پژوهشی
Ahad Habibzadeh; Shahram Roostaei; Mohhamad Reza Nikjoo; Atta Allah Nadiri
Volume 4, Issue 11 , September 2017, Pages 1-20
Abstract
Quaternary deposits as the major sources of fresh water for humans have often been influenced by anthropogenic activities such as agriculture, industry, and the like. The Tasuj plain is located in 45°18 to 45° 32 E and 38°20 to 38°24 N in north of Lake Urmia in East Azarbyjan province. ...
Read More
Quaternary deposits as the major sources of fresh water for humans have often been influenced by anthropogenic activities such as agriculture, industry, and the like. The Tasuj plain is located in 45°18 to 45° 32 E and 38°20 to 38°24 N in north of Lake Urmia in East Azarbyjan province. This plain is one of the sub-basins of Lake Urmia which is surrounded by 12 major plains. The Tasuj basin is about 558 km2. This includes 302 km2 of the Tasuj plain and 256 km2 of Mount Mishu. The study area is surrounded by Lake Urmia (south), Mount Mishu (north), the Salmas Plain (west), and the Shabestar Plain (east). The highest elevation of the Tasuj basin is 3,133 m above the sea level (amsl) at the Peak of Mount Alamdar and the lowest elevation is 1,274 m near Lake Urmia. In the Tasuj basin, only a few seasonal rivers, originating from Mount Mishu, may appear. These seasonal rivers can flood the Tasuj plain in wet seasons. The seasonal rivers are the Amestejan, Angoshtejan, Almas, Chehregan, Tiran, Cheshmekonan, Sheikhvali, Sheikhmarjan, and Ghelmansara. Methodology The conceptual model represents the dimensions, directions, and circumstances of the distribution of the deposits. This research was based on the stratigraphy, the conceptual model of Quaternary deposits of the Tasuj plain, north of Lake Urmia. This simulation was carried out using the GMS software, based on 28 geological logs of observation wells and 78 geoelectrical sounding per geoelectrical sections. The application menus of this software including GIS, TINs, Solids, Boreholes, 3D Gride, and 3D scatter point were used in the research. Results and Discussion Quaternary deposits of the Tasuj plain were divided into 5 classes of strata, including (Qal), (Q3), (Q2), (Q1), and (Qmf). The results showed that Q2 deposits had an average permeability and contained fresh water aquifer in the eastern and southeastern areas. Although Q3 and Qal were located in 1320 m above sea levels (asml), the highest thickness (i.e., 190 m) was shown in 1550 m asml. These deposits spread horizontally in the whole area, but its vertical expansion was more in the northern and, particularly, in the north eastern areas. Q3 and Qal classes were characterized by high permeability and lack of clay. Conclusion The results of this study indicated that the conceptual-stratigraphic model has high efficiency in identifying the Quaternary deposits. The 3D-capable model can expand the point wise characteristics and thickness of Quaternary deposits in the study area using interpolation method. Quaternary deposits of the Tasuj plain were characterized as alluvial deposits (Qal), dry deposits (Q3), medium grain alluvial deposits (possibly water bearing) (Q2), fine grain alluvial deposits (possibly water bearing) (Q1), and clay (Qmf). In addition, the conceptual-spatial model of the quaternary deposits of the Tasuj aquifer showed that aquifer bedrock in the Galemaraghoosh-Shikhvaly was lower than other areas along the coast. There might be a buried deep valley from Almas to Tasuj, Galemaraghoosh.
پژوهشی
Bakhtiar Feizizadeh
Volume 4, Issue 11 , September 2017, Pages 21-38
Abstract
Introduction
The modification of the Earth’s terrestrial surface by human activities is commonly known as the land use/land cover change (LULCC) around the globe. Although the modification of the land by humans to obtain livelihoods and other essentials has been a common practice for thousands ...
