Hossein Bayat

Estimating Water Retention with Pedotransfer Functions Using Multi-Objective Group Method of Data Handling and ANNs

Abstract Pedotransfer functions (PTFs) have been developed to estimate soil water retention curves (SWRC) by various techniques. In this study PTFs were developed to estimate the parameters (θs, θr, α and γ) of the Brooks and Corey model from a data set of 148 samples. Particle and aggregate size distribution fractal parameters (PSDFPs and ASDFPs, respectively) were computed from three fractal models for either particle or aggregate size distribution. The most effective model in each group was determined by sensitivity analysis. Along with the other variables, the selected fractal parameters were employed to estimate SWRC using multi-objective group method of data handling (mGMDH) and different topologies of artificial neural networks (ANNs). The architecture of ANNs for parametric PTFs was different regarding the type of ANN, output layer transfer functions and the number of hidden neurons. Each parameter was estimated using four PTFs by the hierarchical entering of input variables in the PTFs. The inclusion of PSDFPs in the list of inputs improved the accuracy and reliability of parametric PTFs with the exception of θs. The textural fraction variables in PTF1 for the estimation of α were replaced with PSDFPs in PTF3. The use of ASDFPs as inputs significantly improved α estimates in the model. This result highlights the importance of ASDFPs in developing parametric PTFs. The mGMDH technique performed significantly better than ANNs in most PTFs.

Modeling Fentonic advanced oxidation process decolorization of Direct Red 16 using artificial neural network technique

Abstract The present work has focused on the modeling of C.I. Direct Red 16 (DR16) decolorization using Fentonic reagents in a batch reactor. The reactor was equipped with an air bubbling for mixing and a water-flow coil for temperature regulating. Dye concentration was analyzed by measuring its absorbance at λmax = 526 nm. An artificial neural network (ANN) model was developed to predict the behavior of the process. Six operational parameters and decolorization efficiency were employed as inputs and output of the network, respectively. A three layer feed-forward network with back-propagation algorithm was developed. Application of 10 neurons in the hidden layer and 300 iterations for the network calibration prevents overfitting by the model. The K-fold cross-validation method was employed for performance evaluation of the developed ANN model. The results showed high correlation coefficient (R 2 = 0.9984) and low mean square error (MSE = 1.56 × 10−4) for testing data. Sensitivity analysis indicates the or...

Prediction of CEC using fractal parameters by artificial neural networks

Abstract The prediction of cation exchange capacity from readily available soil properties remains a challenge. In this study, firstly, we extended the entire particle size distribution curve from limited soil texture data and, at the second step, calculated the fractal parameters from the particle size distribution curve. Three pedotransfer functions were developed based on soil properties, parameters of particle size distribution curve model and fractal parameters of particle size distribution curve fractal model using the artificial neural networks technique. 1 662 soil samples were collected and separated into eight groups. Particle size distribution curve model parameters were estimated from limited soil texture data by the Skaggs method and fractal parameters were calculated by Bird model. Using particle size distribution curve model parameters and fractal parameters in the pedotransfer functions resulted in improvements of cation exchange capacity predictions. The pedotransfer functions that used fractal parameters as predictors performed better than the those which used particle size distribution curve model parameters. This can be related to the non-linear relationship between cation exchange capacity and fractal parameters. Partitioning the soil samples significantly increased the accuracy and reliability of the pedotransfer functions. Substantial improvement was achieved by utilising fractal parameters in the clusters.

Prediction capability of different soil water retention curve models using artificial neural networks

Direct measurements of soil water retention curve (SWRC) are costly and time consuming. So far, less investigation has been carried out on the prediction capability of different models using artificial neural networks (ANNs). In this study in total 75 soil samples were collected from Guilan province, north of Iran. The basic soil properties namely sand, clay and bulk density were used as predictors and the parameters of ten SWRC models were forecasted by ANNs. The prediction capability of each model was examined based on three criteria in nine groups of samples: total, fine (clay and silty clay) and medium (clay loam, silt loam, silty clay loam and loam) textural groups and six soil texture classes. Overall, the Boltzman, Tani, Gardner, Campbell and van Genuchten models produced the best results. However, bimodal models (Durner, Seki and Dexter) established on non-uniform pore size distribution with two modes (peaks) in soils showed low prediction capability in this study. Therefore, further research is needed. Sensitivity analysis indicated that the residual and saturated water contents were largely dependent on clay content.

