Prediction Of Water Content Research Articles

Neural-Intelligent Water Drops algorithm to select relevant textural features for developing precision irrigation system using machine vision

Sunagoke moss Rachomitrium japonicum is a good potential for greening material. One of the primary determinants of Sunagoke moss growth is water availability. Too much or too little water can cause water stress in plants. Water stress in plants can be detected by imaging. This study is part of on-going research aimed at developing machine vision-based precision irrigation system in a closed bio-production system for cultured Sunagoke moss. The objective of this study is to propose nature-inspired feature selection techniques to find the most significant set of Textural Features (TFs) suitable for predicting water content of cultured Sunagoke moss. The proposed Feature Selection (FS) methods include Neural-Intelligent Water Drops (N-IWD), Neural-Simulated Annealing (N-SA), Neural-Genetic Algorithms (N-GAs) and Neural-Discrete Particle Swarm Optimization (N-DPSO). TFs consist of 120 features extracted from grey, RGB, HSV, HSL and L ∗a ∗b ∗ colour spaces using ten Haralick’s textural equations. Back-Propagation Neural Network (BPNN) model performance was tested successfully to describe the relationship between water content of Sunagoke moss and TFs. Red Colour Co-occurrence Matrix (CCM) TFs, L ∗ CCM TFs, grey CCM TFs, value (HSV) CCM TFs, green CCM TFs and lightness (HSL) CCM TFs are recommended as individual feature-subset to be used for predicting water content of Sunagoke moss using Artificial Neural Networks. However, FS methods improve the prediction performance. The results show a significant difference between model using FS and models using individual feature-subsets or without FS. Comparative analysis shows the superiority of Neural-Intelligent Water Drops (N-IWD) compared to the other FS methods, since it achieve better prediction performance. The best N-IWD’s fitness function converged with the lowest validation-set Root Mean Square Error (RMSE) of 1.07 × 10 −2 when using 36 TFs.

Correlation and Prediction of Water Content in Alkanes Using a Molecular Theory

We present a predictive model for the saturated water concentration in n-alkanes based on a theoretical equation of state for the hydrocarbon rich phase and a water equation of state for the aqueous phase. By considering a polar or associating component at low concentration in a nonpolar solvent, we can neglect polar or hydrogen bonding interactions in the hydrocarbon rich phase, thus reducing the number of fitted parameters. The approach allows us to determine the intrinsic pure component equation of state parameters independent of polar and associating interactions. As an example, the nonpolar, non-associating equation of state parameters for water are determined by fitting water solubility data in liquid hydrocarbons (carbon numbers (CN) = 4–13, 16) at ambient conditions. Using the PC-SAFT equation of state, a predictive model for the solubility of water in n-alkanes is produced. Comparisons of the model are presented with binary mixture experimental data for methane to decane across a wide range of co...

Modification and validation of maize simulation model (MSM) at different applied water and nitrogen levels under furrow irrigation

The model MSM (Maize Simulation Model) was modified and validated, using data on furrow irrigation in Fars province in Iran during 2003 and 2004. The planted cultivar was SC704 (single cross) a late maturity hybrid. Three nitrogen levels (300, 150, and 0 kg N ha−1 as urea) and four irrigation treatments (applied water at 1.2, 1.0, 0.8, and 0.6 ratios of potential maize water requirements as I4, I3, I2, and I1 treatments, respectively) were considered. The potential water requirements were estimated based on the differences between soil field capacity and measured soil water contents at root depth in the I3 treatments before irrigation. The MSM model was modified based on field data in 2003 as: (i) Modification of root N uptake based on soil water pressure head and van Genuchten soil parameters for soil moisture retention curve α, and (ii) modification of grain yield prediction based on seasonal plant stover nitrogen uptake and grain N content. Model subroutines, i.e. leaf area index, dry matter production, prediction of soil water contents at different depths and at different days after planting did not require any modifications. Comparisons between measured data and predicted values by the modified model indicated favorable validation.