Read More
Introduction
The modification of the Earth’s terrestrial surface by human activities is commonly known as the land use/land cover change (LULCC) around the globe. Although the modification of the land by humans to obtain livelihoods and other essentials has been a common practice for thousands of years, the extent, intensity, and rate of LULCC are far greater now than they were in the past. These changes are driving forces for local, regional, and global level unprecedented changes in the ecosystems and environmental processes. The empirical studies conducted by researchers from diverse disciplines have found that changes in the land use/land cover is a key to many diverse applications such as agriculture, environment, ecology, forestry, geology, and hydrology.
Satellite Remote Sensing and GIS are the most common methods for the quantification, mapping, and detection of the patterns of the LULCC, because of their accurate geo-referencing procedures, digital formats suitable for computer processing, and repetitive data acquisition. Technically speaking, the remote sensing based digital satellite images have a high capability for natural resources' management operations. Land use/land cover change detection is considered as one of the most important applications in the domain of the remote sensing satellite images. Related to this applicability, it will be possible to apply multi-temporal satellite images for the detection of the land use change. Based on the results obtained from the change detection operation and modeling of the further land use changes, one will be capable to makes better decision for natural resources' management. Based on this statement, the main objective of this research is to represent the applicability of the satellite images for the detection of the land use changes, particularly on the upper areas of the Allavian dam of the Sofi-chai basin.
Dataset and methods
The study area was the upper area of the Allavian Dam in Maragheh. The research was carried out based on the digital interpretations of the Landsat images (ETM+ and TM) of the years 1989, 2000, 2002, and 2015. Based on these images, the land use changes of this region were separately detected for 3 periods. It should be noted that the widely practiced operations such as image preprocessing, classification, and post processing with those related techniques were considered in this study. Indeed, it is widely known that preprocessing before the the change detection phenomenon is very important in order to establish a more direct relationship between the acquired data and the biophysical phenomena. Accordingly, atmospheric and geometric correction were applied as the first step on satellite images. In doing so, the LSLC classes were determined based on the spatial resolution of the satellite images. Then, image enhancement methods were applied to detect each LULC class on the satellite image. Next, GPS based training data was collected in the field operation and integrated with the satellite images. In addition, the supervised maximum likelihood was applied to derive LULC map for each year. The validation step was also part of this section for the accuracy assessment based on kappa coefficient and error matrix.
Results and Conclusion
After developing LULC maps, the results were transformed into GIS environment for the following steps and GIS analysis. The results indicated a significant changes in LULC of the study area. They also indicated that orchards cover had increased throughout the study periods but rich range lands widely converted into poor range lands because of losing the significant canopy of the native plants. Increasing the trend of the orchards area may be in relation with the population growth and this factor can be affected by ( have an effect on) range land degrading. The water supply out of Allavian dam might be another reason for increasing the orchard’s area. The results also acknowledged the capability of the remote sensing for the LULC and change detection analysis. The results of this research are of great importance for decision making authorities in governmental departments such as the ministry of agriculture and natural resources for the purposes of planning and decision making.
پژوهشی
Gholamabbas Fallah Ghalhari; Elham Kadkhoda
Volume 4, Issue 11 , September 2017, Pages 39-57
Abstract
Introduction
The meaningful, complex, and ongoing connection between the rainfall and other climatic elements causes diversity in space and time. A new approach in climatology is to describe the spatial variability of the rainfall based on the spatial statistics. Unlike the classical statistics, the ...
Read More
Introduction
The meaningful, complex, and ongoing connection between the rainfall and other climatic elements causes diversity in space and time. A new approach in climatology is to describe the spatial variability of the rainfall based on the spatial statistics. Unlike the classical statistics, the spatial statistics shows the statistical data on a map. Therefore, the attention and emphasis on the spatial differences and the identification of the specific and unique points or homogeneous regions will be provided. Modeling of the rainfall behavior is one of the main foundations in any climate research. In this regard, two major efforts are of interest to climatologists. One of them is the precipitation zoning. The other one is the analysis of the spatial temporal variations of the precipitation. This analysis is important for weather forecasting and a wide range of decision makers, including hydrologists, farmers, and industrialists.
