zohreh mosleh

This study evaluated the climatic suitability of several almond cultivars that flower at different times: Sefied, which flowers early, Mamaei and Rabie, which flowers in the middle, and Shahroud 7 and 12, which flowers late. The phenological stages of almond trees were first identified using prior research and discussions with provincial horticultural experts. After gathering long-term climate data, the climate requirements of almond plants were compared with the regional climate factors. Subsequently, the climatic suitability classes were identified, and a corresponding map was created. The evaluation of climatic suitability for early-flowering cultivars revealed that the province's climate presents severe to very severe limitations for growing and cultivating this crop, with a large percentage of the province (roughly 53.3%) experiencing very severe limitations, meaning that the climate is unsuitable for these cultivars.The climate of the province for mid-flowering almond cultivars varies,with regions categorized into severe limitations, very severe limitations (correctable), and non-correctable very severe limitations. Nonetheless, the majority of the province's counties are classified as S3 suitability class (severe limitation) for cultivating and developing mid-flowering cultivars. For late-flowering cultivars, the climate of the province across all counties falls within the S3 suitability class. Therefore, the climatic suitability of a region varies not only for each plant but also for different cultivars of the same plant. Additionally, the most limiting climatic parameter is the average minimum temperature during the flowering stage. In order to maximize production and lessen climate-related constraints, the study emphasizes how crucial it is to choose suitable almond cultivars based on blooming timings and local climate conditions, especially the average minimum temperature during the flowering stage.

Satellite images and remote sensing approaches are important tools for evaluating, mapping, and managing saline lands in different world regions. The main aim of the present study was to investigate the degree of concordance between maps obtained by machine learning methods and kriging estimator about salinity monitoring of a part of the soils of marginal lands of Sirjan Playa in two seasons, i.e., winter and summer, using two remote sensing data sources, i.e., Landsat 8 and Sentinel 2. Ninety surface soil samples (zero to 30 cm) were collected as a regular grid sampling pattern with 750 meters intervals. Some of their most important physical and chemical characteristics were determined using standard measurement methods. After performing radiometric and atmospheric corrections on mentioned satellite images, in addition to the main bands, 13 salinity indices were used to estimate soil salinity using artificial neural network, decision tree, random forest, and support vector machine models. Besides, kriging maps of soil salinity were drawn for both mentioned times. Results showed a higher performance (R2 =0.87 versus= 0.72) of Sentinel-2 than Landsat-8 in predicting soil salinity.  Moreover, results confirmed that the ANN model developed by Sentinel-2A image had the highest performance (R2 =0.77, RMSE% =27.1) to predict ECe in the winter season. Furthermore, RF presents the lowest error (R2 =0.87, RMSE% =17.4) for prediction ECe during the summer season. Among the studied salinity indices, VSSI index was also selected as the most effective index to estimate soil salinity of region. The results also showed that ECe maps obtained by two methods had a high level of concordance and an overal accuracy of over 80%; however, the change of season and type of satellite affectedthe compatibility of the maps.

For the proper use of water resources and prevention of soil degradation, it is necessary to select the best irrigation system. The aim of this study was to map the land suitability evaluation for different irrigation methods (surface and drip) in 46000 ha of Sistan plain including Hirmand, Hamon, Nimroz, Zahak, and Zabol counties. For this purpose, 600 pedons with an approximate distance of 700 to 800 m were excavated, described, and sampled. In this study, land suitability evaluation for different irrigation methods based on soil properties and topography was done using the parametric method. Then, land suitability maps for surface and drip irrigation methods were prepared using the Inverse Distance Weighting (IDW) method. The results showed that in the studied area, the conditions for drip irrigation are better than the surface irrigation method. However, in many studied areas, there are restrictions for drip irrigation, and for proper and efficient use of this irrigation system, the restrictions must be removed. Moreover, the results confirmed that in all studied areas the most important limitations are salinity/alkalinity and limitations due to physical soil properties. The silty clay and silty loam textural were the most limitation classes. Due to the fact that changing the physical properties is not easily possible, it seems that soil remediation based on salinity and alkalinity can help to remove or reduce the limitations.

