جستجوی مقالات مرتبط با کلیدواژه « ga » در نشریات گروه « جغرافیا »

Erosion is one of the main factors restricting the soil fertility and dust production, in several parts of the world, including Iran, has effects on climate agriculture, and human health. Controlling wind erosion would be more effective once sufficient information concerning the effective factors is available. Soil Erodible Fraction (EF) is one of the soil properties that shows the sensitivity of soil particles to wind erosion. The current research aimed to utilize ANN methods and integrating it with GA in order to estimate the soil erodible fraction to wind erosion. Allahabad plain in the southwest of Abiek city in Qazvin province is considered as one of the areas sensitive to wind erosion with strong wind direction from southwest to northeast. The drying up of Allahabad wetland will intensify wind erosion in the region and turn it into a crisis. Determining the extent of land erodibility and identifying its factors affecting can be the basis of a comprehensive plan for soil protection and land sustainability and prioritizing its implementation steps. The present study was conducted to use artificial neural network methods and combine it with genetic algorithm to estimate the soil erodible factor.

In the study area, which was part of the Allahabad plain in Qazvin province, between the coordinates of 50°15 ́- 50°57 ́ east longitude and 35°53 ́- 35°57 ́ north latitude, 95 samples were taken from 10 cm of soil surface. In the samples, the percentage of aggregates with a diameter of less than 0.84 mm as an indicator of EF and percentage of clay, sand and silt, soil saturation capacity, pH, EC, SAR, equivalent calcium carbonate (CCE) and organic matter were measured as input to the models. In this paper, to model the EF using early available characteristics, two methods of artificial neural network (ANN) and its integration with genetic algorithm (GA-ANN) were employed in order to optimize the weights. In this regard, the data were primarily divided into three categories as follows: 60% of the data series was allocated to training, 20% to validation, and 20% to network testing. In this study, MLP networks were used to model the artificial neural network in estimating the values ​​of soil erodible Fracion. In this structure, each artificial neural network includes inputs and hidden and output layers. During the learning process, the degree of network learning by the objective functions was regularly evaluated and networks with the lowest error rate were accepted. To determine the optimal network with the highest level of performance of all stimulus functions defined in the software (axon hyperbolic tangent, axon sigmoid, axon linear hyperbolic tangent, axon linear sigmoid, axon bias, linear axon and axon) by trial and error The most results were used. Levenberg-Marquardt training functions were used to teach defined networks. In this study, genetic algorithm was used to find the optimal point of complex nonlinear functions in combination with artificial neural network (GA-ANN). The genetic algorithm optimizes the weights of the artificial neural network. In fact, the objective function of the genetic algorithm is a function of the statistical results of the artificial neural network.

The results showed that the erodible fraction of soil with five soil properties including pH, electrical conductivity, SAR, clay and organic matter, had a significant correlation at the level of one percent. The models used did not have an appropriate accuracy in estimating EF in both training and testing stages, so that the highest R2 was obtained in the artificial neural network model (0.49) with test series data. Both models were slightly overestimated and the GMER values ​​for the ANN and GA-ANN models were 1.15 and 1.08, respectively, but according to the AIC index, both models had similar predictive power. Sensitivity analysis of the data showed that the greatest effect on EF in the ANN model was related to organic matter (4.07) and in the GA-ANN model was related to clay (8.14).

In the current research, the relationship between soil chemical characteristics and EF might be attributed to their previous effects on vegetation in the region. Additionally, regional evidence indicates the same finding. The highest correlation was observed between EF and soil organic matter. Based on the sensitivity analysis, in the neural network model, the greatest effect on erodible fraction was related to organic matter, pH, and EC, respectively. The effect of pH and salinity on EF could be interpreted due to their effects on vegetation and consequently, the effect of vegetation on aggregates.  An important issue in the research was that the proposed models, which were ANN and its integration with GA for estimating the soil erodible fraction, were not efficient enough for obtaining the highest coefficient of determination (R2) in the model in the neural network in the test phase (R2 = 0.49), which has an accuracy of less than 50% for estimating EF.