Methodology
Using statistical methods, the present study aimed to introduce the fundamentals of the spatial data and the general precipitation behavior of Mashhad’s plain along the space. In this regard, the study used the daily precipitation data of 34 synoptic stations, climatology, and rain gauge during the survey period, 1963-2013. The study initially analyzed the spatial and temporal distributions of the precipitation based on the classical statistical methods. Then, it focused on the central average, standard distance, and directional distribution. In this research, the universal Moran method was used to calculate the spatial autocorrelation data. In addition, the central mean method was used to calculate the basin rainfall gradient. Finally, directional distribution was used to calculate the trend and direction of the precipitation distribution.
Discussion
The results showed that the gravity center, the centroid, of the annual rainfall during the last half-century sustains a displacement of 3.83 km where the distribution arrow demonstrates the magnitude of the tilt and orientation on the amount of the precipitation.
Also, the standard distance of the precipitation in Mashhad, in the fifth decade (2003-2013) compared to the first decade (1963-1973), changed to 1254.57. This change can be one of the reasons of the instability of the linear relationships of the spatial factors and the rainfall in the plains of Mashhad.
Conclusion
The results showed that the center of the rainfall gravity of Mashhad plain was displaced over 3.3 km during the 50-year period. In addition, there was a change of 0.269 degrees in the direction of the distribution of the precipitation in the fifth period compared to the first period. Since, this shift was negative to areas with spatial dependence, it indicated a general drop in the rainfall in the Mashhad plain. The results also showed that the roughness and height might be two important factors affecting the spatial patterns of the rainfall in Mashhad Plain.
پژوهشی
Manuchehr Farajzadeh; Ali Asghar Hodaei; Maryam Mollashahi; Neda Rajabi Rostam Abadi
Volume 4, Issue 11 , September 2017, Pages 59-81
Abstract
Introduction
Soil erosion as one of the most important natural hazards of each country usually results in reduced fertility, crop reduction, and desertification, particularly in arid and semi-arid areas. Two-thirds of Iran is located in the arid and semi-arid areas and one of its climatic features is ...
Read More
Introduction
Soil erosion as one of the most important natural hazards of each country usually results in reduced fertility, crop reduction, and desertification, particularly in arid and semi-arid areas. Two-thirds of Iran is located in the arid and semi-arid areas and one of its climatic features is flood. Consequently, soil erosion is one of its environmental problems. Nowadays, since soil is important for the life of products and is directly related to the balance of the ecosystem and the water cycle, its protection and fertility are two important factors that shouldn't be ignored. The purpose of this study was to compare the suspended sediment in two drainage basins of the Caspian Sea, with a humid climate, and central Iran, with an arid climate.
Methodology
For research surveys, pluviometersdata, sediment and discharge assessment, slope, topography with land use, and lithology were used. Maps were obtained from survey organization, geological survey and mineral exploration, and Natural Rescues of Iran. To this end, land use maps, based on the land use type, were classified into six categories including urban area, forests land, pasture land, agricultural land, swamp land, and arid land, without vegetation cover. In addition, the geological maps, based on the stone resistance and amount of sediment production, were classified into ten categories including the hardest stones, very hard stones, so hard stones, enough hard stones, mediocre stones, enough soft stones, partly soft stones, powder stones, loose stones, and so loose stones. Finally, the data was analyzed using the SPSS software.
Results and Discussion
The results indicated a high and significant correlation between the rainfall and sediment. There was also a direct and significant correlation between the rainfalls, discharge, and yearly sediment of the field. In addition, a fairly good model was achieved from the rainfall, discharge, and sediments variables.
Considering the distribution of the sediment in central Iran, the highest sediment volume was seen in the west of the basin at Shahrokh, Chamriz station. The lowest sediment volume, in contrast, was seen in its north and south. In the Caspian basin, the highest sediment volume was seen in Gharasou and Ran basin at Ghezaghli station. The second highest sediment volume was seen in Gharaghoni station at Sefidrood basin. The lowest sediment volume was seen in Talesh basin and in the southern stations of the Caspian Sea.
