Soil Genesis and Classification
Fatemeh Rahmati; ُSaeid Hojati; Kazem Rngzan; Ahmad Landi
Abstract
Introduction: Knowledge about the spatial distribution of soil organic carbon (SOC) is one of the practical tools in determining sustainable land management strategies. Estimation of carbon contents and stocks are important for carbon sequestration, greenhouse gas emissions and national carbon balance ...
Read More
Introduction: Knowledge about the spatial distribution of soil organic carbon (SOC) is one of the practical tools in determining sustainable land management strategies. Estimation of carbon contents and stocks are important for carbon sequestration, greenhouse gas emissions and national carbon balance inventories. Accurate mapping of SOC’s spatial distribution is a key assumption for soil resource management and land use planning. During the last two decades, the utilization of data mining approaches in spatial modeling of SOC using machine learning algorithms have been widely taken into consideration. The digital environment needs to have soil continuous maps at local and regional scales. However, such information is always not available at the required scale. Therefore, DSM approach is a key solution for quantifying and assessing the variation of soil properties such as SOC using remotely sensed indices and digital elevation model (DEM) as the most commonly useful ancillary data for soil organic carbon prediction. In this way, the data mining techniques is the pathway to create digital soil maps. Therefore, this study was carried out to compare the two common machine learning algorithms including random forest and multiple linear regressions in digital mapping of surface SOC in the Semirom County, Isfahan province. The digital maps of SOC using the two above-mentioned algorithms were also created and the most important variables affecting the distribution of SOC in the study area reported. Materials and Methods: A total number of 200 surface soil samples (0-10 cm) were collected from the Semirom area (51º 17' - 52º 3' E; 30º 42' - 31º 51' N), Isfahan, Iran. Based on the synoptic meteorological station reports, the annual average temperature was in the range of 7.5-12.5 ▫C, the annual precipitation ranged between 350-450 mm. Soil moisture and temperature regimes are Xeric and Mesic, respectively. Then, using the Global Positioning System (GPS), sampling was done from the soil surface layer (0-10 cm). The preparation of soil samples includes air drying, pounding and softening of the collected samples performed, and then the samples were passed through a 2 mm sieve. Then, the amount of organic carbon in the samples was determined utilizing the Walkley-Black method. Also, in order to evaluate the effect of other soil properties on the organic contents of the soils, laboratory analyzes including saturated soil moisture content, soil texture, soil pH in saturated pastes, electrical conductivity of the soil saturation extracts and the calcium carbonate equivalent of the soils were measured utilizing standard laboratory protocols.In this research, auxiliary variables including terrain parameters and vegetation indices were derived from digital elevation model (DEM) and the Landsat 8 OLI satellite images employing ArcMap version 10.4.10 and SAGAGIS version 6.0.4. Then, all auxiliary layers were converted to raster format using the “raster” package and merged with each other using the “Covstack” function. Afterwards, the values of the all environmental covariates at each sampling point were extracted in a single file using the “extract” function of the “sp” package in the RStudio environment. Then, using SPSS software v.19 and the principal component analysis (PCA) method, among the 29 auxiliary variables used in this research, the most important auxiliary covariates were used in the modeling process. The dataset were then split into two groups referred to as calibration (80%) and validation (20%) subsets. Finally, SOC contents of the soils were predicted and mapped using multiple linear regression (MLR) and random forest (RF) algorithms in RStudio environment. MLR and RF algorithms were run employing “lm” and “randomForest” packages, respectively. Five different statistics was used for evaluating the performance of each model including the coefficient of determination (R2), bias, root mean square error (RMSE), nRMSE, and mean bias error (MBE). Results and Discussion Based on the descriptive analysis of the soil samples, soils of the study area were characterized as non-saline, alkaline, and calcareous soils. The SOC contents of the soils ranged from 0.3 % to 2.2% with the mean value of 0.89 %. The coefficient of variation for the SOC contents was 21.7%, based on which soils of the study area are classified as soils with the moderate variability considering the values proposed by Wilding (1985). The results of PCA showed that the most important auxiliary variables could be used for the modeling process are slope aspect, channels network base level, catchment slope, total curvature, height, longitudinal curvature, mass balance index, modified catchment area, slope degree, slope length, topographic position index, vertical distance to channel network, soil adjusted vegetation index, transformed vegetation index, difference vegetation index, ratio vegetation index, and general curvature.These variables explained 80% of the total variance over the study area. The comparison of the two different SOC prediction models, demonstrated that the RF model (ntree =1000 and mtry =10) with the R2, RMSE, nRMSE, and bias values of 0.79, 0.12, 0.13, and 0.002 respectively, had a better performance rather than MLR model in this study. The first five very important variables detected by RF algorithm to predict SOC contents over the study area were transformed vegetation index, ration vegetation index, soil adjusted vegetation index, and slope degree. The final map of the surface SOC distribution over the study area shows that although the estimates made by the RF algorithm have provided better estimates compared with the MLR model, but caused overestimation and/or underestimation in predicting the minimum and maximum values of the surface SOC contents, respectively. Conclusion The results of this study showed the better performance of the RF regression algorithm due to its ability to take into account the nonlinear and complex relationships between SOC contents and the environmental covariates compared to the MLR method.
Soil Genesis and Classification
Azam Jafari; Fereydoon Sarmadian; Ahmad Heidari; Zahra Rasaei
Abstract
Introduction: Machine learning algorithms usually do not consider spatial autocorrelation in soil data, unless it is perspicuity specified. Machine learning algorithms that compute autocorrelated observations have been recently formulated, such as geographic random forest (Georganos et al., 2019), or ...
