Forecasting model of Corylus, Alnus, and Betula pollen concentration levels using spatiotemporal correlation properties of pollen count |
| |
| Authors: | Jakub Nowosad Alfred Stach Idalia Kasprzyk Elżbieta Weryszko-Chmielewska Krystyna Piotrowska-Weryszko Małgorzata Puc Łukasz Grewling Anna Pędziszewska Agnieszka Uruska Dorota Myszkowska Kazimiera Chłopek Barbara Majkowska-Wojciechowska |
| |
| Affiliation: | 1.Institute of Geoecology and Geoinformation,Adam Mickiewicz University,Poznań,Poland;2.Department of Environmental Biology,University of Rzeszów,Rzeszów,Poland;3.Department of Botany,University of Life Sciences in Lublin,Lublin,Poland;4.Department of General Ecology,University of Life Sciences in Lublin,Lublin,Poland;5.Department of Botany and Nature Conservation,University of Szczecin,Szczecin,Poland;6.Laboratory of Aeropalynology, Faculty of Biology,Adam Mickiewicz University,Poznań,Poland;7.Department of Plant Ecology,University of Gdańsk,Gdańsk,Poland;8.Department of Clinical and Environmental Allergology,Jagiellonian University Medical College,Kraków,Poland;9.Faculty of Earth Sciences,University of Silesia,Sosnowiec,Poland;10.Department of Immunology, Rheumatology and Allergy, Faculty of Medicine,Medical University,?ód?,Poland |
| |
| Abstract: | The aim of the study was to create and evaluate models for predicting high levels of daily pollen concentration of Corylus, Alnus, and Betula using a spatiotemporal correlation of pollen count. For each taxon, a high pollen count level was established according to the first allergy symptoms during exposure. The dataset was divided into a training set and a test set, using a stratified random split. For each taxon and city, the model was built using a random forest method. Corylus models performed poorly. However, the study revealed the possibility of predicting with substantial accuracy the occurrence of days with high pollen concentrations of Alnus and Betula using past pollen count data from monitoring sites. These results can be used for building (1) simpler models, which require data only from aerobiological monitoring sites, and (2) combined meteorological and aerobiological models for predicting high levels of pollen concentration. |
| |
| Keywords: | |
| 本文献已被 SpringerLink 等数据库收录！ |
|
