“Experts Say ,Using AI, ML Will Help the Government Tackle Climate Change”
The editors of the Advanced Technology Academic Research Center of Jan. 26 webinar “Leveraging Predictive Analytics to Deal with the Problems of Climate Change” discussed how the use of machine learning and technology can provide short-term and long-term guidance to decision-makers who consider how to make impacts better.
According to the National Centers for Environmental Information, which is part of the National Oceanic and Atmospheric Administration, by 2021 there were 20 weather and climate disasters that caused more than $ 1 billion in losses each. From 1980 to 2021, the annual average was 7.4 events (adjusted for inflation), but from 2017 to 2021, the last five years, the number of events was 17.2 (adjusted for inflation).
In short, the problem is getting worse, and faster.
“One thing has changed over the last 20 years,” said Ed Kearns, Chief Data Officer of First Street Foundation, a nonprofit organization that has been monitoring the effects of major floods across the United States. “The change in conversation comes from ‘Is climate change happening? How do we know?’ It now shifts to ‘How will we cope?'”
Chhakib Chraibi, Chief Scientist, National Technical Information Service, said the Paris Climate Accords may aim to reduce global warming to below 2 degrees Celsius by 2050, but current estimates say temperatures will exceed the target by 2030, which will not stop. a lot of time to slow down.
“Another factor affecting climate change is our use of energy,” says Craibi. “Energy is a major source of economic growth [and] energy consumption has been steadily improving.”
For example, he said, “Scientists [discovered] in August 2021 that we used 100% of the world’s renewable resources … We now live in shortages.”
Craibi said about ML modeling for climate change and its effects depends on a large amount of data, but it should be done at a granular level, not at the regional or national level.
Combining environmental data with economic and social data could help identify some of the most vulnerable communities to natural disasters, Kearns said. “In your heart, those data policies [requiring the government to share its data] give us the opportunity to fight to understand what we need to do, as a nation and as local communities.” He said his organization was working on detailed flood risks, “door-to-door, business by business,” which could be put together to make more comprehensive policy decisions.
“I believe as a scientist that AI is the game changer,” Craibi said. “We are not following clear rules [in our models], we are trying to build a system that imposes rules … Some studies have shown that the use of AI can achieve a 5-10% reduction in CO2 emissions. “In strength, many studies include AI because it allows you to use data to better predict.”
Kearns said about ML that he is considering using machine learning and AI to fill in data spaces to link the connection between CO2 and rain, for example. Then we “try to bond you with dollars and cents,” he said, because politicians and policymakers respond better to a standard they understand.
“One of the best things I’ve ever seen in the last two years is a change of mindset, especially at the level of a cohesive government,” Kearns said. “At the level of state policy climate change has been considered a kind of scientific project, [a] NOAA, NASA, [U.S. Geological Survey problem], but this administration leads the Treasury … They need [climate information] translated into things like jobs, financial laws, and that is starting to happen now. ”
Craibi said the use of AI was limited so far, focusing on a specific area of climate risk. “We need models that can learn from a variety of broadcasts and translate [findings] … machine learning models that are logical models,” providing answers with almost levels of uncertainty. “This is something we have to learn to work with, because that is part of the model. What can we do to reduce [or] reduce uncertainty? ”
Kearns agreed about ML”One of the sacred sciences is how to convey uncertainty … If I get 95% certainty in my analysis, as a scientist bet the house on that, [but] when I say that to a conference member or journalist, they say, ‘So you’re not sure.’ uncertainty ‘but meaning is lost. That’s why bringing in dollars and cents or other ”sensible steps is important, to change something that the public can understand.
