Sellevold Raymond, Vizcaino Miren
Geoscience and Remote Sensing Delft University of Technology Delft The Netherlands.
Geophys Res Lett. 2021 Aug;48(16):e2021GL092449. doi: 10.1029/2021GL092449. Epub 2021 Aug 19.
Future Greenland ice sheet (GrIS) melt projections are limited by the lack of explicit melt calculations within most global climate models and the high computational cost of dynamical downscaling with regional climate models (RCMs). Here, we train artificial neural networks (ANNs) to obtain relationships between quantities consistently available from global climate model simulations and annually integrated GrIS surface melt. To this end, we train the ANNs with model output from the Community Earth System Model 2.1 (CESM2), which features an interactive surface melt calculation based on a downscaled surface energy balance. We find that ANNs compare well with an independent CESM2 simulation and RCM simulations forced by a CMIP6 subset. The ANNs estimate a melt increase for 2,081-2,100 ranging from 414 275 Gt (SSP1-2.6) to 1,378 555 Gt (SSP5-8.5) for the full CMIP6 suite. The primary source of uncertainty throughout the 21st century is the spread of climate model sensitivity.
未来格陵兰冰盖（GrIS）融化的预测受到限制，这是因为大多数全球气候模型缺乏明确的融化计算，且使用区域气候模型（RCMs）进行动力降尺度的计算成本很高。在这里，我们训练人工神经网络（ANNs），以获取全球气候模型模拟中始终可用的量与格陵兰冰盖每年综合表面融化之间的关系。为此，我们使用社区地球系统模型2.1（CESM2）的模型输出训练人工神经网络，该模型基于降尺度的表面能量平衡进行交互式表面融化计算。我们发现，人工神经网络与独立的CESM2模拟以及由CMIP6子集驱动的RCM模拟结果吻合良好。对于完整的CMIP6数据集，人工神经网络估计2081年至2100年融化增加量在414±275 Gt（SSP1-2.6）至1378±555 Gt（SSP5-8.5）之间。整个21世纪不确定性的主要来源是气候模型敏感性的差异。