Soil entities depends on its physical, chemical, and biological characteristics. Soil organic carbon (SOC) stocks is one of the main factors whose variations affect all these parameters. So, this study was performed for mapping the coefficient of variations (CV) of SOC stocks in some parts of the Simineh Roud watershed. Soil sampling performed using the Latin Hypercube method (cLHm) at 210 points from 0 to 30 cm of the soil surface, and the organic carbon was measured, then SOC stocks was calculated. In the next step, using Random Forest (RF) model the effective parameters were calculated (in this step, to model the SOC stocks, standardized spectral reflectance index and extracted data from digital elevation model were used). Finally, RF model was performed 100 times, as well as mapping of the values of upper (95th %), lower (5th %), and average SOC stocks for each pixel with a spatial resolution of 30 × 30 m was obtained. To obtain the CV with a confidence coefficient of 90%, the percentile of 95% and 5% were subtracted. The CV was obtained by dividing it by the mean. The results showed that the accuracy coefficient (R2) for modeling SOC stocks by the RF model was 0.81 and the mean accuracy coefficients including RMSE and MAE were 0.44 and 0.34 (kg/m2), respectively. Also, the results of CV mapping for the amount of SOC stocks in the study area showed that the amount of variation of this parameter varies between 3.9- 55%. Based on the results of the CV mapping of the study area, the most and lowest variations were observed in dry farming and grasslands, respectively. Probably, continuous cultivation and low return of organic matter in dry farming have increased the CV of SOC stocks in dry farming use.

Soil organic carbon (OC) is one of the most important soil properties, especially from an environmental point of view. For this reason, OC modeling and estimating has been highly considered. In modeling, application of pedotransfer functions to estimate soil properties from the other ones have an important place in soil science. Unfortunately, not much attention has been paid to the valuable data that are obtained with the least cost and time in the soil profile description. The aim of this study was to determine the importance of data that obtained from soil profile description to estimate the soil organic carbon in Dehgolan region in Kordestan Province. For this purpose, 30 pedons were excavated and described. Soil samples were collected from different horizons and soil properties such as texture, pH, EC, CCE and gypsum were determined. Modeling was performed in three scenario including laboratory data, data of soil profile description and application of laboratory and soil profile description data simultaneously. The results showed that based on laboratory data, soil organic carbon has a significant relationship with silt and CCE properties with a coefficient of determination about 25% (R2 = 0.25); While, the two soil profile description data of soil color (chroma) and genetic horizon with coefficients of determination about 65% (R2 = 0.65). With compilation of laboratory and soil profile description data the coefficient of determination was also obtained 65%. This level of accuracy clearly shows the value and importance of data related to the soil profile description data.

Introduction Landscape represents a large portion of land/terrain that is either formed by a repetition of similar or dissimilar relief/molding types or an association of dissimilar relief/molding types (e.g., valley, piedmont, mountain, etc.). It is usually affected by a set of natural (e.g., climate, organisms, parent material, topography, time, erosion, sedimentation, etc.) and/or artificial (e.g., artifacts) factors. Soil is one of the most important components of landscape that is affected by various factors such as water and wind. Aeolian or alluvial sediments (from seasonal rivers) in arid areas cause the formation of different landforms and change the landscapes in these areas. Therefore, the study of geoforms in arid regions can lead to a better understanding of geomorphological processes and soil change in these areas. There are various methods, including soil micromorphology and clay mineralogy, to understand the alteration of landscapes and the soils change on them. The aim of this study was to investigate the physical and chemical properties, clay mineralogy and micromorphology of soils in various geomorphic units of Davaran Region, Rafsanjan. Materials and Methods Seven dominant geomorphic units (geoforms) of the region, including pediment, margin of fan and cultivated clay flat, alluvial fan, desert pavement, margin of pediment and sand sheet, active drainage, margin of fan and uncultivated clay flat were selected using Google Earth images and field studies. Nineteen pedons were excavated and described in the geomorphic units. After selecting a representative pedon in each of the geoforms, their genetic horizons were sampled. Besides, in order to conduct soil micromorphology studies, undisterbed and oriented samples were collected from selected horizons. After transferring the samples to the laboratory, their physical and chemical properties were measured using standard methods. In addition, clay mineralogy studies were performed by X-ray diffraction method and micromorphological studies were done using a petrographic microscope. Finally, soil classification was performed based on both Soil Taxonomy (2014) and WRB (2015) systems. Results and Discussion Results showed that gypsification and calcification are the dominant soil forming processes in the studied region, which have led to the formation of Gypsic and Calcic horizons. This has placed the soils in the Gypsids and Calcids suborders based on the Soil Taxonomy system and the Gypsisols and Calcisols reference soil groups according to WRB system. The representative pedon in the margin of fan and cultivated clay flat (pedon 2) geoform lacks a salic horizon based on the Soil Taxonomy; while it is in the Solonchak reference soil group of the WRB. Also, the presence of argillic horizon in the representative pedon of the margin of fan and uncultivated clay flat geoform (pedon 7) indicates presence of a more humid paleoclimate in the history of the region. The results of clay mineralogy showed that the predominant minerals in the region include chlorite, illite, kaolinite, and smectite. The illite, chlorite, and kaolinite are inherited from papent materials of the soils, and the smectite has a transformation origin (from palygorskite and illite). Addition of this mineral by aeolian or alluvial sediments could not also be neglected. The micromorphological results indicated that the soil pores were mainly chamber. The presence of carbonates and gypsum in the studied soils has caused that the b-fabric in the most horizons to be Calcitic Gypsic Crystallitic. Gypsum was observed in the form of vermicular, lenticular, interlocked gypsum plates and subhedral shapes. Other pedofeatures in the studied soils include calcite nodule and limestone. Conclusion The simultaneous presence of aeolian and alluvial sediments in the different geoforms of Davaran region has caused the formation of stratified soils. Existence of dry climate and lack of significant vegetation in the region from one hand, and the addition of different sedimentary layers at different times (which causes soil rejuvination) on the other hand, has caused that the soils of the region, in general, not to be highly developed. As a result, few differences were observed among soils in different geoforms. Comparing the results of two soil classification systems for the studied soils showed that in general there is a relatively good correlation between them. Totally, the role of climate and parent material in alteration of the studied soils is evident; so that the physical and chemical properties, clay mineralogy and micromorphology of soils in different geoforms have been affected.

