AI has become a tool in the search for climate solutions
JUANA SUMMERS, HOST:
All sorts of companies and researchers have embraced artificial intelligence, and that includes people working on climate solutions. Julia Simon from NPR's Climate Desk is here to explain how AI is being used to tackle global warming. Hi, Julia.
JULIA SIMON, BYLINE: Hello.
SUMMERS: So Julia, climate change means more wildfires, and I understand that there are some companies and researchers who think AI might be able to help out with that?
SIMON: Yes. One way researchers hope AI can help prevent big wildfires is with something called controlled burns. That's when Native tribes, people from the Forest Service, utilities set controlled fires to remove excess brush vegetation - basically removing fuel for megafires.
SUMMERS: OK. But, of course, if you do not plan out that controlled fire correctly, it seems like something that could spin out of control, right?
SIMON: Exactly. Teams of so-called burn managers, they need lots of data to keep those fires safe. They need to know about the wind, the moisture in the vegetation, how much vegetation. Yolanda Gil is director of strategic AI at the Information Science Institute at USC. To help prevent controlled burns from getting out of control, they're working on an AI-powered tool.
YOLANDA GIL: These are intelligent assistants. It's kind of like Siri, but for burn managers.
SUMMERS: Huh, OK. Intelligent assistants are like Apple's Siri or, I take it, Amazon's Alexa. Help me understand this. What would Siri for burn managers look like?
SIMON: Yeah. Well, Siri uses AI, right? When I ask it a question, it combs through a bunch of data, feeds me back an answer. Gil and their team are making a Siri-like assistant for those people making controlled fires. It works like this.
GIL: The burn manager will say, what model would be good? I want to do a controlled fire in this particular area.
SIMON: The Siri-like system would then figure out the weather patterns for that area, the topography, vegetation and come back and say, here's a potential burn model, a way to make a controlled fire that's safe. Gil says the hope is that by giving AI-powered assistance to more agencies, utilities, they can make lots more safe, controlled burns.
SUMMERS: OK, Julia, tell us about another way that AI can help us in climate solutions.
SIMON: From solar panels to electric vehicles, many climate solutions require minerals. Think lithium, copper, cobalt. The world needs a lot more of these minerals than our current supplies. The question is where to find them. This is where companies and the U.S. government are using AI to help. They're using AI to sift through big data sets to better identify what places across the world have potential for mining these minerals. Because exploring for minerals - it's really expensive. These mining companies are finding that using AI can save a lot of time and money.
SUMMERS: And, Julia, I understand you've brought us one more use of AI to tackle climate change. Tell us about it.
SIMON: I do. It involves methane, this really potent planet-heating pollution. Antoine Halff is chief analyst at Kayrros, a climate analytics firm. He says for years, people knew methane emissions were rising in the atmosphere, but...
ANTOINE HALFF: We had no idea where methane was coming from. We had an understanding of the climate risk. But there was no understanding of the sources and therefore very limited scope for actions.
SIMON: Then they started using AI to interpret all this data. They now track, on a daily basis, where the big leaks and other releases of methane are coming from. They're being - this AI data is used by the U.N. to verify if companies' reports on methane are accurate.
SUMMERS: NPR's Julia Simon. Thank you, Julia.
SIMON: Thank you so much. Transcript provided by NPR, Copyright NPR.