Fatemeh Bahmani; Hosin Pirisahragard; Jamshid Piri
Volume 26, Issue 1 , June 2019, , Pages 201-213
Abstract
Estimation of the soil temperature in arid regions is one of the most important issues in planning the projects of desertification, water resource management, and establishment of vegetation.The present study aimed to compare the accuracy of artificial intelligence methods in order to estimate soil daily ...
Read More
Estimation of the soil temperature in arid regions is one of the most important issues in planning the projects of desertification, water resource management, and establishment of vegetation.The present study aimed to compare the accuracy of artificial intelligence methods in order to estimate soil daily temperatures using meteorological data (daily minimum and maximum of temperatures, sunshine, and evaporation), as well as, identifying the most important factors on soil temperature in Zabol and Shiraz synoptic stations. For this purpose, soil daily temperature was estimated at 5, 10, 20, 30, 50 and 100 cm depths by using the three-year period data (2011-2014) and artificial neural network, neuro-fuzzy adaptive genetic programming, and combined neural network-genetic algorithm approaches. Thae results were evaluated using the root mean square error (RMSE) and mean absolute error (MAE) and determination coefficient. Based on the results, there was more dependence between the air temperature and soil temperature at the topsoil so that, the highest and the lowest correlation between actual and simulated data were observed at 5 cm (mean R2=0.92) and 100 cm depths (mean R2=0.56), respectively. The accuracy of the methods used was different from each other in estimating the soil daily temperature. Based on results, in Zabol and Shiraz stations, combined neural networks - genetic algorithm approach and artificial neural network methods provided the most accurate estimation of soil daily temperature, respectively (the mean RMSE=3.69, 2.86 and mean MAE=3.23, 2.57 respectively). According to the results of the present study, it is suggested that in order to choose appropriate time and depth of seeding in the vegetation reclamation projects in arid regions, through considering of climatic conditions of each region, precise artificial intelligence techniques could be used to estimate the soil daily temperature.
Mohammad reza Jamalizadeh Tajabadi; Ali reza Moghadam nia; Jamshid piri; Mohammad reza Ekhtesasi
Volume 17, Issue 2 , September 2010, , Pages 205-220
Abstract
Dust storms are common climatic events in arid, semi arid and desert regions of the world. These events impact human resources by foundation losses, every year. Accurate prediction of these events can be effective for decision support in environmental, health, army, and other related fields. An artificial ...
Read More
Dust storms are common climatic events in arid, semi arid and desert regions of the world. These events impact human resources by foundation losses, every year. Accurate prediction of these events can be effective for decision support in environmental, health, army, and other related fields. An artificial neural network is a method which can predict nonlinear problems. In this study we attempted to predict dust storms and low visibility in Zabol city using synoptic data. Result indicates that this method is somewhat successful and appears that via identification of much more dust storm occurrence process, we can do more accurate prediction.
Naser Mirzamostafa; Davar Khalili; Mohammad jafar Nazemossadat; Gholam reza Hadarbadi
Volume 15, Issue 1 , January 2008, , Pages 85-69
Abstract
Zabol region is one of the places that is exposed to severe wind erosion, which is located in southeast Iran Due to the fact that, some stations like Zabol suffers from missing data (having five observations instead of eight), thus, the effects of missing data on prediction of wind speed and direction ...
Read More
Zabol region is one of the places that is exposed to severe wind erosion, which is located in southeast Iran Due to the fact that, some stations like Zabol suffers from missing data (having five observations instead of eight), thus, the effects of missing data on prediction of wind speed and direction also needed to be considered. This study aim to determine the minimum years of data required in predicting hourly wind speed and direction, and predicts hourly wind speed and direction, also to verify suitability of Weibull distribution in predicting hourly wind speed and direction and finally to analyze the erosive winds in Zabol region. In this study, the regression coefficients (r) of probability of wind occurrence in various speeds for 16 cardinal directions in two different periods (1986- 1990 and 1986-1995) were separately calculated and compared. To predict hourly wind speed and direction by Weibull distribution, at first its scale and shape parameters (c and k) were determined using the least square method. Then, wind direction distribution, the ratio of maximum to minimum of wind speed, and the hours with maximum wind speed during any month were determined. Using these parameters along with generation of random numbers, the hourly wind speed and direction were simulated. The results indicated five years instead of ten years of data can be used to predict wind speed and direction with a confidence level at 99%. Weibull distribution provided best fit during the months that both the probability of calm periods or standard deviation of probability of wind occurrence in different directions were low. The maximum and minimum wind speed occurred at about 6:00 AM and 6:00 PM, respectively. The probability of occurrence of erosive winds (V≥8m/s) were maximum in June, July, August, and September. The analyses of wind data indicated that the most erosive winds were from North-Northwest, Northwest, and North. The wind speed and direction were predicted by Weibull distribution in the region with 99% accuracy. The results obtained from this research can help researchers and soil conservationists to predict and control wind erosion.