پژوهشی
Vahid Nourani; Saleh Mohsenzadeh
Volume 4, Issue 11 , September 2017, Pages 83-103
Abstract
Introduction
In this study, the MPSIAC model was used to consider the effects of the dominant factors in sediment production in order to estimate the rate of the erosion and sediment load in sub-basins of the Aji Chay River. Since the sediment rate of this model is the annual average, the variations ...
Read More
Introduction
In this study, the MPSIAC model was used to consider the effects of the dominant factors in sediment production in order to estimate the rate of the erosion and sediment load in sub-basins of the Aji Chay River. Since the sediment rate of this model is the annual average, the variations of the nine fold factors of this model was examined in order to calculate the sediment for each year. Then, the annual and monthly sediment rates were quantified using a cascading method.
Methodology
In order to estimate the sediment production and the relationship between the degree of the sediment yield and the amount of production, equation (1) which was based on determining the scores of the factors considered in the PSIAC model and obtaining their total scores in each hydrological unit was used
38.77e0.0353R = Equation(1): QS
Qs=sediment yield (m3/km2/year) R= sedimentation rate
The PSIAC model specifies some variations for each factor, which is somewhat selective and requires an expert judgment. Johnson and Gombard (1982) have made the nine-fold factors for this method as numerical equations.
The estimated sediment rate using MPSIAC method is based on the annual average. Therefore, the variations of the factors of MPSIAC model were examined and compared to estimate the sediment for each year. Due to the fact that sediment is not the same throughout the year, it was not possible to equally consider annual sediment for all months of the year. Thus, for the purpose of the quantification of the monthly sediment, the cascading micro-scale was used through verifying the existing data and filling the deficiencies of the data. In the process of disintegration, the sediment, which was the annual sediment in the initial intervals, was sequentially broken into smaller surfaces with specific coefficients and calibrated.
Equation(2): SNij = Sij
Equation(3): SijNky = Sk
Results and discussion
In this paper, the annual sediment rate was estimated using remote sensing, GIS techniques, and the application of the experimental model of MPSIAC in hydrological units and its zoning in the area. Then, by inserting the DEM into the GIS environment and by modifying the ups and downs, the flow direction, the network of waterways, and the primary and secondary sub-basins were produced. As a result, the production rate of the sediment and the scores of the each of the factors in the sub-basins were calculated using the equations presented in the MPSIAC model. The results showed that there was a high correlation between the estimated sediment load with the MPSIAC model and the observed and recorded results.
The results of the MPSIAC model for the estimated sediment rate were based on the annual average, so the existing data and nine-fold factors of MPSIAC model, which were time-consuming, were used for the monthly sedimentation. To measure the amount of the precipitation and runoff for different months of each statistical year and to study the amount and manner of changes in vegetation and land use in the studied area, the annual precipitation and annual erosion were calculated for each statistical year. Then, sub-scaling was done through the calculation of the sub-scale coefficients of annual to monthly sediment.
Conclusion
The estimated sediment rate using MPSIAC model and observational and measured data of the sediment in the hydrometric stations of the Aji Chay basin has high accuracy and acceptable correlation. In addition, by comparing and verifying the available and measured data in the hydrometric stations of the AjiChay basin at low scales with extractive data of this method, it turns out that the sediment values can be estimated at low scales by specifying the sub-scale coefficients and calculating the sediment for each year.
پژوهشی
Abolghasem Amir Ahmadi; Mahnaz Naemi Tabar; Bahar Gholkar ostadi
Volume 4, Issue 11 , September 2017, Pages 105-125
Abstract
Absract:
Introduction
Landslide is one of the natural phenomena causing many financial losses and casualties in Iran every year (Kamranzadeh, 2014: 101). This phenomenon occurs when the force of materials’ weight is higher than the shear strength of the soil shear force (Memarian et al. 2006: ...