Read More
Introduction: Machine learning algorithms usually do not consider spatial autocorrelation in soil data, unless it is perspicuity specified. Machine learning algorithms that compute autocorrelated observations have been recently formulated, such as geographic random forest (Georganos et al., 2019), or spatial ensemble techniques (Jiang et al., 2017). In theory, if we include all relevant environmental variables to model a soil property or class, there should be no spatial autocorrelation in the residuals of the fitted models. If this happens, some important predictors are likely to be missed. Despite the availability of the data set and the care taken during modeling, residual autocorrelation is still likely to occur. Several researchers have suggested the use of spatial alternative covariates as an indicator of spatial location in the SCORPAN model. The most common alternative is to use geographic coordinates (east and north) as covariates in the model, which leads to synthetic maps, especially when used in combination with tree-based algorithms. On the other hand, distance maps from observation locations are proposed by Hengl et al. (2018). Distance maps to observation locations usually do not have a clear meaning in terms of soil processes in an area (e.g., distance from a river). In the field of digital soil mapping, the current use of distance maps is not satisfactory for several reasons. The presence of pseudo-covariates with a set of covariates related to pedology is not very useful because it prevents the analysis of residuals and the creation of new hypotheses from these residuals. It also hinders the interpretation of the most important key predictors. Finally, pseudo-distance covariates may be well integrated into multiple pedology-related covariates, making them better predictors or masking the effect of pedology-related covariates. In spatial ecology, spatial eigen-vector maps, spatial filters or trend level regression replace distance maps in reducing or eliminating spatial autocorrelation (Kuhn et al., 2009). The purpose of this study is first to detect and calculate the spatial autocorrelation in the soil data. In the second step, it is going to develop a non-spatial model without considering the spatial autocorrelation, then to extract the spatial eigenvectors as an index of the spatial autocorrelation, and finally to use them as independent variables in spatial modeling.Materials and Methods: In this study, the soil salinity data utilized of 297 soil samples from a section of the Qazvin plain. The first and second derivatives of a digital elevation model as topography factors, remote sensing indices, parent material map, geoform map, and annual average temperature and rainfall maps were used to select the most important auxiliary variables. Finally, in order to select the best and most relevant environmental variables for modeling, the correlation between these variables and the dependent variable i.e. soil salinity in 297 study points was used using FSelector package of R software. Moran's I and Jerry's C indices were used to evaluate the spatial autocorrelation of soil data. First, the non-spatial ordinary least square (OLS) model was fitted to predict the spatial distribution of soil salinity. At this stage, spatial autocorrelation was not considered. Then spatial regression was fitted by calculating spatial filters through spatial eigenvectors as independent variables. Finally, the comparison of the outputs of the non-spatial OLS model and the spatial regression model was done with criteria such as R2, Akaike information criteria (AIC), autocorrelation of residuals and root mean of square error (RMSE).Results and Discussion: Statistical analysis indicated the high variability of soil salinity in the study area (coefficient of variation or CV more than 35%). Also, soil salinity shows high skewness and kurtosis, indicating its abnormal distribution. The high variability of this soil characteristic emphasizes the interaction of complex and numerous factors, including soil forming processes and different management strategies. The most important variables selected based on the correlation analysis include elevation, Multi-resolution Valley Bottom Flatness (MrVBF), wetness index, drainage basin, greenness index, normalized differential vegetation index (NDVI) and the corrected and transformed vegetation index (CTVI). A total of 7 variables were selected, which include four topography variables and three remote sensing variables. Among the topographical variables, the MrVBF had the most importance (correlation: 0.70). The spatial distribution map of soil salinity shows that the soil salinity is low in the northern, northeastern and northwestern parts towards the center of the studied area. The highest amount of salinity is found in the southern and southeastern regions. Moran's I and Jerry's C indices were 0.57 and 0.4, respectively. Based on both indices, soil salinity in the study area exhibits spatial autocorrelation. In the spatial regression model, by considering spatial autocorrelation, compared to the non-spatial model, the results are improved. By considering the spatial autocorrelation, the value of R2 increased, while the values of AIC, spatial autocorrelation of the residuals and RMSE decreased. The distribution maps of residuals from the non-spatial OLS model and the spatial regression model differ in terms of the spatial sign of the residuals and the spatial autocorrelation distribution that can be recognized in the form of clusters. Clusters (red or blue) indicate the presence of spatial autocorrelation in the residuals. In the distribution map of the residuals of the non-spatial model, more and larger clusters (marked with green ovals) are identified, indicating the existence of spatial autocorrelation in the residuals of the model. The presence of spatial autocorrelation in the residuals of a model shows that the model is not able to remove the spatial dependence, which may be due to not considering an important auxiliary variable in the modeling.Conclusion: This study was conducted in order to investigate the effect of spatial autocorrelation on the results of soil salinity modeling. Soil salinity prediction was done by non-spatial OLS model (without considering spatial autocorrelation) and spatial regression model (with spatial autocorrelation considered). The results indicated the improvement of the performance of the spatial regression model compared to the non-spatial ordinary least squares model. In the spatial model, considering the spatial autocorrelation as a covariate, the value of R2 increased, while the values of AIC, spatial autocorrelation of the residuals, and RMSE decreased.
Soil Genesis and Classification
Mozhdeh Taghipour; Nafiseh Yaghmaeian Mahabadi; Mahmoud Shabanpour
Abstract
Introduction: Soil quality index is used as a quantitative tool for assessing the impact of land use and management practices on soil condition. Soil quality is a sensitive indicator for revealing the dynamics of soil conditions, and it may vary with different land use and ecological restoration measures. ...
Read More
Introduction: Soil quality index is used as a quantitative tool for assessing the impact of land use and management practices on soil condition. Soil quality is a sensitive indicator for revealing the dynamics of soil conditions, and it may vary with different land use and ecological restoration measures. The land use affects the physical and chemical properties, biological processes, and land productivity, which lead to the change in soil quality. Land use change and agricultural development can lead to degradation, erosion and reduction of surface and subsurface soil quality. In most of the conducted studies, the surface soil quality has been evaluated; but these studies provide incomplete information because subsurface soil have the greatest impact on soil function and crop. In spite of various soil quality assessment methods developed in former researches, there are fewer attempts for selecting suitable and sensitive soil quality index, especially in different land uses. In this study, soil quality indicators were evaluated using multivariate analysis in three different land uses to select the most suitable and appropriate soil quality index in Tootkabon area of Guilan province.Materials and Methods: The study area is located in Tootkabon in Guilan province (latitude 36º 53' 21" N, longitude 49º 33' 44" E). Parent material is limestone and geomorphologic units that are comprised of hill land and plateau. In order to achieve the objectives of the research, 20 composite soil samples were taken from two depths of 0 to 15 and 15 to 30 cm from each of the land use, including forest, cropland and rangeland (60 soil samples in total) with the same parent material. The three land uses were located next to each other and at a close distance. In this research, using the principal component analysis (PCA) method, among 12 physical, chemical and biological soil indicators as total data set (TDS), clay percent, mean weight diameter, organic matter and available phosphorus were determined as the minimum data set. Then, the soil quality was evaluated by integrated quality index (IQI) and Nemoro quality index (NQI) using two linear and non-linear scoring methods (LS and NLS) and two soil indicator selection approaches, a total data set (TDS) and a minimum data set (MDS). Finally, to prioritize the soil quality indices based on sensitivity index (SI) and efficiency ratio (ER), the ranks of both criteria were summed and then made appropriate decision. All soil parameters were tested using one-way analysis of variance and the differences among means were analyzed using Duncan's significant difference test at the probability level of 0.05.Results and Discussion: The results of the present study showed that some soil properties including clay percentage, mean weight diameter, organic matter and available phosphorus had the greatest effect on soil quality in the study area. Most of the soil properties in rangeland and forest had a higher stratification ratio compared to cropland. The soil quality indices calculated using linear function for MDS indicated soil quality of forest and cropland were higher than rangeland. Maximum SI belonged to IQI-LS-TDS and IQI-LS-MDS with values of 1.56 and 1.40, respectively. Efficiency ratios (ER) were calculated to specify the power of each soil quality index being as representative index for whole soil parameters set. IQI-LS-MDS and IQI-NLS-MDS have the highest value of ER (75.0 %), it is obviously deducted that these developed soil quality indices correlate with much indicators than other indices. It has more efficiency ratio and therefore represents the soil overall condition highly. Finally prioritizing according to ranks of SI and ER showed that IQI-LS-MDS is the most suitable approach in soil quality assessment of study area. Conclusion: Minimum data set selection using principal component analysis as a multivariate statistical method could adequately represent total data set method. Therefore, it seems to be an appropriate approach for choosing more effective indicators with respect to saving time and money in the developing countries The linear soil quality indices showed higher capability than non-linear indices to differentiate soil quality among different land uses. Overall results of the prioritization soil quality indices imply that the IQI-LS-MDS has the most efficiency and sensitivity for variation in land uses, so it is suggested to use this quality index for further and comprehensive soil quality assessments plans.
