Cross-Scale Reservoir Computing for large spatio-temporal forecasting and modeling
Machine Learning
2025-10-14 v1 Computational Physics
Abstract
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.
Cite
@article{arxiv.2510.11209,
title = {Cross-Scale Reservoir Computing for large spatio-temporal forecasting and modeling},
author = {Nicola Alboré and Gabriele Di Antonio and Fabrizio Coccetti and Andrea Gabrielli},
journal= {arXiv preprint arXiv:2510.11209},
year = {2025}
}