Spatiotemporal Prediction of Monthly Coastal Upwelling Scenario in SST Fields Using Deep-Learning-Based Models

Abstract

This study leverages advancements in deep learning (DL) to enhance the analysis of satellite image time series (SITSs) in marine geoscience, focusing on the prediction of sea surface temperature (SST) and the detection of coastal upwelling. By employing convolutional neural networks (CNNs) and recurrent neural networks (RNNs), including long short-term memory (LSTM) networks, we introduce a novel approach utilizing convolutional LSTM (ConvLSTM) and 3-D Unet-LSTM models. These techniques provide a nuanced analysis and understanding of complex oceanographic phenomena, specifically coastal upwelling, which significantly impacts marine ecosystems and climate. The adoption of these sophisticated DL models has led to a notable improvement in predicting SST fields, achieving a reduction in root mean square error (RMSE) to 0.038 and an increase in the correlation coefficient (CC) to 0.95. This enhancement over the baseline ConvLSTM model, which had an RMSE of 0.045 and a CC of 0.92, underscores our models’ capability to accurately capture the dynamic and intricate nature of coastal upwelling. The results offer promising directions for future research in marine geoscience and remote-sensing applications, highlighting the potential of DL techniques in interpreting intricate patterns in satellite-derived data and improving predictions in environmental sciences.