Soil Genesis and Classification
Mastaneh Rahimi Mashkaleh; Mohammad Amir Delavar; Mohammad Jamshidi
Abstract
Introduction: Imbalanced data remains a widespread and significant challenge, particularly impacting machine learning algorithms. Therefore, addressing imbalanced data classification has emerged as a crucial research area within the field of data mining. This issue, often characterized by a limited number ...
Read More
Introduction: Imbalanced data remains a widespread and significant challenge, particularly impacting machine learning algorithms. Therefore, addressing imbalanced data classification has emerged as a crucial research area within the field of data mining. This issue, often characterized by a limited number of instances in one class and a substantial number in other classes, poses substantial hurdles for machine learning algorithms. Consequently, data mining experts and machine learning professionals are actively working on refining methods and models for classifying imbalanced data with the aim of improving the accuracy of such classifications. The principal objective of this study is to precisely detect and categorize samples from the minority class, ultimately enhancing the precision of soil class classification. This research is conducted in a specific region, encompassing the southwestern territories of Zanjan province.Materials and Methods: To achieve this objective, a total of 148 soil profiles were excavated using a regular grid pattern with an average spacing of 500 meters (and in some locations, up to 700 meters based on expert recommendations). After the samples were air-dried, they were transported to the laboratory. Physical and chemical analyses were conducted on all collected samples, including assessments of soil texture, soil pH, calcium carbonate equivalent, cation exchange capacity, electrical conductivity, organic carbon content, and gypsum content. Subsequently, the soil samples were meticulously classified and described up to the family level, following the comprehensive standards of the soil classification system. The most appropriate covariates were selected among 57 covariates including geomorphological and geological maps, digital elevation model (DEM), and data from Landsat 8 satellite images, using principal component analysis (PCA) and expert knowledge approaches for predicting soil classes selected. Saga-GIS and ENVI software were used to extract environmental covariates. Modeling of the soil-landscape relationship was performed using three algorithms, namely multinomial logistic regression (MNLR), random forest (RF), boosted regression tree (BRT) and ensemble model (after data balancing) in “R studio” software. To check the accuracy of the used model, the data was randomly divided into training and validation data. 80% of the data (118 profiles) were used for model training and 20% (30 profiles) were used as validation data for evaluation.Results and Discussion: The results of the selection of covariates showed that 10 information covariates of geomorphological maps, geological information and features extracted from the digital elevation model (DEM), including Analytical hill shading (AHS), sunrise, valley depth (VD), LS Factor, Channel network distance (CND), Topographic wetness index (TWI) and Multi-resolution ridge top flatness (MRRTF) were selected as input variables. Based on the results of profile analysis, the soils of the region at the subgroup level were categorized into five classes, with imbalanced distribution, including Typic Calcixerepts, Typic Haploxerepts, Gypsic Haploxerepts, Typic Xerorthents, and Lithic Xerorthents. The results of evaluation metrics such as overall accuracy and Kappa index were 65% and 0.32 for the RF algorithm, %60 and 0.35 for the boosted regression tree algorithm, 65% and 0.41 for the MNLR algorithm and after balancing the data with the ensemble model approach, it was 70% and 0.62 respectively. The results of two statistics of user’s accuracy and producer’s accuracy showed that among individual models, the multinomial logistic regression model has higher accuracy in predicting soil classes. Although the ensemble model has succeeded in predicting the soil minority classes well, due to the fact that the two weaker models of the RF and BRT are involved in the modeling, It showed lower values compared to the individual multinomial logistic regression model, in predicting some classes of the majority of soil, especially the two classes of Typic Haploxerepts and Typic Xerorthents.Conclusion: Conclusions: In summary, the results have demonstrated that when learning algorithms are individually applied, they do not exhibit high accuracy in spatially predicting soil classes. However, when these algorithms are amalgamated into an ensemble model, they exhibit remarkable accuracy in spatial soil class prediction, outperforming individual models in terms of performance and accuracy. Moreover, the ensemble model substantially enhances prediction accuracy and reduces the occurrence of misclassifications, especially at the subgroup level. While each specific model excels in predicting a particular soil classification, the cumulative ensemble models consistently outperform individual models in terms of overall performance and accuracy, underscoring the effectiveness of ensemble modeling in improving spatial soil classification.
Soil Genesis and Classification
Vahideh Sadeghizadeh; seyed ali abtahi; Majid Baghernejad; Azam Jafari; Seyed Ali Akbar Moosavi
Abstract
Introduction: The number of environmental variables used in digital soil mapping has increased rapidly, which has made it a challenge to select and focus on the most important covariates. No environmental covariates have the same predictability in modeling, and some covariates may introduce noise that ...
