hossin shekofte; maryam doustaky; aezam maseodi
Abstract
Introduction: Soil quality is defined as the capacity of a soil to function within different land uses and ecosystem boundaries, sustain biological productivity, maintain environmental quality and promote plant, animal, and human health. Soil quality cannot be directly measured but can be evaluated on ...
Read More
Introduction: Soil quality is defined as the capacity of a soil to function within different land uses and ecosystem boundaries, sustain biological productivity, maintain environmental quality and promote plant, animal, and human health. Soil quality cannot be directly measured but can be evaluated on the basis of several parameters; the type of parameter to be used depends on research scale and goals. Soil quality indicators (SQIs) are used to evaluate the effect of different management and types of land use on soil quality and can be achieved by easily-measured soil physicochemical properties. Soil quality indicators are measurable characteristics of the soil affecting the soil capacity for crop production or environmental performance. Air capacity (AC), relative field capacity (RFC) and plant available water (PAWC) are the most important indicators. Selection of appropriate input parameters is the first and most important step in predicting SQIs. Feature selection can be defined as the identification and selection of a subset of useful features among the primary data collected. One of the methods for choosing the features is the Pearson coefficient, which shows the correlation between the input variables and target variable. When the coefficient is close to one, there is a strong relationship between the input and the target variable. The features having a correlation coefficients of greater than or equal to 0.9 are considered important and less than that are considered non-important. Decision tree algorithm is one of the prediction approaches in statistics and data mining literature. This algorithm can select the property with the highest separation capability. Working with this algorithm and interpret its results is very straightforward. The aims of this study were to select the best set of input properties influencing SQIs using Pearson correlation coefficient and then model the effect of the input properties by decision tree and multiple linear regression.
Materials and Methods: In this study, the Pearson correlation coefficient was used for selecting effective soil properties influencing SQIs and these indices were modeled and predicted by the decision tree algorithm with selected input properties. For this purpose, 104 soil samples were collected from the soil surface (0-15 cm depth) of four land uses including a garden with 20 year-old walnut trees, pasture, agriculture and a mountain almond in a semi-arid area in Iran (Rabor region, 29 27′ N to 38 54′ N and 56 45′ E to 57 16′ E). A multiple linear regression (MLR) model was constructed as the benchmark for the comparison of performances. Sensitivity analysis of decision tree model was performed with input variables using StatSoft method. The predictive capabilities of the proposed models were evaluated by the mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R2) between measured and predicted SQIs values.
Results and Discussion: The soil properties including porosity, bulk density, clay and sand content for air capacity, porosity and sand, clay and silt content for relative field capacity, and bulk density, electrical conductivity, porosity, and sand, clay and silt content for plant available water were selected as important input parameters. In addition, the values of r2 for the decision tree model for air capacity, relative field capacity and plant available water were 0.95, 0.84 and 0.85, respectively, while the r2 values for multiple linear regression for AC, RFC and PAWC were 0.63, 0.62 and 0.61, respectively. According to the evaluation indices, it appears that the conventional regression model was poor in predicting SQIs. Therefore, conventional regression techniques (i.e., multiple-linear regression) may not be reliable for predicting the SQIs. The results of sensitivity analysis for decision tree model showed that porosity and bulk density for air capacity, porosity for relative field capacity and bulk density for plant available water had the greatest influence.
Conclusion: This research work provided a basis for predicting soil physical quality indicators and identifying important parameters impacting these indicators in agricultural soils, grassland and forests in semi-arid regions which can be generalized to other areas. Further studies are needed to assess the effects of selected input variables under different conditions.
Mehdi Zangiabadi; manoochehr gorji; Mehdi Shorafa; Saeed Khavari Khorasani; Saeed Saadat
Abstract
Introduction: Soil is the main source of water retention and availability for plant uptake. The supplement of water is completely dependent on soil physical properties. The soils with higher values of available water are generally more productive because they can supply adequate moisture to plants during ...
Read More
Introduction: Soil is the main source of water retention and availability for plant uptake. The supplement of water is completely dependent on soil physical properties. The soils with higher values of available water are generally more productive because they can supply adequate moisture to plants during the intervals between irrigation or rainfall events. Generally according tothe spatial and temporal distribution of precipitation, Iran has an arid climate in which most of the relatively low annual precipitation falls from October through April. Thus, water deficiency along with the lack of organic carbon in the soil justifies the necessity of studying the soil, water and plant relationships that may improve the efficiency of water consumption in agricultural practices. For that reason, this research was conducted to investigate the relationship between some soil physical properties and Integral Water Capacity (IWC) index as one of the soil physical quality indices.
Materials and Methods: This study was conducted in Torogh Agricultural and Natural Resources Research Station in Khorasan-Razavi province, north-eastern Iran during 2013-2014. This station is located in south-east of Mashhad city with a semi-arid climate, annual precipitation of 260 mm and mean air temperature of 13.5 °C. The soil was classified in Entisols and Aridisols with a physiographic unit of alluvial plain that generally had medium to coarse textures in topsoil. Thirty points with different soil textures and organic carbon contents were selected as experimental plots. In order to measure different properties of the soil, two soil cores (8 cm diameter × 4 cm length cylinder for bulk density and 5 cm diameter × 5.3 cm length cylinder for sandbox measurements) and one disturbed soil sample (for other measurements) were collected from 0-30 cm depth of each plot. After conducting required laboratory analysis and field measurements using standard methods, the soil moisture curve parameters (RETC program), Porosity (POR), Air Capacity (AC), Relative Field Content (RFC) and Integral Water Capacity (IWC) index, were calculated. In this regard, integration calculations were done by Mathcad Prime 3 software. Finally, the relationship between the measured properties and IWC index were analyzed using Pearson correlation coefficient and stepwise multiple linear regression by SAS (9.1) statistical software.
Results and Discussion: Laboratory analysis results showed that the soil texture classes of samples were loam (40%), silt loam (23%), silty clay loam (17%), clay loam (13%), and sandy loam (7%). On average, very fine sand particles were dominant between five size classes of sand and the lowest values were devoted to very coarse sand particles. Soil porosity and air capacity calculation results indicated that on average bulk soil porosity (PORt) and bulk soil air capacity (ACt) were 0.46 and 0.20 (cm3cm-3), respectively. According to the results, RFC of 60% of studied soil samples were lower than 0.6, 7% were higher than 0.7 and only 33% were between 0.6-0.7 (optimal range). IWC index calculations were resulted in 0.13-0.25 (cm3cm-3) in different soil textures. The highest IWC were related to Loam and Clay Loam textures, respectively. Statistical analyses indicated that there were no significant relationship between soil particles (sand, silt and clay) and organic carbon content with IWC index. The factors of soil bulk density and RFC were negatively correlated with IWC index that means decreasing the soil bulk density and RFC would lead to the reduction of the effects of water uptake limitation factors by increasing the values of weighting functions (IWC calculations), and improvement of soil physical quality. High significant (P < 0.001) positive correlation coefficients were observed between IWC index and the factors of soil PORt, ACt and soil matrix air capacity (ACf) in this study. Multiple regression analysis results showed that IWC index could be estimated by the factors of ACt and PORt with the determination coefficient of 0.63. The partial determination coefficients indicated that ACt factor accounted for 50% and PORt accounted for 13% of IWC index variations.
Conclusion: The results indicated that in medium to coarse-textured soils, IWC index could be estimated using the bulk soil air capacity (ACt) and bulk soil porosity (PORt) factors that are derived from soil volumetric water content at saturation and field capacity points.
