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 Biology, Biochemistry and Biotechnology
Majid Baghernejad
Abstract
Abstract Introduction Drought stress is one of the important environmental factors that limit distribution and productivity of major crops. Drought stress caused by reducing the availability of external water, which makes reduces the ability of the plant’s roots to take up nutrients and induced ...
Read More
Abstract Introduction Drought stress is one of the important environmental factors that limit distribution and productivity of major crops. Drought stress caused by reducing the availability of external water, which makes reduces the ability of the plant’s roots to take up nutrients and induced cellular and photo-oxidative damages, through the increased accumulations of reactive oxygen species. Plant growth promoting rhizobacteria and arbuscular mycorrhizal fungi by using different mechanisms such as production of siderophores, organic acids, proton, growth regulators, and other chelating agents, and creative of reductive conditions, increase dissolution of minerals and mobility of non-soluble nutrients and thus improve nutrients uptake and yield of plants. They can influence plant root morphology and change the quantity and quality of root exudates. Mycorrhizal symbiosis involves a complex interaction among plant, soil and mycorrhizal fungi. Arbuscular mycorrhizal associations' relationship are rather important in crops because they are believed to increase nutrients uptake, improve plant fitness, and plant water relations and thus increase the drought resistance of host plants. Plant growth promoting rhizobacteria improve water relations of plants in part due to increases of plant growth, nutrient uptake and antioxidant activities. Maize is an effective host of arbuscular mycorrhiza in infertile and drought conditions and its root system consists of different root types. Therefore, the objectives of this study was to evaluate the effects of Glomus intraradices, Pseudomonas fluorescens (as a PGPR bacterium) and drought stress on growth characteristics and micro-nutrients uptake of maize in a calcareous soil under maize cultivation. Materials and Methods A greenhouse experiment in a factorial completely randomized design was conducted to evaluate the effects of arbuscular mycorrhizal (AM) fungus (Glomus intraradices), Pseudomonas fluorescence, and drought stress on root colonization and absorption of micro-nutrients (Fe, Mn, Zn, Cu) by maize (Zea mays). The factors were consisted of arbuscular mycorrhizal fungus at two levels: G0 (not inoculated with fungus) and G1 ( inoculated with Glomus intraradices), bacteria at two levels: B0 (not inoculated with bacterium) and B1 (inoculated with Pseudomonas fluorescence) and drought stress at four levels: S0 (without stress), S1 (75% FC), S2 (50% FC) and S3 (25% FC). Mycorrhizal inoculum was prepared through the trap culture of forage sorghum (Sorghum biocolor L.) with spore of Glomus intraradices. The potential of inoculum (spore numbers of 12 g-1 substrates and root colonization of 80%) was measured for spore extraction and counting, and evaluation of root colonization. The bacterium used in the present experiment was Pseudomonas fluorescens and provided by soil biology and biotechnology laboratory of College University of Agriculture and Natural Resources of Tehran University, Karaj, Iran. The bacterium had a high ability to dissolve poorly soluble organic and inorganic phosphate compounds, to produce siderophores, indole acetic acid (IAA), and 1-aminocyclopropane-1-carboxylate (ACC)-deaminase enzyme. A non-sterile composite soil sample was collected from depth of 0-30 cm soil surface of Agriculture Research Station of Shiraz University, Shiraz, Iran (fine, mixed, mesic, Calcixerollic Xerochrept). The samples were air-dried and passed through a 2mm sieve. Some physical and chemical properties of studied soil are measured. The seeds were inoculated with 1mL fresh and active suspension of bacterium (population of 1×108 colony-forming units (CFU) per milliliter). After a growth period of 4 months, plant materials harvested and data were subjected to analysis of variance and means were compared by least significant difference. Results and Discussion In non microbial treatments, wet and dry weights of shoot significantly decreased whereas other measured parameters had not significant changes under drought stress of 25% FC. At each level of drought stress, root colonization significantly higher in mycorrhizal treatments than non mycorrhizal treatments. The highest root colonization percent was observed in treatments of co-inoculation of plant with both inoculants. Co-inoculation of plant with both inoculants significantly increased morphological properties and shoot nutrients uptake except Fe uptake in comparison with non microbial treatments up to drought stress of 50% FC. Conclusion All measured parameters ( leaf area, wet and dry weights of root, root colonization, shoot micronutrient uptake) except wet and dry weights of shoot significantly decreased with increasing of drought stress up to 25% of FC. Single and co-application of bacterium and fungus decreased the negative effects of drought stress under low levels of water stress. Root colonization significantly increased with single application of fungus and co-inoculation of plant with fungus and bacterium. Co-application of fungus and bactrieum increased shoot nutrients uptake except Fe uptake up to 50% FC in comparison with non inoculated treatments.