Read More
Introduction: The number of environmental variables used in digital soil mapping has increased rapidly, which has made it a challenge to select and focus on the most important covariates. No environmental covariates have the same predictability in modeling, and some covariates may introduce noise that reduces the predictive power of the models used. On the other hand, it is beneficial to identify all environmental variables to obtain spatial information that can improve predictions. In this regard, the feature selection algorithms help reduce the dimensions of the predictive model by identifying the associated covariates. Therefore, this study aims to investigate different feature selection algorithms in the selection of auxiliary variables and evaluation their effect on the predictive model. Materials and Methods: The area under study is a part of Darab city in the southeast of Fars province with an area of about 31000 hectares. In the study area 140 profiles were determined and excavated according to the diversity of geomorphological units and thus the type of soils. After excavating the profiles and checking the morphological characteristics of each soil profile, a sufficient amount of soil samples were collected from the genetic horizons and transported to the laboratory for further analysis. Some of the physical and chemical parameters of soils were tested using accepted techniques after air drying and passing through a 2 mm sieve. Finally, all profiles up to the great group level were classified using the U.S. Soil Taxonomy based on the data collected from field observations and the outcomes of laboratory analysis. Environmental variables include the parameters derived from the Digital Elevation Model, Landsat 8 images, geology and geomorphology maps of the study area. All parameters were derived using ArcGIS, SAGAGIS and ENVI softwares. In the present study, four different feature selection techniques including Variance Inflation Factor (VIF), Principal Component Analysis (PCA), Boruta and Recursive Feature Elimination (RFE), were used to identify an optimal set of covariates for predicting spatial classification of soil classes at the great group level. In addition, a Random Forest model (RF) with 10-fold cross-validation and the 5-repeat method, was used to compare different feature selection strategies in soil class mapping. The comparison of different feature selection techniques in estimating soil classes, was based on the evaluation criteria of accuracy and Kappa coefficient between observed and predicted values.Results and Discussion: The results showed that the prediction accuracy increased by using variables selected with different feature selection methods compared to using all variables in the model. In addition, the improvement in predictive performance is different between the four types of feature selection. The VIF and PCA methods had the highest and lowest accuracy index and Kappa coefficient, respectively. The Boruta method, with the lowest number of variables, improved the model's performance after the VIF method. However, the Kappa coefficient showed poor agreement between predicted and observed values for all approaches. The imbalance of soil classes could be a reason for decreasing the accuracy index and Kappa coefficient. However, the random forest model, with and without feature selection methods, identified all soil great groups in the study area. Therefore, it can be concluded that the Random Forest algorithm is a very powerful technique for spatial prediction of soil classes in the study area. Although the performance of the model varied using different feature selection algorithms, the predicted soil maps had similar spatial patterns. Based on the prediction of model with the variables selected by the VIF, the resulting map indicates that Ustorthents soils are mainly located in high altitude regions with steep slopes. Haplustepts, Calciustepts, and Calciusterts great groups have developed in places with low to medium slopes. Haplosalids have developed downstream of the salt dome. Great groups of Ustifluvents were discovered in fluvial sedimentary plains. Endoaquepts were found in the floodplains, which had the smallest area on the predicted map. Conclusion: Overall, the findings indicate that the feature selection methods can utilize significant dependencies among relevant covariates to predict soil classes and to improve modeling accuracy. In the current study, the environmental factors, obtained from the Digital Elevation Model, were selected as key variables, showing the importance of topography and morphology in the classification of soil types in the area. Although the selected variables improved the performance of the model, the prediction of soil classes was random. This could be attributed to the imbalance of soil classes.
Soil Genesis and Classification
Mahyar Moshtaghi; hasan ramezanpour; Nafiseh Yaghmaeian Mahabadi; Mahmoud Shabanpour
Abstract
Introduction: Soil classification categorizes soils into different classes on the basis of their distinguishing characteristics and provides a structured conceptual framework for describing and understanding soil properties. There are two soil classification schemes that are generally regarded as having ...
Read More
Introduction: Soil classification categorizes soils into different classes on the basis of their distinguishing characteristics and provides a structured conceptual framework for describing and understanding soil properties. There are two soil classification schemes that are generally regarded as having worldwide application, the Soil Taxonomy (ST) and the World Reference Base (WRB) which are also popular in Iran. These systems of classification consider diagnostic horizons and factors of soil formation as the basis of classification. The aim of this study was to determine the classification of soils of tobacco farms in the Talesh County of Guilan Province based on ST (2022) and WRB (2022) according to the soil diagnostic characteristics, then comparing two systems for soils of tobacco farms to determine the ability of better description of soils by these two systems of soil classification.Materials and Methods: Talesh County is considered to be the most important tobacco production areas in Guilan Province and IRAN. The most extensive area of tobacco cultivation in Guilan Province is located in this County and in Jokundan and Mountain districts. The study area has a humid climate with cold winter and hot summer. The mean annual temperature is between 15.6 and 17.2 degrees Celsius and the annual rainfall is between 786 and 1370 mm. Based on the map of moisture and temperature regimes of Iran and with the help of jNSM software, the moisture and temperature regimes were determined as Udic and the Thermic respectively. In the study area twenty pedons (eight pedons for Mountain and twelve pedons for Jokandan) were described and the morphological characteristics of the pedons layers were studied in the field according to the Soil Survey Manual. Then, the soil of each horizon was collected, air-dried, and sieved by passing through a 2 mm sieve before analyzing the properties of the soil. Soil pH, Electrical Conductivity, Texture, Organic Carbon, Calcium Carbonate Equivalent, Cation Exchange Capacity and Base Saturation were determined in all the samples according to Methods of Soil Analysis. Soils were then classified according to classification criteria of ST (2022) and WRB (2022) systems. For showing changes of tobacco farms soils, eleven pedons were selected as representative pedons and the reference between ST (2022) and WRB (2022) was established for tobacco soils at the level of the subgroup or secondary classification unit.Results and Discussion: The results revealed that according to ST (2022), representative pedons of Mountain district were classified as Entisols, Inceptisols and Mollisols orders while, Jokandan had Entisols, Inceptisols, Mollisols and Vertisols pedons. WRB (2022) Reference Soil Groups (RSGs) for Mountain was Regosols, Umbrisols and Phaeozems and for Jokandan district were Fluvisols, Cambisols, Phaeozems and Vertisols. At lower levels of classification, ST (2022) uses climatic data as soil moisture regime whereas WRB (2022) does not use. Therefore, the suborders or great groups of all soils were separated based on the Udic moisture regime. Finally, representative pedons were classified as Typic Udorthents, Mollic Udifluvents, Oxyaquic Udifluvents, Typic Humudepts, Dystric Eutrudepts, Typic Hapludolls, Fluventic Hapludolls, Aquic Argiudolls, Typic Argiudolls and Aquic Hapluderts at great group level. In regard to the WRB (2022), in the secondary levels, each section had its own series of principal and supplementary qualifications. Among those, the principal qualifications were mainly Eutric, Cambic and so on, and the supplementary qualifications were mainly Clayic, Loamic, Siltic, Humic and so on. Conclusion: It was found that when compared with ST (2022), the WRB (2022) had stronger abilities to distinguish soil properties for tobacco cultivation which was mainly reflected in the following aspects: 1- The climate-related soil moisture regimes were generally used to classify the suborders in ST (2022). It was found that the soil moisture status of all pedons was Udic, as well as the fixed format of naming soils in ST (2022), Therefore, divisions were limited in the suborders, 2- The flexibility of WRB with the utilization of multiple qualifiers brings out more sensitivity in reflecting soil characteristics in the soil name if compared with Soil Taxonomy. Also, the emphasis put on soil morphology compared with laboratory data makes the system suitable for application in areas with rather modest facilities, 3- The existence of the Mollic or Umbric horizon in pedons is well defined by WRB (2022), while this issue is ambiguous in ST (2022), 4- WRB (2022) have not fixed naming formats, the number of secondary levels qualifiers of the WRB system could be increased or decreased with the number of diagnostic characteristics of the soil pedons. 5- Nomenculture is very complicated in both systems, nevertheless, it is inevitable to transfer information to non- specialist users in a more simpler language, in WRB (2022) this information can be extracted more easily from the soil name.
Soil Genesis and Classification
mastaneh rahimi mashkale; Mohammad Amir Delavar; mohammad jamshidi; amin sharififar
Abstract
Introduction: Despite the great use of digital soil maps, the problems of imbalance in classification disrupt the classification performance of many machine learning algorithms, and for this reason, it has attracted the attention of many researchers. Therefore, the aim of this research is to improve ...
