After spending nearly a decade working in computer science and artificial intelligence (AI), Sasha Luccioni was ready to uproot her entire life three years ago after she became deeply concerned about the climate crisis.
But her partner convinced her not to give up on her career entirely, but to apply her AI knowledge to some of the challenges posed by climate change.
“You don’t have to quit your job in AI to help fight the climate crisis,” he said. “There are ways that almost any AI technique can be applied to different parts of climate change.”
He joined the Montreal-based AI research center Mila and became a founding member of Climate Change AI, an organization of volunteer academics advocating the use of AI to solve problems related to the climate change.
- Have a question about climate change and what’s being done about it? Email ask@cbc.ca.
Sasha Luccioni, a founding member of the non-profit group Climate Change AI, decided to apply her knowledge of computer science to problems related to climate change. (Camille Rochefort-Boulanger)
Luccini is part of a growing community of researchers in Canada using AI in this way.
In 2019, she co-authored a report arguing that machine learning can be a useful tool for mitigating and adapting to the effects of climate change.
Computer scientists define machine learning as a form of artificial intelligence that allows computers to use historical data and statistical methods to make predictions and decisions without having to be programmed to do so.
Common applications of machine learning include predictive text, spam filters, language translation applications, streaming content recommendations, malware and fraud detection, and social media algorithms.
Applications for machine learning in climate research include weather forecasting and optimization of electricity, transportation and energy systems, according to the 2019 report.
Preparation for crop diseases
Researchers at the University of Prince Edward Island (UPEI) are using AI modeling to warn farmers of risks to their crops as the weather becomes more unpredictable.
“If you have a dry year, you see very little disease, but in a wet year, you can have some disease around the plants,” said Aitazaz Farooque, interim associate dean of the School of Climate Change and Adaptation at UPEI
Aitazaz Farooque is the interim associate dean of UPEI’s School of Climate Change and Adaptation, who is piloting a project that aims to use weather forecasting to predict crop diseases. (Jane Robertson/CBC)
Researchers can plug weather data from previous years into an AI model to predict the type of diseases that might endanger crops at different times of the year, Farooque said.
“Then the grower can be a little bit proactive and understand what they’re getting into,” he said.
LOOK | Check out UPEI’s School of Climate Change and Adaptation:
A tour of the new climate change laboratory in Sant Pere Bay
From drones to dormitories, the state-of-the-art research facility in St. Peter’s Bay will be home to world-class students and researchers studying the many facets of climate change.
PEI’s agriculture is mostly rain-fed, and providing farmers with more accurate rainfall predictions can also help them have higher crop yields, Farooque said.
“With climate change, we’re seeing different trends where the total accumulated precipitation doesn’t change much, but the timing matters,” he said.
“If it doesn’t happen at the right time, the sustainability of our agriculture may be at risk.”
Study behavior in the face of disruptive climate
Another application of AI is being studied at McGill University, where researchers are using historical and recent weather data to predict the social impacts of extreme weather events that are affected by climate change, such as heat waves, droughts and floods .
According to Renee Sieber, associate professor in McGill’s geography department, the researchers hope to find out how people responded to disruptive weather events in the past and whether that can teach us anything about how resilient we will be in the future.
The McGill Observatory holds weather records dating back to 1863 that will be used in an AI project to analyze people’s responses to extreme weather events. (McGill University Archives)
The team will use a form of AI called natural language processing to analyze social narratives related to weather events in newspapers and other media.
“AI is very good at organizing, synthesizing, finding trends or some sentiment from large amounts of unstructured text,” Sieber said.
“Basically, what you do is throw magazine articles into a bucket and see what comes out.”
Sieber said his team will take findings from past articles and current social media and compare them to corresponding weather records to identify people’s responses to weather events over time.
The McGill Observatory records are the longest and most detailed continuous written records of weather patterns in Canada and contain a massive amount of information, Sieber said. Weather recording there began in 1863 and continued into the 1950s.
“This data is the only direct measure of climate change we have [in Canada]” said Sieber.
Optimization of energy consumption
Some Canadian companies are using AI to minimize waste and build more energy-efficient infrastructure.
Scale AI, a Montreal-based investor group that funds projects related to supply chains, has worked with grocery chains such as Loblaws and Save-on-Foods to identify purchasing patterns. Using AI, companies can better predict demand and less food will be wasted, said Scale AI CEO Julien Billot.
“Every optimization we can achieve improves the resilience of supply chains and contributes to the use of fewer resources,” he said.
Another Montreal company, BrainBox Al, focuses on improving energy efficiency by optimizing air conditioning systems in commercial buildings.
The machine learning technology is contained in a 30 cm wide box that plugs into a building’s HVAC system. It raises or lowers temperatures based on input such as weather forecasts, utility prices and carbon emissions calculations.
BrainBox AI technology optimizes a building’s HVAC system using data such as weather forecasts and utility prices. (BrainBox AI)
The system has been able to reduce the energy consumed by some HVAC systems by 25 percent, said BrainBox CEO Sam Ramadori, and over two years, the company has installed the technology in 350 buildings in 18 countries
“The same kind of intelligence that we’re bringing to buildings has probably an infinite number of applications. You just have to pick an industry,” Ramadori said.
“How we make cement, how we ship goods, all of that has to become more efficient over time as part of the fight against climate change.”
According to Ramadori, BrainBox AI is working on technology that will allow buildings to connect with each other and communicate with energy networks through the company’s cloud server.
Researchers work in the BrainBox AI office. (BrainBox AI)
This has the potential to minimize energy waste at the city scale, as energy networks more accurately sense where and when energy is needed, he said.
“The power grid can say, ‘Hey, the next two hours are going to be busy. I need you to find a way to reduce consumption.” And with the AI brain on top, it’s able to say, “Okay, I can reduce a little bit here and a little bit there. I got you covered,” Ramadori said.
Limitations of equity in AI
Access to the kind of AI that can help solve climate-related problems is unequal across the globe.
Wildfires in North America, for example, tend to get more attention from developers than locust infestations in East Africa, said David Rolnick, an assistant professor of computer science at McGill and a member of Mila.
“The way climate change affects a community varies greatly between different geographies,” said Rolnick, who is also the president of Climate Change AI.
David Rolnick, an assistant professor at McGill University’s School of Computer Science and a member of Mila, said relying on AI to solve climate-related problems raises some equity concerns. (Guillaume Simoneau)
AI technology relies on datasets, and many communities don’t have access to enough of the kind of robust data needed to build machine learning algorithms, Rolnick said.
In Canada, some indigenous and remote northern communities still face significant digital gaps compared to other parts of the country, he said.
“Working to democratize this is fundamentally important,” Rolnick said.
Rolnick co-authored a study last year outlining several limitations to implementing AI for climate change solutions in Canada. He called for increased funding for AI research and more AI education in primary and secondary education, as well as standards and protocols for sharing data related to climate projects.
Rapid implementation of large-scale AI literacy programs for policymakers and leaders in climate-relevant industries could help “demystify” AI, the report said.
“We often see a lack of relevant knowledge, and educational programs can help people understand what these tools can and cannot do,” Rolnick said.