Alireza Ghaemi; Mahdi Azhdary Moghaddam; Sarina Keikha
Abstract
Introduction
Rivers are known as the vital resources of nature and the main foundations of sustainable development. Therefore, the quantity and quality of river water are considered valuable parameters. The increase in agricultural and industrial activities has reduced the quality of water resources ...
Read More
Introduction
Rivers are known as the vital resources of nature and the main foundations of sustainable development. Therefore, the quantity and quality of river water are considered valuable parameters. The increase in agricultural and industrial activities has reduced the quality of water resources in many places. The discharge of sewage, garbage and chemical fertilizers in the villages along the rivers is one of the most important sources of water quality pollution. The amount of urban and agricultural wastewater entering this surface has caused an increase in the amount of pollutants, so that in the period of 1993 to the end of 2017, the average amounts the three pollutants of total dissolved solid, chlorine and sodium in Varand Station are respectively 507.49, 2.16 and 2.47. Therefore, accurate estimation of water quality parameters is a basic requirement for water quality management, human health, public consumption and domestic use.
Materials and methods
Tajan River basin with an area of about 4147.22 square kilometers has an average river discharge and annual rainfall of 20 cubic meters per second and 539 mm respectively. The highest and lowest elevations of this River basin have been reported as 3728 and 26 meters, respectively. Various human activities such as agriculture and dam construction are carried out in this river. Therefore, evaluationg the water quality of this river basin is required. In this research, the combination of two Gene Expression Programming Models (GEP) and Artificial Neural Network (ANN) with a data preprocessing algorithm called Empirical Mode Decomposition (EMD) was used to estimate one of the important parameters of water quality called Total Dissolved Solids (TDS). For this purpose, in this research, some of qualitative parameters including sodium, calcium, magnesium, sulfate bicarbonate, sulfuric acid and chlorine, which were measured in the period of 1993 to the end of 2017 at Varand station, were used to estimate the concentration of total dissolved solids.
Results and discussion
At first, the results of the observation data during the sampling period indicated that the TDS values in about 80% of the samples were in the range of 300 to 600 mg.liter-1, which reprsented the good quality of the water of this river. In order to compare the performance of independent and integrated approaches in estimating the quality parameters of the Tajan River in the training and testing stages, the evaluation benchmarks including Correlation Coefficient (R), Root Mean Square Error (RMSE), Mean Deviation of Error (MBE), Nash Coefficient (NSE), Objective Function (OBJ) and RSD ratio were applied. The results of this study demonestrated that the integrated model of Gene Expression Programming and Empirical Mode Decomposition (EMD-GEP) with the lowest error (RSD=0.23 and RMSE=24.41) was the most accurate model in TDS estimating compared to other models such as GEP (RSD=0.44 and RMSE=47.27). In addition, the integrated model of Artificial Neural Network and Empirical Mode Decomposition (EMD-ANN) with RMSE=36.64 and R=0.95 was stood at the second rank. Additionally, the outcomes of the Objective Function (OBJ) represented that EMD-GEP model could achieved the lowest OBJ value (15.92) than other techniques in the TDS modeling. While, the highest value of the OBJ=29.34 belonged to the GEP model.
Conclusion
ANN and GEP methods were applied in this research to estimate TDS concentarion in the Tajan River. After that, to increase the accuracy of the models, EMD technique was recruited to decompose the time series dataset. The results obtained from the integrated models were evaluated using some error statistical benchmarks such as correlation coefficient, root mean square error. The results showed that the EMD method could play an essential role in increasing the ANN and GEP performance so as to estimate this water quality parameter in Varand station. So that EMD-GEP and EMD-ANN could reduce the RMSE error by 48.35% and 14.02%, respectively, compared to the two independent models of GEP and ANN.
Negar Einnollahzadeh; Atabak Feizi; Farnaz Daneshvar vousoughi
Abstract
Introduction
In recent years, factors such as the growth of industrial activities and environmental destruction have led to an increase in greenhouse gases, resulting in disruption of the climate balance known as climate change. The negative impact of this phenomenon on various systems, such as water ...
Read More
Introduction
In recent years, factors such as the growth of industrial activities and environmental destruction have led to an increase in greenhouse gases, resulting in disruption of the climate balance known as climate change. The negative impact of this phenomenon on various systems, such as water resources, agriculture and industry, has raised concerns in human society. Consequently, addressing the issue of climate change regarding water resources has become one of the primary causes of concern today. Climate change and its effects pose significant challenges to water and energy resource management, necessitating thorough investigation and developing plans to mitigate its impact on water resources. This study aims to identify the region's most suitable climate change model and assess the effectiveness of artificial intelligence methods in studying the climate change phenomenon.
