S. Nazari; M. Rostaminia; shamsollah Ayoubi; A. Rahmani; S.R. Mousavi
Abstract
Abstract Background and objectives: High-accuracy of soil maps is a powerful tool for achieving land sustainability in agricultural and natural resources. The present study was conducted in Vargar lands of Abdanan city related to Ilam province for digital mapping of soil classes at two taxonomic level ...
Read More
Abstract Background and objectives: High-accuracy of soil maps is a powerful tool for achieving land sustainability in agricultural and natural resources. The present study was conducted in Vargar lands of Abdanan city related to Ilam province for digital mapping of soil classes at two taxonomic level from subgroup up to family by random forest (RF) and fuzzy logic models. Materials and methods: Study area with 1027 hectare have 628.6 mm and 22.6 C° mean annual precipitation and temperature respectively. Three major physiographic units included Hilland, Piedmont plain and Alluvial plain were observed. Soil moisture and temperature regimes are ustic and hyperthermic calculated based on Newhall model in JNSM 6.1 version software. A total of 44 soil profile observation with random sampling pattern was determined based on standardized soil surveys then digging, description and after sampling from all genetic horizons then soil samples were transferred to laboratory. Finally, all of soil profiles were classified based on soil taxonomy system (2014) up to family level. Geomorphometric covariates as a representative of soil forming factors were prepared from digital elevation model (ALOS PALSAR Satellite,2011) with 12.5 m resolution in SAGA GIS 7.4 version software. Three feature selection approaches included Boruta, Variance inflation factors (VIF) and Mean decrease accuracy (MDA) with two Random forest (RF) and Fuzzy logic data mining algorithms were applied for relating soil-landscape relationship by using “randomforest”, “caret” packages in R 3.5.1 and SoLIM solution version 2015 software. Sample based project used for predicting soil classes in Fuzzy logic modeling process. In totally observation profile split into two data set included 80 percent (n=36) for calibrating and 20 percent for validating (n=8) based on bootstraps sampling algorithm random forest. Internal validation of random forest algorithm was done based on out of bag error percentage (OOB%). The best model performance was determined based on overall accuracy (OA) and kappa index, also for each individual class user accuracy (UA) and producer accuracy (PA) were applied. Results: The results shown that from number of 40 geomorphometrics covariates, six covariates included Terrain classification index for lowlands, Annual insolation, Topographic position Index, Upslope curvature, Real surface area and Terrain surface convexity were selected by MDA as the best environmental covariates. Also, RF-MDA method with overall accuracy 84% and Kappa index 0.56 had the best performance compared to other methods (RF_VIF, RF-BO, Fuzzy-MDA) in subgroup level with 58, 55, 50 and 0.3, 0.67 and 0.18 respectively. Out of bag error results (%OOB) for RF-MDA, RF-VIF and RF-Boruta were obtained that 72.42%, 67.86% and 82.76% for subgroup level and 93.10%, 93.10% and 86.21% for family level respectively. while there was little difference between the accuracy of the method at the family taxonomic level and performed similar results in modeling of soil classes process. The results of the fuzzy approach showed that the kappa index values and overall accuracy of this method were similar to the other three scenarios and there was a slight difference between the accuracy of the results at the soil family level. In the fuzzy method, it was observed that the kappa and overall accuracy values at the subgroup level were lower than the other scenarios. Fuzzy approaches in contrasted to RF modeling prevented continues spatial variability by generating of fuzzy maps for each of soil class in the landscape. These results indicate that the random forest method is superior to the fuzzy method in family class mapping and soil subgroups. Based on MDA sensitivity analysis index, similarly, three geomorphometrics covariate included Terrain surface convexity (convexity), Terrain classification index for lowlands (TCI_Low) and Real surface area (Surface_Ar) had highest importance for predicting soil classes at two taxonomic level. With regarded to final soil predicted maps area, two classes (Fine-silty, carbonatic, hyperthermic Typic Haplustepts) and Typic Calciustolls with 32.70% and 48.90% and (Fine-silty, carbonatic, hyperthermic Typic Calciustolls) and Typic Haplustepts with 0.18% and 1.85% had the highest and lowest content at family and subgroup maps respectively. Conclusion: In general, using different variable selection approaches in situations where soil classes have a relatively imbalanced abundance can increase the accuracy of digital mapping in soil studies. Increasing the number of field observations and the use of other environmental variables affecting soil formation can also be used for gradating in prediction low-accuracy soil classes.
