资源环境科技发展态势分析平台

Forecasting monsoon rainfall using dynamical climate models has met with little success, partly due to models' inability to represent the monsoon climatological state accurately. In this article the nature and dynamical causes of their biases are investigated. The approach is to analyze errors in multimodel-mean climatological fields determined from CMIP5, and to carry out sensitivity experiments using a coupled model [the Coupled Model for the Earth Simulator (CFES)] that does represent the monsoon realistically. Precipitation errors in the CMIP5 models persist throughout the annual cycle, with positive (negative) errors occurring over the near-equatorial western Indian Ocean (South Asia). Model errors indicate that an easterly wind stress bias Dt along the equator begins during April-May and peaks during November; the severity of the Dt is that the Wyrtki jets, eastward-flowing equatorial currents during the intermonsoon seasons (April-May and October-November), are almost eliminated. An erroneous east-west SST gradient (warm west and cold east) develops in June. The structure of the model errors indicates that they arise from Bjerknes feedback in the equatorial Indian Ocean (EIO). Vertically integrated moisture and moist static energy budgets confirm that warm SST bias in the western EIO anchors moist processes that cause the positive precipitation bias there. In CFES sensitivity experiments in which Dt or warm SST bias over the western EIO is artificially introduced, errors in the EIO are similar to those in the CMIP5 models; moreover, precipitation over South Asia is reduced. An overall implication of these results is that South Asian rainfall errors in CMIP5 models are linked to errors of coupled processes in the western EIO, and in coupled models correct representation of EIO coupled processes (Bjerknes feedback) is a necessary condition for realistic monsoon simulation.