Binned Spectral Power Loss for Improved Prediction of Chaotic Systems

ArXi:2502.00472v3 Announce Type: replace Forecasting multiscale chaotic dynamical systems, such as turbulent flows, with deep learning remains a formidable challenge due to the spectral bias of neural networks, which hinders the accurate representation of fine-scale structures in long-term predictions. This issue is exacerbated when models are deployed autoregressively, leading to compounding errors and instability. In this work, we