Read More
Absract:
Introduction
Landslide is one of the natural phenomena causing many financial losses and casualties in Iran every year (Kamranzadeh, 2014: 101). This phenomenon occurs when the force of materials’ weight is higher than the shear strength of the soil shear force (Memarian et al. 2006: 105). The Shannon entropy is a function of probability distribution and standard for measuring uncertainty in the information content of a parameter, and by considering occurrence frequency of subgroups of that parameter, it shows heterogeneity level. As a result, it calculates the effect of each parameter on the results of the system (Hosseinpour Mil Arghadan et al. 2014). Objectives of the present study are the selection of criteria and standards, preparation of digital factors layers, preparation of the landslide hazard zonation map, diagnosis of high risk points via the Shannon entropy, presentation of strategies appropriate for preventing possible risks and solutions to reduce damages in the study area. Bajgiran is the central district of Bajgiran County and a part Doulatkhaneh Rural District of Ghouchan Township. According to climate divisions, Bajgiran has a moderate mountainous climate. Geologically and structurally, it is a part of Kopeh Dagh Sedimentary Basin. In terms of stratigraphy, outcrops from the Jurassic rock units to the present era can be observed in the study area.
Materials and methods
In the present study, first of all factors affecting the occurrence of landslide including height, precipitation, slope, slope direction, slope shape, distance from the waterway, distance from the road, distance from the fault, land cover and lithology were identified as factors affecting the occurrence of landslides, and the mentioned maps were digitized in GIS. to this end, using the topographic map on a scale of 1:50000, the Digital Elevation Model Map (DEM), factors of slope degree, slope direction, slope shape, height level, distance from the waterway, and distance from the road were prepared. Using the land-use map on a scale of 1:25000, information layers of land use were extracted. To draw the lithological map, the distance from the fault of the geological map on a scale of 1:50000 was used. To draw the precipitation map, statistics of the rain gauge stations of five Daroungar, Mohammad Taghi Beig, Aman Gholi, Kikan, Hey Hey Ghouchan, and Bahman Jan Stations were used. The information content available in the decision matrix in entropy process is calculated via equation 1:
Equation 1: Ej = -K
Where Ej is the entropy value and Pi,j is the decision matrix.
Equation 2: Pij =
Where rij is the value or the special score assigned to each layer.
Equation 3: K= (lnm)-1
Where k is the fixed coefficient and m is the number of landslides.
After the formation of the decision matrix and extraction of the value of Ej, the value of Vj can be calculated via equation 4:
Equation 4: Vj = 1- Ej
Where Vj is the deviation degree of uncertainty.
And finally, to calculate the final weight of all factors (Wj), equation 5 is employed.
Equation 5: Wj =
To prepare the final map, equation 6 is used:
Equation 6:
Where Hi is the landslide hazard occurrence coefficient, Wj is the final weight of all factors, rij is the weight of each factors (Moghimi et al. 2012: 82).
Results and discussion
After converting criteria into integers and the formation of the initial matrix, the value of Pij was calculated via equation 1 and the value of K was calculated via equation 2. To calculate Ej for each criterion, equation 2 was used. The results are indicated table 2. In this equation, the value of E which is a function of n, for each n where Pi is equal, the value of E becomes maximum which is statistically calculated via probability distribution of Pi. Then, uncertainty or degree of deviation of each criterion (dj) obtained from the fraction of the value of Ej from 1 were calculated per each indices effective on landslides of the study area (table 2). After that, using equation 5, the weight of each parameters used in the entropy matrix of landslides (Wj) including height (0.02113), precipitation (0.031142), shape of slope (0.0116110), slope (0.011342), distance from the waterway (0.045161), distance from the road (0.113401), distance from the fault (0.099871), land use (0.997110), and lithology (0.095148) were obtained. Therefore, the regional model of the landslide hazard degree in the area was obtained via equation 6. Hi is the landslide hazard degree in the area (equation 7).