Choosing the best land suitability method to determine land suitability classes has always been questioned and researched. Many land suitability surveys are conducted using four conventional methods, including: 1-simple limitation, 2- number and intensity of limitations, 3- Khiddir (square root) and 4- storie. In the parametric approach, the land index is calculated using the Khiddir method or the Storie method, and then based on this index, the land suitability classes are determined. The land index is in two forms: the uncorrected land index and the corrected land index. Numerous studies on land suitability evaluation have shown that the results of different land suitability methods are very different. However, the results of many studies suggest that the two methods of simple limitation and Khiddir are more consistent. Since these researches have been for different products and different regions, it has not been possible to evaluate the degree of adaptation of different methods without considering the type of product and its location. On the other hand, the numerical value of the adaptation or conformity of these methods with each other has not been determined. So, regardless of the type of product and location, a basic question that arises is how well do the different land suitability methods fit together, and are the degree of adaptation different for various land suitability classes? Current research seeks to answer this question.

In this study, land suitability classes were determined using numerical simulation, without considering any product and location. In numerical simulation, each of the eight factors involved in determining the suitability classes accounted for a random number from zero to 100, and then based on these simulated numbers the land suitability classes were determined with the four conventional methods and in two forms of the uncorrected land index and the corrected land index. The simulation process for each proportional class, including classes S1(suitable), S2(Moderately suitable), S3(Marginally suitable), N1 (temporary unsuitable), and N2 (permanently unsuitable), was performed one million times. So a total of five million simulations were done. In the next step, the degree of adaptation for each class and each method was calculated based on the Overall Accuracy(OA) formula.

The results showed that the numerical value of the degree of adaptation of different land suitability methods in various classes are very different; Overall, however, the least and most adaptation between the different methods occurs for Class N1 and N2, respectively. After class N2, there is the greatest adaptation between the different methods in class S1. For classes S2 and S3, the degree of adaptation between different methods does not follow a specific trend. Among the various methods, in the case of using the uncorrected index, the simple limitation method was more consistent with the Khiddir method. However, using the corrected land index, the greatest correlation was observed between the simple limitation method and the parametric approach (both Khiddir and Storie method) and in this case there was not much difference between the results of Khiddir method and Storie method. Therefore, the corrected index is superior to the uncorrected index.

Based on the findings of this study, it can be said that the results obtained from the uncorrected land indices may be far from reality, and this issue is much more severe for the Storie method. The use of the uncorrected index causes a large difference between the parametric approach with the two methods of simple limitation and the number and intensity of limitations. Therefore, it is necessary to use corrected indices to determine the suitability classes so that the results of different methods are as close as possible.

