100,000 people across Canada. The most recent bout of fires burning in Ontario and Quebec has sent smoke southward into the Eastern U.S., causing record levels of air pollution in New York and warnings against outside activity as far south as Virginia.
Only a little over a month into the wildfire season, fires have already burned 13 times more land area than the 110-year average for this time of year, and they show no sign of stopping, according to Canadian publication The Star. Indigenous communities, some of whom live year-round in remote bush cabins, have been particularly harmed by the blazes.
According to Woodwell Climate Senior Scientist Dr. Jennifer Francis, the phenomenon of winds pushing smoke down to the northeastern U.S. has been linked to rapid Arctic warming caused by climate change.
In the upper atmosphere, a fast wind current called the jet stream flows from west to east in undulating waves, caused by the interaction of air masses with different temperatures and pressures, particularly between the Arctic and temperate latitudes.
As global temperatures have risen, the Arctic has warmed two to four times faster than the average global rate. Dr. Francis stated in an interview in the Boston Globe that the lessening of the temperature differences between the middle latitudes and the Arctic has slowed down the jet stream, which results in a more frequent occurrence of a wavy path.
Another factor contributing to the widespread smoke is an ongoing oceanic heat wave in the North Pacific Ocean. The blob of much-above-normal sea water tends to create a northward bulge in the jet stream, which creates a pattern that sends cooler air down to California and warm air northward into central Canada—resulting in the persistent heat wave there in recent weeks. Farther east, the jet stream then bends southward and brings the wildfire smoke down to the Northeast.
“Big waves in the jet stream tend to hang around a long time, and so the weather that they create is going to be very persistent,” Dr. Francis said. “If you are in the part of the wave in the jet stream that creates heat and drought, then you can expect it to last a long time and raise the risk of wildfire.”
The wildfires are also decimating North American and Canadian boreal forests, the latter of which holds 12 percent of the “world’s land-based carbon reserves,” according to the Audubon Society<./a> And three quarters of Canada’s woodlands and forests are in the boreal zone according to the Canadian government.
“The surface vegetation and the soil can dry out pretty dramatically given the right weather conditions. For this fuel, as we call it in fire science, it often just takes one single ignition source to generate a large wildfire,” said Woodwell Climate Associate Scientist Dr. Brendan Rogers.
As the climate continues to warm, Dr. Rogers said the weather conditions that lead to fuel drying and out-of-control wildfires also increase. This creates a feedback loop. Heat waves caused by greenhouse gas emissions increase the prevalence of wildfires. The fires in turn destroy these natural carbon sinks and, in turn, speed up climate change.
While the ultimate solution to breaking this feedback loop lies in reducing emissions and curbing climate change, Dr. Rogers and other researchers at Woodwell Climate have conducted research into fire suppression strategies that could help prevent large boreal fires from spreading and help keep carbon in the ground.
A study conducted in collaboration with Woodwell and other institutions found that suppressing fires early may be a cost-effective way to carbon mitigation. Woodwell Climate’s efforts also include mapping fires, using geospatial data and models to estimate carbon emissions across large scales, and looking at the interplay between fires and logging.
“Reducing boreal forest fires to near-historic levels and keeping carbon in the ground will require substantial investments. Nevertheless, these funds pale in comparison to the costs countries will face to cope with the growing health consequences exacerbated by worsening air quality and more frequent and intense climate impacts expected if emissions continue to rise unabated. Increased resources, flexibility, and carbon-focused fire management can also ensure wildlife, tourism, jobs, and many other facets of our society can persevere in a warming world,” Dr. Rogers said.
Record pollution and heat herald a season of climate extremes
Scientists have long warned that global warming will increase the chance of severe wildfires like those burning across Canada and heat waves like the one smothering Puerto Rico.
It’s not officially summer yet in the Northern Hemisphere. But the extremes are already here.
Fires are burning across the breadth of Canada, blanketing parts of the eastern United States with choking, orange-gray smoke. Puerto Rico is under a severe heat alert as other parts of the world have been recently. Earth’s oceans have heated up at an alarming rate.
Human-caused climate change is a force behind extremes like these. Though there is no specific research yet attributing this week’s events to global warming, the science is unequivocal that global warming significantly increases the chances of severe wildfires and heat waves like the ones affecting major parts of North America today.
Continue reading on New York Times.
The wildfires in Canada are abnormally early and widespread this year. What’s at play?
In recent years, the word “wildfire” has conjured heartbreaking images that became grimly predictable: California ablaze, from its mighty forests to gracious vineyards and traffic-clogged highways of fleeing people.
It’s different this year, as the East Coast chokes on smoke blown south from abnormally early and widespread wildfires in Canada. Pennsylvania and New Jersey are now facing critical risks of fire danger, and more broadly the Northeast and Midwest also face elevated risks of wildfires, while California is at lower risk thanks to a record-high snow pack from this past winter.
What’s at play, climate scientists said, is an atmosphere increasingly roiled by conditions that can unpredictably shift areas of drought to deluge, as has happened in California, only to sow drought and excessive heat in another.
Continue reading on The Boston Globe.