Ruhollah Taghizadeh-Mehrjardi

Digital Mapping of Soil Classes Using Decision Tree and Auxiliary Data in the Ardakan Region, Iran

Digital soil mapping (DSM) involves acquisition of field soil observations and matching them with environmental variables that can explain the distribution of soils. The harmonization of these data sets, through computer-based methods, are increasingly being found to be as reliable as traditional soil mapping practices, but without the prohibitive costs. Therefore, the present research developed decision tree models for spatial prediction of soil classes in a 720 km2 area located in an arid region of central Iran, where traditional soil survey methods are difficult to undertake. Using the conditioned Latin hypercube sampling method, the locations of 187 soil profiles were selected, which were then described, sampled, analyzed, and allocated to six Great Groups according to the USDA Soil Taxonomy system. Auxiliary data representing the soil forming factors were derived from a digital elevation model (DEM), Landsat 7 ETM+ images, and a map of geomorphology. The accuracy of the decision tree models was evaluated using overall, user, and producer accuracy based on an independent validation data set. Our results showed some auxiliary variables had more influence on the prediction of soil classes which included: topographic wetness index, geomorphological map, multiresolution index of valley bottom flatness, elevation, and principal components of Landsat 7 ETM+ images. Furthermore, the results have confirmed the DSM model successfully predicted Great Groups with overall accuracy up to 67.5%. Our results suggest that the developed methodology could be used to predict soil classes in the arid region of Iran.

Effects of drought stress and rewatering on antioxidant systems and relative water content in different growth stages of maize (Zea mays L.) hybrids

Drought is a problem of the expanding universe which seriously influences crop production and quality. Approximately one-third of the cultivated area of the world suffers from constantly inadequate supplies of water. The present study aimed to determine the effects of drought and rewatering on activities of antioxidant enzymes, chlorophyll, proline, and relative water contents (RWC). In this experiment, six maize hybrids (Sc260, Sc370, Sc500, Sc647, Sc700, and Sc704) were examined in a pot study during the maize-growing season of 2011. Results indicated that the growth of hybrids was retarded under drought stress conditions and regained growth speed during rewatering. RWC, chlorophyll, and carotenoid contents were markedly decreased by the water deficit and reached normal values during rewatering in Sc647, Sc704, and Sc700. Our findings also indicated significantly higher activity levels of peroxidase and catalase and proline content in water-stressed plants than in well-watered plants, which decreased when the plants were rewatered, showing an inverse relationship to gluthatione reductase activity. According to the results, the better upregulation of the protective mechanism in Sc704 and Sc647 probably induced higher drought resistance. We concluded that antioxidant enzyme activity could provide a useful tool for depicting drought tolerance in maize hybrids in arid and semiarid regions.

Digital mapping of cation exchange capacity using genetic programming and soil depth functions in Baneh region, Iran

This study evaluates the performances of a combination of genetic programming and soil depth functions to map the three-dimensional distribution of cation exchange capacity (CEC) in a semiarid region located in Baneh region, Iran. Using the conditioned Latin hypercube sampling method, the locations of 188 soil profiles were selected, which were then sampled and analyzed. In general, results showed that equal-area quadratic splines had the highest R2, 89%, in fitting the vertical CEC distribution compared to power and logarithmic functions with R2 of 81% and 84%, respectively. Our findings indicated some auxiliary variables had more influence on the prediction of CEC. Normalized difference vegetation index (NDVI) had the highest correlation with CEC in the upper two layers. However, the most important auxiliary data for prediction of CEC in 30–60 cm and 60–100 cm were topographic wetness index and profile curvature, respectively. Validation of the predictive models at each depth interval resulted in R2 values ranging from 66% (0–15 cm) to 19% (60–100 cm). Overall, results indicated the topsoil can be reasonably well predicted; however, the subsoil prediction needs to be improved. We can recommend the use of the developed methodology in mapping CEC in other parts in Iran.

