Fig. 5: Schematic diagram of the structures of the FuXi Subseasonal-to-Seasonal (FuXi-S2S) model.
From: A machine learning model that outperforms conventional global subseasonal forecast models
a Inference stage of the FuXi-S2S model. ht represents the hidden feature generated by the Encoder from the input data. The perturbation vector zt is generated by the perturbation module, resulting in the perturbed hidden feature \({\tilde{{{{\rm{h}}}}}}^{t}\). b Training stage of the FuXi-S2S model. \({{{\rm{N}}}}({\Theta }_{p}^{t})\) and \({{{\rm{N}}}}({\Theta }_{q}^{t})\) are the low-rank multivariate Gaussian distributions generated by encoders P and Q, respectively. The Kullback–Leibler (KL) divergence loss measures the discrepancy between the distributions predicted by both encoders, \({{{\rm{N}}}}({\Theta }_{p}^{t})\) and \({{{\rm{N}}}}({\Theta }_{q}^{t})\).