Urmia Lake is located in the North West of Iran and its area between 4750 to 6100 square kilometers at an altitude of 1250 meters above sea level. This lake is a permanent lake in Iran. In fact, Urmia Lake is one of the lowest parts of the catchment area North West of Iran. The total surface area of Urmia Lake is 51,876 km square, which is 3.15% of the total area of Iran and 7% of all the water’s surface in the country. The depth varies between 6 and 16 meters, the length of the lake is 50 km and its width varies between 128 km to 140 km. In the catchment area of the lake, there is the main river with annual input about 2 billion cubic meters. Annual rainfall in the catchment area is variable between 200 and 300 mm. Air temperature the area around the lake in winter to 20°C and 40°C in summer increases. Urmia Lake is important in terms of economically, transport, exploitation of the mineral wealth of biodiversity, mitigating climate, and tourism. This unique Lake addition to the previous is habitat for kind of native artemia its name is urumiana artemia that this artemia is unique to this lake. Also, Urmia Lake is the world's second largest habitat for Artemia. According to the research, the main elements in the Urmia Lake include Cl-, Na , Ca2, Mg2, HCo3-, K, Li, So42- and F.
In this study, newly launched Landsat series (Landsat-8) was used for monitoring Urmia Lake salinity and retrieving the salinity map. By incorporating the Landsat-8 datasets, this study determined the salinity changes and created a model to estimate the salinity in Urmia Lake with processing Landsat-8 satellite images as a result; we can obtain salinity map regularly without ground operations. We can also monitor the health of the habitat in terms of salinity and examine the impact of increasing salinity on the plants, animals, and ecosystems of the region. This study applied remote sensing techniques to develop a salinity prediction model for Urmia Lake. In this study, we use Landsat-8 satellite images radiances of Urmia Lake and some salinity indices and in-situ data so we have 17 features to make water surface salinity model with support vector regression (SVR) with all features. After that, we use two algorithms; GA and SFS for selecting suitable features and make models with those features.
Results with all features model show RMSE=24.55 and R2=41% and result with GA feature selection model shows RMSE=21.97 and R2=54% and results with SFS feature selection model shows RMSE=21.93 and R2=53%.
Discussion and Satellite images show that from 1995 to 2003, the lake water surface dropped and proportionate to the dropping water salinity increased to 220 to 300 grams per liter. Also although Artemia is resistant to salt, appropriate salinity is below 100 grams per liter. When water salt is more than 100 grams per liter contents of his tiny body lost and die. Now because of reduction in salinity, the lake has arrived at about 300 grams per liter. Dissolved salt in water has a direct effect on the electrical conductivity of water. In this regard, incorporating high spatial resolution satellite like Landsat-8 images is inevitable. Also, the proposed modeling methods show these changes in multi-data and in widespread Urmia Lake very well

Many catchment erosion studies focus on formation and land use as the primary source of sediment. It is important to improve information on sediment sources, especially in large catchments and sediment source information which can support catchment management decisions. Erosion control projects need to be understood as the relative contributions of different sediment sources from catchments. Fingerprinting methods identify soil erosion sources where geologic variations or different land uses span watershed boundaries. Sediment fingerprinting studies often rely on the collection of sediment from different sources within a catchment. Few studies have focused on using the Hughes mixed model to identify sediment sources. This model can quickly process a large number of samples from the main samples based on Monte Carlo simulation. The main objectives of this research were to determine the contribution of sediment sources by applying a fingerprinting mixing model in a Tange Bostanak drainage catchment.
Material and Methods.Case Study Our study area was located in the Tange Bostanak catchment (30°16′ to 30°25′ N and 52°03′ to 52°13′ E),in the Southern Zagros Mountains, 80 km Northwest of Shiraz, Iran. The drainage area of the Tange Bostanak catchment is 81.73 km2.
Sediment source samples were collected throughout the study catchment from each of the three principal source types (cultivated land, pasture, forest, gardens and also six formations in catchment). 43 representative samples were collected from these potential sources at different locations within the study catchment. Samples were initially oven-dried to 40 °C in order to remove the bias associated with the grain-size effects, only the C, N, Cu, Ti, Si and Sr were identified by the Kruskal–Wallis test to discriminate the potential sediment sources in land use and Nd, Si, C, N, Ti and Nd144/Nd143 were identified by the Kruskal–Wallis test to discriminate the potential sediment sources in the formations. In stepwise multivariate discriminant function analysis, four tracers(C, Cu, Si, Ti) were capable of correctly distinguishing the land use source type. Four tracers (Nd143/144, Cu, Si, Ti) verified the ability to discriminate between geology information source categories. The results on geology information showed that the mean relative contributions related to the areas of Asmary (84.51%) and Quaternary (5.37%) were highest, respectively in Local optimization with 99.94 GOF index. For land uses, the results showed that the GOF index with 97.84 associated with GA optimization were the greatest. The relative contributions related to the areas of range lands (63.04%) and forest (31.81%) were the highest, respectively. Pabedeh Gorpi and Bakhtyari information with 0.24 and 0.27 were the lowest relative importance; also cultivation and forest land uses with 0.022 and 0.55 were the lowest relative importance, respectively. This study suggested that the future sediment fingerprinting studies use models that combine the best explanatory parameters provided by the Hughes (relying on iterations involving all data, and not only their mean values) models with the optimization using genetic algorithms to best predict the relative contribution of sediment sources. Comparing the applications in this catchment, the Hughes mixed model appears a more robust method in Tange Bostanak catchment using the GA optimization method.

