Blog
About

0
views
0
recommends
+1 Recommend
1 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found

      Trace-Norm Regularized Multi-Task Learning for Sea State Bias Estimation

      Read this article at

      ScienceOpenPublisher
      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Sea state bias (SSB) is an important component of errors for the radar altimeter measurements of sea surface height (SSH). However, existing SSB estimation methods are almost all based on single-task learning (STL), where one model is built on the data from only one radar altimeter. In this paper, taking account of the data from multiple radar altimeters available, we introduced a multi-task learning method, called trace-norm regularized multi-task learning (TNR-MTL), for SSB estimation. Corresponding to each individual task, TNR-MLT involves only three parameters. Hence, it is easy to implement. More importantly, the convergence of TNR-MLT is theoretically guaranteed. Compared with the commonly used STL models, TNR-MTL can effectively utilize the shared information between data from multiple altimeters. During the training of TNR-MTL, we used the JASON-2 and JASON- 3 cycle data to solve two correlated SSB estimation tasks. Then the optimal model was selected to estimate SSB on the JASON- 2 and the HY-2 70-71 cycle intersection data. For the JSAON-2 cycle intersection data, the corrected variance ( M) has been reduced by 0.60 cm 2 compared to the geophysical data records (GDR); while for the HY-2 cycle intersection data, M has been reduced by 1.30 cm 2 compared to GDR. Therefore, TNR-MTL is proved to be effective for the SSB estimation tasks.

          Related collections

          Author and article information

          Journal
          JOUC
          Journal of Ocean University of China
          Science Press and Springer (China )
          1672-5182
          15 November 2020
          01 December 2020
          : 19
          : 6
          : 1292-1298
          Affiliations
          1Department of Computer Science and Technology, Ocean University of China, Qingdao 266100, China
          2Department of Physics, Ocean University of China, Qingdao 266100, China
          3Department of Computer Science, Sultan Qaboos University, P. O. B 36, AlKhod 123, Muscat, Oman
          Author notes
          *Corresponding author: ZHONG Guoqiang, Tel: 0086-532-66781719, E-mail: gqzhong@ 123456ouc.edu.cn
          Article
          s11802-020-4267-x
          10.1007/s11802-020-4267-x
          Copyright © Ocean University of China, Science Press and Springer-Verlag GmbH Germany 2020.

          The copyright to this article, including any graphic elements therein (e.g. illustrations, charts, moving images), is hereby assigned for good and valuable consideration to the editorial office of Journal of Ocean University of China, Science Press and Springer effective if and when the article is accepted for publication and to the extent assignable if assignability is restricted for by applicable law or regulations (e.g. for U.S. government or crown employees).

          Product
          Self URI (journal-page): https://www.springer.com/journal/11802

          Comments

          Comment on this article