Google grant to advance artificial intelligence methods in Center science Machine learning and neural networks will help track Arctic change Maddie Rocklin Associate Vice President, 90 West Sarah Ruiz Science Writer/Editor
With advances in artificial intelligence technologies, computers can be trained to imitate human language, play chess, categorize images, solve puzzles, write college essays, and even restore damaged ancient texts. With the help of a new $5 million grant from Google.org, the tech company’s philanthropic arm, Woodwell Climate will be putting AI to yet another use—fighting climate change.
landscapes, have held us all back,” says Dr. Liljedahl. “This project will be groundbreaking in speeding up data analysis and unlocking completely new technological capabilities in how we do science in swiftly evolving landscapes, and, ultimately, what science itself can do.”
The grant will be used to expand the development of the Permafrost Discovery Gateway (PDG), an open-access resource that allows users to visualize and explore data on changing Arctic landscapes. Under the leadership of Woodwell Climate Associate Scientist, Dr. Anna Liljedahl, AI methods will help speed up data processing, allowing researchers to rapidly identify patterns and trends in permafrost thaw. The results will be essential to informing climate mitigation and adaptation strategies.
Although AI seems to be a new tool, methods like machine learning and neural networks have been used for decades for their unique talent at recognizing patterns in large datasets. Several projects in Woodwell’s Arctic program already use AI to churn through thousands of satellite images to detect specific features in the landscape.
“Timely tracking of permafrost thaw is critical to assessing impacts and informing action, but current limitations in technology, combined with the rapid pace of change in Arctic
6
AI is nothing new
Data science specialist at the Center, Dr. Yili Yang, uses AI models trained to spot retrogressive thaw slumps (RTS) in permafrost rich regions of the Arctic. Thaw slumps are features that form in response to subsiding permafrost and can be indicators of greater thawing on the landscape, but they are hard to identify in images.
Climate Science for Change
Fall 2023