Improvement in estimation of soil water retention using fractal parameters and multiobjective group method of data handling

Soil water retention characteristic is required for modeling of water and substance movement in unsaturated soils and need to be estimated using indirect methods. Point pedotransfer functions (PTFs) for prediction of soil water content at matric suctions of 1, 5, 25, 50, and 1500 kPa were developed and validated using a data-set of 148 soil samples from Hamedan and Guilan provinces, Iran, by multiobjective group method of data handling (mGMDH). In addition to textural and structural properties, fractal parameters of the power-law fractal models for both particles and aggregates distributions were also included as predictors. Their inclusion significantly improved the PTFs’ accuracy and reliability. The aggregate size distribution fractal parameters ranked next to the particle size distribution (PSD) in terms of prediction accuracy. The mGMDH-derived PTFs were significantly more reliable than those by artificial neural networks but their accuracies were practically the same. Similarity between the fractal behavior of particle and void size distributions may contribute to the improvement of the derived PTFs using PSD fractal parameters. It means that both distributions of the pore and particle size represent the fractal behavior and can be described by fractal models.

Novel impacts of nanoparticles on soil properties: tensile strength of aggregates and compression characteristics of soil

ABSTRACT Nanoparticles (NPs) affect most soil properties but there have been no assessments of their effects on the compression behavior of soil and the strength of aggregates. Therefore, we assessed the impact of NPs on the bulk density and the confined compression and tensile strength of aggregates of a calcareous loamy soil. Using a factorial design, we assessed the effects of two factors on the soil properties, i.e., NP type (first factor) at two levels comprising Fe nano-oxide (Fe3O4, N1) and Mg nano-oxide (MgO, N2), and treatment amount (second factor) at four levels with dry mass percentages of 0%, 1%, 3%, and 5%. The soil bulk density increased with the Fe level but decreased with the Mg level in ranges of 0.02–0.04 and 0.02–0.08 g cm–3, respectively. The compression curve characteristics were not affected by the NPs. Compared with N1, the N2 treatment significantly increased the soil void ratio in 86% of the applied stresses. N1 also significantly enhanced the soil tensile strength at suctions of 30, 100, and 1500 kPa, ranging from 0.5 to 15.3 kPa. The 3% Mg and 1% Fe dosages of nano-oxides had the optimal effects, so they should be considered in future investigations.

Estimation of the soil water retention curve using penetration resistance curve models

Abstract In this study, pedotransfer functions (PTFs) were developed for estimating the gravimetric water content based on the model of Dexter et al. (2008) using feed-forward artificial neural networks. Soil samples were collected from 148 locations in the West Azarbaijan, Hamedan, Fars, and Kurdistan provinces of Iran. The cation exchange capacity (CEC), organic matter content, electrical conductivity and equivalent CaCO3, bulk density, penetration resistance (PR) curve, soil water retention curve (SWRC), and particle size distributions of the soils were measured. Various PR models were fitted to the experimental PR data and the model parameters were then used to estimate the SWRC with nine versions via the model of Dexter et al. Among the two PR models that described the PR versus the water content, the parameters of the model proposed by Mielke et al. (1994) obtained more accurate PTFs and improved the water content estimates. In addition, using the parameters in the model of Stock and Downes (2008) based on suction and organic matter improved the water content estimates. Measuring the PR and water content is cheaper and requires less time than measuring the PR and matric suction, so we recommend using the parameters in model of Mielke et al. (1994) as water content predictors.

Estimation of soil saturated hydraulic conductivity by artificial neural networks ensemble in smectitic soils

The saturated hydraulic conductivity (Ks) of the soil is one of the main soil physical properties. Indirect estimation of this parameter using pedo-transfer functions (PTFs) has received considerable attention. The Purpose of this study was to improve the estimation of Ks using fractal parameters of particle and micro-aggregate size distributions in smectitic soils. In this study 260 disturbed and undisturbed soil samples were collected from Guilan province, the north of Iran. The fractal model of Bird and Perrier was used to compute the fractal parameters of particle and micro-aggregate size distributions. The PTFs were developed by artificial neural networks (ANNs) ensemble to estimate Ks by using available soil data and fractal parameters. There were found significant correlations between Ks and fractal parameters of particles and microaggregates. Estimation of Ks was improved significantly by using fractal parameters of soil micro-aggregates as predictors. But using geometric mean and geometric standard deviation of particles diameter did not improve Ks estimations significantly. Using fractal parameters of particles and micro-aggregates simultaneously, had the most effect in the estimation of Ks. Generally, fractal parameters can be successfully used as input parameters to improve the estimation of Ks in the PTFs in smectitic soils. As a result, ANNs ensemble successfully correlated the fractal parameters of particles and micro-aggregates to Ks.