Read More
Introduction: Despite the great use of digital soil maps, the problems of imbalance in classification disrupt the classification performance of many machine learning algorithms, and for this reason, it has attracted the attention of many researchers. Therefore, the aim of this research is to improve the classification of unbalanced soil data using resampling pretreatment technique in three forecasting models including Random forest (RF), Boosted regression trees (BRT) and Multinomial logistic regression (MNLR) in a part of the lands of Zanjan province in Iran.
Materials and Methods: Sampling was done based on a regular grid pattern with 500 meters intervals, and 148 soil surfaces were randomly studied and classified. The region's soils at the subgroup level were in five classes with imbalanced distribution, including Typic Calcixerepts, Typic Haploxerepts, Gypsic Haploxerepts, Typic Xerorthents, and Lithic Xerorthents. Environmental covariates included geomorphological and geological maps, digital elevation model (DEM), and remote sensing (RS), selected by principal component analysis (PCA) and expert knowledge methods AND a number of environmental variables including geomorphological map information, Geological information and features extracted from the DEM were selected as the most effective environmental variables for predicting soil classes and as input to the model. Extraction of environmental covariates was done in ENVI and SAGA_GIS software and modeling of soil-landscape relationship was done using the aforementioned algorithms in Rstudio software. The resampling technique was applied to the minority and majority soil classes prior to modeling.
Results and Discussion: The results showed that using original data that have imbalanced classes for mapping resulted in loss of the minority classes and relatively low Kappa agreement values and overall accuracy for RF (ovrall=65%, k=0.32) and BRT models (ovrall=60%, k=0.35). However, after resampling the data, two overall accuracy and Kappa coefficient statistics increased in all models. In addition, the BRT model provided an acceptable estimate by maintaining the minority classes and the Kappa coefficient of 0.64 and the overall accuracy of 75% in the spatial prediction of soil subgroups. The producer accuracy (PA) and user accuracy (UA) results showed that the two classes of Gypsic Haploxerepts and Lithic Xerorthents, which were excluded when training using imbalanced datasets in RF and BRT algorithms, showed significant improvement after balancing the data. Results show that they were well predicted in RF algorithm (UA =100%, 78%) and BRT algorithm (UA= 60% and 70%) using treated data. Also, these minority classes showed Producer accuracy in RF algorithm (PA= 75%, 88%) and BRT algorithm (PA=100%, 78%) in compared to zero accuracy when training using imbalanced data. On the other hand, the validation results of the MNLR algorithm showed that despite maintaining the minority classes after balancing the data, the minority classes were predicted with less accuracy. Results showed that modeling using imbalanced distribution of class observation caused uncertain maps with minority classes being lost and relatively poor accuracies. After data treatment, with over- and under-sampling, all models showed significant improvement in maintaining the minority classes, in evaluations. Data resampling technique can be a useful solution for dealing with imbalanced class observations to produce more certain digital soil maps. Despite the great use of digital soil maps, the problems of imbalance in classification disrupt the classification performance of many machine learning algorithms, and for this reason, it has attracted the attention of many researchers. Therefore, the aim of this research is to improve the classification of unbalanced soil data using resampling pretreatment technique in three forecasting models including Random forest (RF), Boosted regression trees (BRT) and Multinomial logistic regression (MNLR) in a part of the lands of Zanjan province in Iran.Sampling was done based on a regular grid pattern with 500 meters intervals, and 148 soil surfaces were randomly studied and classified. The region's soils at the subgroup level were in five classes with imbalanced distribution, including Typic Calcixerepts, Typic Haploxerepts, Gypsic Haploxerepts, Typic Xerorthents, and Lithic Xerorthents. Environmental covariates included geomorphological and geological maps, digital elevation model (DEM), and remote sensing (RS), selected by principal component analysis (PCA) and expert knowledge methods AND a number of environmental variables including geomorphological map information, Geological information and features extracted from the DEM were selected as the most effective environmental variables for predicting soil classes and as input to the model. Extraction of environmental covariates was done in ENVI and SAGA_GIS software and modeling of soil-landscape relationship was done using the aforementioned algorithms in Rstudio software. The resampling technique was applied to the minority and majority soil classes prior to modeling.The results showed that using original data that have imbalanced classes for mapping resulted in loss of the minority classes and relatively low Kappa agreement values and overall accuracy for RF (ovrall=65%, k=0.32) and BRT models (ovrall=60%, k=0.35). However, after resampling the data, two overall accuracy and Kappa coefficient statistics increased in all models. In addition, the BRT model provided an acceptable estimate by maintaining the minority classes and the Kappa coefficient of 0.64 and the overall accuracy of 75% in the spatial prediction of soil subgroups. The producer accuracy (PA) and user accuracy (UA) results showed that the two classes of Gypsic Haploxerepts and Lithic Xerorthents, which were excluded when training using imbalanced datasets in RF and BRT algorithms, showed significant improvement after balancing the data. Results show that they were well predicted in RF algorithm (UA =100%, 78%) and BRT algorithm (UA= 60% and 70%) using treated data. Also, these minority classes showed Producer accuracy in RF algorithm (PA= 75%, 88%) and BRT algorithm (PA=100%, 78%) in compared to zero accuracy when training using imbalanced data. On the other hand, the validation results of the MNLR algorithm showed that despite maintaining the minority classes after balancing the data, the minority classes were predicted with less accuracy.
Conclusion: Results showed that modeling using imbalanced distribution of class observation caused uncertain maps with minority classes being lost and relatively poor accuracies. After data treatment, with over- and under-sampling, all models showed significant improvement in maintaining the minority classes, in evaluations. Data resampling technique can be a useful solution for dealing with imbalanced class observations to produce more certain digital soil maps.
Soil Genesis and Classification
samaneh Tajik; shamsollah ayoubi; mohmmad mehdi darvisihi; hossein khademi
Abstract
Introduction Soil snails constitute an important part of the forest ecosystem and play an essential role in litter decomposition and soil calcium concentration. Snails are known as bioindicators because of narrow distribution, short lifetime, and high sensitivity (22, 24). The abundance and distribution ...
