An artificial neural network approach to the estimation of stem water potential from frequency domain reflectometry soil moisture measurements and meteorological data

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 50cm 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.

[1]  Isabel Abrisqueta,et al.  Irrigation scheduling of peach trees (Prunus persica L.) by continuous measurement of soil water status , 2008 .

[2]  D. Intrigliolo,et al.  Continuous measurement of plant and soil water status for irrigation scheduling in plum , 2004, Irrigation Science.

[3]  Lutz Prechelt,et al.  Automatic early stopping using cross validation: quantifying the criteria , 1998, Neural Networks.

[4]  Gaylon S. Campbell,et al.  Irrigation Scheduling Using Soil Moisture Measurements: Theory and Practice , 1982 .

[5]  J. A. Taylor,et al.  A model for the spatial prediction of water status in vines (Vitis vinifera L.) using high resolution ancillary information , 2010, Precision Agriculture.

[6]  Guillermo Palau-Salvador,et al.  Integrated Emitter Local Loss Prediction Using Artificial Neural Networks , 2010 .

[7]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[8]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[9]  H. Jones.  Irrigation scheduling: advantages and pitfalls of plant-based methods. , 2004, Journal of experimental botany.

[10]  Wojtek J. Krzanowski,et al.  Cross-Validation in Principal Component Analysis , 1987 .

[11]  L. S. Pereira,et al.  Crop evapotranspiration : guidelines for computing crop water requirements , 1998 .

[12]  I. Jolliffe.  Principal Component Analysis , 2002 .

[13]  Neil C. Turner,et al.  Techniques and experimental approaches for the measurement of plant water status , 1981, Plant and Soil.

[14]  Anthony E. Hall,et al.  Interpreting Leaf Water Potential Measurements with a Model of the Soil‐Plant‐Atmosphere Continuum , 1972 .

[15]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[16]  Gerard Arbat,et al.  Prediction by neural networks of filtered volume and outlet parameters in micro-irrigation sand filters using effluents , 2012 .

[17]  Karl Pearson F.R.S..  LIII. On lines and planes of closest fit to systems of points in space , 1901 .

[18]  María Gasque,et al.  Regulated deficit irrigation effects on yield, fruit quality and vegetative growth of 'Navelina' citrus trees , 2010 .

[19]  Martin T. Hagan,et al.  Neural network design , 1995 .

[20]  Ali Fares,et al.  Advances in Crop Water Management Using Capacitive Water Sensors , 2006 .

[21]  Robert G. Evans,et al.  Leaf Water Potentials for Management of High Frequency Irrigation on Apples , 1984 .

[22]  Pau Martí,et al.  Improvement of temperature-based ANN models for solar radiation estimation through exogenous data assistance , 2011 .

[23]  Sylvia Dayau,et al.  Significance and limits in the use of predawn leaf water potential for tree irrigation , 1999, Plant and Soil.

[24]  Elias Fereres,et al.  Irrigation scheduling protocols using continuously recorded trunk diameter measurements , 2001, Irrigation Science.

[25]  J. Alarcón,et al.  Relationships Between Climatic Variables and Sap Flow, Stem Water Potential and Maximum Daily Trunk Shrinkage in Lemon Trees , 2006, Plant and Soil.

[26]  O. Mounzer,et al.  Contenido de agua en el suelo medido con sondas FDR y umbrales para manejo de riego por goteo en durazno , 2008 .

[27]  Kathy Steppe,et al.  A step towards new irrigation scheduling strategies using plant-based measurements and mathematical modelling , 2008, Irrigation Science.

[28]  J. Castel,et al.  Regulated deficit irrigation in `Clementina de Nules' citrus trees. I. Yield and fruit quality effects , 1999 .

[29]  R. Zakaluk,et al.  Artificial Neural Network Modelling of Leaf Water Potential for Potatoes Using RGB Digital Images: A Greenhouse Study , 2007, Potato Research.

[30]  Pau Martí,et al.  Reference evapotranspiration estimation without local climatic data , 2011, Irrigation Science.

[31]  Pau Martí,et al.  Assessment of a 4-input artificial neural network for ETo estimation through data set scanning procedures , 2010, Irrigation Science.

[32]  Gaylon S. Campbell,et al.  A SIMPLE METHOD FOR DETERMINING UNSATURATED CONDUCTIVITY FROM MOISTURE RETENTION DATA , 1974 .

[33]  Cornelis van Leeuwen,et al.  Stem Water Potential is a Sensitive Indicator of Grapevine Water Status , 2001 .

[34]  P. González-Altozano,et al.  Regulated deficit irrigation in ‘Clementina de Nules’ citrus trees. II: Vegetative growth , 2000 .

[35]  Steve B. Orloff,et al.  Monitoring soil moisture helps refine irrigation management , 2000 .

[36]  Inmaculada Pulido-Calvo,et al.  Demand Forecasting for Irrigation Water Distribution Systems , 2003 .

[37]  J. E. Jackson.  A User's Guide to Principal Components , 1991 .

[38]  W. Rawls,et al.  Estimating generalized soil-water characteristics from texture , 1986 .

[39]  Juan Ramón Castel Sánchez.  Consumo de agua por plantaciones de cítricos en Valencia , 2001 .

[40]  Antonio Odair Santos,et al.  Grapevine leaf water potential based upon near infrared spectroscopy , 2009 .

[41]  Pol Coppin,et al.  Determining the water status of Satsuma mandarin trees [Citrus Unshiu Marcovitch] using spectral indices and by combining hyperspectral and physiological data , 2010 .

[42]  Santiago Tosetti,et al.  Neural Network-Based Irrigation Control for Precision Agriculture , 2008, 2008 IEEE International Conference on Networking, Sensing and Control.

[43]  Oussama Hussein-Mounzer,et al.  Soil water content measured by FDR probes and thresholds for drip irrigation management in peach trees , 2008 .

[44]  A. Naor,et al.  Irrigation Scheduling and Evaluation of Tree Water Status in Deciduous Orchards , 2010 .

[45]  N. S. Raghuwanshi,et al.  Artificial neural networks approach in evapotranspiration modeling: a review , 2010, Irrigation Science.

[46]  Giancarlo Diana,et al.  Cross-validation methods in principal component analysis: A comparison , 2002 .

[47]  J. Starr,et al.  Real-time soil water dynamics using multisensor capacitance probes : Laboratory calibration , 1997 .

[48]  S. Wold.  Cross-Validatory Estimation of the Number of Components in Factor and Principal Components Models , 1978 .

[49]  E. Garnier,et al.  Testing water potential in peach trees as an indicator of water stress , 1985 .