The most important factor in environmental degradation and pressure on ecological resources is rapid population growth combined with unsustainable exploitation of resources. Soil is one of the most important and worthful natural resources of environment. Land use change and deforestation decrease soil quality. Land use change also causes destruction of the evolved soils and decrease soil quality which result in permanent destruction of land fertility. Therefore, studying land use management effects on the soil quality has got an attention in recent years. Destroying the vegetation especially in the last 50 years resulted in important problems like soil erosion, land slide as well as increasing flood in the Bazoft area. In this area, degradation of the forests and their convert to other land uses like pasture, agriculture and urban or rural land use, occurs annually at high extent, in which make high damages to natural resources. In this study, the effect of land use change on soil quality indices in this area located at Chaharmahal-Va-Bakhtiari province was investigated.

In this research, four different managements with relatively similar conditions in terms of the influence of soil producing processes were chosen. Then, 10 composite samples from 0-30 cm depth of each land use (40 samples in total) were taken and different soil properties including soil texture, mean weight diameter of aggregates (MWD), porosity, bulk density, soil acidity, electrical conductivity and calcium carbonate equivalent were determined. One-way ANOVA was used to analyze the dataset. Tukey HSD test was applied to compare the means at the probability level of 5%. The first land use includes the natural forest with predominant cover of Iranian oak and the highest density and cover with the least human interference. Another land use is the degraded forest, caused by deforestation over the last 50 years. The third land use is the agricultural land which transformed from forest land use by deforestation in the last 50 years. The fourth land use is the walnut garden which established from agricultural land about 20 years ago.

The results showed that land use change from natural forest to other uses had a significant effect on most of the studied parameters. The percentage of particle size distribution was affected by different land uses, so that the percentage of clay was significantly higher in the land use of natural forest and walnut orchard than other land uses. The results also showed that the mean weight diameter of aggregates was influenced by the land use change (P <0.001). Factors like soil compaction due to livestock grazing and machinery traffic, agricultural operations and reduced biological activity increased the bulk density in all land uses compared with the forest land use. Deforestation also resulted in 6.92%, 12.05% and 14.16% porosity reduction in walnut orchard, agricultural land and deforestation, respectively. Changing management from farmland to walnut orchards also improved soil porosity by 6 percent. In the study area, the problem of changing vegetation, grazing, planting and other mismanagement increased soil pH in other land uses compared with the forest land use. The comparison of means showed that degraded forest and agriculture land uses had the highest rate of electrical conductivity which showed significant difference with natural forest land use and walnut orchard. Analysis of variance indicated that the land use had a significant effect on calcium carbonate equivalent at the probability level of 0.001. The comparisons also showed that the equivalent calcium carbonate content in agricultural land was higher than the other land uses, and there was no significant difference between walnut orchard and natural forest.

The results of the present study showed that the soil physical and chemical properties were significantly affected by land use change. Overall, it can be stated that the rate of changes in soil quality under human management and different utilization systems indicates failure in sustainable management of soil resources in the study area. Some characteristics such as soil particle size distribution percentage, soil porosity and calcium carbonate equivalent shows that there is no significant difference between walnut orchard and natural forest. However, the walnut orchards can be selected as the best management in areas where it is impossible to restore natural forests. Also, the need for stopping deforestation in Zagros ecosystem is highly recommended.

The main purpose of this research was to study the effect of soil physicochemical properties on aggregate stability and magnetic susceptibility in two aeolian geomorphic units (desert pavement and aeolian clay flat) of Davarn plain in Rafsanjan. After taking 50 samples from the surface soil (0 to 10 cm) of desert pavement and 43 samples of aeolian clay flat, the magnetic susceptibility, mean weight diameter of aggregates and some of their most important physical and chemical characteristics were determined. Results showed that the mean magnetic susceptibility in desert pavement was 842.53 and in clay flat was 632.13 (*10-8 m3 kg-1) which is very high compared to those in soils of Iran and its main reason could be attributed to the parent material of the area. The low mean frequency-dependent magnetic susceptibility in the both study units also confirms this issue. The mean weight diameter of aggregates in the desert pavement varied from 1.20 to 1.93 mm and in the clay flats from 0.54 to 1.80 mm. The findings of this research showed a direct correlation between iron forms (Fed and Feo) with aggregate stability in the both of studied geoforms; however, the level of this correlation was high and significant for Fed. The results also indicated that there is a negative correlation between magnetic susceptibility with electrical conductivity (EC), organic matter (OM) and calcium carbonate equivalent (CCE) in the both of studied units. A positive and significant correlation was seen between total silt, total sand and its fractions with magnetic susceptibility in both geomorphic units. In addition, a negative correlation was seen between the mean weight diameter of aggregates and magnetic susceptibility, which its possible reason can be the presence of a large amounts of sand resulted from aeolian losses and its adverse effects on aggregate stability. The results of regression model indicated that dithionate iron and sand had a significant effect on the magnetic susceptibility; and sand, clay and electrical conductivity had a significant effect on aggregate stability.

