天津气传花粉预测模型研究

Study of Airborne Pollen Prediction Model

使用1999～2004年3～10月天津市河西区铁塔花粉监测数据和同地点的气候观测站(54517)气象资料,进行了天津市72h气传花粉浓度预测模型研究。设计了全花粉季、分季节(春、夏、秋)、分阶段的3种不同预测方案,利用多元线性和非线性回归技术分别建立了花粉预测模型,并对各个方案及预测模型进行了对比分析。结果发现,除夏季以外,多元非线性预测模型优于多元线性回归预测模型,分阶段预测方案优于全花粉季和分季节预测方案,且预测准确率也随之提高。

The 72-hour airborne pollen concentration （PMPC） prediction model is devised by using the observation data of pollen from the meteorological observing tower in the Hexi district of Tianjin from 1999 to 2004 and the conventional meteorological data. The different PMPC models are established by means of the multiple linear/nonlinear regression techniques with three schemes for the whole pollen season, spring, summer, and autumn, as well as for various stages, respectively. The comparisons are also conducted between various schemes and models. The results show that the multiple nonlinear regression method is better than that of linear one, and the vari-season scheme is better than others, except that for summer.