Read More
Introduction Soil snails constitute an important part of the forest ecosystem and play an essential role in litter decomposition and soil calcium concentration. Snails are known as bioindicators because of narrow distribution, short lifetime, and high sensitivity (22, 24). The abundance and distribution of soil snails are dependent on different environmental conditions, such as precipitation, pH, soil calcium, and plant cover. Also, soil properties are mainly related to topographic parameters. Because ecosystem components have complex relationships, we need powerful models to find effective factors and spatial variations of the soil fauna (23). Linear Regression and random forest are popular and applicable models in soil science. Up to the present, no study has investigated the effect of soil parameters on snail abundance using linear regression and random forest. This study was performed to investigate the effect of soil properties and topographic parameters on the abundance of soil snails and their distribution in a part of forest area located in Bahramnia forest, an experimental site in Golestan Province, in the north of Iran. Materials and Methods This study was conducted in Shast Kalate (Bahramnia) forest, an experimental forest of Gorgan University of Agricultural Sciences and Natural Resources, located at the eastern Caspian region, north of Iran (36° 43′ 27″ N latitudes, 54°24′ 57″ E longitudes). 153 soil samples were collected from 0-10 cm; then soil snails were gathered and classified into the Gastropoda taxonomic class group. Soil properties, such as Soil particle size distribution (clay, silt, and sand), soil pH, electrical conductivity (EC), calcium carbonate equivalent (CCE), soil organic carbon (OC), total nitrogen (TN), and Soil microbial respiration (Resp), were measured via laboratory analysis. Also, digital elevation model and satellite images were used to determine the topographic parameters, such as Elevation, slope, slope aspect (Aspect), land surface temperature (land temp) wetness index (WI) and normalized difference vegetation index (NDVI). We used linear regression and nonlinear random forest models for investigating linear and nonlinear relationships between soil properties, topographic parameters, and the abundance of soil snails. Likewise, sensitive analysis was done to find the importance of the input parameters. Results and Discussion The PCA analysis showed that first and second components explain 38 and 21 percent of the variation. In the first component, EC, OC, TN, pH, and silt were the most variable, and in the second component CCE, Clay, OC, sand, and EC were the most important parameters. In both components, topographic parameters had no effect. The PCA graph showed that CCE, sand, and pH had the most correlation with snail abundance and EC, Resp, OC, and TN affected their abundance. The validation results of regression and random forest models showed that random forests have more accuracy (0.49) and low error (1.82). In addition, the sensitive analysis showed that CCE, pH, EC, OC, aspects, elevation, and land temp are the most important parameters on snail abundance. Different studies reported that pH and CCE are effective parameters on snail abundance (20, 17). Also, Ondina., et al. (27) reported that EC has an important effect on soil snail abundance. We hypothesize that topographic parameters affect soil snail nonlinearly and by affecting soil properties. Aspect is one of the topographic parameters that, via an effect on land temperature, land cover, and pH (8), has an important role in soil snails. In this way, elevation, by affecting pH, wetness, land temperature, OC, and TN, affects soil snail abundance (13). Land temperature is the other topographic parameter that is affected by aspect and elevation and had a significant effect on snail abundance by affecting OC and wetness (17). Conclusion Based on the results, nonlinear random forest model had more accuracy than linear regression in predicting snail abundance. Results showed that calcium carbonate equivalent, pH, EC, and organic carbon were the most effective soil priorities on snail abundance. There was no linear relation between soil properties and soil snails, but in the nonlinear model, we found their role. Aspect, elevation, and land temperature were the most effective parameters on snail abundance that probably affected soil properties, such as calcium carbonate and soil moisture.
Soil Genesis and Classification
Mehdi Taheri
Abstract
Introduction During the last decade, considerable progress has been made in the study of known loess deposits and their paleoclimatic implications in Northern Iran, whereas little information is available about the red soils which are beneath the these loess. So, in this study, major and trace element ...
Read More
Introduction During the last decade, considerable progress has been made in the study of known loess deposits and their paleoclimatic implications in Northern Iran, whereas little information is available about the red soils which are beneath the these loess. So, in this study, major and trace element concentrations were analyzed on the samples from a red sequence of Iranian Loess Plateau at Golestan province. The main objectives of this research are a) to address the origin of the red soils with compare to the other geochemical results such as upper Pleistocene loess-paleosol, upper continental crust and Jiaxian Red Clays in China, b)to examine the geochemical behaviors of certain elements and their ratios such as Al2O3/Na2O, Na2O/K2O, MgO/TiO2, Rb/Sr and Chemical Index of Alteration (CIA) during pedogenesis and finally, to reconstruct the early Pleistocene climate. Materials and Methods This study was carried out on a 19-m-thick sequence of deposits exposed in a limestone quarry located near the Agh Band village of Golestan province in the east of the Iranian Loess Plateau (latitude 37.688889 N and longitude 55.158333 E). The so-called Agh Band red sequence underlies an upper Pleistocene loess-paleosol sequence and covers yellow limestone of the Akchagyl formation belonging to the Upper Pliocene of Kopet Dagh sedimentary basin. It is the first sequence one of red soils described for the loess plateau of Iran. Based on the paleomagnetically dating, this section is formed during ~2.4-1.8 Ma. The present-day climate of the study area is semi-arid, with mean annual precipitation and temperature of ca. 300 mm and 17◦ C, respectively. The soil moisture regime is Xeric-Aridic and the temperature regime is Thermic. In a field campaign in autumn 2014 the morphological characteristics of the section were recorded. Based on field observations, the sequence has been subdivided into 24 units, designated consecutively as U1-U24 from the top of limestone to the bottom of the Upper Pleistocene Loess. From each unit, representative samples were taken for color measurements, grain-size and geochemical analysis. Each air-dried sample was gently crushed, taking care not affect the grain size, and then measured using a Konica-Minolta CM-700 color meter. Grain size was measured using a Malvern Mastersizer 2000 laser grain-size analyzer following the pre-treatment procedures described in the text and the concentrations of major and trace elements were determined using a PANalytical PW2403/00 X-ray fluorescence spectrometer. All of the measurements were made in the Key Laboratory of Western China’s Environmental systems, Lanzhou University.Results and Discussion The grain-size distribution of the red section is dominated by fine-grained silts with the average of 86.6 percent, in addition, the amount of clay and sand are 10.9 and 2.6 percent, respectively. Angular or sub-angular blocky structures are dominated in the red sequence. The section is mainly characterized by alternations of reddish yellow )10 YR 6/6) and brownish-red (7.5 YR 3/6) to reddish (5YR) layers. In general, the color of the soil horizons in the red deposits is much redder than that in the overlying loess (7.5YR vs.10YR, respectively), and this is one of the principal differences between the red soils and the overlying loess. Another different is the amount of carbonate nodules and the size of them (up to~20 cm diameter). These soils have been subjected to relatively intensive pedogenesis, as demonstrated by the presence of clay skins and Fe-Mn coatings. The high correlation of major and trace element compositions between Agh Band red soils section, upper loess and paleosol and the Jiaxian red clay in China supports the proposal that the Agh Band red soils was wind-blown in origin. The value of CIA index (69.6 for red soils versus 59.8 for the upper loess deposits), Al2O3/Na2O, K2O/Na2O and Rb/Sr ratios are higher in the red deposits than in the upper Pleistocene loess, also, the lower amount of MgO/TiO2 ratio in reddish soils, suggesting stronger chemical weathering and thus a wetter climate during the formation of red soils in early Pleistocene.Conclusion Finally, our main findings are as follows: 1) The geochemical composition of the red-colored sedimentsis similar to the overlying upper Pleistocene loess suggesting a similar origin; 2) wind-blown origin of the red deposits and continuous atmospheric dust deposition in the Iranian Loess Plateau during the Early Pleistocene; 3) red soil sequence formed under wetter and more humid climate compared with the Upper Pleistocene loess.