Soil maps have considerable significance as basic maps in many environmental and natural resources studies. Digital soil maps are based on the relationship between environmental variables and soil properties. The main purpose of this research was to analyze error and uncertainty of digital soil classes predicted at different taxonomic levels of Soil Taxonomy system using an artificial neural network. One hundred and twenty soil profiles were described and sampled based on a regular grid scheme in Shahrekord plain. Two groups of soil properties (qualitative and quantitative) and auxiliary parameters (including geologic map, landform map, landform-phase map, traditional soil map, normalized difference vegetation index, and some derivatives of digital elevation model) were used to estimate soil classes. After preparing the soil properties maps and checking their accuracy, these maps were used along with auxiliary parameters for estimating soil classes using an artificial neural network model in the R software. Finally, the accuracy and uncertainty of the model were evaluated by overall accuracy and confusion index, respectively. Results showed that the entry of more details in the soils classification at the lower levels of the Soil Taxonomy system, while increasing the number of classes, leads to decreasing the overall accuracy and increasing uncertainty. It is noticeable that the artificial neural network model has a good accuracy up to the great group level through the acceptable level of overall accuracy (i.e., 75 %), hence it has a high degree of uncertainty. Therefore, the accuracy of the model could not be effective in its selection trough the modeling process; however, paying attention to its uncertainty is also very important along with the model error. Accordingly, we suggest using the other methods of soft computing for modeling in plain areas or in low relief regions.

  In addition to the genetic effects on the morphological characteristics and quality of the medicinal plants, environmental factors have an important role on the plant growth and their quality. Soil properties have effect on the characteristics of medicinal plants. Unfortunately, investigation of the effect of soil properties and manure application on the morphological characteristics of medicinal plants is rarely considered. Therefore, the main objective of the present study was to find out the effect of the different soil properties and manure application on the morphological characteristics and quality of peppermint (Mentha piperita L.). The pot experiment was performed as a factorial in a randomized complete block design (RCBD) with three replications. Factors were consisting of three soils series (Chaharmahal, Boldaji and Sefid-dasht) of Shahrekord plain in Chaharmahal-Va-Bakhtiari Province and two levels of control (no application of animal manure) and application of animal manure (147 g per pot equal to 30 ton/ha). Firstly, the soil physicochemical properties were determined and after the cultivation period, the vegetative characteristics, plant yield, essential oil content and yield were measured. The results showed that the effect of soil, animal manure and their interaction on leaf length and width, number of leaf per stem, stem height, leaf fresh and dry weight, stem dry weight, biological yield and essential oil yield were significant at 1% probability level in both cutting. Also, means comparison showed significant differences between different soils. The sefid-dasht soil with more phosphorous, soluble magnesium and K and less calcium carbonate equivalent caused increase in growth, biological yield and essential oil yield in both cuttings. Moreover, fertilization had a positive and significant effect on the leaf length and width, leaf number per stem, leaf fresh and dry weight, biological yield and essential oil percentage and yield. Means comparison of interaction showed that the most biological yield and essential oil yield were obtained in sefid-dasht soil and usage of manure in both cuttings. The results showed that morphological characteristics and quality of peppermint (Mentha piperita L.) were statistically different at the studied soil series. Also, results demonstrated that the Sefid-dasht and Boldaji soil series have the highest and lowest potential for peppermint (Mentha piperita L.) production, respectively. Moreover, fertilization had a positive and significant effect on the leaf length and width, leaf number per stem, leaf fresh and dry weight, biological yield and essential oil percentage and yield.
Keywords: Soil series, Peppermint, Manure, Morphological characteristics, Essential oil