Prediction of soil surface salinity in arid region of central Iran using auxiliary variables and genetic programming

ABSTRACT Spatial information on soil salinity is increasingly needed for decision making and management practices in arid environments. In this article, we attempted to investigate soil salinity variation via a digital soil mapping approach and genetic programming in an arid region, Chah-Afzal, located in central Iran. A grid sampling strategy with 2-km distance was used. In total, 180 soil surface samples were collected and then analyzed. A symbolic regression was then adopted to correlate electrical conductivity (ECe) with a suite of auxiliary data including predicted maps of apparent electrical conductivity (vertical: ECav and horizontal: ECah), Landsat spectral data and terrain attributes derived from a digital elevation model. The accuracy of the genetic programming model was evaluated using root mean square error (RMSE), mean error (ME), and coefficient of determination (R2) based on an independent validation data set (20% of database or thirty soil samples). In general, results showed that ECah had the strongest influence on the prediction of soil salinity followed by salinity index wetness index, Landsat Band 3, multi-resolution valley bottom flatness index, elevation, and normalized difference vegetation index. Furthermore, results indicated that the genetic programming model predicted ECe over the study area accurately (R2 = 0.87, ME = −1.04 and RMSE = 16.36 dSm−1). Overall, it is suggested that similar applications of this technique could be used for mapping soil salinity in other arid regions of Iran.

Monitoring and assessment of soil erosion at micro-scale and macro-scale in forests affected by fire damage in northern Iran

Understanding the occurrence of erosion processes at large scales is very difficult without studying them at small scales. In this study, soil erosion parameters were investigated at micro-scale and macro-scale in forests in northern Iran. Surface erosion and some vegetation attributes were measured at the watershed scale in 30 parcels of land which were separated into 15 fire-affected (burned) forests and 15 original (unburned) forests adjacent to the burned sites. The soil erodibility factor and splash erosion were also determined at the micro-plot scale within each burned and unburned site. Furthermore, soil sampling and infiltration studies were carried out at 80 other sites, as well as the 30 burned and unburned sites, (a total of 110 points) to create a map of the soil erodibility factor at the regional scale. Maps of topography, rainfall, and cover-management were also determined for the study area. The maps of erosion risk and erosion risk potential were finally prepared for the study area using the Revised Universal Soil Loss Equation (RUSLE) procedure. Results indicated that destruction of the protective cover of forested areas by fire had significant effects on splash erosion and the soil erodibility factor at the micro-plot scale and also on surface erosion, erosion risk, and erosion risk potential at the watershed scale. Moreover, the results showed that correlation coefficients between different variables at the micro-plot and watershed scales were positive and significant. Finally, assessment and monitoring of the erosion maps at the regional scale showed that the central and western parts of the study area were more susceptible to erosion compared with the western regions due to more intense crop-management, greater soil erodibility, and more rainfall. The relationships between erosion parameters and the most important vegetation attributes were also used to provide models with equations that were specific to the study region. The results of this paper can be useful for better understanding erosion processes at the micro-scale and macro-scale in any region having similar vegetation attributes to the forests of northern Iran.

Artificial bee colony feature selection algorithm combined with machine learning algorithms to predict vertical and lateral distribution of soil organic matter in South Dakota, USA

ABSTRACT The main purpose of this study, is to evaluate an advanced feature selection technique, artificial bee colony (ABC) algorithm; to reduce the number of auxiliary variables derived from a digital elevation model (DEM) and remotely sensed data (e.g. Landsat images). A combination of depth functions (e.g. power, logarithmic and spline) and data miner methods (artificial neural network: ANN and support vector regression: SVR) were applied for three-dimensional mapping of soil organic matter (SOM) in Big Sioux River watershed, South Dakota, USA. Unsurprisingly, the ABC feature selection algorithm indicated that remote sensing data (e.g. NDVI) are powerful predictors at soil surface, however, with the increasing soil depth, the terrain parameters (e.g. wetness index) became more relevant. Our findings from this study demonstrated that both the spatial models generally performed well. The mean R2 values calculated by 10-fold cross validation suggested that SVR and ANN models could explain approximately 50 and 57% of total SOM variability, respectively. However, predictive power of both models increased when ABC feature selection algorithm applied, particularly when it combined with the ANN model. Results showed that DSM approaches are very important and powerful tool to explain the 3D spatial distribution of SOM across the study watershed.