Modelling soil water and salt dynamics under pulsed and continuous surface drip irrigation of almond and implications of system design

The HYDRUS-2D model was experimentally verified for water and salinity distribution during the profile establishment stage (33 days) of almond under pulsed and continuous drip irrigation. The model simulated values of water content obtained at different lateral distances (0, 20, 40, 60, 100 cm) from a dripper at 10, 20, 30, 40, 50, 60, 70, 80, 90, 100, 120, 140 and 160 cm soil depths at different times (5, 12, 19, 26 and 33 days of profile establishment) were compared with neutron probe measured values under both irrigation scenarios. The model closely predicted water content distribution at all distances, times and soil depths as RMSE values ranged between 0.017 and 0.049. The measured mean soil water salinity (ECsw) at 25 cm from the dripper at 30, 60, 90 and 150 cm soil depth also matched well with the predicted values. A correlation of 0.97 in pulsed and 0.98 in continuous drip systems with measured values indicated the model closely predicted total salts in the root zone. Thus, HYDRUS-2D successfully simulated the change in soil water content and soil water salinity in both the wetting pattern and in the flow domain. The initial mean ECsw below the dripper in pulsed (5.25 dSm−1) and continuous (6.07 dSm−1) irrigations decreased to 1.31 and 1.36 dSm−1, respectively, showing a respective 75.1 and 77.6% decrease in the initial salinity. The power function [y = ax−b] best described the mathematical relationship between salt removal from the soil profile as a function of irrigation time under both irrigation scenarios. Contrary to other studies, higher leaching fraction (6.4–43.1%) was recorded in pulsed than continuous (1.1–35.1%) irrigation with the same amount of applied water which was brought about by the variation in initial soil water content and time of irrigation application. It was pertinent to note that a small (0.012) increase in mean antecedent water content (θi) brought about 8.25–9.06% increase in the leaching fraction during the profile establishment irrespective of the emitter geometry, discharge rate, and irrigation scenario. Under similar θi, water applied at a higher discharge rate (3.876 Lh−1) has resulted in slightly higher leaching fraction than at a low discharge rate (1.91 Lh−1) under pulsing only owing to the variation in time of irrigation application. The influence of pulsing on soil water content, salinity distribution, and drainage flux vanished completely when irrigation was applied daily on the basis of crop evapotranspiration (ETc) with a suitable leaching fraction. Therefore, antecedent soil water content and scheduling or duration of water application play a significant role in the design of drip irrigation systems for light textured soils. These factors are the major driving force to move water and solutes within the soil profile and may influence the off-site impacts such as drainage flux and pollution of the groundwater.

Bio-inspired feature selection to select informative image features for determining water content of cultured Sunagoke moss

One of the primary determinants of Sunagoke moss Rachomitrium japonicum growth is water availability. There is need to develop a non-destructive method for sensing water content of cultured Sunagoke moss to realize automation and precision irrigation in a close bio-production systems. Machine vision can be utilized as non-destructive sensing to recognize changes in some kind of features that describe the water conditions from the appearance of wilting Sunagoke moss. The goal of this study is to propose and investigate bio-inspired algorithms i.e. Neural-Ant Colony Optimization, Neural-Genetic Algorithms, Neural-Simulated Annealing and Neural-Discrete Particle Swarm Optimization to find the most significant sets of image features suitable for predicting water content of cultured Sunagoke moss. Image features consist of 8 colour features, three morphological features and 90 textural features (RGB, HSV, HSL colour co-occurrence matrix and gray level co-occurrence matrix textural features). Each colour space of textural features consist of energy, entropy, contrast, homogeneity, inverse difference moment, correlation, sum mean, variance, cluster tendency and maximum probability. The specificity of this problem is that we are not looking for single image feature but several associations of image features that may be involved in determining water content of cultured Sunagoke moss. All feature selection models showed that prediction performance is getting better through all the iterations. It indicates that all models are effective. Neural-Ant Colony Optimization had the best performance as a feature selection technique. The minimum average prediction mean square error (MSE) achieved was 1.75 × 10 −3. There is significant improvement between method using feature selection and method without feature selection.

Comparison of near infrared and microwave resonance sensors for at-line moisture determination in powders and tablets

In this paper we demonstrate the feasibility of replacing KF for water content testing in bulk powders and tablets with at-line near infrared (NIR) or microwave resonance (MR) methods. Accurate NIR and MR prediction models were developed with a minimalistic approach to calibration. The NIR method can accurately predict water content in bulk powders in the range of 0.5–5% w/w. Results from this method were compared to a MR method. We demonstrated excellent agreement of both NIR and MR methods for powders vs. the reference KF method. These methods are applicable to in-process control or quality control environments. One of the aims of this study was to determine if a calibration developed for a particular product could be used to predict the water content of another product (with related composition) but containing a different active pharmaceutical ingredient (API). We demonstrated that, contrary to the NIR method, a general MR method can be used to predict water content in two different types of blends. Finally, we demonstrated that a MR method can be developed for at-line moisture determination in tablets.