Digital soil mapping (DSM) predicts the soil variability based on the relationship between the soil classes and auxiliary information. Therefore, it is expected that if two regions have similar auxiliary information, the model developed to estimate soil variability for one of these regions could be generalized to the other. The aim of this study was to predict the soil classes up to great group level of Soil Taxonomy (ST) and Reference Soil Group (RSG) level of World Reference Base for the Soil Resources (WRB) across the area with little soil data (recipient site) on the basis of constructed model in area that has sufficient soil data (reference site) using DSM approaches in the Shahrekord plain of Chaharmahal-Va-Bakhtiari Province. The reference and recipient sites are located in the Shahrekord region of Chaharmahal-Va-Bakhtiari Province. The Mahalanobis distance is used to determine the distance between the mean of the reference’s soil forming factors and the recipient’s soil forming factors (Mallavan et al. 2010). The reference site for this study was surveyed using digital soil mapping approaches at semi-detailed scale (i.e., raster maps with pixel size 50×50 m) up to family level by Mosleh (2016). Different machine learning algorithms consisting of artificial neural networks (ANNs), boosted regression tree (BRT), random forest (RF) and multinomial logistic regression (MLR) were considered for each soil taxonomic level to identify the relationship between soil classes and auxiliary information. Fifteen pedons were excavated at the recipient site with 750 m intervals. All the pedons were described and the soil samples were taken from different genetic horizons, air dried, crashed and passed through a 2 mm sieve. The soil samples were classified the soils according to the Soil Taxonomy (Soil Survey Staff 2014) and the WRB (IUSS Working Group WRB 2015) up to great group and Reference Soil Group levels, respectively. The results showed that the Mahalanobis distance at the reference and recipient sites is equal. Therefore, the two studied sites are entirely similar and can be considered as Homosoil. Summary statistics of auxiliary information for the reference and recipient sites indicated that the difference between the mean of the reference’s soil forming factors and the recipient’s soil forming factors is negligible. Extrapolated models across the recipient site lead to similar results with the reference site. These results include: (i) no significant differences were observed between different models to predict soil classes based on the ST system; (ii) OA values showed a decreasing trend with increasing the taxonomic levels for all the studied models (Figure 3); (iii) the MLR model has the highest performance to predict the RSG. The results indicated that DSM could be used for prediction of the soil classes in the Homosoil framework (both sites have similar auxiliary information or soil forming factors). It is expected that the accuracy of predictions is accrued if there is a high agreement between the reference and the recipient sites in terms of the auxiliary information.