Ali reza Karimi; Isa Esfandiarpour Borujeni
Abstract
Soil maps are the common sources of soil information for land evaluation and land use planning. The objective of this study was to evaluate the capability of conventional and geostatistical methods for mapping selected physical (sand, silt and clay) and chemical (carbonate calcium equivalent and pH) ...
Read More
Soil maps are the common sources of soil information for land evaluation and land use planning. The objective of this study was to evaluate the capability of conventional and geostatistical methods for mapping selected physical (sand, silt and clay) and chemical (carbonate calcium equivalent and pH) soil properties. Based on interpretation of aerial photographs, satellite images and field observations, five geopedologic map units were identified in an area of about 12 km2 in southern Jiroft. 100 surface soil samples (0-20 cm) were taken from a regular grid of 500 × 250 m. The results indicated that geopedological map units were significantly different in at least one soil property. Differences of characteristics between units are resulting differences in geomorphic processes. Continuous soil maps prepared by the ordinary kriging also revealed continuous variations of characteristics in accordance with the changes in geomorphic processes. However, variations between units obviously recognizable in the boundary of units were not revealed by the geostatistical method. Based on results of this study, the conventional method is proposed for large areas (small scale maps) and geostatisticals method for small areas (large scale maps) are proposed for soil mapping.
Z. Rashidi Koochi; Isa Esfandiarpour Borujeni; A. Abbaspoor
Abstract
Geopedology which is a systematic approach to analyze the influence of the geomorphic levels on soil mapping, makes it possible to generalize the soil survey results in one geomorphic unit to the other similar units of a studied area that resulted in reducing the time and costs of soil survey. The main ...
Read More
Geopedology which is a systematic approach to analyze the influence of the geomorphic levels on soil mapping, makes it possible to generalize the soil survey results in one geomorphic unit to the other similar units of a studied area that resulted in reducing the time and costs of soil survey. The main question, in this regard, is to what extent the soil data generalization can be valid? To answer this question the effect of landform's kind on the reliability of the geopedology approach was studied in an area of about 1500 ha on the east of Damavand. For this purpose, the geomorphic units were determined by interpreting the 1:55000 scale air-photos of the study area. In the next step, two similar delineations were selected in the piedmont landscape and two similar ones were selected in the hill-land landscape as well. Then, according to semi-detail soil surveys, some pedons were studiedin each of similar delineations. Through the description and sampling of all of pedons and through physical and chemical analyses on all of the pedons’ master horizons, the pedons were classified up to the family level according to Soil Taxonomy system. The results indicated a significant effect of landform's kind on the results of geopedology approach. Although the kind of map unit for similar landforms was the same; the similarity was lower among the pedons in the hill-land landscape than the piedmont in all levels of Soil Taxonomy system. It was probably due to the more slope variations in the hill-land (compared to piedmont areas), and as a result, a greater spatial variation of the nature of exist soils on this landscape.
Z. Rashidi Koochi; I. Esfandiarpoor Borujeni; A. Abbaspour; A. Kamali; A.A. Naderi
Abstract
Geopedology is a systematic approach to analyze the geomorphic levels for soil mappingwhich organizes natural terrains in a hierarchical order in accordance with their scale. Hereon, the effect of mapping scale and kinds of soil classification system on the reliability of the geopedologic approach was ...
Read More
Geopedology is a systematic approach to analyze the geomorphic levels for soil mappingwhich organizes natural terrains in a hierarchical order in accordance with their scale. Hereon, the effect of mapping scale and kinds of soil classification system on the reliability of the geopedologic approach was investigated. In view of that, after air-photos interpretation (1:55,000 and 1:40,000 scales) of an area (1500 ha) on the east of Damavand, two similar delineations (named A and B) were selected on the geoform map. Then, some pedons were dug in the similargeoforms based on semi-detailed soil surveys. The pedons were classified up to the family level according to Soil Taxonomy and up to the subunit level (including suffix and prefix qualifiers) based on WRB soil classification systems. This was the conducted when description and sampling from all genetic horizons and physical and chemical analyses had been already done. The results showed that mapping scale affected the results of the geopedologic approach significantly, so that relative similarity in all taxonomic levels was lower in 1:40,000 scale than the 1:55,000 scale for all studied pedons. Besides, Soil Taxonomywas more adaptable than WRB in predicting the relative similarity among soils in the same geoforms. On the whole, the geopedologic approach is still not able to estimate and determine the complete variability of soils and define their chaotic nature precisely, and the performance of this approach is limited to semi-detailed surveys and smaller ones.
