جستجوی مقالات مرتبط با کلیدواژه "spatial prediction" در نشریات گروه "آب و خاک"

Digital soil mapping plays an important role in upgrading the knowledge of soil survey in line with the advances in the spatial data of infrastructure development. The main aim of this study was to provide a digital map of the soil family classes using the random forest (RF) models and boosting regression tree (BRT) in a semi-arid region of Ilam province. Environmental covariates were extracted from a digital elevation model with 30 m spatial resolution, using the SAGAGIS7.3 software. In this study area, 46 soil profiles were dug and sampled; after physico-chemical analysis, the soils were classified based on key to soil taxonomy (2014). In the studied area, three orders were recognized: Mollisols, Inceptisols, and Entisols. Based on the results of the environmental covariate data mining with variance inflation factor (VIF), some parameters including DEM, standard height and terrain ruggedness index were the most important variables. The best spatial prediction of soil classes belonged to Fine, carbonatic, thermic, Typic Haploxerolls. Also, the results showed that RF and BRT models had an overall accuracy and of 0.80, 0.64 and Kappa index 0.70, 0.55, respectively. Therefore, the RF method could serve as a reliable and accurate method to provide a reasonable prediction with a low sampling density.

Today, supplying water to meet the sustainable development goals is one of the most important concerns and challenges in most countries. Therefore, identification of the areas with groundwater potential is an important tool for conservation, management and exploitation of water resources. The purpose of this research was to prepare the potential groundwater map in Nahavand, Hamedan Province, using the weight of evidence model and combining it with logistic regression. For this purpose,  the information layers of slope angle, slope aspect, slope length, altitude, plan curvature, profile curvature, TWI, SPI, distance from fault, fault density, distance from river, drainage density, lithology and land use were identified as the  factors affecting groundwater potential and digitized in the ArcGIS software. After designing the groundwater potential map with these three methods, ROCs were used to evaluate the results. Of 273 springs identified in this study, 191 (70%) were used to prepare the groundwater potential map and 82 springs (30%) were used to evaluate the model. The area under curve (AUC) obtained from the ROC curve showed an accuracy of 80.4% for the weight of evidence model and 82.5% for the weight of the evidence- regression combined model

Today, there is great demand for accurate soil information to determine the relationship between soil and landscape, and easy updating of soil maps has increasingly gained importance. Digital soil mapping techniques can be cost-effective solutions to obtain information dealing with the soil types over large areas. The objective of this study was to provide a digital soil map in the Abyek region of Qazvin province using random forest model for management purposes and sustainable land use planning. To this end, soil samples were collected based on cLHS. After the laboratory analysis, using random forest model and auxiliary variables derived from a digital elevation model with a spatial resolution of 30 m and Landsat 8 imagery, the modeling and preparation of regional soil maps were performed. Out of 7261 ha, the dominant soil was classified as Loamy-skeletal, mixed, superactive, thermic Typic Calcixerepts. The results showed that soil modeling using random forest algorithm could accurately predict (Kappa coefficient ~ 0. 83) soil classes in the region.

This study presents a new method for interpolation by use of copula for groundwater quality zoning. In this regard, the data of the concentration of bicarbonate in 87 piezometric wells on the plains of Kerman and Ravar in September 2013 were examined. For this purpose, four Archimedean copula including Clayton, Frank, Gumbel and Joe have been used. Then, the obtained results were compared to the results obtained from conventional zoning methods to evaluate the performance of copulas. Analysis of the results with respect to the root mean square error criterion in the zoning was obtained about 1.84 and 1.95 mg/L based on median and mean respectively, by use of copula which had a better performance compared to kriging method with an error of 2.21 meq/l, kriging method within Box-Cox transformation and error of 2.14 meq/l, kriging with Logarithmic transformation of 1.98 meq/l and inverse distance weighting method with an error of 2.83 meq/l.

In response to the demand for soil spatial information، the acquisition of digital auxiliary data and matching it to field soil observation is increasing. With the harmonization of these data sets، through computer based methods، so-called Digital soil Maps are increasingly being found to be as reliable as traditional soil mapping practices but without the prohibitive costs. Therefore، at present research، we have attempted to develop decision tree (DTA) and artificial neural network (ANN) models for spatial prediction of soil taxonomic classes in an area covering 720 km2 located in arid region of central Iran where traditional soil survey methods are very difficult to undertake. In this area، using the conditioned Latin hypercube sampling method، location of 187 soil profiles were selected، which 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 the DTA had the higher accuracy than ANN about 7% for prediction of soil classes. Determination of coefficient (R2)، overall accuracy and kappa coefficient calculated for two models were 0. 34، 0. 46، 48%، 52%، 0. 13 and 0. 25، respectively. Our results showed some auxiliary variables had more influence on predictive soil class model which included: wetness index، geomorphology map and multi-resolution index of valley bottom flatness. In general، results showed that decision tree models had higher accuracy than ANN models and also their results are more convenient for interpretation. Therefore، it is suggested using of decision tree models for spatial prediction of soil properties (category and continuous soil data) in future studies.