There is a concern with assessment of land performance when used for specific purposes. Land evaluation analysis is considered as an interface between land resources and land use planning and management. However, the conventional soil surveys are usually not useful for providing quantitative information about the spatial distribution of soil properties that are used in many environmental studies. Development of the computers and technology lead to digital and quantitative approaches have been developed. These new techniques rely on finding the relationships between soil and the auxiliary information that explain the soil forming factors or processes and finally predict soil patterns on the landscape. Different types of the machine learning approaches have been applied for digital soil mapping of soil classes, such as the logistic and multinomial logistic regressions, neural networks and classification trees. To our knowledge, most of the previous studiesapplied land suitability evaluation based on the conventional approach. Therefore, the main objective of this study was to assess the performance of digital mapping approaches for the qualitative land suitability evaluation in the Shahrekord plain of Chaharmahal-Va- Bakhtiari province.
An area in the Shahrekord plain of Chaharmahal-Va-Bakhtiari Province, Iran, across 32º13′ and 32º 23′N, and 50º 47′ and 51º 00′E was chosen. The soils in the study area have been formed on Quaternary shale and foliated clayey limestone deposits. Irrigated crops such as wheat, potato, maize and alfalfa are the main land uses in the area. According to the semi-detailed soil survey, 120 pedons with approximate distance of 750 m were excavated and soil samples were taken from different soil horizons. Soil physicochemical properties were determined. The average of soil properties was determined by considering the depth weighted coefficient up to 100 and 150 centimeters for annual and perennial crops, respectively. Qualitative land suitability evaluation for main crops of the area including wheat, maize, alfalfa and potato was determined by matching the site conditions (climatic, hydrology, vegetation and soil properties) with studied crop requirement tables presented by Givi (5). Land suitability classes were determined using parametric method. Land suitability classes reflect degree of suitability as S1 (suitable), S2 (moderately suitable), S3 (marginally suitable) and N (unsuitable). Different machine learning techniques, namely artificial neural networks (ANNs), boosted regression tree (BRT), random forest (RF) and multinomial logistic regression (MLR) were used to test the predictive power for mapping the land suitability evaluation. Terrain attributes, normalized difference vegetation index (NDVI), clay index, carbonate index, perpendicular vegetation index (PVI), geology map, existing soil map (1:50000 scale) and geomorphology map were used as auxiliary information. Finally, all of the environmental covariates were projected onto the same reference system (WGS 84 UTM 39 N) and resampled to 50 * 50 m since the soil samples were collected with approximate distance of 750 m (1:50,000 scale). According to the suggested resolutions for digital soil maps, the pixel size 50 *50 m fits to a 1:50,000 cartographic scale. Training the models was done with 80% of the data (i.e., 96 pedons) and their validation was tested by the remaining 20% of the dataset (i.e., 24 pedons) that were split randomly. The accuracy of the predicted soil classes was determined using error matrices and overall accuracy.
The results showed that climatic conditions are suitable (S1) for wheat and potato whereas the most important limiting factors for maize and alfalfa were the average of minimum temperature and average temperature, respectively. Results demonstratedthat among the studied models, random forest showed the highest performance to predict the land suitability classes and subclasses. However, different models had the same ability for prediction. In addition, the overall accuracy decreased from class to subclass for all of the crops. The terrain attributes and remote sensing indices (normalized difference vegetation index and perpendicular vegetation index) were the most important auxiliary information to predict the land suitability classes and subclasses.
Results suggest that the DSM approaches have enough accuracy for prediction of the land suitability classes that affecting land use management. Although digital mapping approaches increase our knowledgeabout the variation of soil properties, integrating the management of the sparse lands with different owners should be considered as the first step for optimum soil and land use management.

Effective and sustainable soil management requires knowledge about the spatial patterns of soil variation and soil surveys are important and useful sources of data that can be used. Prior knowledge about the spatial distribution of the soils is the first essential step for this aim but this requires the collection of large amounts of soil information. However, the conventional soil surveys are usually not useful for providing quantitative information about the spatial distribution of soil properties that are used in many environmental studies. Recently, by the rapid development of the computers and technology together with the availability of new types of remote sensing data and digital elevation models (DEMs), digital and quantitative approaches have been developed. These new techniques relies on finding the relationships between soil properties or classes and the auxiliary information that explain the soil forming factors or processes and finally predict soil patterns on the landscape. Different types of the machine learning approaches have been applied for digital soil mapping of soil classes, such as the logistic and multinomial logistic regressions, neural networks and classification trees. In reality, soils are physical outcomes of the interactions happening among the geology, climate, hydrology and geomorphic processes. Diversity is a way of measuring soil variation. Ibanez (9) first introduced ecological diversity indices as measures of diversity. Application of the diversity indices in soil science have considerably increased in recent years. Taxonomic diversity has been evaluated in the most previous researches whereas comparing the ability of different soil mapping approaches based on these indices was rarely considered. Therefore, the main objective of this study was to compare the ability of the conventional and digital soil maps to explain the soil variability using diversity indices in the Shahrekord plain of Chaharmahal-Va- Bakhtiari province.
The soils in the study area have been formed on Quaternary shale and foliated clayey limestone deposits. Irrigated crops such as wheat, barley and alfalfa are the main land uses in the area. According to the semi-detailed soil survey, 120 pedons with approximate distance of 750 m were excavated and described according to the “field book for describing and sampling soils”. Soil samples were taken from different genetic horizons and soil physicochemical properties were determined. Based on the pedons description and soil analytical data, pedons were classified according to the Soil Taxonomy (ST) up to subgroup level. Using aerial photo interpretation, geology map, google earth image and field observations primary soil map was created. With considering the taxonomic level, the representative pedons were determined and soil map was prepared. Multinomial logistic regression was used to predict soil classes at great group and subgroup levels. The map units that have the highest frequency were selected as indicator to calculate diversity indices in the conventional soil map at each taxonomic level. The selected map units were overlay to digital soil map and further diversity indices were calculated. Diversity indices including the Shannon’s diversity, evenness and richness index. In order to know whether the means of Shannon’s diversity for two approaches are significantly different, means comparison was done.
The results confirmed that the Shannon's diversity index was higher in the digital soil map than the conventional soil map for most soil map units. At great group and subgroup levels, a significant difference was observed for the Shannon's diversity index at 0.05 and 0.001 probability levels, respectively. Comparing the conventional and the digital soil maps showed the numbers of soil map units with significant difference regarding the Shannon's diversity index decreased from great group to the subgroup level. Although the conventional soil map did not show a good efficiency to explain the soil variability in this region considering more soil information to select the representative pedons at subgroup level in the conventional soil mapping could increase the ability of this approach.
A significant difference for the Shannon's diversity index between the conventional and the digital soil maps demonstrated that conventional soil mapping has not enough ability to explain the soil variability. It is recommended to test the effect of soil mapping approaches on explanation of the soil variability in other areas. Despite the deficiencies of traditional soil survey, it is still difficult to state about their replacement by digital methods.