Parameterization and Evaluation of Predictions of DSSAT/CANEGRO for Brazilian Sugarcane

The DSSAT/CANEGRO model was parameterized and its predictions evaluated using data from five sugarcane (Saccharum spp.) experiments conducted in southern Brazil. The data used are from two of the most important Brazilian cultivars. Some parameters whose values were either directly measured or considered to be well known were not adjusted. Ten of the 20 parameters were optimized using a Generalized Likelihood Uncertainty Estimation (GLUE) algorithm using the leave‐one‐out cross‐validation technique. Model predictions were evaluated using measured data of leaf area index (LAI), stalk and aerial dry mass, sucrose content, and soil water content, using bias, root mean squared error (RMSE), modeling efficiency (Eff), correlation coefficient, and agreement index. The Decision Support System for Agrotechnology Transfer (DSSAT)/CANEGRO model simulated the sugarcane crop in southern Brazil well, using the parameterization reported here. The soil water content predictions were better for rainfed (mean RMSE = 0.122 mm) than for irrigated treatment (mean RMSE = 0.214 mm). Predictions were best for aerial dry mass (Eff = 0.850), followed by stalk dry mass (Eff = 0.765) and then sucrose mass (Eff = 0.170). Number of green leaves showed the worst fit (Eff = −2.300).The cross‐validation technique permits using multiple datasets that would have limited use if used independently because of the heterogeneity of measures and measurement strategies.

Application of Near Infrared Spectroscopy in Wood Water Content Prediction

Water content of Korean pine samples was studied using near infrared spectrascopy (NIR) combinded with parial least squares regression (PLS) analysis. Seven typical wave lengths were selceted to characterize the wood water content of Korean pine. Prediction models of wood water content were developed based on the original NIR spectra at seven varied wave lengths. The best model was showed between wavelengths from 1000 to 2100 nm with correlation coefficient (R) of 0.9871, standard error of calibration (SEC) and root mean square error of calibration (RMSEC) of 0.0337 and 0.0334, respectively. The correlation coefficient（R） for model validation was 0.9817 with standard error of prediction (SEP) and root mean square error of prediction (RMSEP) of 0.0470 and 0.0465, respectively. This study indicated that NIR is a useful tool for fast prediction of wood water content of Korean pine. The modeling proficiency could be improved significantly for some certain wave length. It could be a research focus for future related studies.

Comparison of Petrophysical Relationships for Soil Moisture Estimation using GPR Ground Waves

Soil water content measurement using ground‐penetrating radar (GPR) requires an appropriate petrophysical relationship between the dielectric permittivity and volumetric water content of the soil. The suitability of different relationships for GPR soil water content estimation has not been thoroughly investigated under natural field conditions for a complete range of seasonal soil conditions. In this study, we examined the ability of various empirical relationships, volumetric mixing formulae, and effective medium approximations to predict near‐surface volumetric soil water content using high‐frequency direct ground wave (DGW) velocity measurements for three soil textures. The estimated water contents were compared with values obtained from gravimetric sampling. The accuracy of soil water content predictions obtained from the various relationships ranged considerably. The best predictions for the overall data set in terms of RMSE were obtained with a differential effective medium approximation based on a coated sphere model (RMSE = 0.045 m3 m−3); however, an empirical relationship (RMSE = 0.052 m3 m−3) and a volumetric mixing formula (RMSE = 0.048 m3 m−3) also performed well. These best‐fitting relationships do exhibit some degree of textural bias that should be considered in the choice of petrophysical relationship for a given data set. Further improvements in water content estimates were obtained using our best‐fit third‐order polynomial relationship (RMSE = 0.041 m3 m−3) and our three‐phase volumetric mixing formula with geometric parameter α = 0.36 (RMSE = 0.042 m3 m−3); these optimized relationships were developed using the DGW permittivity and soil water content data collected in this study.

