Fig. 8
From: Ocean environment prediction methods based on deep learning and spatiotemporal feature fusion
Multi-time scale prediction index comparison across models, compares the performance of MSSTN and baseline models at different forecasting horizons. Lower IMAPE and IRMSEL indicate better prediction accuracy. The results show that MSSTN consistently achieves lower error values across all time scales, confirming its ability to maintain accuracy even in longer-term forecasts.