Soil classification generally aims to establish a taxonomy based on breaking the soil continuum into homogeneous groups that can highlight the essential differences in soil properties and functions between classes.The two most widely used modern soil classification schemes are Soil Taxonomy (ST) and World Reference Base for Soil Resources (WRB).With the development of computers and technology, digital and quantitative approaches have been developed. These new techniques that include the spatial prediction of soil properties or classes, relies on finding the relationships between soil and the auxiliary information that explain the soil forming factors or processes and finally predict soil patterns on the landscape. These approaches are commonly referred to as digital soil mapping (DSM) (14). A key component of any DSM mapping activity is the method used to define the relationship between soil observation and auxiliary information (4). Several types of machine learning approaches have been applied for digital soil mapping of soil classes, such as logistic and multinomial logistic regressions (10,12), random forests (15), neural networks (3,13) and classification trees (22,4). Many decisions about the soil use and management are based on the soil differences that cannot be captured by higher taxonomic levels (i.e., order, suborder and great group) (4). In low relief areas such as plains, it is expected that the soil forming factors are more homogenous and auxiliary information explaining soil forming factors may have low variation and cannot show the soil variability.
The study area is located in the Shahrekord plain of Chaharmahal-Va-Bakhtiari province. According tothe semi-detailed soil survey (16), 120 pedons with approximate distance of 750 m were excavated and described according to the “field book for describing and sampling soils” (19). Soil samples were taken from different genetic horizons, air dried and grounded. Soil physicochemical properties were determined. Based on the pedon description and soil analytical data, pedons were classified according to the ST (20) and WRB (11). Terrain attributes, remote sensing indices, geology, soil and geomorphology map were considered as auxiliary information. All of the auxiliary information were projected onto the same reference system (WGS 84 UTM 39N) and resampled to 50×50 m according to the suggested resolution for digital soil maps (14). Four modeling techniques (multinomial logistic regression (MLR), artificial neural networks (ANNs), boosted regression tree (BRT) and random forest (RF)) were used for each taxonomic level to identify the relationship between soil classes and auxiliary information in each classification system. The models were trained with 80 percent of the data (i.e., 96 pedons) and their validation was tested by remaining 20 percent of the dataset (i.e., 24 pedons) that split randomly. The accuracy of the predicted soil classes was determined by using overall accuracy and Brier score.For each classification system, the model with the highest OA and the lowest BS values were considered as the most accurate model for each taxonomic level.
The results confirmed that ST showedmore accessory soil properties compared to WRB. The ST described the cation-exchange activity, soil depth classes, temperature and moisture regime. The different models had the same ability for prediction of soil classes across all taxonomic levels based on ST. Among the studied models, MLR had the highest performance to predict soil classes based on WRB. For all the studied models and both classification system, OA values showed a decreasing trend with increasing the taxonomic levels. Predicted soil classes based on the ST had the higher accuracy. Different models selected different auxiliary information to predict soil classes. For most of the models and both classification systems, the terrain attributes were the most important auxiliary information at each taxonomic level.
Results demonstrated that although ST showed more accessory soil properties compared to WRB, the DSM approaches have not enough accuracy for prediction of the soil classes at lower taxonomic levels. More investigations are needed in this issue to make a firm conclusion whether DSM approaches are appropriate for prediction of soil classes at the levels that are important for soil management. Prediction accuracy of soil classes can be influenced by the target taxonomic level and classification system, soil spatial variability in the study area, soil diversity, sampling density and the type of auxiliary information.