Manizheh Razavi Hosain Abad; Alireza Amirian Chekan; Mohammad Faraji; Jamal Mosavian
Abstract
Soil aggregate stability and its spatial distribution can be considered as a good indicator for assessing the results of measures conducted for mitigation soil erosion. This study was conducted in two adjacent sites in Chahmari region, Kuzestan province. At one site afforestation and contour furrowing ...
Read More
Soil aggregate stability and its spatial distribution can be considered as a good indicator for assessing the results of measures conducted for mitigation soil erosion. This study was conducted in two adjacent sites in Chahmari region, Kuzestan province. At one site afforestation and contour furrowing were conducted to control soil erosion and the adjacent site with no controlling measures was considered as control. A total of 150 soil samples were collected from the surface layer (0-5 cm) of two sites and mean weight diameter of aggregates (MWD) were measured using dry and wet sieving (MWDd and MWDw, respectively). Based on digital soil mapping (DSM) approach and to map MWD spatially, several environmental covariates were derived from a Landsat 8 image and a digital elevation model (DEM). Two machine learning algorithms including artificial neural networks (ANN) and regression trees (RT) were used to predict MWD with covariates as inputs. Results indicated a significant difference between MWDd in two sites, but no significant difference was found between MWDw. Correlation analysis revealed no correlation between MWDw and all terrain attributes derived from the DEM, but significant correlations were obtained between MWDd and some terrain attributes. Most covariates derived from Landsat images had significant correlation with both MWDw and MWDd. ANN and TR had relatively high and almost the same accuracy in predicting MWDw, but in predicting MWDd, ANN was superior to RT. In general, the findings showed good performance of DSM techniques in predicting and spatial mapping of MWD.
Gholamreza Zehtabian; Hassan Ahmadi; Aliakbar Nazari Samani; amir houshang ehsani; Mahdi Tazeh
Abstract
Plains are one of the most important geomorphological units and different parameters have been considered for classification of plain areas. One of most common classifications in natural resources studies in Iran entailing different qualitative and quantitative factors is: bare plains, apandazh plain ...
Read More
Plains are one of the most important geomorphological units and different parameters have been considered for classification of plain areas. One of most common classifications in natural resources studies in Iran entailing different qualitative and quantitative factors is: bare plains, apandazh plain and covered plain. Such classifications are used to make plains distinguishable from one another. In this study, the geomorphometrical parameters were considered for plain classification by using artificial neural networks and sensitivity analysis. These parameters were extracted by using mathematical equations and applying the corresponding relations on digital elevation models and they are not widely used in Iran. Geomorphometric parameters that were used in this study included Percent of slope, Plan Curvature, Profile Curvature, Minimum Curvature, the Maximum Curvature, Cross sectional Curvature, Longitudinal Curvature and Gaussian Curvature. These parameters were calculated in an area of 125000 hectare and at 1500 points, and the result was compared and calibrated with ground truth map. Sampling method in this study was Latin Hyper cube that is a kind of stratified random sampling. Results of this study show that the most important geomorphometric parameters to classify desert plains include Plan Curvature and Profile Curvature that have the highest sensitivity among different plain types. The more the topography of the area reduced the more the contribution and importance of these factors for separating plain types decreased so that these parameters were most prominent in bare plains but had the lowest efficiency in covered plains.