Skip to main content
QUICK REVIEW

[论文解读] ACE2-SOM: Coupling an ML atmospheric emulator to a slab ocean and learning the sensitivity of climate to changed CO$_2$

Spencer K. Clark, Oliver Watt‐Meyer|arXiv (Cornell University)|Dec 5, 2024
Ocean Acidification Effects and Responses被引用 4
一句话总结

ACE2-SOM 提出了一种机器学习大气模拟器(ACE2-SOM),与滑动海洋模型耦合,以高效模拟二氧化碳强迫下的气候敏感性。通过在高分辨率气候模型数据上进行训练,该模型准确再现了辐射通量、降水和大气动力学,以极低的计算成本实现了3xCO₂平衡气候响应的高保真模拟。

ABSTRACT

While autoregressive machine-learning-based emulators have been trained to produce stable and accurate rollouts in the climate of the present-day and recent past, none so far have been trained to emulate the sensitivity of climate to substantial changes in CO$_2$ or other greenhouse gases. As an initial step we couple the Ai2 Climate Emulator version 2 to a slab ocean model (hereafter ACE2-SOM) and train it on output from a collection of equilibrium-climate physics-based reference simulations with varying levels of CO$_2$. We test it in equilibrium and non-equilibrium climate scenarios with CO$_2$ concentrations seen and unseen in training. ACE2-SOM performs well in equilibrium-climate inference with both in-sample and out-of-sample CO$_2$ concentrations, accurately reproducing the emergent time-mean spatial patterns of surface temperature and precipitation change with CO$_2$ doubling, tripling, or quadrupling. In addition, the vertical profile of atmospheric warming and change in extreme precipitation rates up to the 99.9999th percentile closely agree with the reference model. Non-equilibrium-climate inference is more challenging. With CO$_2$ increasing gradually at a rate of 2% year$^{-1}$, ACE2-SOM can accurately emulate the global annual mean trends of surface and lower-to-middle atmosphere fields but produces unphysical jumps in stratospheric fields. With an abrupt quadrupling of CO$_2$, ML-controlled fields transition unrealistically quickly to the 4xCO$_2$ regime. In doing so they violate global energy conservation and exhibit unphysical sensitivities of and surface and top of atmosphere radiative fluxes to instantaneous changes in CO$_2$. Future emulator development needed to address these issues should improve its generalizability to diverse climate change scenarios.

研究动机与目标

  • 开发一种计算高效的气候模拟器,以捕捉在二氧化碳条件改变下的关键气候反馈。
  • 将基于机器学习的大气模拟器(ACE2-SOM)与滑动海洋模型耦合,以模拟平衡气候状态。
  • 学习并再现辐射通量、降水和大气动力学对二氧化碳强迫变化的敏感性。
  • 将模拟器性能与高分辨率气候模型在1x和3xCO₂条件下的模拟结果进行验证。
  • 与完整的大气环流模型相比,实现在极低计算开销下对气候敏感性的快速探索。

提出的方法

  • 在高分辨率气候模型(SHiELD-SOM)输出数据上训练机器学习模型(ACE2-SOM),以模拟大气动力学和辐射过程。
  • 使用滑动海洋模型表示海洋热吸收和海表温度演变,其中海冰和海洋覆盖比例作为随时间变化的输入。
  • 输入变量包括大气状态(温度、风速、湿度)、地表条件(2米气温、气压)以及强迫因子(CO₂、地形、陆地覆盖比例)。
  • 模型预测关键诊断变量,如顶气候(TOA)和地表辐射通量、潜热和感热通量,以及500 hPa高度等大气状态变量。
  • 模拟器被训练以预测时间平均值(均值)和瞬时值(快照)变量,重点关注辐射和水文反馈。
  • 该框架通过学习大气对二氧化碳扰动的非线性响应,实现了在1x和3xCO₂强迫下对平衡气候状态的快速模拟。
Figure 1: Histograms of daily-mean precipitation rate in C96 SHiELD-SOM (black) and ACE2-SOM (blue) in the 1xCO 2 (thin lines) and 3xCO 2 (thick lines) equilibrium climates at \qty 1 resolution.
Figure 1: Histograms of daily-mean precipitation rate in C96 SHiELD-SOM (black) and ACE2-SOM (blue) in the 1xCO 2 (thin lines) and 3xCO 2 (thick lines) equilibrium climates at \qty 1 resolution.

实验结果

研究问题

  • RQ1机器学习大气模拟器在3xCO₂强迫下能否高保真地再现辐射通量和降水?
  • RQ2与完整的大气环流模型相比,ACE2-SOM框架预测的平衡气候敏感性(ECS)如何?
  • RQ3该模拟器在二氧化碳强迫下能否准确捕捉大气环流的变化,如500 hPa高度和850 hPa温度的变化?
  • RQ4在气候变化条件下,该模拟器能否保持对水文循环分量(如降水和水汽路径变化率)的高保真再现?
  • RQ5将机器学习模拟器与滑动海洋模型耦合,对平衡气候状态的稳定性和真实性有何影响?

主要发现

  • ACE2-SOM在3xCO₂强迫下成功以高保真度再现了平衡气候状态,与SHiELD-SOM模拟结果对比验证了其有效性。
  • 模拟器准确捕捉了日均降水直方图的变化,显示出在3xCO₂条件下强降水事件的强度和频率均有所增加。
  • 顶气候(TOA)和地表辐射通量(如DSWRF、ULWRF)被准确预测,表明辐射反馈得到恰当表征。
  • 模型对500 hPa位势高度和850 hPa温度等关键大气变量的模拟结果与参考模拟高度一致。
  • 潜热和感热通量对二氧化碳强迫的响应合理,表明地表能量交换过程被准确模拟。
  • 该框架以远低于完整大气候模型的计算成本,实现了快速气候模拟,展现出其在高效气候敏感性研究中的巨大潜力。

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。