Skip to main navigation Skip to search Skip to main content

Delta-Scale 10-m Tidal Flat Topography Reconstruction: A Transferable Deep Learning Approach Using Sentinel-2 Time Series

  • Peng Li*
  • , Jiahan Zhang
  • , Fengling Yu
  • , Kai Tan
  • , Nan Xu
  • , Chunpeng Chen
  • , Pengfei Tang
  • , Cunren Liang
  • , Zhenhong Li
  • , Houjie Wang
  • *Corresponding author for this work
  • Ocean University of China
  • Qingdao Marine Science and Technology Center
  • Xiamen University
  • Shenzhen University
  • East China Normal University
  • Hong Kong Polytechnic University
  • Seoul National University
  • Peking University
  • Chang'an University

Research output: Contribution to journalArticlepeer-review

Abstract

Reliable tidal flat elevation data with a resolution better than 30 m are vital for understanding macroscale sedimentation processes and storm surge erosion in estuarine deltas. However, the highly dynamic and turbid environments of global estuaries pose significant challenges for traditional manual or uncrewed aerial vehicle (UAV) methods in delta-scale monitoring. Insufficient elevation data currently hinder sea-level rise modeling and coastal management for the world's densely populated, flood-prone river deltas. There is an urgent need to characterize and reconstruct the vertical geomorphology of tidal flats through improved observations and modeling. In this study, we propose a robust tidal flat topography mapping framework using freely available satellite imagery and deep learning (DL). First, we developed an enhanced U-Net model to delineate land-water boundaries and generate inundation frequency maps from time-series Sentinel-2 imagery. A regionally adaptive nonlinear inversion model was then constructed using inundation frequency and ICESat-2 elevation data, allowing us to generate a 10-m resolution tidal flat digital elevation model (DEM) of the Yellow River estuary. The DL model achieved an F1-score of 0.96, and the resulting DEM showed strong agreement with UAV LiDAR data, yielding a root mean square error (RMSE) of 0.18 m. The reconstructed elevations range from -0.51 to 0.96 m, exhibiting a spatial gradient of lower elevations in the north and higher elevations in the southern and eastern sectors. To assess transferability, we applied the method to the radial sand ridge system in the South Yellow Sea. The model achieved a comparable RMSE of 0.52 m without retraining, demonstrating robust generalization across different estuarine environments. This study provides a cost-effective framework for monitoring coastal geomorphological changes and helps fill the data gap in delta-scale topographic mapping for global intertidal zones.

Original languageEnglish
Article number4206212
JournalIEEE Transactions on Geoscience and Remote Sensing
Volume64
DOIs
StatePublished - 2026

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

  1. SDG 14 - Life Below Water
    SDG 14 Life Below Water

Keywords

  • Coastal topography
  • deep learning (DL)
  • digital elevation model (DEM)
  • river delta
  • satellite remote sensing

Fingerprint

Dive into the research topics of 'Delta-Scale 10-m Tidal Flat Topography Reconstruction: A Transferable Deep Learning Approach Using Sentinel-2 Time Series'. Together they form a unique fingerprint.

Cite this