Behnaz Attaeian; Ali Badrestani; Saeid Khosrobeigi Bozchelui; Mohammad Mehdi Artimani
Abstract
Soil organic carbon as a key factor in soil stability and fertility is considered as one of the important environmental challenges in the context of climate change. The aim of this study was to determine soil organic carbon zonation in Gonbad paired-watershed, Hamedan province. In this research, the ...
Read More
Soil organic carbon as a key factor in soil stability and fertility is considered as one of the important environmental challenges in the context of climate change. The aim of this study was to determine soil organic carbon zonation in Gonbad paired-watershed, Hamedan province. In this research, the information of meteorology, soil science and erosion and sedimentation study of Gombad watershed was used, including the information of 49 profiles in the 0-15 cm soil layer. After collecting data, tests of normality (Shapiro-Wilkα test <0.05), homogeneity of variance, and then the relationship between independent variables and organic carbon were performed using Pearson's linear correlation in SAS software. Also, determining the most effective independent variable using multivariate analysis, PCA factor analysis was used in XlStat 2.1 software. In order to determine the distribution and amount of soil organic carbon in the Gonbad representative watershed, modeling using SVM support vector machine learning algorithms and RF random forest was used in R software.The results showed that 78.18% of soil organic carbon changes depend on four components. Clay and nitrogen percentage were selected as the most effective variables on soil organic carbon content, so that the first component of clay content explained 34% and the second component nitrogen explained 18% of variations. According to the results of the implementation of the SVM and RF Models, the SVM model with a CE factor of 0.86 and RMSE of 0.05 in the test stage is a more accurate model in this study.
Saeid Khosrobeigi Bozchelui; Arash Malekian; Alireza Moghaddam Nia; Shahra,m Khalighi
Abstract
Flood is one of the most devastating natural disasters, causing financial and human losses each year. At the same time, many rivers in Iran's watersheds lack complete and accurate statistics and information. On the other hand, estimating the flow of floods is one of the most important factors for the ...
Read More
Flood is one of the most devastating natural disasters, causing financial and human losses each year. At the same time, many rivers in Iran's watersheds lack complete and accurate statistics and information. On the other hand, estimating the flow of floods is one of the most important factors for the design and implementation of water structures. In such cases, one of the appropriate solutions to estimate the maximum flow rate with different return periods is flood analysis. In order to conduct the present study, 55 hydrometric stations with a common statistical period of 20 years were considered to perform the work after the statistical deficiencies were eliminated. Then, based on the distribution of the third type of Pearson logo with the lowest error rate and the highest number of first rank as the most suitable fit function, the amount of discharge in different return periods was estimated. The following information was collected on the types of physiography, land use, climate and geology variables. After collecting information about all independent variables using Gamma test, the most important variables affecting the maximum instantaneous flow, including area, drainage density, maximum 24-hour rainfall and watershed environment, were selected and modeled using methods. Random forest modeling and support vector modeling were performed and their efficiency was determined based on statistical indicators With an efficiency coefficient of 74 to 83%, the error of 3.05 to 32.11 m3 and the coefficient of explanation of 76 to 91 are more accurate than the random forest model.
