English   español  
Por favor, use este identificador para citar o enlazar a este item: http://hdl.handle.net/10261/90363
COMPARTIR / IMPACTO:
Estadísticas
logo share SHARE   Add this article to your Mendeley library MendeleyBASE
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL
Exportar a otros formatos:
Título

Using SVM for soil water retention modelling

AutorLamorski, Krzysztof; Sławiński, Cezary; Moreno Lucas, Félix ; Skierucha, Wojciech; Arrúe Ugarte, José Luis
Fecha de publicaciónjun-2011
CitaciónInternational Conference. Protection of agricultural soils against joint stress of natural and anthropogenic factors (Pulawy , Poland. 13th – 16th June 2011)
ResumenThis work presents point pedotransfer function models of the soil water retention curve. Developed models allow for estimation of the soil water content based on following soil characteristics: soil granulometric composition, total porosity and bulk density. Soil water content is evaluated for the specified soil water potentials: -0.98 kPa, -3.10 kPa, -9.81 kPa, - 31.02 kPa, -491.66 kPa and -1554.78 kPa. Support Vector Machines (SVM) methodology was used for model development. Alternative to previous attempts ν-SVM method was used for models development and results compared with C-SVM based models. In the work two different types of the SVM kernel function was used and results compared: radial basis kernel function with the linear one. Soil properties used as input variables for the PTF models are: sand fraction, clay fraction, total porosity and bulk density. Models approximate value of the soil water content for seven fixed values of the soil water potential.
Descripción1 copia .pdf (a-3) del póster original presentado (2 Figs., 2 Tabls.)
URIhttp://hdl.handle.net/10261/90363
Aparece en las colecciones: (EEAD) Comunicaciones congresos
(IRNAS) Comunicaciones congresos
Ficheros en este ítem:
Fichero Descripción Tamaño Formato  
ArrueJL_IntConf-Post_Pulawy_2011.pdf104,77 kBAdobe PDFVista previa
Visualizar/Abrir
Mostrar el registro completo
 


NOTA: Los ítems de Digital.CSIC están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.