Self-Attention Convolutional Long Short-Term Memory for Short-Term Arctic Sea Ice Motion Prediction Using Advanced Microwave Scanning Radiometer Earth Observing System 36.5 GHz Data

被引:1
作者
Zhong, Dengyan [1 ,2 ]
Liu, Na [2 ]
Yang, Lei [2 ]
Lin, Lina [2 ]
Chen, Hongxia [2 ]
机构
[1] Shandong Univ Sci & Technol, Coll Ocean Sci & Engn, Qingdao 266590, Peoples R China
[2] Minist Nat Resources, Inst Oceanog 1, Key Lab Marine Sci & Numer Modeling, Qingdao 266061, Peoples R China
基金
美国国家科学基金会;
关键词
Arctic sea ice; Advanced Microwave Scanning Radiometer Earth Observing System (AMSR-E); deep learning; Self-Attention Memory; Self-Attention ConvLSTM; optical flow; motion prediction; DRIFT; FORECAST; EXTENT;
D O I
10.3390/rs15235437
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Over the past four decades, Arctic sea ice coverage has steadily declined. This loss of sea ice has amplified solar radiation and heat absorption from the ocean, exacerbating both polar ice loss and global warming. It has also accelerated changes in sea ice movement, posing safety risks for ship navigation. In recent years, numerical prediction models have dominated the field of sea ice movement prediction. However, these models often rely on extensive data sources, which can be limited in specific time periods or regions, reducing their applicability. This study introduces a novel approach for predicting Arctic sea ice motion within a 10-day window. We employ a Self-Attention ConvLSTM deep learning network based on single-source data, specifically optical flow derived from the Advanced Microwave Scanning Radiometer Earth Observing System 36.5 GHz data, covering the entire Arctic region. Upon verification, our method shows a reduction of 0.80 to 1.18 km in average mean absolute error over a 10-day period when compared to ConvLSTM, demonstrating its improved ability to capture the spatiotemporal correlation of sea ice motion vector fields and provide accurate predictions.
引用
收藏
页数:18
相关论文
共 53 条
  • [31] Pithan F, 2014, NAT GEOSCI, V7, P181, DOI [10.1038/NGEO2071, 10.1038/ngeo2071]
  • [32] Improved algorithm for determining the freeze onset of Arctic sea ice using AMSR-E/2 data
    Qu, Zhifeng
    Su, Jie
    [J]. REMOTE SENSING OF ENVIRONMENT, 2023, 297
  • [33] Revaud J, 2015, PROC CVPR IEEE, P1164, DOI 10.1109/CVPR.2015.7298720
  • [34] An explainable self-attention deep neural network for detecting mild cognitive impairment using multi-input digital drawing tasks
    Ruengchaijatuporn, Natthanan
    Chatnuntawech, Itthi
    Teerapittayanon, Surat
    Sriswasdi, Sira
    Itthipuripat, Sirawaj
    Hemrungrojn, Solaphat
    Bunyabukkana, Prodpran
    Petchlorlian, Aisawan
    Chunamchai, Sedthapong
    Chotibut, Thiparat
    Chunharas, Chaipat
    [J]. ALZHEIMERS RESEARCH & THERAPY, 2022, 14 (01)
  • [35] Accuracy of short-term sea ice drift forecasts using a coupled ice-ocean model
    Schweiger, Axel J.
    Zhang, Jinlun
    [J]. JOURNAL OF GEOPHYSICAL RESEARCH-OCEANS, 2015, 120 (12) : 7827 - 7841
  • [36] Shi XJ, 2015, ADV NEUR IN, V28
  • [37] Skea J., 2019, CLIMATE CHANGE LAND
  • [38] The Regional Ice Ocean Prediction System v2: a pan-Canadian ocean analysis system using an online tidal harmonic analysis
    Smith, Gregory C.
    Liu, Yimin
    Benkiran, Mounir
    Chikhar, Kamel
    Colan, Dorina Surcel
    Gauthier, Audrey-Anne
    Testut, Charles-Emmanuel
    Dupont, Frederic
    Lei, Ji
    Roy, Francois
    Lemieux, Jean-Francois
    Davidson, Fraser
    [J]. GEOSCIENTIFIC MODEL DEVELOPMENT, 2021, 14 (03) : 1445 - 1467
  • [39] Sperber M, 2018, Arxiv, DOI [arXiv:1803.09519, 10.48550/arXiv.1803.09519]
  • [40] Trends in Arctic sea ice drift and role of wind forcing: 1992-2009
    Spreen, Gunnar
    Kwok, Ron
    Menemenlis, Dimitris
    [J]. GEOPHYSICAL RESEARCH LETTERS, 2011, 38