Journal article · 2025 · Open access

A Comparative Evaluation of Two Bias Correction Approaches for SST Forecasting: Data Assimilation Versus Deep Learning Strategies

Wanqiu Dong, Guijun Han, Wei Li, Haowen Wu, Qingyu Zheng, Xiaobo Wu, Mengmeng Zhang, Lige Cao, Zenghua Ji

Remote Sensing, 17(9), 1602 · Published 30 April 2025 · DOI 10.3390/rs17091602

Open PDFView at the publisherCite this paper

In brief

“A Comparative Evaluation of Two Bias Correction Approaches for SST Forecasting: Data Assimilation Versus Deep Learning Strategies” is a 2025 journal article by Wanqiu Dong and 8 co-authors, published in Remote Sensing. OpenAlex counts 5 citations as of 20 November 2026. It is open access under a CC BY licence: the full text is free to read at Remote Sensing.

Citations
5
Most cited in
2026 (4)
Field-weighted impact
1.65
References
37
Authors
9

Abstract

This study introduces two distinct post-processing strategies to address systematic biases in sea surface temperature (SST) numerical forecasts, thereby enhancing SST predictive accuracy. The first strategy implements a spatiotemporal four-dimensional multi-grid analysis (4D-MGA) scheme within a three-dimensional variational (3D-Var) data assimilation framework. The second strategy establishes a hybrid deep learning architecture integrating empirical orthogonal function (EOF) analysis, empirical mode decomposition (EMD), and a backpropagation (BP) neural network (designated as EE–BP). The 4D-MGA strategy dynamically corrects systematic biases through a temporally coherent extrapolation of analysis increments, leveraging its inherent capability to characterize intrinsic temporal correlations in model error evolution. In contrast, the EE–BP strategy develops a bias correction model by learning the systematic biases of the SST numerical forecasts. Utilizing a satellite fusion SST dataset, this study conducted bias correction experiments that specifically addressed the daily SST numerical forecasts with 7-day lead times in the Kuroshio region south of Japan during 2017, systematically quantifying the respective error reduction potentials of both strategies. Quantitative verification reveals that EE–BP delivers enhanced predictive skill across all forecast horizons, achieving 18.1–22.7% root–mean–square error reduction compared to 1.2–9.1% attained by 4D-MGA. This demonstrates deep learning’s unique advantage in capturing nonlinear bias evolution patterns.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Dong, W., Han, G., Li, W., Wu, H., Zheng, Q., Wu, X., Zhang, M., Cao, L., & Ji, Z. (2025). A Comparative Evaluation of Two Bias Correction Approaches for SST Forecasting: Data Assimilation Versus Deep Learning Strategies. Remote Sensing, 17(9), 1602. https://doi.org/10.3390/rs17091602

MLA 9

Dong, Wanqiu, et al. “A Comparative Evaluation of Two Bias Correction Approaches for SST Forecasting: Data Assimilation Versus Deep Learning Strategies.” Remote Sensing, vol. 17, no. 9, 2025, p. 1602. https://doi.org/10.3390/rs17091602.

Chicago

Dong, Wanqiu, Guijun Han, Wei Li, Haowen Wu, Qingyu Zheng, Xiaobo Wu, Mengmeng Zhang, Lige Cao, and Zenghua Ji. 2025. “A Comparative Evaluation of Two Bias Correction Approaches for SST Forecasting: Data Assimilation Versus Deep Learning Strategies.” Remote Sensing 17 (9): 1602. https://doi.org/10.3390/rs17091602.

Harvard

Dong, W. et al. (2025) ‘A Comparative Evaluation of Two Bias Correction Approaches for SST Forecasting: Data Assimilation Versus Deep Learning Strategies’, Remote Sensing, 17(9), p. 1602. doi:10.3390/rs17091602.

IEEE

W. Dong et al., “A Comparative Evaluation of Two Bias Correction Approaches for SST Forecasting: Data Assimilation Versus Deep Learning Strategies,” Remote Sensing, vol. 17, no. 9, p. 1602, 2025, doi: 10.3390/rs17091602.

BibTeX

@article{dong2025comparative,
  title     = {{A Comparative Evaluation of Two Bias Correction Approaches for SST Forecasting: Data Assimilation Versus Deep Learning Strategies}},
  author    = {Dong, Wanqiu and Han, Guijun and Li, Wei and Wu, Haowen and Zheng, Qingyu and Wu, Xiaobo and Zhang, Mengmeng and Cao, Lige and Ji, Zenghua},
  journal   = {Remote Sensing},
  year      = {2025},
  volume    = {17},
  number    = {9},
  pages     = {1602},
  doi       = {10.3390/rs17091602},
  url       = {https://doi.org/10.3390/rs17091602}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Earth and Planetary Sciences › Oceanography › Oceanographic and Atmospheric Processes

  • sea surface temperature prediction
  • forecast bias correction
  • data assimilation
  • 3D-Var
  • deep learning
  • empirical orthogonal functions
  • empirical mode decomposition
  • BP neural network

Work with this paper

Most-cited papers in Earth and Planetary Sciences

All highly cited Earth and Planetary Sciences papers

Questions about this paper

How do I cite this paper in APA style?

Dong, W., Han, G., Li, W., Wu, H., Zheng, Q., Wu, X., Zhang, M., Cao, L., & Ji, Z. (2025). A Comparative Evaluation of Two Bias Correction Approaches for SST Forecasting: Data Assimilation Versus Deep Learning Strategies. Remote Sensing, 17(9), 1602. https://doi.org/10.3390/rs17091602

How many times has this paper been cited?

5 times, according to OpenAlex on 20 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Remote Sensing: sign in and open the PDF from this page.

Who wrote this paper?

Wanqiu Dong, Guijun Han, Wei Li, Haowen Wu, Qingyu Zheng, Xiaobo Wu, Mengmeng Zhang, Lige Cao, Zenghua Ji.

What is the DOI of this paper?

10.3390/rs17091602, permanently at https://doi.org/10.3390/rs17091602. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 20 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.