A comparison of metrics for assessing state-of-the-art climate models and implications for probabilistic projections of climate change
A comparison of metrics for assessing state-of-the-art climate models and implications for probabilistic projections of climate change
复制标题
DOI：
10.1007/s00382-017-3737-3
复制
发表时间：
2018-03
期刊：
影响因子：
4.6
通讯作者：
Christoph Ring;F. Pollinger;Irena Kaspar‐Ott;E. Hertig;J. Jacobeit;H. Paeth
中科院分区：
文献类型：
--
作者：
Christoph Ring;F. Pollinger;Irena Kaspar‐Ott;E. Hertig;J. Jacobeit;H. Paeth
气候科学的一项主要任务是对未来气候变化进行可靠的预测。为了使结果更可靠并减少不确定性的范围，我们采用2 × 2列联表方法对全球大气环流模式和区域气候模式进行了评估，以生成模式权重。这些权重之间的比较不同的方法和概率预测的温度和降水变化的影响进行了研究。模拟的季节性降水和温度的50年的趋势和气候的手段进行了评估，在两个空间尺度：在七个研究区域周围的地球仪和八个分区域的地中海地区。总体而言，耦合模型比对项目第3阶段的24个模型和第5阶段的38个模型，针对20世纪的ERA-20 C再分析，总共评估了四种排放情景的159个降水瞬态模拟和119个温度瞬态模拟。结果表明，与以前的模型评价研究高度一致。这些指标表明，降水量的平均值和温度的平均值和趋势与参考数据集一致，并表明最近的集合平均值，特别是温度的改善。该方法是高度可转移到气候科学的各种进一步的应用。总体而言，模拟质量存在区域差异，但这些差异不如50年平均值和趋势结果之间的差异明显。趋势结果适合于为气候模式分配权重因子。然而，概率气候预测的影响严格依赖于地区和季节。
A major task of climate science are reliable projections of climate change for the future. To enable more solid statements and to decrease the range of uncertainty, global general circulation models and regional climate models are evaluated based on a 2 × 2 contingency table approach to generate model weights. These weights are compared among different methodologies and their impact on probabilistic projections of temperature and precipitation changes is investigated. Simulated seasonal precipitation and temperature for both 50-year trends and climatological means are assessed at two spatial scales: in seven study regions around the globe and in eight sub-regions of the Mediterranean area. Overall, 24 models of phase 3 and 38 models of phase 5 of the Coupled Model Intercomparison Project altogether 159 transient simulations of precipitation and 119 of temperature from four emissions scenarios are evaluated against the ERA-20C reanalysis over the 20th century. The results show high conformity with previous model evaluation studies. The metrics reveal that mean of precipitation and both temperature mean and trend agree well with the reference dataset and indicate improvement for the more recent ensemble mean, especially for temperature. The method is highly transferrable to a variety of further applications in climate science. Overall, there are regional differences of simulation quality, however, these are less pronounced than those between the results for 50-year mean and trend. The trend results are suitable for assigning weighting factors to climate models. Yet, the implications for probabilistic climate projections is strictly dependent on the region and season.