期刊
INTERNATIONAL JOURNAL OF BIOMETEOROLOGY
卷 55, 期 2, 页码 235-241出版社
SPRINGER
DOI: 10.1007/s00484-010-0329-x
关键词
Ganoderma sp.; Artificial neural network; Multivariate regression tree; Meteorological parameter
Ganoderma sp. is an airborne fungal spore type known to trigger respiratory allergy symptoms in sensitive patients. Aiming to reduce the risk for allergic individuals, we analysed fungal spore circulation in Szczecin, Poland, and its dependence on meteorological conditions. Statistical models for the airborne spore concentrations of Ganoderma sp.-one of the most abundant fungal taxa in the area-were developed. Aerobiological sampling was conducted over 2004-2008 using a volumetric Lanzoni trap. Simultaneously, the following meteorological parameters were recorded: daily level of precipitation, maximum and average wind speed, relative humidity and maximum, minimum, average and dew point temperatures. These data were used as the explaining variables. Due to the non-linearity and non-normality of the data set, the applied modelling techniques were artificial neural networks (ANN) and mutlivariate regression trees (MRT). The obtained classification and MRT models predicted threshold conditions above which Ganoderma sp. appeared in the air. It turned out that dew point temperature was the main factor influencing the presence or absence of Ganoderma sp. spores. Further analysis of spore seasons revealed that the airborne fungal spore concentration depended only slightly on meteorological factors.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据