ClimateBench v1.0: A Benchmark for Data‐Driven Climate Projections
ClimateBench v1.0: A Benchmark for Data‐Driven Climate Projections
复制标题
DOI：
10.1029/2021ms002954
复制
发表时间：
2022-09
影响因子：
6.8
通讯作者：
D. Watson‐Parris;Y. Rao;D. Oliviè;Ø. Seland;P. Nowack;Gustau Camps-Valls;P. Stier;S. Bouabid;M. Dewey;E. Fons;J. Gonzalez;P. Harder;K. Jeggle;J. Lenhardt;P. Manshausen;M. Novitasari;L. Ricard;C. Roesch
中科院分区：
文献类型：
--
作者：
D. Watson‐Parris;Y. Rao;D. Oliviè;Ø. Seland;P. Nowack;Gustau Camps-Valls;P. Stier;S. Bouabid;M. Dewey;E. Fons;J. Gonzalez;P. Harder;K. Jeggle;J. Lenhardt;P. Manshausen;M. Novitasari;L. Ricard;C. Roesch
有许多不同的排放途径与巴黎气候协议兼容，还有更多的排放途径可能无法实现这一目标。虽然一些最复杂的地球系统模型模拟了一小部分共享社会经济路径，但使用这些昂贵的模型来充分探索可能性是不切实际的。因此，这种探索主要依赖于一维脉冲响应模型，或简单的模式缩放方法来近似物理气候对给定情景的响应。在这里，我们提出了ClimateBench-第一个基准框架，该框架基于一套耦合模型相互比较项目，AerChemMIP和检测归因模型相互比较项目模拟，由一个完整的复杂性地球系统模型执行，以及一组基线机器学习模型，模拟其对各种强制因素的响应。这些模拟器可以预测全球温度、昼夜温差和降水量（包括极端降水量）的年平均分布，并给出二氧化碳、甲烷和气溶胶的各种排放量和浓度，使它们能够有效地探测以前未探索过的情景。我们讨论这些仿真器的准确性和可解释性，并考虑其鲁棒性的物理约束，如总能量守恒。未来的机会，将这种物理约束直接在机器学习模型，并使用模拟器的检测和归因研究进行了讨论。这为改进预测、鲁棒性和数学易处理性提供了广泛的机会。我们希望通过明确的例子和指标来阐述气候模型仿真的原则，鼓励统计学家和机器学习专家积极参与，以应对这一重要而艰巨的挑战。
Many different emission pathways exist that are compatible with the Paris climate agreement, and many more are possible that miss that target. While some of the most complex Earth System Models have simulated a small selection of Shared Socioeconomic Pathways, it is impractical to use these expensive models to fully explore the space of possibilities. Such explorations therefore mostly rely on one‐dimensional impulse response models, or simple pattern scaling approaches to approximate the physical climate response to a given scenario. Here we present ClimateBench—the first benchmarking framework based on a suite of Coupled Model Intercomparison Project, AerChemMIP and Detection‐Attribution Model Intercomparison Project simulations performed by a full complexity Earth System Model, and a set of baseline machine learning models that emulate its response to a variety of forcers. These emulators can predict annual mean global distributions of temperature, diurnal temperature range and precipitation (including extreme precipitation) given a wide range of emissions and concentrations of carbon dioxide, methane and aerosols, allowing them to efficiently probe previously unexplored scenarios. We discuss the accuracy and interpretability of these emulators and consider their robustness to physical constraints such as total energy conservation. Future opportunities incorporating such physical constraints directly in the machine learning models and using the emulators for detection and attribution studies are also discussed. This opens a wide range of opportunities to improve prediction, robustness and mathematical tractability. We hope that by laying out the principles of climate model emulation with clear examples and metrics we encourage engagement from statisticians and machine learning specialists keen to tackle this important and demanding challenge.