1. Advances in Machine Learning Techniques Can Assist Across a Variety of Stages in Sea Ice Applications.
- Author
-
Eayrs, Clare, Lee, Won Sang, Jin, Emilia, Lemieux, Jean-François, Massonnet, François, Vancoppenolle, Martin, Zampieri, Lorenzo, Bennetts, Luke G., Blockley, Ed, Chung, Eui-Seok, Fraser, Alexander D., Ham, Yoo-geun, Im, Jungho, Kim, Baek-min, Kim, Beong-Hoon, Kim, Jinsuk, Kim, Joo-Hong, Kim, Seong-Joong, Kim, Seung Hee, and Korosov, Anton
- Subjects
- *
SEA ice , *MACHINE learning , *ARTIFICIAL neural networks , *CONVOLUTIONAL neural networks , *SEA ice drift , *ATMOSPHERIC boundary layer - Abstract
A three-day workshop was held in Gwangmyeong, South Korea, to discuss recent advances in sea ice modeling. Researchers from South Korea, China, Australia, Canada, Belgium, France, Italy, and Norway attended the workshop. The workshop focused on four themes: emerging model technologies, the role of artificial intelligence (AI) in sea ice applications, model/observation integration, and future research needs and opportunities. The use of AI techniques in sea ice research and forecasting was highlighted, including applications such as forecasting sea ice concentration and thickness, correcting biases in atmospheric boundary conditions, and detecting landfast sea ice. The workshop also emphasized the need for collaboration across geographies and highlighted the research bubbles that exist in different regions. The workshop provided a valuable forum for collaboration and knowledge sharing, and a follow-up workshop is planned for fall 2025. [Extracted from the article]
- Published
- 2024
- Full Text
- View/download PDF