Modelling and prediction of soil water contents at field capacity and permanent wilting point of dryland cropping soils

Field capacity (FC) and permanent wilting point (PWP) are two critical input parameters required in various biophysical models. There are limited published data on FC and PWP of dryland cropping soils across north-western Victoria. Direct measurements of FC and PWP are time-consuming and expensive. Reliable prediction of FC and PWP from their functional relationships with routinely measured soil properties can help to circumvent these constraints. This study provided measured data on FC using undisturbed samples and PWP as functions of geomorphological unit, soil type, and soil texture class for dryland cropping soils of north-western Victoria. We used a balanced, nested sampling strategy and developed functional relationships of FC and PWP with routinely measured soil properties using residual maximum likelihood based mixed-effects regression modelling. Using the data, we also tested the adequacy of nine published pedotransfer functions (PTFs) in predicting FC and PWP. Significant differences were observed among the three soil types and nine texture classes for most soil properties. FC and PWP were higher for Grey Vertosols (FC 43.7% vol, PWP 29.1% vol) than Hypercalcic Calcarosols (38.4%, 23.5%) and Red Sodosols (20.2%, 9.2%). Of the several functional relationships developed for prediction of FC and PWP, a quadratic single-predictor model based on dg (geometric mean particle size diameter) performed better than other models for both FC and PWP. It was nearly bias-free, with a root mean square error (RMSE) of 3.18% vol and an R2 of 93% for FC, and RMSE 3.47% vol and R2 89% for PWP. Another useful model for FC was a slightly biased, two-predictor quadratic model based on clay and silt, with RMSE 3.14% vol and R2 94%. For PWP, two other possibly useful, though slightly biased, models included a single-predictor quadratic model based on clay (RMSE 3.45% vol, R2 89%) and a three-predictor model based on clay, silt, and σg (geometric standard deviation of particle size diameter) (RMSE 3.27% vol, R2 90%). We observed a strong quadratic relationship of FC with PWP (RMSE 1.61% vol, R2 98%). This suggests the possibility to further improve the prediction of FC indirectly through PWP. These predictive models for FC and PWP, though developed for the dryland cropping soils of north-western Victoria, may be applicable to other regions with similar soil and climatic conditions. Some validation is desirable before these models are confidently applied in a new situation. Of the nine published PTFs, the multiple linear regression and artificial neural network based NTh5 for FC and NTh3 and CAM for PWP performed better on our data for the prediction of FC and PWP. The root mean square deviation of these PTFs, for both FC and PWP, was higher than the RMSE of our models. Our models are therefore likely to perform better under the dryland cropping soils of north-western Victoria than these PTFs. As a safeguard against arriving at optimistic inferences, we suggest that the modelling of functional relationships needs to account for the hierarchical structure of the sampling design using appropriate mixed effects regression models.

Determining an ANN pre-treatment algorithm to predict water content of moss using RGB intensities

Sunagoke moss is one of the plant products that are cultivated in a plant factory. One of the primary determinants of moss growth is water availability. The present work attempts to apply precision irrigation system using machine vision in plant factories. The specific objective was to evaluate the ability of bio-inspired approaches as pre-treatment algorithm of Artificial Neural Network (ANN) for determining water content of moss. The results showed that ANN was capable for predicting water content of moss using RGB intensities, and then some bio-inspired approaches such as Honey Bees Mating Optimization (HBMO), Ant Colony Optimization (ACO), Genetic Algorithms (GAs), Simulated Annealing (SA) and Discrete Particle Swarm Optimization (DPSO) were capable of optimizing the feature selection process.

Development of Micro Precision Irrigation System in Plant Factory

AbstractComputer integrated systems and Artificial Intelligence (AI) have become an apparent need for control in a plant factory. Sunagoke moss Rachomitrium japonicum is one of the plant products which are cultivated in plant factory. One of the primary determinants of moss growth is water availability. The present work attempted to apply machine vision-based micro-precision irrigation system which is able to optimize water use in plant factory and maintain the water content of moss constantly in optimum growth condition. The objective of this study is to propose nature-inspired algorithms to find the most significant set of image features suitable for predicting water content of cultured Sunagoke moss. Multi-Objective Optimization (MOO) was used in this study which consisted of prediction accuracy maximization and feature-subset size minimization. Feature Selection (FS) methods included Neural-Intelligent Water Drops (N-IWD), Neural-Simulated Annealing (N-SA), Neural-Genetic Algorithms (N-GAs), Neural-Ant Colony Optimization (N-ACO), Neural-Honey Bee Mating Optimization (N-HBMO), and Neural-Fish Swarm Intelligent (N-FSI). Image features consist of colour features and textural features with the total of 212 features extracted from grey, RGB, HSV, HSL, L*a*b* XYZ, LCH and Luv colour spaces. Back-Propagation Neural Network (BPNN) model performance was tested successfully to describe the relationship between water content of Sunagoke moss and image features. FS methods improve the prediction performance of BPNN.