Conclusion
The aim of the present study was to prioritize factors affecting the occurrence landslides and zone their sensitivity in Bajgiran Region via the Shannon entropy. The results of the study shows that the most important factors affecting landslides in the study area are slope layers, slope direction, lithology, distance from the fault, and height. After weighting parameters and formatting the entropy matrix, the zonation mapping were conducted. To this end, information layers were prepared in Arc GIS and converted into Raster formats. With regard to zoning maps obtained from the entropy model, 15 landslides have occurred in the area among which 9 landslides have occurred in a high risk zone (42%), 4 landslides in a moderate risk zone (31%), and 2 landslides in a low risk zone (27%). Regarding the factor of slope, it can be said that the most landslides have occurred in slopes with 60%. It may because the lack of the soil-formation process prone to slippery movements. In case of the factor of slope direction, the most landslides have occurred in northern domains and in heights with 1600 m high. This results is compatible with the faults and calcareous, marl, and Pyura Chilensis organizations of the area. The results of the present study also show that the entropy model has appropriate performance in identifying risk areas and their zonation. In addition, the results can be used in decision making and management of land use and urban planning.
پژوهشی
Keyvan Mohammadzadeh; Seiran Bahmani; Mohammad Hossein Fathi
Volume 4, Issue 11 , September 2017, Pages 127-148
Abstract
Introduction
Iranian territory has the main prerequisites for the occurrence of a wide range of landslides due to its mountainous topography, tectonic activities, high seismicity, and different geological and climatic conditions. Therefore, reducing the effects of natural disasters, particularly landslides, ...
Read More
Introduction
Iranian territory has the main prerequisites for the occurrence of a wide range of landslides due to its mountainous topography, tectonic activities, high seismicity, and different geological and climatic conditions. Therefore, reducing the effects of natural disasters, particularly landslides, is one of the key challenges for land-use planners and policymakers in this field. In this study, the southern side of the Ahar Chai basin from Nasirabad Village to Sattarkhan Dam is evaluated for the probability of the landslide occurrence. This region is highly susceptible to landslide occurrence because of the extensive manipulation and its natural conditions. Indeed, the occurrence of the large shallow landslides in this region is an indication of this susceptibility. In this study, Linear Regression Model has been used to prepare the landslide zonation.
Methodology
The study area was the southern sides of the Ahar Chai River, from Nasirabad village in Varzaghan to the Sattarkhan Dam, with an area of 128 km2. In order to study the potential of the landslide occurrence in this region, nine main factors including slope, slope direction, lithology, land use, precipitation, distance from the fault, distance from the river, distance from the road, and vegetation were identified. The model which was used in this study was Logistic Regression. This model is one of the predictive statistical methods for dependent variables in which zero and one respectively indicate the occurrence and non-occurrence of landslides. In addition, instead of being linear, the regression of the variables is S-shaped or logistic curve and the estimations are in the range of zero-one. Indeed, values close to zero indicate the low probability of the occurrence and values close to one indicate the high probability of the occurrence.
Discussion
In Logistic Regression model, after entering the data into the Logistic Regression model and using the effective parameters in Idrisi software, the coefficients of the model were extracted. A value of 965, which represents a very high correlation between the independent and dependent variables, was obtained for the ROC index. After determining the validity of the Logistic Regression model, using the above indicators, landslide sensitivity zonation map was prepared. In the present model, the land use factor with the highest coefficient was the best predictive variable in determining the probability of the landslide occurrence in this region. In addition, the SPI index and the distance from the fault had respectively the second and third highest coefficients. After zoning the landslide, the slip area was calculated for each class and its results showed that zones with highest risk had the lowest area percentage and these areas were located in the western slopes.