Materials and methods
One of the most reliable approaches for studying the parameters influencing hydrological phenomena under climate change is atmospheric general circulation models. To employ these models on a regional scale, downscaling operations are necessary. Given the large number of parameters derived from Earth's General Circulation Models (GCMs), selecting the most influential parameters is essential before proceeding with the exponential downscaling process. In this study, the meteorological and hydrological parameters of the Ardabil synoptic station were determined using 25 models from the fifth series of the IPCC report. The linear correlation coefficient between monthly precipitation and observed temperature with the output of GCM was used to identify the most appropriate model among the reviewed models. Artificial Neural Network (ANN) was also utilized to downscale the GCMs output. Before employing the neural network, the linear correlation coefficient, the standard information function, and the M5 decision tree were used to identify the most suitable input parameters from the parameters of the best GCMs in the region, to obtain an ideal and optimal network.
Results and discussion
This research investigated 25 models from the fifth series of the IPCC report to explore the uncertainty of GCMs. The results indicated that three models-MRI-CGCM3, CMCC-CMS, and MPI-ESMMR-demonstrated the most suitable correlation coefficients at the Ardabil synoptic station. The findings related to determining the most appropriate input parameters for exponential downscaling, using three methods: linear correlation coefficient, standard information function, and M5 decision tree, revealed that the decision tree algorithm provided the most suitable parameters. Moreover, the results obtained from the downscale analysis using the neural network with the variables selected by the decision tree method exhibited the excellent performance of this approach in selecting the effective input parameters of the neural network. Specifically, using the selected parameters of the MRI-CGCM3 model as input for the neural network as a downscaling method yielded better outcomes. The results obtained using the selected parameters of the MRI-CGCM3 model indicated that for the precipitation parameter, the values of the Determination Coefficient (DC), Root Mean Square Error (RMSE), and Correlation Coefficient (CC) for the test data were 0.39, 0.04, and 0.63, respectively. For the temperature parameter, the values of DC, RMSE, and CC for the test data of the superior model were 0.9, 0.03, and 0.95, respectively.
Conclusion
The performance of exponential downscaling networks is determined by the climatic conditions of the region. The superiority of a particular model in one study cannot be regarded as a valid argument for selecting that model for all regions. It is advisable to utilize different models of the general earth circulation within the region to identify an optimal model. Conducting such studies can assist researchers in investigating various hydrological phenomena that may occur in the future, which may have irreparable consequences.
Omid Asadi Nalivan; Alireza Rabet; Farzaneh Vakili tajareh; Marziyeh Ramezani; Mohamad Momeni; Kohzad Heydari
Abstract
Extended abstractIntroductionGully erosion is a water erosion that has a great contribution to land degradation and is known as one of the most important environmental hazards in the world and especially in Iran. In recent years, machine learning techniques and geographic information systems have been ...
Read More
Extended abstractIntroductionGully erosion is a water erosion that has a great contribution to land degradation and is known as one of the most important environmental hazards in the world and especially in Iran. In recent years, machine learning techniques and geographic information systems have been highly effective in determining areas sensitive to gully erosion and have increased accuracy and speed in the evaluation and potential of gully erosion and in determining effective factors on gully erosion has also been effective. The loess lands of Golestan Province are more susceptible to water erosion due to sufficient depth and almost uniform silty graining, excessive use, cultivation on sloping lands, and wrong land management so that all types of erosion can be observed in these areas. The most common type of erosion in these sediments is gully erosion. The studied watershed is faced with the increase of dry and abandoned land, land use change, the presence of surplus livestock in the forests, and also the population increase. Therefore, this area is facing an increase in sensitivity to gully erosion, and areas with the potential for gully erosion should be identified and managed. Materials and methodsThe studied watershed with an area of 222,000 ha and an elevation range of 58 to 2168 m is located in the northeast of Golestan Province. The average rainfall of the area is between 224 and 736 mm. In this research, first, the location of the gullies was obtained from the General Directorate of Natural Resources and Watershed Management of Golestan Province. Then, from the total of 1127 gullies position, 70% were randomly classified as training data and 30% as validation data. To determine the effective variables in gully erosion sensitivity, 14 factors were identified and in the next step, the collinearity test between the variables was performed using SPSS software. By using the indices of tolerance coefficient and variance inflation factor, if there is collinearity between the variables, they were removed from the modeling process. Considering the importance of the DEM map and its application in the preparation of various factors of the current research, a DEM was prepared using ALOS satellite images. The layers of slope and aspect are prepared by using a digital elevation model and slope and aspect functions respectively. Slope length index in SAGA GIS software, layers of distance from stream based on the map of stream, and distance from roads based on existing roads, and using the Euclidean distance function in the ArcGIS software was prepared. Stream density and road density layers were obtained based on the map of existing streams and roads in the region and using the line density function in ArcGIS. The lithology layer was extracted from the geological map of the region and the land use layer was obtained from the General Directorate of Natural Resources and Watershed Management of Golestan province. The rainfall map has been prepared using the information from 35 rain gauge stations. First, the average rainfall of 26 years was calculated for each station, and then rainfall zoning was done using the global Kriging Method (due