A071
Machine Learning for ocean-atmosphere sciences: advance, challenges and the way forward
Session ID#: 251076
Session Description:
This session seeks to showcase cutting-edge developments, address critical challenges, and explore future directions in the application of machine learning to ocean-atmosphere sciences. We invite contributions addressing (but not limited to) the following themes: 1) Data-driven approaches, algorithms and models (e.g., computer vision, language, foundation and large models) that are suitable to solve atmosphere-ocean problems; 2) Predictions/projection of ocean-atmosphere phenomena at different timescales including nowcasting, weather forecast, subseasonal to seasonal climate prediction, and decadal projection; 3) Data qualification, reconstruction and assimilation for multiple sources of data provided by different monitoring techniques; 4) Monitoring, detection, classification, and segmentation of environmental disasters including coastal pollutions, bush fires, storms and compound extremes; 5) Dynamical model bias traceback, correcting and downscaling; 6) Explainable or interpretable AI and “physics + AI” hybrid modelling including model parameter optimization and inversion from observational data; 7) Usefulness and applicability of data-driven models to the society.
Co-Sponsor(s):
Index Terms:
3305 Climate change and variability [ATMOSPHERIC PROCESSES]
3315 Data assimilation [ATMOSPHERIC PROCESSES]
4522 ENSO [OCEANOGRAPHY: PHYSICAL]
4564 Tsunamis and storm surges [OCEANOGRAPHY: PHYSICAL]
Primary Convener: Jing-Jia Luo, NUIST Nanjing University of Information Science and Technology, Institute for Climate and Application Research (ICAR), Nanjing, China
Conveners: X. Li, CAS Key Laboratory of Ocean Circulation and Waves, Institute of Oceanology, Chinese Academy of Sciences and Center for Ocean Mega-Science, Chinese Academy of Sciences, Qingdao, China, Yoo-Geun Ham, Seoul National University, Seoul, South Korea and Swadhin K. Behera, JAMSTEC, Yokohama, Japan
Data-driven Global Ocean Modeling for Seasonal to Decadal Prediction (1854777)
Jing-Jia Luo1, Fenghua Ling2, Zijie Guo3, Lei Bai4, Niklas Boers5, Pumeng Lyu4, Takeshi Izumo6, Sophie E Cravatte7, Antonietta Capotondi8, Toshio Yamagata9 and Wanli Ouyang10, (1)NUIST Nanjing University of Information Science and Technology, Institute for Climate and Application Research (ICAR), Nanjing, China, (2)Nanjing University of Information Science and Technology, Institute for Climate and Application Research (ICAR), Nanjing, China, (3)Fudan University, Shanghai, China, (4)Shanghai Artificial Intelligence Laboratory, Shanghai, China, (5)Ecole Normale Supérieure Paris, Paris, France, (6)IRD (Institut de Recherche pour le Développement) / EIO laboratory / University of French Polynesia, Faa'a, French Polynesia, (7)LEGOS, Université de Toulouse, (IRD, CNES, CNRS, UPS), Toulouse, France, (8)University of Colorado, CIRES, Boulder, United States, (9)Japan Agency for Marine-Earth Science and Technology, Yokohama, Japan, (10)The Chinese University of Hong Kong, Hongkong, China
Post-hiatus enhancement of ENSO forecast skill via salinity-mediated Indo-Pacific inter-basin coupling (1877260)
Jing Wang, Institute of Oceanology, Chinese Academy of Sciences, Qingdao, China, Janet Sprintall, Univ California San Diego, La Jolla, United States, Haoyu Wang, Institute of Oceanography, Chinese Academy of Sciences, Qingdao, China and X. Li, CAS Key Laboratory of Ocean Circulation and Waves, Institute of Oceanology, Chinese Academy of Sciences and Center for Ocean Mega-Science, Chinese Academy of Sciences, Qingdao, China
Application and Evaluation of a Deep Learning-Based Vertical Mixing Parameterization in an Ocean Model (1889731)
Jin Li1,2, Yongqiang Yu1,2 and Xiaojie Li3, (1)University of Chinese Academy of Sciences, Beijing, China, (2)Institute of Atmos. Physics, Beijing, China, (3)Chengdu University of Information Technology, Chengdu, China
Prediction of Marine Ecological Environment Based on Deep Neural Network (1916019)
Guantao Pu1, Keyi Yang2, Yijun Chen2, Jin Qi3, Prof. Sensen Wu2 and Zhenhong Du2, (1)School of Earth Sciences, Zhejiang University, Hangzhou, Zhejiang, CHINA, (2)Zhejiang University, Hangzhou, China, (3)ZheJiang University, Hangzhou, China
Application of Machine Learning on Bias-Correction for High-Resolution Ocean Model Data (1975196)
Yifan Zhu1, Trinity Mink1,2, Samantha Siedlecki1 and Felipe Soares1, (1)University of Connecticut, Department of Marine Sciences, Groton, United States, (2)University of Connecticut, School of Computing, Storrs, United States
