Enhancing Seasonal Arctic Sea Ice Prediction for Late Summer by Transfer Learning of PIOMAS and CryoSat-2-Observed Sea Ice Thickness Data
文献类型：期刊论文
| 作者 | Ren, Yibin1,3; Liu, Fangyi1,2,3; Li, Xiaofeng1,3 |
| 刊名 | IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
 |
| 出版日期 | 2026 |
| 卷号 | 23页码:5 |
| 关键词 | Feedback Circuits Cellular technology Mobile communication 3G mobile communication 5G mobile communication Electronic mail Wireless Access in Vehicular Environments Protocols Fuses Arctic sea ice CryoSat-2 sea ice thickness (SIT) seasonal prediction transfer learning |
| ISSN号 | 1545-598X |
| DOI | 10.1109/LGRS.2026.3680499 |
| 通讯作者 | Li, Xiaofeng(xiaofeng.li@ieee.org) |
| 英文摘要 | Sea ice thickness (SIT) is essential for predicting Arctic sea ice concentration (SIC) on seasonal timescales. This study develops a transfer learning approach that combines long-term Pan-Arctic Ice-Ocean Modeling and Assimilation System (PIOMAS) reanalysis (1989-2010) with satellite-based CryoSat-2 SIT (2011-2019) in a deep learning (DL) model, SICNet(DB), to enhance summer SIC predictions. The model is pretrained on PIOMAS SIT and then fine-tuned with CryoSat-2-observed SIT to leverage their advantages. Results indicate that fusing PIOMAS and CryoSat-2 SIT improves September SIC prediction skill by 0.21-0.45 in the anomaly correlation coefficient (ACC) compared to models that rely solely on SIC, and by 0.14-0.26 compared to models using only PIOMAS SIT. In years with less ice, such as 2012 and 2019, transferring CryoSat-2 SIT data results in a five-unit reduction in mean absolute error (MAE) and an improvement in binary accuracy (BACC) of up to 11%. These enhancements are especially noticeable at seven and eight biweekly lead times, demonstrating that transfer learning effectively fuses PIOMAS and CryoSat-2 SIT datasets to optimize the spring prediction barrier (SPB). |
| WOS关键词 | MODEL |
| 资助项目 | National Science Foundation of China[42576205] ; National Science Foundation of China[42206202] ; National Science Foundation of China[42221005] ; IOCAS Foundation[IOCASZZZX301] ; IOCAS Foundation[IOCASZZCG003] ; Laoshan Laboratory Innovation Project[LSKJ202202302] ; Ocean Artificial Intelligence Research Center[IOCASZZCG003] ; Ocean Artificial Intelligence Research Center[LSKJ202202302] ; Oceanographic Data Center, Chinese Academy of Sciences[42576205] ; Oceanographic Data Center, Chinese Academy of Sciences[42206202] ; Oceanographic Data Center, Chinese Academy of Sciences[42221005] ; Oceanographic Data Center, Chinese Academy of Sciences[IOCASZZZX301] |
| WOS研究方向 | Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology |
| 语种 | 英语 |
| WOS记录号 | WOS:001740770900004 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 源URL | [http://ir.qdio.ac.cn/handle/337002/204898]  |
| 专题 | 海洋研究所_海洋环流与波动重点实验室 |
| 通讯作者 | Li, Xiaofeng |
| 作者单位 | 1.Chinese Acad Sci, Inst Oceanol, Qingdao 266071, Peoples R China 2.Univ Chinese Acad Sci, Coll Marine Sci, Beijing 101408, Peoples R China 3.Chinese Acad Sci, Key Lab Ocean Observat & Forecasting, Lab Ocean Circulat & Waves, Qingdao 266071, Peoples R China |
| 推荐引用方式 GB/T 7714 | Ren, Yibin,Liu, Fangyi,Li, Xiaofeng. Enhancing Seasonal Arctic Sea Ice Prediction for Late Summer by Transfer Learning of PIOMAS and CryoSat-2-Observed Sea Ice Thickness Data[J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,2026,23:5. |
| APA | Ren, Yibin,Liu, Fangyi,&Li, Xiaofeng.(2026).Enhancing Seasonal Arctic Sea Ice Prediction for Late Summer by Transfer Learning of PIOMAS and CryoSat-2-Observed Sea Ice Thickness Data.IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,23,5. |
| MLA | Ren, Yibin,et al."Enhancing Seasonal Arctic Sea Ice Prediction for Late Summer by Transfer Learning of PIOMAS and CryoSat-2-Observed Sea Ice Thickness Data".IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 23(2026):5. |
入库方式： OAI收割
来源：海洋研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。