Martí Pérez, PC.; Gasque Albalate, M.; González Altozano, P. (2013). An artificial neural network approach to the estimation of stem water potential from frequency domain reflectometry soil moisture measurements and meteorological data. Computers and Electronics in Agriculture. 91:75-86. https://doi.org/10.1016/j.compag.2012.12.001
Por favor, use este identificador para citar o enlazar este ítem: http://hdl.handle.net/10251/37059
Title:
|
An artificial neural network approach to the estimation of stem water potential from frequency domain reflectometry soil moisture measurements and meteorological data
|
Author:
|
Martí Pérez, Pau Carles
Gasque Albalate, Maria
González Altozano, Pablo
|
UPV Unit:
|
Universitat Politècnica de València. Departamento de Física Aplicada - Departament de Física Aplicada
Universitat Politècnica de València. Departamento de Ingeniería Rural y Agroalimentaria - Departament d'Enginyeria Rural i Agroalimentària
|
Issued date:
|
|
Abstract:
|
Stem water potential seems to be a sensitive measure of plant water status. Nonetheless, it is a labour-intensive measurement and is not suited for automatic irrigation scheduling or control. This study describes the ...[+]
Stem water potential seems to be a sensitive measure of plant water status. Nonetheless, it is a labour-intensive measurement and is not suited for automatic irrigation scheduling or control. This study describes the application of artificial neural networks to estimate stem water potential from soil moisture at different depths and standard meteorological variables, considering a limited data set. The experiment was carried out with `Navelina¿ citrus trees grafted on `Cleopatra¿ mandarin. Principal components analysis and multiple linear regression were used preliminarily to assess the relationships among observations and to propose other models to allow a comparative analysis, respectively. Two principal components account for the systematic data variation. The optimum regression equation of stem water potential considered temperature, relative humidity, solar radiation and soil moisture at 50 cm as input variables, with a determination coefficient of 0.852. When compared with their corresponding regression models, ANNs presented considerably higher performance accuracy (with an optimum determination coefficient of 0.926) due to a higher input-output mapping ability.
[-]
|
Subjects:
|
Frequency domain reflectometry
,
Irrigation scheduling
,
Principal component analysis
,
Artificial neural networks
|
Copyrigths:
|
Reserva de todos los derechos
|
Source:
|
Computers and Electronics in Agriculture. (issn:
0168-1699
)
|
DOI:
|
10.1016/j.compag.2012.12.001
|
Publisher:
|
Elsevier
|
Publisher version:
|
http://dx.doi.org/10.1016/j.compag.2012.12.001
|
Project ID:
|
info:eu-repo/grantAgreement/GVA//2007TAHAVAL0001/
|
Thanks:
|
The authors are grateful to TECVASA, which obtained a subsidy from the Conselleria de Agricultura, Pesca y Alimentacion de la Generalitat Valenciana (DOCV 5493, 19 April 2007, no. exp.: 2007TAHAVAL00018), and to the Valencian ...[+]
The authors are grateful to TECVASA, which obtained a subsidy from the Conselleria de Agricultura, Pesca y Alimentacion de la Generalitat Valenciana (DOCV 5493, 19 April 2007, no. exp.: 2007TAHAVAL00018), and to the Valencian Institute for Agricultural Research (IVIA) for providing the meteorological data for this study.
[-]
|
Type:
|
Artículo
|