Seeing a chance to help the cause, some of the biggest names in AI and machine learning—a discipline within the field—recently published a paper called “Tackling Climate Change with Machine Learning.” The paper, which was discussed at a workshop during a major AI conference in June, was a “call to arms” to bring researchers together, said David Rolnick, a University of Pennsylvania postdoctoral fellow and one of the authors.
“It's surprising how many problems machine learning can meaningfully contribute to,” says Rolnick, who also helped organize the June workshop.
The paper offers up 13 areas where machine learning can be deployed, including energy production, CO2 removal, education, solar geoengineering, and finance. Within these fields, the possibilities include more energy-efficient buildings, creating new low-carbon materials, better monitoring of deforestation, and greener transportation. However, despite the potential, Rolnick points out that this is early days and AI can’t solve everything.
“AI is not a silver bullet,” he says.
And though it might not be a perfect solution, it is bringing new insights into the problem. Here are three ways machine learning can help combat climate change.
Better climate predictions
This push builds on the work already done by climate informatics, a discipline created in 2011 that sits at the intersection of data science and climate science. Climate informatics covers a range of topics: from improving prediction of extreme events such as hurricanes, paleoclimatology, like reconstructing past climate conditions using data collected from things like ice cores, climate downscaling, or using large-scale models to predict weather on a hyper-local level, and the socio-economic impacts of weather and climate.
AI can also unlock new insights from the massive amounts of complex climate simulations generated by the field of climate modeling, which has come a long way since the first system was created at Princeton in the 1960s. Of the dozens of models that have since come into existence, all represent atmosphere, oceans, land, cryosphere, or ice. But, even with agreement on basic scientific assumptions, Claire Monteleoni, a computer science professor at the University of Colorado, Boulder and a co-founder of climate informatics, points out that while the models generally agree in the short term, differences emerge when it comes to long-term forecasts.
“There’s a lot of uncertainty,” Monteleoni said. “They don't even agree on how precipitation will change in the future.”
One project Monteleoni worked on uses machine learning algorithms to combine the predictions of the approximately 30 climate models used by the Intergovernmental Panel on Climate Change. Better predictions can help officials make informed climate policy, allow governments to prepare for change, and potentially uncover areas that could reverse some effects of climate change.
Showing the effects of extreme weather
Some homeowners have already experienced the effects of a changing environment. For others, it might seem less tangible. To make it more realistic for more people, researchers from Montreal Institute for Learning Algorithms (MILA), Microsoft, and ConscientAI Labs used GANs, a type of AI, to simulate what homes are likely to look like after being damaged by rising sea levels and more intense storms.
“Our goal is not to convince people climate change is real, it’s to get people who do believe it is real to do more about that,” said Victor Schmidt, a co-author of the paper and Ph.D. candidate at MILA.
So far, MILA researchers have met with Montreal city officials and NGOs eager to use the tool. Future plans include releasing an app to show individuals what their neighborhoods and homes might look like in the future with different climate change outcomes. But the app will need more data, and Schmidt said they eventually want to let people upload photos of floods and forest fires to improve the algorithm.
“We want to empower these communities to help,” he said.
Measuring where carbon is coming from
Carbon Tracker is an independent financial think-tank working toward the UN goal of preventing new coal plants from being built by 2020. By monitoring coal plant emissions with satellite imagery, Carbon Tracker can use the data it gathers to convince the finance industry that carbon plants aren't profitable.
A grant from Google is expanding the nonprofit’s satellite imagery efforts to include gas-powered plants’ emissions and get a better sense of where air pollution is coming from. While there are continuous monitoring systems near power plants that can measure CO2 emissions more directly, they do not have global reach.
“This can be used worldwide in places that aren’t monitoring,” said Durand D’souza, a data scientist at Carbon Tracker. “And we don’t have to ask permission.”
AI can automate the analysis of images of power plants to get regular updates on emissions. It also introduces new ways to measure a plant’s impact, by crunching numbers of nearby infrastructure and electricity use. That’s handy for gas-powered plants that don’t have the easy-to-measure plumes that coal-powered plants have.
Carbon Tracker will now crunch emissions for 4,000 to 5,000 power plants, getting much more information than currently available, and make it public. In the future, if a carbon tax passes, remote sensing Carbon Tracker’s could help put a price on emissions and pinpoint those responsible for it.
“Machine learning is going to help a lot in this field,” D’souza said.