Cross-Scale Reservoir Computing for large spatio-temporal forecasting and modeling
This is an incremental improvement for researchers in spatiotemporal forecasting, specifically applied to climate data like Sea Surface Temperature.
The paper tackles forecasting high-resolution spatiotemporal data by proposing a cross-scale reservoir computing method that combines multi-resolution inputs, and it outperforms standard models in long-term Sea Surface Temperature forecasting with improved predictive accuracy.
We propose a new reservoir computing method for forecasting high-resolution spatiotemporal datasets. By combining multi-resolution inputs from coarser to finer layers, our architecture better captures both local and global dynamics. Applied to Sea Surface Temperature data, it outperforms standard parallel reservoir models in long-term forecasting, demonstrating the effectiveness of cross-layers coupling in improving predictive accuracy. Finally, we show that the optimal network dynamics in each layer become increasingly linear, revealing the slow modes propagated to subsequent layers.