A Data-Driven Multiple Parametric Field-Coupled Co-Forecasting Approach for Accurately Forecasting Sea Surface Temperature and Geostrophic Current Field Simultaneously Based on a Deep Learning Method

Accurate spatiotemporal forecasting of sea surface temperature (SST) makes a great difference to offshore wind power development, since SST is a crucial factor influencing wind field patterns. In this work, a remote sensing-driven, multi-parameter field-coupled co-forecasting approach is proposed to utilize the cross-field interaction mechanisms among different physical fields to enhance forecasting performance. With this approach, more than one physical field can be simultaneously forecasted, thus improving forecasting efficiency. Compared with pure SST forecasting cases, the advanced enhancement of SST forecasting performance based on this approach is achieved by coupling SST with geostrophic current (GC) in data-driven forecasting. Also, both the spatiotemporal SST and GC fields are demonstrated to be accurately forecasted simultaneously. In addition, the causal effects between SST and GC are demonstrated as a reliable factor for evaluating the coupling scheme. To further improve co-forecasting performance, an exponential cross-entropy loss function is proposed for multi-physical field co-forecasting scenes, and shows more satisfying performance than a classical cross-entropy loss function. The results demonstrate that the data-driven multi-physical field-coupled co-forecasting approach is an advanced, highly efficient method that can accurately forecast more than one physical field at the same time.