Soil Genesis and Classification
Farideh Abbaszadeh Afshar
Abstract
Introduction Mapping the spatial distribution of soil taxonomic classes is important for informing soil use and management decisions. Digital soil mapping (DSM) can quantitatively predict the spatial distribution of soil taxonomic classes. DSM is the computer-assisted production of digital maps of soil ...
Read More
Introduction Mapping the spatial distribution of soil taxonomic classes is important for informing soil use and management decisions. Digital soil mapping (DSM) can quantitatively predict the spatial distribution of soil taxonomic classes. DSM is the computer-assisted production of digital maps of soil type and soil properties. It typically implies use of mathematical and statistical models that combine information from soil observations with information contained in correlated variables and remote sensing images. Machine learning is a general term for a broad set of models used to discover patterns in data and to make predictions. Although machine learning is most often applied to large databases, it is an attractive tool for learning about and making spatial predictions of soil classes because knowledge about relationships between soil classes and environmental covariates is often poorly understood. Our objective was to compare multiple machine learning models (multinomial regression logistic, boosted regression trees and decision tree) for predicting soil great groups at Bam distinct in Kerman province.Materials and Methods The study area, Bam district was located between 58°4΄17˝ to 58°28΄8˝ E longitudes and 28°52΄51˝ to 29°9΄29˝ N latitudes (Fig. 1), at Kerman province, (Southeastern Iran). The area is surrounded by mountains (dominantly limestone and volcanic) from northwest toward southeast with major landforms included young alluvial fans and pediment, clay flat and hills. The mean annual precipitation, temperature and potential evapotranspiration are respectively 64 mm, 23.8◦C and 3000 mm with Aridic and Hyper thermic soil moisture and temperate regimes Stratified sampling scheme were defined in 100000 hectares, and 126 soil profiles were excavated and described by Key of soil taxonomy. Our objective was to perform and compare multiple machine learning models for predicting soil taxonomic classes (great group level). The models were used in this study including, multinomial logistic regression (MLR), boosted regression trees (BRT) and decision tree (DT). We used 80/20 training/testing split (80% of the pedon observations were used for model training and 20% for model testing). Kappa index (KI), overall accuracy (OC), Brier scores (BS), User accuracy (UA) and producer accuracy (PA) were used to compare model accuracy.Results and Discussion The profile description revealed the presence of two soil orders: Entisols and Aridisols that, subdivided in six suborders and eight great groups: Haplosalids, Haplocambids, Haplocalcids, Haplogypsids, Calcigypsids, Calciargids, Petrocalcids and Torriorthents. This testifies to the wide pedodiversity of the study area, considering that is characterized by the presence of eight soils great groups. Results showed that the geomorphology map contributed importantly to the prediction accuracy. This can be explained by the fact that the geomorphological surfaces have formed recently, or during a geological period with soil formation under conditions close to those of current processes in the arid regions. Terrain attributes and finally remote sensing indices after geomorphic surface were imported as predictors in the prediction. The best prediction result was obtained when characteristics derived from terrain, remote sensing and geomorphological processes were used together and when differentiation of geomorphological processes and overall heterogeneity identification and stratification of the study area was made. In areas where the distribution of predictors was more homogenous, the models can better understand and connect predictors and response. The spatial distribution of soils in the study area followed the distribution pattern of most geomorphological and terrain attributes. The results of model comparing indicated that decision tree was consistently the most accurate. The results of prediction accuracy of soil groups showed that the highest accuracy related Haplosalids, Calcigypsids and Petrocalcids soil great groups. The lowest of predictive quality was observed for Haplocalcids in three approaches. As a reliable and flexible approach, decision tree could be used successfully to prepare continuous digital soil maps.Conclusion The application of decision trees for prediction of soil types could be a promising alternative. In digital soil mapping, the best prediction result was obtained when parameters derived from terrain, remote sensing and geomorphological processes were used together and when differentiation of geomorphological processes and overall heterogeneity identification and stratification of the study area was made. In areas where the distribution of predictors was more homogenous, the models can better understand and connect predictors and response. Altogether, an extended digital terrain analysis approach and clear description of geomorphological, geological and pedological processes could be a promising key technology in future soil mapping.
Soil Genesis and Classification
Mansooreh Khaleghi; Azam Jafari; Mohammad Hadi Farpour
Abstract
Introduction Soil digital mapping represents a set of mathematical computations to predict the distribution of soil classes in the landscape. This approach relies on statistical relationships between measured soil observations and environmental covariates at the sampling locations. The need for digital ...
Read More
Introduction Soil digital mapping represents a set of mathematical computations to predict the distribution of soil classes in the landscape. This approach relies on statistical relationships between measured soil observations and environmental covariates at the sampling locations. The need for digital soil mapping as an addition to conventional soil surveys results from a worldwide growing demand for high- resolution digital soil maps for environmental protection and management as well as projects of the public authorities. Digital soil data is increasing based on new processing tools and various digital data. The digital identification of soils as a tool for creating soil spatial data provides ways to address the growing need for high-resolution soil maps. The main objective of this study is to generate the digital soil map based on the legacy soil data. Materials and methods The study area is located in southeastern Iran, 330 km from Kerman city, in Faryab distinct. In this study, a Latin hypercube sampling design was applied and the sampling was done according to the difference in landforms (geomorphology map), topography (including digital elevation map) and geology. The geographic locations of 70 profiles were identified. Soil profiles were described according to U.S. Soil Taxonomy (Soil Survey Staff, 2014) and finally, the soil samples were taken from their diagnostic horizons. The collected soil samples were transferred to the laboratory, and some physical and chemical analyzes were performed based on routine standard methods. Environmental data include the parameters derived from the digital elevation model, Landsat satellite images (remote sensing indexes), geology map, geomorphic units (geomorphology map) and legacy soil map of the study area. All environmental variables were derived using ENVI and SAGA software. In this research, a multinomial logistic regression model was used to predict soil classes and the modeling was done in two scenarios: 1- modeling without the legacy soil map and 2- modeling with the legacy soil map. Estimation of predictive accuracy of soil classes was also done using the overall accuracy index and Kappa coefficient. Results and discussion The result of the modeling with the multinomial logistic regression method in two sets of input variables showed that the topographic position index is the most effective variable in predicting soil classes. This confirms topographic importance on soil genesis in the studied area. After topographic variables, the legacy soil data is an effective parameter in modeling. The legacy data of soil is a strong and valuable database for predicting soil characteristics. The old soil map consists of the salt surfaces and Inceptisols order. Unlike the hot and arid climate of the study area, Inceptisols order was identified in the old soil map. Soil survey with very small scale was probably led to generalization of the studied soils and hiding the main soils of the study area. However, the small-scale mapping and the presentation of different soils in the region do not prevent the presence of the old soil map as an important predictor. It seems that there is a high concordance between the borders of old soil map and the described soils diversity in the study area. The matching and concordance between the boundaries of the old map and the described soil profiles help the model to differentiate different soils, although the correspondence between the soils type of the old soil map and the observed soils can play a more effective role in predicting by the model. Soil legacy information is a powerful and valuable database for predicting any feature of the soil. In both predicted maps, four major groups of Haplosalids, Haplocambids, Haplocalcids and Torriorthents were identified. The great group of Torriorthents is located in the north of the region and in the alluvial fan landform. Haplosalids great groups were most commonly found in clayey surfaces. Haplocambids and Haplocalcids great groups are located more in the geomorphic surface of the cultivated fan and the piedmont plain, respectively. The results of the predictive quality of the logistic regression model showed that the number of well-estimated soils in the presence of the old soil map is more than when there is no old soil map in the modeling. In addition, the results of the validation of the models showed that the map accuracy and kappa index increased in presence of the legacy soil map. As a result, the model's validation indices including the map purity and Kappa index increased from 0.47 and 0.16 to 0.63 and 0.43, respectively. In both models, the highest accuracy of the estimation was obtained for Haplocambids great group. Conclusions The results showed that topographic position index was the most important and powerful variable for forecasting in both models, and confirms that topography or relief is the most important soil forming factor in the study area. Using the legacy soil map as one of the environmental variables in modeling, efficiency and accuracy are more accurate than modeling without the legacy soil map. If the old soil maps as legacy information are used in digital soil mapping, the similarity and matching of the soils of the studied area shoud be cheched even with the very small scale because the high concordance leads to rational prediction, and random and chance predictions do not occur.
