Session Details
[S5-S6-O]S5:Approaches to Sea Ice and Climate Predictions, Process Studies for Advancing Understanding and Forecasting, and Their Utilization for Stakeholders / S6:Sea ice research and machine learning: Opportunities to fill knowledge gaps
Thu. Oct 30, 2025 11:15 AM - 12:45 PM JST
Thu. Oct 30, 2025 2:15 AM - 3:45 AM UTC
Thu. Oct 30, 2025 2:15 AM - 3:45 AM UTC
Room 1
Chair: Jun Ono (National Institute of Polar Research)
S5 : This session addresses the critical role of sea ice in the Earth's climate system, highlighting recent Arctic and Antarctic trends observed via satellite. It seeks contributions focused on enhancing sea ice prediction through integrated approaches, including observations, modeling, and theoretical studies. Emphasis is placed on improving forecast accuracy and exploring practical applications in marine ecosystems, socio-economic planning, and Arctic shipping. The session also welcomes interdisciplinary insights from the humanities and social sciences to tackle the complex implications of sea ice change.
S6 : Sea ice is a vital component of Earth's climate system, and improving its monitoring and modeling is essential for understanding environmental change in polar regions and informing global mitigation and adaptation strategies. Despite recent advances, significant observational and modeling gaps remain. This session highlights the growing role of Machine Learning (ML) in enhancing sea ice research by improving predictive accuracy, addressing data voids, and correcting model biases across various climate scenarios. It will showcase interdisciplinary approaches-including remote sensing, in-situ measurements, and physical modeling-that integrate ML techniques to better forecast sea ice dynamics. Bringing together experts in sea ice physics, biology, biogeochemistry, remote sensing, and data science, the session aims to foster cross-disciplinary collaboration, spotlight innovative methodologies, and outline challenges and opportunities in this fast-evolving field.
S6 : Sea ice is a vital component of Earth's climate system, and improving its monitoring and modeling is essential for understanding environmental change in polar regions and informing global mitigation and adaptation strategies. Despite recent advances, significant observational and modeling gaps remain. This session highlights the growing role of Machine Learning (ML) in enhancing sea ice research by improving predictive accuracy, addressing data voids, and correcting model biases across various climate scenarios. It will showcase interdisciplinary approaches-including remote sensing, in-situ measurements, and physical modeling-that integrate ML techniques to better forecast sea ice dynamics. Bringing together experts in sea ice physics, biology, biogeochemistry, remote sensing, and data science, the session aims to foster cross-disciplinary collaboration, spotlight innovative methodologies, and outline challenges and opportunities in this fast-evolving field.
[S5-S6-O-06]Evaluation of the 2024 Mid-Term Arctic Summer Sea Ice Forecast by ASIC in Comparison to Observations
*Motomu Oyama1, Noriaki Kimura2, Hironori Yabuki3 (1. Graduate School of Engineering, Kogakuin University (Japan), 2. Atmosphere and Ocean Research Institute, The University of Tokyo (Japan), 3. National Institute of Polar Research (Japan))
[S5-S6-O-07]NIPR’s Short-term Sea Ice Forecast Service for the Whole Arctic Ocean Based on Ice-Ocean Coupled Simulations
*Yoshihiro Niwa1, Motomu Oyama2, Takeshi Sugimura1, Hironori Yabuki1 (1. National Institute of Polar Research (Japan), 2. Graduate School of Engineering, Kogakuin University (Japan))
[S5-S6-O-08]An Information Support System for Arctic Research Cruises of R/V MIRAI II
*Genki Sagawa1 (1. Weathernews Inc. (Japan))
[S5-S6-O-09]Optimizing sea ice parameters mitigates the underestimation of Arctic marine access in CMIP6 climate models
*Chao Min1,2, Qinghua Yang1, Hao Luo1, Frank Kauker2,3, Qi Shu4, Xin Wang5, Jiping Liu1, Dake Chen1 (1. School of Atmospheric Sciences, Sun Yat-sen University, and Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai) (China), 2. Alfred Wegener Institute, Helmholtz Centre for Polar and Marine Research (Germany), 3. O.A.Sys. - Ocean Atmosphere Systems (Germany), 4. First Institute of Oceanography, Ministry of Natural Resources (China), 5. Beijing Globe MetRoute Technology Co., Ltd., China Meteorological Administration (China))
[S5-S6-O-10]Toward seasonal-to-interannual Arctic sea-ice forecast using a climate model
*Jun Ono1, Yoshiki Komuro2, Hiroaki Tatebe2, Noriaki Kimura3, Hironori Yabuki1 (1. National Institute of Polar Research (Japan), 2. Japan Agency for Marine-Earth Science and Technology (Japan), 3. Atmosphere and Ocean Research Institute, The University of Tokyo (Japan))