New neural framework improves long-horizon PDE forecasting

Researchers have developed a new neural forecasting framework called Latent Structured Spectral Propagators (SSP) to improve the long-horizon forecasting of time-dependent partial differential equations (PDEs). This method addresses the error accumulation and dynamic drift issues common in existing neural operators when used autoregressively. SSP reformulates PDE rollout by learning a propagator in a latent space, separating physical state mapping, projection into a compact propagation state, and spectral mode evolution, which enhances stability and accuracy in temporal extrapolation. AI

影响 Introduces a novel method for more stable and accurate long-term forecasting of complex physical systems, potentially impacting scientific simulation and prediction.

排序理由 The cluster contains a new academic paper detailing a novel method for scientific forecasting. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

• Latent Structured Spectral Propagators
• partial differential equations

• 论文
• 模型发布

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →