用机器学习模拟海冰变化，跨气候条件更准且守恒质量
FloeNet: A mass-conserving global sea ice emulator that generalizes across climates
- 基于物理模型数据训练的守恒型海冰机器学习模型
- 南极海冰体积相关性超0.96，北极超0.76，跨气候泛化能力强
- 输出可解释的物理解释结果，适合气候模拟与极地研究者
我们提出FloeNet，一个基于地球物理流体动力学实验室全球海冰模型SIS2训练的机器学习代理模型。FloeNet是一个质量守恒模型，能模拟海冰及雪-海冰系统在6小时内的质量与面积变化趋势，包括生长、融化和输运过程。训练数据来自再分析强迫的冰-海洋模拟，测试其在前工业控制态与1% CO2气候下的泛化能力。相比非守恒模型，FloeNet在再现海冰与雪-海冰平均状态、趋势及年际变率方面表现更优，南极体积异常相关性达0.96以上，北极达0.76以上，覆盖所有强迫情景。同时，模型正确区分热力与动力响应，具备物理可解释性。此外，其输出包含高保真耦合变量，如冰面表层温度、冰到海洋盐通量及融化能量通量。我们推测FloeNet可提升现有大气与海洋代理模型中的极地气候过程模拟精度。
原文摘要 · Abstract (English)
We introduce FloeNet, a machine-learning emulator trained on the Geophysical Fluid Dynamics Laboratory global sea ice model, SIS2. FloeNet is a mass-conserving model, emulating 6-hour mass and area budget tendencies related to sea ice and snow-on-sea-ice growth, melt, and advection. We train FloeNet using simulated data from a reanalysis-forced ice-ocean simulation and test its ability to generalize to pre-industrial control and 1% CO2 climates. FloeNet outperforms a non-conservative model at reproducing sea ice and snow-on-sea-ice mean state, trends, and inter-annual variability, with volume anomaly correlations above 0.96 in the Antarctic and 0.76 in the Arctic, across all forcings. FloeNet also produces the correct thermodynamic vs dynamic response to forcing, enabling physical interpretability of emulator output. Finally, we show that FloeNet outputs high-fidelity coupling-related variables, including ice-surface skin temperature, ice-to-ocean salt flux, and melting energy fluxes. We hypothesize that FloeNet will improve polar climate processes within existing atmosphere and ocean emulators.
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。