Classification of Automobile Lubricant by Near-Infrared Spectroscopy Combined with Machine Classification

The main objective of this paper is to classify four kinds of automobile lubricant by near-infrared (NIR) spectral technology and to observe whether NIR spectroscopy could be used for predicting water content. Principle component analysis (PCA) was applied to reduce the information from the spectral data and first two PCs were used to cluster the samples. Partial least square (PLS), least square support vector machine (LS-SVM), and Gaussian processes classification (GPC) were employed to develop prediction models. There were 120 samples for training set and test set. Two LS-SVM models with first five PCs and first six PCs were built, respectively, and accuracy of the model with five PCs is adequate with less calculation. The results from the experiment indicate that the LS-SVM model outperforms the PLS model and GPC model outperforms the LS-SVM model.

Determining an ANN pre-treatment algorithm to predict water content of moss using RGB intensities

Determining an ANN pre-treatment algorithm to predict water content of moss using RGB intensities

Funções de pedotransferência do conteúdo de água em Latossolos Amarelos e Argissolos Amarelos

The objective of the study was to develop pedotransfer functions (PTF) to predict soil water content in the -33 (field capacity) and -1,500kPa (permanent wilting point) potentials and available water content, from granulometric data, bulk density, and organic carbon from soil profiles. The soil database used in the study comprised 682 horizons from Yellow Oxisols and Ultisols, developed from Barreiras Formation and similar sediments, from different Brazilian localities. The PTF were developed using the backward stepwise selection method. Evaluation prediction efficiency of each pedofunction was obtained on the basis of determination coefficient (R2), the estimate standard error (ESE) and graphic interpretation. The developed equations presented good determination coefficients, indicating that they could be used for prediction of water content at the –33 and -1,500kPa potentials in Oxisols and Ultisols. Water availability variable shows high percentage of factors not explained by the equation variables. The PTF for the water availability variable underestimates the values higher than 0.10 kg kg-1.

Modeling directional–hemispherical reflectance and transmittance of fresh and dry leaves from 0.4 μm to 5.7 μm with the PROSPECT-VISIR model

Vegetation water content retrieval using passive remote sensing techniques in the 0.4–2.5 μm region (reflection of solar radiation) and the 8–14 μm region (emission of thermal radiation) has given rise to an abundant literature. The wavelength range in between, where the main water absorption bands are located, has surprisingly received very little attention because of the complexity of the radiometric signal that mixes both reflected and emitted fluxes. Nevertheless, it is now covered by the latest generation of passive optical sensors (e.g. SEBASS, AHS). This work aims at modeling leaf spectral reflectance and transmittance in the infrared, particularly between 3 μm and 5 μm, to improve the retrieval of vegetation water content using hyperspectral data. Two unique datasets containing 32 leaf samples each were acquired in 2008 at the USGS National Center, Reston (VA, USA) and the ONERA Research Center, Toulouse (France). Reflectance and transmittance were recorded using laboratory spectrometers in the spectral region from 0.4 μm to 14 μm, and the leaf water and dry matter contents were determined. It turns out that these spectra are strongly linked to water content up to 5.7 μm. This dependence is much weaker further into the infrared, where spectral features seem to be mainly associated with the biochemical composition of the leaf surface. The measurements show that leaves transmit light in this wavelength domain and that the transmittance of dry samples can reach 0.35 of incoming light around 5 μm, and 0.05 around 11 μm. This work extends the PROSPECT leaf optical properties model by taking into account the high absorption levels of leaf constituents (by the insertion of the complex Fresnel coefficients) and surface phenomena (by the addition of a top layer). The new model, PROSPECT-VISIR (VISible to InfraRed), simulates leaf reflectance and transmittance between 0.4 μm and 5.7 μm (at 1 nm spectral resolution) with a root mean square error (RMSE) of 0.017 and 0.018, respectively. Model inversion also allows the prediction of water (RMSE = 0.0011 g/cm²) and dry matter (RMSE = 0.0013 g/cm²) contents.

