Conference Agenda

Within the joint Sino-European project “Remote Sensing of Changing Coastal Marine Environments” (ReSCCoME) we have been developing techniques for the use of Synthetic Aperture Radar (SAR) data for the monitoring of European and Chinese coastal areas. A new neural network has been developed, which is based on the YOLO (You Only Look Once) single network, and which is capable of detecting sub-mesoscale eddies on SAR imagery of ocean surfaces at high precision. We demonstrate that a classification of sediments on exposed intertidal flats is possible, when complex SAR data acquired at different radar bands is used. Single-band SAR data can already be used to generate Digital Elevation Maps (DEM) through an identification of waterlines at different water levels. Here, two approaches, including a new neural network, are yielding promising results. We further demonstrate that SAR wind fields yield a useful and robust tool to assess the potential of possible future wind farms, and to demonstrate the impact of existing windfarms on their surrounding environment, particularly the deficit in local wind speed.

Ocean waves are a crucial aspect of seawater movement, and understanding the generation and propagation mechanisms of ocean waves is essential for marine disaster prevention, shipping and marine engineering construction. Traditional methods of observing ocean waves, such as buoys, ships and coastal stations, have limitations due to their sparse spatiotemporal distribution. Remote sensing techniques, including altimeters, SAR and wave spectrometers, offer new avenues for wave observation, helping to address the issue of sparse spatiotemporal resolution in traditional methods. However, the challenge remains in efficiently and accurately obtaining large-scale continuous wave data.

This study utilizes multi-source satellite remote sensing observation data, buoy measurements and reanalysis data. Deep learning techniques are employed to investigate the spatiotemporal expansion of wave remote sensing data. This includes intelligent inversion of wide swath ocean wave height based on multiple satellite scatterometer data, spatial gap filling of wide swath wave height data, and prediction of a two-dimensional wave height field. Specifically, the study focuses on wide swath wave height inversion using HY-2B/C/D and CFOSAT synchronous observations of sea surface wind field and ocean wave height data through deep learning methods. The DINCAE method is utilized for the fusion of HY-2B/C/D wide swath ocean wave height data, resulting in global ocean wave height reconstruction grid data. Additionally, the ConvLSTM model is used for prediction research on the global ocean wave height reconstruction grid data. This study introduces a novel method for acquiring comprehensive global ocean wave remote sensing data with high spatiotemporal coverage.