DPI: Deep Prior-based Interpolation for Satellite Altimetry Data Reconstruction
ID:985 View Protection:ATTENDEE Updated Time:2026-08-31 21:09:05 Hits:118 Oral Presentation

Start Time:2027-01-14 13:45(Asia/Shanghai)

Duration:15min

Session:S9 Session 9 - Ocean Dynamics in the SWOT Era: New Methods, Discoveries, Insights and Challenges » S9-1Ocean Dynamics in the SWOT Era: New Methods, Discoveries, Insights and Challenges

No files

Abstract
Mesoscale ocean eddies shape ocean circulation and transport heat, carbon, and momentum, but their structure is often smoothed in conventional satellite altimetry maps. Here, we use DPI(deep prior interpolation) to improve global estimates of sea level anomaly by merging nadir altimeter and SWOT KaRIn observations. Without prescribing covariance structures or using labeled training data, the method learns a high-resolution spatiotemporal field directly from satellite observations through a self-supervised deep prior. A leave-one-out Top-k ensemble further limits noise fitting and improves reconstruction stability. In observing system simulation experiments, our method achieves lower errors and finer effective resolution than DUACS, and substantially improves eddy-detection F1 scores. Experiments with real observations also outperform optimal interpolation and demonstrate the feasibility of producing global 2-km SLA maps. These results suggest that deep prior interpolation can provide a new paradigm for high-resolution satellite oceanography and more reliable observations of mesoscale eddy dynamics.
Keywords
Speaker
Yepeng Jiang
Peking University

Submission Author
Yepeng Jiang Peking University
Submit Comment
Verify Code Change Another
All Comments
Important Date
  • Conference Date

    Jan 12

    2027

    to

    Jan 15

    2027

  • Jul 21 2026

    Draft paper submission deadline

  • Jan 15 2027

    Registration deadline

Sponsored By
State Key Laboratory of Marine Environmental Science, Xiamen University (MEL)
Department of Earth Sciences, National Natural Science Foundation of China (NSFC)
Contact Information
Previous Conferences