用图神经网络替代气候模型，提速千倍且精度达标。
Graph Convolutional Neural Networks as Surrogate Models for Climate Simulation
- 用GCNN构建气候模拟代理模型，替代复杂微分方程系统。
- 80年气候模拟仅需310秒，均温误差低于0.1℃，最大误差低于2℃。
- 适合需要快速评估的气候研究前期工作，提升实验效率。
许多气候过程由大量非线性微分方程描述；加之参数化复杂相互作用所需的数据量巨大，地球系统模型（ESM）在大型集群上运行一次可能需数周时间。不确定性量化往往需要数千次运行，使ESM在初步评估中难以应用。传统方法包括简化模型过程，但近期研究更聚焦于使用机器学习补充甚至完全替代这些模型。本文利用机器学习，特别是全连接神经网络（FCNN）和图卷积神经网络（GCNN），实现快速模拟与不确定性量化，以支持更广泛的ESM模拟。所提出的代理模型在单个A100 GPU上仅用约310秒即完成80年模拟，而原ESM模型需数周时间，且均温误差低于0.1℃，最大误差低于2℃。
原文摘要 · Abstract (English)
Many climate processes are characterized using large systems of nonlinear differential equations; this, along with the immense amount of data required to parameterize complex interactions, means that Earth-System Model (ESM) simulations may take weeks to run on large clusters. Uncertainty quantification may require thousands of runs, making ESM simulations impractical for preliminary assessment. Alternatives may include simplifying the processes in the model, but recent efforts have focused on using machine learning to complement these models or even act as full surrogates. \textit{We leverage machine learning, specifically fully-connected neural networks (FCNNs) and graph convolutional neural networks (GCNNs), to enable rapid simulation and uncertainty quantification in order to inform more extensive ESM simulations.} Our surrogate simulated 80 years in approximately 310 seconds on a single A100 GPU, compared to weeks for the ESM model while having mean temperature errors below $0.1^{\circ}C$ and maximum errors below $2^{\circ}C$.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。