Please use this identifier to cite or link to this item: https://ruomo.lib.uom.gr/handle/7000/1268
Full metadata record
DC FieldValueLanguage
dc.contributor.authorTsagalidis, Evangelos-
dc.contributor.authorTsitouridis, Kyriakos-
dc.contributor.authorDervos, Dimitris A.-
dc.contributor.authorEvangelidis, Georgios-
dc.date.accessioned2022-08-30T14:26:20Z-
dc.date.available2022-08-30T14:26:20Z-
dc.date.issued2008-
dc.identifier.urihttp://erad2008.fmi.fi/proceedings/extended/erad2008-0072-extended.pdfen_US
dc.identifier.urihttps://ruomo.lib.uom.gr/handle/7000/1268-
dc.description.abstractIn this study we examine the existence of interesting patterns among the Greek National Hail Suppression Program data using Data Mining techniques. More specifically, we focus on hail size estimation and prediction from meteorological radar and sounding data. The sought objective is to examine existing relationships and, by doing so, construct a hail size prediction model. Two data mining techniques are applied in order to identify the optimum number of independent variables and, consequently, build a simple, yet effective, model. A model easily applied by the meteorologist in order to quickly interpret radar and atmospheric measurements to possible hail size on the ground.en_US
dc.language.isoenen_US
dc.rightsAttribution-NonCommercial-ShareAlike 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/*
dc.subjectFRASCATI::Natural sciences::Computer and information sciencesen_US
dc.titleHail Size Estimation and Prediction using Data Mining Techniquesen_US
dc.typeConference Paperen_US
dc.contributor.departmentΤμήμα Εφαρμοσμένης Πληροφορικήςen_US
local.identifier.volumetitleProceedings of the 5th European Conference on Radar in Meteorology and Hydrology (ERAD), Helsinki, Finlanden_US
Appears in Collections:Department of Applied Informatics

Files in This Item:
File Description SizeFormat 
2008_ERAD_Tsagalidis.pdf142,93 kBAdobe PDFThumbnail
View/Open


This item is licensed under a Creative Commons License Creative Commons