深度学习方法在北极海冰预报中的应用  

Application of deep learning methods to Arctic sea ice prediction

作　　者：刘泉宏 张韧[1,2] 汪杨骏 闫恒乾 LIU Quanhong;ZHANG Ren;WANG Yangjun;YAN Hengqian(College of Meteorology and Oceanography,National University of Defense Technology,Changsha 410000,China;Key Laboratory of Meteorological Disaster,Ministry of Education(KLME)/Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters(CIC-FEMD),Nanjing University of Information Science and Technology,Nanjing 210044,China)

机构地区：[1]国防科技大学气象海洋学院,湖南长沙410000 [2]南京信息工程大学气象灾害教育部重点实验室/气象灾害预报预警与评估协同创新中心,江苏南京210044

出　　处：《大气科学学报》2022年第1期14-21,共8页Transactions of Atmospheric Sciences

基　　金：国家自然科学基金资助项目(41976188)。

摘　　要：在全球气候变暖背景下,北极海冰呈现出逐年消融的趋势。海冰的消融给北极的开发利用带来了重要机遇,例如北极航道通航潜力的显现。但北极航道开通还面临着诸多困难,尤其是海冰变化机理的复杂性和海冰预报的不确定性以及由此带来的航行安全风险。近年来,深度学习因其强大的非线性拟合能力,逐渐在海冰预报领域中崭露头角。本文对近年来深度学习在北极海冰预报中的国内外研究状况进行了梳理,分析了深度学习在海冰预报中的应用背景,指出了单纯地应用深度学习进行海冰预报的局限性,阐述了深度学习方法与气象海洋专业知识的结合点,展望了未来的研究动态和发展趋势。Arctic sea ice continues to shrinking with the global warming,creating a significant chance to shipping on the Arctic routes.However,some issues still hinder the opening of Arctic shipping routes.Especially,the navigation safety is threatened by the uncertainty of sea ice prediction due to the complex physical mechanism of sea ice change.In recent years,deep learning algorithms,having excellence in tackling nonlinear fitting problems,have shown increased evidence of potential to address the problem of sea ice prediction.This paper provides a critical review of existing deep learning methods developed for sea ice prediction.First,the deficiency of numerical model in sea ice prediction was analyzed,leading out the advantage of deep learning methods.Second,the limitations of adopting deep learning methods only were pointed out in light of the characteristics of sea ice.Finally,the possible paths to adopting specialized knowledge of meteorology and oceanography into deep learning methods so as to provide a better prediction model were discussed.

关 键 词：北极海域 海冰预报 深度学习 北极航道 

分 类 号：P731.32[天文地球—海洋科学]