Soil Genesis and Classification
Maryam Mohammadzadeh Mohammadabad; F. Khormali; Farshad Kiani; mohammad ajami
Abstract
Introduction Soil degradation is a widespread environmental problem that occurs as a result of land use change and destruction of vegetation cover that may lead to changes in soil structure and porosity. Land use change and land management have significant effects on physical and chemical properties ...
Read More
Introduction Soil degradation is a widespread environmental problem that occurs as a result of land use change and destruction of vegetation cover that may lead to changes in soil structure and porosity. Land use change and land management have significant effects on physical and chemical properties and biological capabilities of soil. The investigating of undisturbed and natural soil structure using microscopic and ultramicroscopic techniques provides invaluable information about the physicochemical, mineralogical, morphological properties and soil genesis and calcification. Image analysis is an advanced method for quantifying soil properties and increasing the precision of morphological and micromorphological studies. Materials and Methods In this study, in order to investigate the impact of different land uses on porous and microstructure of surface soil horizons, 9 profiles in different land uses, including natural forests, artificial forest, abandoned land, orchard and cropland were extracted and described. Then one sample was taken from each horizon for physical and chemical analysis as well as a few undisturbed samples for micromorphological studies. Physical and chemical parameters such as texture, bulk density (BD), calcium carbonate equivalent (CCE), organic carbon (OC) and mean weight diameter (MWD) were measured. After preparation of thin sections of soil, micromorphological studies were conducted by polarizing microscope. Then from each thin section, 20 photos were taken randomly in plane polarized light (PPL) and cross polarized light (XPL) and transferred to image tool software. The percentage of total porosity of soil, feret diameter and area pores parameters were studied quantitatively. Three classes of feret diameter in micrometer and five classes of area in square micrometers were considered for pores in the soil thin sections. After importing photos to the software and performing calibration, grayscale and subtracting two images, the range of pores was identified by the software. Then in the classification section of software, the highest level of classes in each part was determined and the percentage of pores in each class was calculated and data obtained were analyzed by SPSS 16.0 software. Results and Discussion Micromorphological observations showed that in natural and artificial forests, a significant amount of organic matter in the soil has resulted in the formation of granular and subangular blocky dominant microstructure. While in cropland land use the type of microstructure is mainly massive and angular blocky, due to deforestation and agricultural practices, which resulted in the degradation of soil microstructure. Appropriate environmental conditions and dense vegetation in natural and artificial forests land use lead to significant biological features in comparison to other land uses that were subjected to deforestation. In natural and artificial forests land uses, the percentage of channel and large vughs pores is more than other land uses mentioned above. Tillage results in degradation of soil structure in cropland land use, the majority of pores observed in thin section are vugh and plane. Also, the results of image analysis showed that in natural forests and orchard land uses, pores with diameters ranging from 2 to greater than 10 micrometer and areas ranging from 500 to greater than 1000 square micrometers had the highest frequency in terms of percentage of soil pores. Hence, these soils are considered as quite porous class, while in cropland land use, tillage results in the degradation of large pores showed that pores with diameters less than 2 to 10 micrometers and areas smaller than 5 to 50 square micrometers comprised and the highest percentage of soil pores. Conclusion Asignificant amount of organic matter and low bulk density, and the highest percentage of total porosity are found in natural forest and orchard land uses, while deforestation and cultivation in cropland land use has led to compression and destruction of soil structure. This fact reflects itself in the increased bulk density and decreased total porosity. Agricultural practice has a significant effect on destruction of surface soil structure. Microstructure and voids of cropland land use are mainly massive and angular blocky and plane and vughs, respectively. With changes of land use from forest to cropland, and consequently incorrect land management causes decrease in organic matter. Shortage of organic matter causes decreasing biological activity in surface soils. The best way to prevent degradation of the soil in this area is to preserve natural forests and change cropland land use to orchard and artificial forest land uses.
Precision Agriculture
R. Taghizadeh-Mehrjardi; F. Sarmadian; M. Omid; N. Toomanian; M.J. Rousta; M.H. Rahimian
Volume 37, Issue 2 , March 2015, , Pages 101-115
Abstract
In recent years, there has been a great development in the digital soil mapping which has led to production of maps for countries and the continents. Although many studies have been conducted all over the world, few Iranian soil scientists have shown interests in digital mapping. Therefore, in the present ...
Read More
In recent years, there has been a great development in the digital soil mapping which has led to production of maps for countries and the continents. Although many studies have been conducted all over the world, few Iranian soil scientists have shown interests in digital mapping. Therefore, in the present research, different data mining techniques (i.e. regression logistic, artificial neural network, genetic algorithm, decision tree and discriminant analysis) were applied to spatial prediction of great group soils in the area covering of 72000 ha in Ardakan. In this area, by using the conditioned Latin hypercube sampling method, location of 187 soil profiles was selected, which was then described, sampled, analyzed and allocated in taxonomic classes according to soil taxonomy of America. Auxiliary data used in this study to represent predictive soil forming factors were terrain attributes, Landsat 7 ETM+ data and a geomorphologic surfaces map. Results showed that decision tree model had the highest accuracy while it could increase the accuracy of prediction up to 44% in comparison with discriminant analysis technique. Results also indicated using the taxonomic distances led to improving the overall accuracy of decision tree up to 3%. Results confirmed capability of decision tree, artificial neural networks, genetic algorithm, logistic regression, and discriminant analysis with 70%, 65%, 65%, 55%, and 47% accuracy, respectively. Moreover, results showed that decision tree model could predict soil classes in sub-great group with the overall accuracy of 84.2%.