Analyzing multi-temporal remotely sensed images is a powerful technique for monitoring land use and land cover changes in urban areas. Apart from the change detection (CD) technique, the features space have an enormous impact on the CD accuracy.To achieve satisfactory CD results in urban area, optimum selection of textural and spectral features is necessary. Although an exhaustive search guarantees the optimality of the selected features, but it is computationally prohibitive. Data reduction techniques such as PCA considers the independence of the data to find a smaller set of variables with less redundancy without intending to improve the CD accuracy. Difficulty in setting the best threshold for JM distance in separability analysis algorithm (SAA) reduces its efficiency. The aim of this paper is finding the optimal textural and spectral features to enhance the CD accuracy using genetic algorithms (GA) and Bayesian classifier. To evaluate the effectiveness of the proposed approach, a case study using IRS-P6 and GeoEye1 satellite imagery acquired on July 15, 2006, and September 1, 2013, respectively, from Sahand New Town (Northwest of Iran) was performed. All the mentioned feature selection methods (PCA, SAA and proposed GA-based method) were implemented in MATLAB R2013a. Results show that, textural features provides a complementary source of data for CD in urban areas. Results show that features selection is an effective procedure in change detection based on textural and spectral features. Each of feature selection methods has its own limitation and advantages, but in general they increase the CD accuracy. The proposed GA-based feature selection approach was found to be relatively effective when compared to PCA and SSA approaches. Overall accuracy and Kappa coefficient of CD were increased from 53.66% to 88.49% and 58.94% to 90.39%, respectively using proposed method in compared with that using only spectral information.

Extended abstract 1- Introduction Exposure to fine particulate matter with aerodynamic diameters less than 10 μm (PM10) has negative effects on human health and may induce respiratory problems, cardiovascular and lung diseases, and additional health problems. Both short-term and long-term exposures to PM10 have been linked to increased morbidity. The measurement of ground-level PM 10 concentration on a regular basis is therefore of great importance to epidemiological studies; it also provides valuable information for an effective management and forecasting of air quality. Air quality monitoring networks have been established in many industrialized countries to take measurement of pollutant concentrations at different locations, on a daily or hourly basis. 2-Methodology Anumber of data fromvarious sourceswere collected for this research, including the historical air quality data sets, MODIS aerosol imagery, and ground-based meteorological measurements. In this work, a semi-empirical model is coupled with the Genetic Algorithms (GA) to enhance the estimation of the particulate matter concentration in a local scale and at the satellite passing time. For this, the corrected values of Aerosol Optical Depth (AOD) retrieved from MODIS images are used. Hence the AODs were corrected for the effects of air humidity and the air mixing height. In semi-empirical method, using genetic algorithm, few weather data were introduced to the model and their effects were considered. Temperature and humidity caused improvement in assessment of PM concentration. 3– Discussion Finally the method was evaluated for Tehran where an acceptable correlation of R2=0. 51 with RMSE of 28 was achieved. However, in the procedure of AOD correction, limitations such as insufficient number of ground-based weather stations and approximate determination of the air mixing height may cause some uncertainties in the proposed method. 4– Conclusion This paper has proposed an effective semi-empirical model for the prediction of ground-level PM10 concentration (GL-[PM10]). Remotely sensed MODIS AOD, and ground-based measurements of surface temperature and surface relative humidity have been found to be highly significant in the prediction. Although MODIS extracted AOD may contain valuable information about particulate matter but this parameter is highly affected by the atmospheric conditions where usually it is hard to acquire the weather data during many satellite overpasses.