Soil structure changes due to different land-use practices in the central Zagruos region, Iran

In this study, the effect of land-use treatments and the feasibility of fractal dimension to quantify soil aggregate stability were investigated in the central Zagrous, Iran. For this purpose, the non-linear fractal dimension (Dnl), linear fractal dimension (Dl) and the mean weight diameter (MWD) of aggregates were compared. Soil samples from three sites with four adjacent land-use types, namely: forest area (F), cultivated lands adjacent to forest (CAF), pasture (P) and cultivated lands adjacent to pasture (CAP) were collected. Results showed that soils under cultivated lands had higher bulk density (BD) (1.30–1.38 Mg m−3) compared to the adjacent soils under forest (1.19 Mg m−3) and pasture (1.21 Mg m−3). In the 0–15 cm layer, soil organic matter (SOM) content in the cultivated plots were respectively 30% and 31% lower compared to the forest and pasture soils. The lowest CVs belonged to Dnl (5–8%) demonstrating that Dnl was more accurate than Dl (8–14%) and MWD (30–53%) methods. CAP had the largest value of Dnl, while P had the smallest value of Dnl. Difference of Dnl between forest and pasture was not significant, whereas both of them significantly differed from CAF and CAP. Dl did not differ significantly between forest and CAF. There were significant differences between forest and pasture for the measured MWD. Both fractal dimensions had negative correlation with MWD, SOM, hydraulic conductivity (HC) and macroaggregates (>0.25 mm) and positive correlation with BD and total porosity (TP).

Estimating mass fractal dimension of soil using artificial neural networks for improved prediction of water retention curve

Abstract Fractal geometry appears to be a useful tool to simulate a porous medium that can be quantified by scaling exponent(s), which is a fractal dimension(s). The objective of this study was to estimate the mass fractal dimension of the Rieu and Sposito (RS) model from readily available parameters, such as clay, silt, and sand contents; geometric mean diameter and geometric S.D. of soil particles; and total soil porosity by developing an artificial neural network (ANN) model. Two databases with a total of 190 soil samples of 12 soil texture classes were used to develop and validate the ANN model. To determine the mass fractal dimension, the RS model was fitted to measured soil-water retention data. A sensitivity analysis was also performed on the RS model parameters. The results of sensitivity analysis showed that the most sensitive parameter of the RS model is the mass fractal dimension, whereas this model is less sensitive to air entry value and soil porosity. We used the cross-validation technique, for example, repeated random splitting of the data set into subsets for the development and validation processes of the ANN model. To evaluate the developed ANN model, the estimated mass fractal dimension, measured soil porosity, and air entry value combined with the RS model were consequently used to determine soil-water content corresponding to each prescribed tension head. Results showed that the developed ANN model estimated the soil-water retention curve accurately.

Comparison of different methods for reconstruction of instantaneous peak flow data

AbstractIn arid and semi-arid regions, documentary data of past floods remain justly rare and highly fragmentary in most cases. Existence of many effective parameters on maximum flood discharge and the complex relationships between them is an important challenge in the reconstruction of these data and hence, it limited the application of traditional methods. In this paper, an alternative approach (i.e. artificial intelligence methods) has been evaluated to determine the interactive relations of them. To this end, flow data was collected from 29 gauging stations in the central part of Iran for the period 1965 to 2007. Following quality and homogeneity controls of the data, reconstruction of instantaneous peak flow time series were made using maximum daily data by four different methods; regression method (REG), artificial neural network (ANN), genetic algorithm (GA) and adaptive neuro-fuzzy inference system (ANFIS). Results showed that in all studied stations, ANFIS reconstructs instantaneous peak flow val...

Assessing and monitoring the soil quality of forested and agricultural areas using soil-quality indices and digital soil-mapping in a semi-arid environment

ABSTRACT In recent decades, the conversion of forest to agricultural land has been a major worldwide concern and a cause of environmental and soil-quality degradation. In this study, soil-quality indices (SQIs) were applied using several soil properties to determine the effects of land use on soil quality in a 206.50 km2 area in Kurdistan Province, Iran. The Weighted Additive Soil Quality Index (SQIw) was calculated using two scoring methods and two soil indicator selection approaches. Nine soil-quality indicators/variables were measured for 124 soil samples (0–30 cm depth). Calculated SQIs were digitally mapped with a random forest (RF) model using auxiliary data. The RF model was the best predictor of the SQI computed using the total dataset (TDS) and linear score function (SQIw-TDS-linear). Soil quality was better estimated using non-linear scoring (r2 = 0.82) than with linear scoring (r2 = 0.73). The mean values of all SQIs were significantly greater in forestland than cropland. It is clear that soil quality is considerably reduced by deforestation, and that best management practices that maintain soil quality and reduce erosion must be developed for the soils of this region if they are to remain productive.