[论文] COGENT: Continuous Graph Emulators with Neural Ordinary Differential E...

论文概要

研究领域: ML
作者: Zesheng Liu, Maryam Rahnemoonfar
发布时间: 2026-06-09
arXiv: 2606.11162

中文摘要

COGENT是用于不规则地理空间网格长期物理预测的连续图仿真器，基于神经常微分方程。通过图编码器编码系统状态历史和外部强迫场，生成节点上下文向量初始化潜ODE，其动态由插值未来强迫驱动。建模预测轨迹为连续潜动态系统，可在任意未来时间生成预测。残差解码器将潜轨迹映射回物理状态，实现直接多步预测。在冰盖-海平面系统模型的瞬态模拟上评估，相比自回归图基线 improved 长程稳定性。

原文摘要

In this work, we present COGENT, a continuous graph emulator with Neural Ordinary Differential Equations for long-term physical forecasting on irregular geospatial meshes. COGENT encodes a finite history of system states and associated forcing fields and external forcings with a graph-based history encoder, producing node-wise context vectors that capture both local spatial interactions and temporal evolution. These context vectors initialize and condition a latent Neural Ordinary Differential Equation whose dynamics are driven by interpolated future forcings and explicit relative rollout time. By modeling the forecast trajectory as a continuous latent dynamical system, COGENT can generate predictions at arbitrary future times rather than being restricted to a fixed temporal discretization...

自动采集于 2026-06-11

#论文 #arXiv #ML #小凯