Climate change is wreaking havoc on the planet. The Earth has warmed by about 1.1 degrees Celsius since the late 1800s, resulting in intensified heat waves, rising sea levels, reduced agricultural yields and more adverse effects.
A main driver of climate change is greenhouse gas emissions, which warm the globe by trapping the sun’s heat. Emissions must reach net zero by 2050 to limit global warming to 1.5 degrees Celsius, as called for in the Paris Agreement. The world is not on track to reach this goal, according to the United Nations, but AI may help.
“In terms of stabilizing the climate, the science tells us unequivocally that the one thing we need to do is rapidly reduce emissions,” says Mathew Barlow, a professor in the Department of Environmental, Earth & Atmospheric Sciences (EEAS). “Where AI can be used to further that goal, for instance, is by allowing us to process and understand large amounts of data more quickly.”
Barlow uses AI for data analysis in his climate research. For example, he and a team of researchers used machine learning to develop a better understanding of heat waves in the Northeast. Their findings can serve as a basis for future research into heat wave predictability, model assessment and climate projections.
“AI can be important for improving our decision-making and the speed and efficiency with which we can reduce emissions,” he says.
Working with Juliette Rooney-Varga, an EEAS professor and the Climate Change Initiative director, environmental studies master’s student Lucia Cheney ’22 uses machine learning to analyze politicians’ tweets on climate change. Instead of going through each tweet individually, AI does the grunt work, allowing Cheney to study the main drivers be-hind the frequency of climate change-related tweets among politicians.
“It’s important to analyze what politicians say, because it affects the public’s view on climate change,” Cheney says.
AI can be used in several other ways when it comes to tackling climate change. It can be trained to measure changes in icebergs and sea levels, predict weather patterns, map deforestation, track greenhouse gas emissions and optimize heating, ventilation and air conditioning in buildings.
While AI can be a part of the solution to mitigating climate change, Barlow warns that it also comes with risks. He fears people may think they do not need to reduce emissions under the false hope that AI will somehow fix the problem in the future. He adds that AI can also be used to transmit false information, fueling skepticism about climate change. Generative AI, like ChatGPT, also requires large amounts of energy, which adds to emissions.
“AI can be a powerful tool in helping—or hindering— our efforts to tackle climate change, and—as with all powerful tools—we need to think carefully about its ethical use,” Barlow says.—BC