“We want to have results within a week so that we can really accelerate decision-making for climate scientists,” says the Jacobs School of Engineering and Halcheol Data Science Institute.
Ambitious? yes. But that’s where artificial intelligence comes in.Thanks to his $3.6 million grant awarded by Department of Energy Yu in 2021 Two colleagues from the University of California, San Diego Yian Ma and Lawrence Saul collaborate with researchers at Columbia University and UC Irvine to develop new machine learning techniques that can speed up these climate models, predict the future more accurately, and better understand climate extremes. developed.
Understanding exactly how climate change is impacting our planet, our communities, and our daily lives, and how to use this new knowledge to combat climate change. This work is being done at a very critical time, as it is becoming more and more important. To date, the team has published over 20 of his papers in both machine learning and climate science-related journals and continues to push the boundaries of science and engineering in this very important field.
To improve prediction accuracy and quantify inherent uncertainty, the team is working on customizing algorithms that embed the laws of physics and first principles into deep learning models. This is a form of machine learning that basically mimics how the human brain works. This is not an easy task, but it gave them the opportunity to work closely with climate scientists who are incorporating these machine learning techniques into practical algorithms for climate modeling.
“Thanks to this grant, we have established new connections and new collaborations to expand the impact of AI methods on climate science,” said Yu. “We started working on algorithms and models with climate applications in mind, and now we can work closely with climate scientists to validate our models.”