Conclusion
The results showed that while land use, lithology factors, and SPI index with positive coefficients had higher correlation, the other factors with negative coefficients had lower correlation. Based on the map, the western, southern, and the north-eastern parts of the region have the highest potential for landslide occurrence. Furthermore, the high value of the ROC index and its proximity to number one indicates that landslides in the study area have a strong correlation with the probability values derived from the Logistic Regression Model. In addition, the assessment of the SCAI scaling hazard zonation map shows that there is a high correlation between the hazard map with the existing slip points and the field observations of the area. It can be said that, in addition to the natural factors, some human factors including unstructured road construction may play an important role in the occurrence of the landslides. It is also necessary to avoid making changes in the ecosystems and land use. Finally, any policies to construct structures should be commensurate with the geomorphologic and geological conditions.
پژوهشی
Hamidreza Babaali; Reza Dehghani
Volume 4, Issue 11 , September 2017, Pages 149-168
Abstract
Introduction
Flood is one of the hazardous natural disasters that causes loss of life and financial problems every year. Therefore, scientists have tried to assess the quantitative variability of this phenomenon as much as possible. In this study, the recorded data in Kahman Aleshtar watershed area, ...
Read More
Introduction
Flood is one of the hazardous natural disasters that causes loss of life and financial problems every year. Therefore, scientists have tried to assess the quantitative variability of this phenomenon as much as possible. In this study, the recorded data in Kahman Aleshtar watershed area, which is located in Lorestan province, was used to investigate the precision of the different flood peak discharge prediction models. In addition, the wavelet and artificial neural network models were selected for the modeling of the flood peak discharge and the results were compared to examine the accuracy of the studied models.
Methodlogy
Daily flood peak discharges of the basin in Kahman station, which were applied for the calibration and validation of the models, were selected and observed. For this purpose, maximum daily precipitation rate, at a daily scale and between the years 2001-2012, and flood peak discharge were respectively used as the input and output parameters. The wavelet-based neural network which was based on the combination of the wavelet theory and neural networks were created. Indeed, it has the benefits and features of the neural networks and the charm, flexibility, strong mathematical foundations, and the analysis of the multi-scale wavelets. The combination of the wavelet theory with the neural network concepts for the creation of the wavelet neural network and feed-forward neural shock can be a good alternative for estimating the approximate nonlinear functions. Feed-forward neural network with sigmoid activation function is in the hidden layer. While at the nerve shocked wavelet, the wavelet functions as the activation of the hidden layer feed-forward networks are considered, in both these networks and scale wavelet, the transformation parameters are optimized with their weight. Artificial neural networks inspired by the brain's information processing systems, designed and emerged into. To help the learning process and with the use of the processors called neurons, there was an attempt to understand the inherent relationships among the data mapping, the input space, and the optimal space. The hidden layer or layers, the information received from the input layer, and the output layer are the processing and disposal.
Based on the artificial neural network structure, its major features are high processing speed and the ability to learn the pattern, the ability to extend the model after learning, the flexibility against unwanted errors, and no disruption to the error on the part of the connection due to the weight distribution network.
The first practical application of the synthetic networks with the introduction of the multilayer perceptron networks was consultation. For training this network, back propagation algorithm is used. The basis of this algorithm is based on the error correction of the learning rule. That consists of two main routes. By adjusting the parameters in the MLP model, error signal and input signal occurs. Determining the number of the layers and neurons is the most important issue in simulation with the artificial neural network. The criteria of the correlation coefficient, the root mean square error, and the mean absolute error were used to evaluate and compare the performance of the models.
Results
The results showed that both models in a structure, consisting of 1 to 4 delay, gives better results than any other structure. In addition, based on the results of the evaluation criterion, the model which was used to wavelet neural network model, was the most accurate (R=0.921), and the lowest root mean square error RMSE=0.005m3/s and the lowest average absolute error MAE=0.003m3/s the validation phase is capable.
Conclusions
Wavelet neural network model outperformed the artificial neural network. Consequently, it can be effective in forecasting the daily flood peak discharge. It can also facilitate the development and the implementation of the surface water management strategies. Finally, predicting the piver flow process is a major step in water engineering studies and water resources' management.
