中国降水季节性的预估

Projection of Precipitation Seasonality over China

本文使用国际耦合模式比较计划第五阶段(CMIP5)中共46个全球气候模式的数值试验数据,通过评估择优选取了14个模式来预估21世纪中国各季节降水百分率及其变率。结果表明,模式集合平均能够较好地模拟各季节降水百分率及其变率,但模式与观测间、各模式间都存在一定不同,空间上西部差异较大,季节上夏季差异明显。21世纪中国降水百分率整体表现为夏季大冬季小,但存在区域性,如华南春季降水百分率大于夏季。与1986～2004年相比,中国降水百分率整体表现为在夏季显著减少,冬春季显著增加,但高原则与之相反。此外,模式对于长江中下游地区降水百分率的预估存在较大不确定性。RCP8.5情景下降水季节性变幅要大于RCP4.5情景。降水季节性的变率在四季均表现出一定的增加趋势,但21世纪早、中和末期与1986～2004年相比并无显著差异(置信水平为95%)。

Based on historical experiments of 46 Coupled Model Intercomparison Project Phase Five（CMIP5） models, all models are systematically evaluated, and 14 models with reliable performance are chosen to project seasonal precipitation proportion and its variability over China in the 21 st century. It is found that the 14-model ensemble reasonably simulates the observed seasonal proportion of precipitation and its variability, while there are some differences between models and observations and between individual models. The differences are relatively large in western China and in the summer. For the whole country, seasonal precipitation proportion is the highest in the summer and lowest in the winter during the 21 st century. The spatial pattern is region-dependent, for example, the proportion of precipitation in South China is larger in the spring than in the summer. Compared to that during 1986–2004, there is a significantly decreasing trend in the summer and an increasing trend in the winter and spring, whereas an increasing trend in the summer and a decreasing trend in the winter and spring are found for the Tibetan Plateau in the 21 st century. In addition, the model results have considerable uncertainties with respect to the projection of precipitation in the middle and lower Yangtze River basin. The Representative Concentration Pathways 8.5（RCP8.5） scenario shows a higher rate of seasonal change than the RCP4.5 scenario does. The variability of seasonal precipitation proportion has an increasing trend in all seasons, but there is no statistically significant difference at the 95% confidence level in the early, middle, and late 21 st century compared with the 1986–2004 period.