Soghra Andaryani; Mohammad Hosein Rezaei Moghadam; khalil Valizadeh Kamran; Farhad Almaspour
Abstract
Forecasting models of Land Use/ Cover changes are the main resources for managers and policy-makers in order to develop a sustainable land management plan. Changes of Orchard-lands have an effect on water resources as well as soil permeability. Thus simulation of this land use changes, in areas where ...
Read More
Forecasting models of Land Use/ Cover changes are the main resources for managers and policy-makers in order to develop a sustainable land management plan. Changes of Orchard-lands have an effect on water resources as well as soil permeability. Thus simulation of this land use changes, in areas where there is a shortage of water resources, can provide more information about the occurred changes during a specified time scales along current management. The present study was carried out to simulate and predict the spatial-temporal changes of the orchard by 2026. For this purpose, Geomod method was used to simulate spatial changes of the orchard. Due to the lack of ability of this model in temporal simulation, Markov chain analysis method was used to solve the mentioned problem with the error proportional of 0.012. Orchard was extracted using Landsat 5, 7, and 8 satellite data after necessary corrections as well as SVM in 1987, 2000, and 2013. Then, to understand the impact of each of the criteria used to change this type of land use, instead of Delphi methods, logistic regression, Fuzzy standardization and, after all, WLC were used. The ROC index was used to validate the model. The results showed, this model has a good performance to simulate spatial changes because of area under Curve 0.91 for both of the 2000 and 2013. In the 26-years period, there are 294 hectares of orchard development, and the hybrid model showed that this land use will increase to 304 hectares till 2026
Elham Kakaei Lafdani; Ali Reza Moghaddam Nia; Azadeh Ahmadi; Heydar Ebrahimi
Abstract
This study aimed to examine the influence of pre-processing input variables by Gamma Test on performance of Support Vector Machine in order to predict the suspended sediment amount of Doiraj River, located in Ilam Province from 1994-2004. The flow discharge and rainfall were considered as the input variables ...
Read More
This study aimed to examine the influence of pre-processing input variables by Gamma Test on performance of Support Vector Machine in order to predict the suspended sediment amount of Doiraj River, located in Ilam Province from 1994-2004. The flow discharge and rainfall were considered as the input variables and sediment discharge as the output model. Also, the duration of the model training period was determined through GT. Thereafter, in order to carry out the influence of pre-processing input variables on performance of model, the suspended sediment was predicted using SVM model while no pre-processing has been done on its input variables and the results were compared to each other. Results show the performance of the GT-SVM model in the test phase with minimum RMSE was equal to 0.96 (ton/day) and the maximum coefficient of R2 was equal to 0.98 between the predicted and actual values, was better than SVM model.