An examination of direct ground wave soil moisture monitoring over an annual cycle of soil conditions

Direct ground wave (DGW) measurements obtained with ground‐penetrating radar have been used in a number of previous studies to estimate volumetric water content in the shallow soil zone; however, these studies have generally involved controlled field experiments or measurements collected across limited natural ranges of soil moisture conditions. To further investigate the capacity of this method, we have undertaken an extensive field study using multifrequency (i.e., 225, 450, and 900 MHz) DGW measurements to monitor a complete annual cycle of soil water content variations typical of midlatitude climates at three sites with different soil textures. The use of common‐midpoint surveys allowed us to understand the nature and evolution of the near‐surface electromagnetic wavefields and their impact on DGW moisture predictions. We present the novel characterization of a wide‐range of seasonal moisture dynamics including soil freezing and thawing process using multifrequency DGW measurements for a range of soil textures. These data showed significant temporal variations in both the near‐surface wavefield and multifrequency DGW velocities corresponding to both seasonal and shorter‐term variations in soil conditions. Although all of the measurement sites displayed similar temporal responses, the rate and magnitude of these velocity variations corresponded to varying soil water contents, which were controlled by the soil textural properties. Although there were no observed systematic differences in DGW velocities due to frequency dispersion for the 225–900 MHz range, the DGW measurements obtained using higher‐frequency antennas was less impacted by near‐surface wavefield interference due to their shorter signal pulse duration. DGW velocity measurements combined with an appropriate dielectric mixing formula provided quantitative predictions of soil water content that accurately replicated the soil sample data over the annual cycle of moisture conditions.

Prediction of water content of sour and acid gases

Estimating the feasibility of acid gas geological disposal requires the knowledge of the water content of the gas phase at moderate pressures and temperatures (typically below 50 MPa, below 380 K) and up to 6 mol NaCl. In this paper, a non-iterative model is developed to predict the water content of sour and acid gases at equilibrium with pure water and brine. This model is based on equating the chemical potential of water and using the modified Redlich–Kwong equation of state to calculate the fugacity of the gas phase. The water content of pure CH 4, CO 2 and H 2S are represented with average absolute deviations of less than 3.36, 7.04 and 8.4%, respectively. Experimental data of the water content of mixtures of the acid gases were reproduced with average absolute deviations of less than 6.32%.

Comparison of Pattern Recognition, Artificial Neural Network and Pedotransfer Functions for Estimation of Soil Water Parameters

This paper presents the comparison of three different approaches to estimate soil water content at defined values of soil water potential based on selected parameters of soil solid phase. Forty different sampling locations in northeast of Iran were selected and undisturbed samples were taken to measure the water content at field capacity (FC), -33 kPa, and permanent wilting point (PWP), -1500 kPa. At each location solid particle of each sample including the percentage of sand, silt and clay were measured. Organic carbon percentage and soil texture were also determined for each soil sample at each location. Three different techniques including pattern recognition approach (k nearest neighbour, k-NN), Artificial Neural Network (ANN) and pedotransfer functions (PTF) were used to predict the soil water at each sampling location. Mean square deviation (MSD) and its components, index of agreement (d), root mean square difference (RMSD) and normalized RMSD (RMSDr) were used to evaluate the performance of all the three approaches. Our results showed that k-NN and PTF performed better than ANN in prediction of water content at both FC and PWP matric potential. Various statistics criteria for simulation performance also indicated that between kNN and PTF, the former, predicted water content at PWP more accurate than PTF, however both approach showed a similar accuracy to predict water content at FC.

Performance evaluation of evapotranspiration estimations in a model of soil water balance

AbstractSoil water content models have huge applications from an agronomic point of view and they are usually used as a sub‐model for weather and climate modelling. They are also useful tools for efficient water management irrigation practices. The aim of this investigation is to evaluate the performance of two different parameterizations of evapotranspiration when applied to a soil water balance model. Experimental data of a maize crop is used to evaluate model accuracy. The first methodology proposes a parallel resistance arrangement to represent the latent heat fluxes of the soil surface and the leaves in the canopy layer considering the leaf area index (LAI). The second methodology uses the parameterization proposed by the United Nations Food and Agriculture Organization (FAO), based on the crop coefficient (Kc) and the potential evapotranspiration obtained from the Penman–Monteith equation. The crop was divided into five plots with different irrigation systems according to their phenological stages. The model suitably predicts daily soil water content in five different irrigation systems. Predictions of soil water content using the LAI or Kc methodology tend to overestimate observations. In addition, the model has better predictions using the LAI methodology than the Kc methodology. The root mean square error and the determination coefficient were 0.059 and 0.92, respectively, with the LAI methodology and 0.063 and 0.87, respectively, using the Kc methodology. Copyright © 2010 Royal Meteorological Society