WRF模式对高影响浙江型台风微物理和边界层参数化方案的优化试验

OPTIMIZATION TEST FOR MICROPHYSICAL AND BOUNDARY LAYER PARAMETERIZATION OF HIGH-IMPACT ZHEJIANG TYPHOONS BY WRF MODEL

选取近年来在浙江和福建登陆高影响浙江的9个西太平洋台风,利用WRF中尺度数值模式,选取多种微物理和边界层参数化方案,量化评估不同方案下的台风路径、强度和降水的模拟性能。结果表明,Kessler和SBU-YLin微物理方案对台风路径和强度模拟较好;而SBU-YLin在浙江降水上比Kessler评分相对更优、误差更小、相关性更佳,但其漏报率相对较高。MYNN2和BouLac边界层方案的最优台风路径和强度比例较高,而BouLac对浙江降水有更好的表现,其降水误差更小、相关性更好,且有更高的TS评分,特别是大雨以上量级或台风登陆前12 h。因此,SBU-YLin微物理和BouLac边界层方案相对更适合浙江台风模拟。此外,浙江沿海地区模拟雨量比实况偏少,且绝对误差较大,内陆反之;雨量误差与浙江地形有较好的对应关系。

This paper selected nine Western Pacific typhoons that had highimpact on Zhejiang in recent years to find a relatively good parameterization scheme for local typhoon forecasting based on the WRF mesoscale model. We evaluated the simulating performance on typhoon track, intensity and precipitation under different microphysical and boundary layer schemes. The results indicated that for microphysical schemes, the Kessler and SBU-YLin were better for simulating typhoon track and intensity while the SBU-YLin had better precipitation scores, smaller errors and better correlation than the Kessler, but the missing report rate was comparatively high, when it comes to Zhejiang precipitation. For PBL schemes, the MYNN2 and BouLac had higher proportions in the best typhoon track and intensity schemes, while the BouLac had a better precipitation effect, which had smaller precipitation errors, better correlation and better TS scores, particularly in more-than-heavy rain levels or during the 12 hours before typhoon landfall. Therefore the SBU-YLin and BouLac schemes were more suitable for simulating Zhejiang typhoons. In addition, the simulated precipitation was less than the reality, with the absolute errors significantly larger in the coastal region of Zhejiang. The opposite is true for the inlandarea. The rainfall errors corresponded well with terrains in Zhejiang.