A spatiotemporal attention-augmented ConvLSTM model for ocean remote sensing reflectance prediction

Abstract

Remote sensing reflectance (Rrs) is an essential parameter in ocean color remote sensing and a fundamental input for the estimation of ocean color elements. Predicting Rrs has the potential to enable simultaneous prediction of multiple marine environmental parameters, facilitating multi-perspective analysis of marine environmental changes. This paper proposes a spatiotemporal attention-augmented ConvLSTM-based model for ocean Rrs prediction. The developed model can predict Rrs for up to seven days by simultaneously learning spatiotemporal features from time series Rrs and auxiliary environmental variables. According to the experiments, the proposed model achieves optimal performances on Rrs predictions at 443, 488, and 555 nm, with Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE) for the first four prediction days less than 5.6*10-4 sr-1 and 8.6 %, respectively, which are better than the performance of the convolutional neural network (CNN), the LSTM, CNN-LSTM, and the ConvLSTM. The spatial and temporal variations of Rrs are also compared to evaluate the effectiveness of the model, presenting a consistent spatiotemporal pattern between predicted and observed Rrs. We also found that integrating sea surface temperature (SST), photosynthetically available radiation (PAR), and aerosol optical thickness at 869 nm (AOT869) into the model can improve the prediction accuracy in various degrees. This work suggests the proposed deep learning model can predict Rrs for 7 days with a convincing performance, providing critical data and technical support for ocean-related applications, such as algae bloom monitoring.