to the lowest RMSE) in ArcGIS. The TPI layer was prepared using the DEM and using the SAGA GIS software. The HAND index is a topographic-hydrological index of the DEM of the nearest drain, representing the hydrological behavior of the watershed. To evaluate the models, the relative performance detection curve (ROC) was used for the predictive power of the models. Results and discussionThe results showed that there is no co-linearity between the variables and therefore all the variables were used in the modeling process. The relationship between gully erosion and elevation showed that lower elevations are more sensitive than higher elevations and more susceptible to gully erosion near waterways. The results showed that with the increase in drainage density, the sensitivity of gully erosion increases, and the possibility of gully erosion increases. The results showed that the old barracks, shale, and loess have the greatest impact on the sensitivity of gully erosion. The results show a decrease in the sensitivity of gully erosion with a decrease in the HAND index. This result indicates that in the areas where the level of saturation in the watershed level increases, the possibility and sensitivity of gully erosion increases. The results showed that among the types of land use, canals, poor pastures, and agricultural land use have the highest sensitivity to gully erosion. This is even though the forest areas have the lowest sensitivity to this erosion. The results showed that in the rainfall range of 220 to 420 mm, the possibility of gully erosion has increased, and the range of 420 to 500 mm has shown the highest level of sensitivity, and with the increase of rainfall from 500 mm to above, a reduction in the sensitivity of gully erosion has been encountered. One of the reasons for reducing the sensitivity of gully erosion in higher rainfalls is the increase in vegetation and the creation of suitable conditions for landslides. The results showed that the depth of the valley up to 235 meters have increased the probability of gully erosion, and from 235 meters above, it has decreased the probability of erosion. The results showed that the sensitivity of gully erosion increases near roads, and this case shows the effects of road construction and the aggravation of conditions for gully erosion. ConclusionThis research was conducted to determine the effective factors on gully erosion and zone its spatial distribution in the northeast of Golestan Province. In this study, by considering 14 important factors and using RF, ANN, and CART models, a sensitivity map of gully erosion was prepared. Because the identification of gully erosion-sensitive areas based on traditional methods and expert opinions do not have acceptable accuracy, it is necessary to use modern machine learning methods. The results showed that the factors of distance from the road and land use are the most important factors affecting the sensitivity of gully erosion, which requires land use management as human activities. The ROC curve showed that the accuracy of the models in estimating areas with gully erosion sensitivity was excellent in the test stage (ANN) and very good in the test and validation stage (RF and CART), which means the excellent performance of the models.
Mahmoudreza Tabatabaei; Amin Salehpour Jam
Abstract
Relationships between river water quality parameters and physical, geochemical and biological processes carried between basin resources (soil, vegetation, geology, land use, etc.), meteorological variables (temperature, precipitation, snowmelt, etc.), River hydrological variables (flow discharge), as ...
Read More
Relationships between river water quality parameters and physical, geochemical and biological processes carried between basin resources (soil, vegetation, geology, land use, etc.), meteorological variables (temperature, precipitation, snowmelt, etc.), River hydrological variables (flow discharge), as well as human interventions are often very complex, nonlinear and non–deterministic in a way that makes their complete understanding impossible. In this situation, the use of computational intelligence (such as artificial neural networks) is a useful tool in simulating and estimating river water quality variables such as suspended sediment load. In the present study, by combining open source GIS libraries and neural network models (with and without supervisor), an intelligent GIS system has been designed and coded that can estimate daily suspended sediment load under univariate or multivariate conditions. The results of applying this system to Mazaljan River Watershed at Razin hydrometric station showed that this system is able to simulate suspended sediment load with proper performance and validation (with root mean square error of 1033 tonday-1, mean absolute error of 455 tonday-1 and Nash-Sutcliffe efficiency of 0.89 for the test data set). In general, this system can be used as a national infrastructure in the simulation and management of suspended sediment in all hydrometric stations in the country by relevant organizations.
Saeid Afkhamifar; Amirpouya Sarraf
Abstract
Today, due to the importance of sustainable groundwater management, groundwater level modeling and forecasting are used to assess and evaluate water resources. The purpose of this study is to evaluate the performance of two models of Extreme Learning Machines (ELM) and Artificial Neural Network (ANN) ...
Read More
Today, due to the importance of sustainable groundwater management, groundwater level modeling and forecasting are used to assess and evaluate water resources. The purpose of this study is to evaluate the performance of two models of Extreme Learning Machines (ELM) and Artificial Neural Network (ANN) and the combination of two models with wavelet transmission algorithms (W-ELM and W-ANN), which ultimately to increases the predictive power and optimization of input weights (the weights between the input and hidden layers) of models, Quantum Particle Swarm Optimization algorithm (QPSO) has been used. Also, in this study, the data of Ground Water Level of observation wells (GWL), precipitation (P) and average temperature (T) of Urmia Plain aquifer with a time series of 36 years (1981 – 2017) which were collected on monthly scale, are used. Also, in order to evaluate the performance of models, correlation coefficient (R), Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) were used. In this regard, 80% of the data (September 1981 to August 2010) are used for training section and 20% of data (September 2010 to August 2017) used for the test section of models. Based on the results of this study, the hybrid model of W-ELM-QPSO with correlation coefficient (R) 0.991, 0.983 and 0.975, respectively for periods of one, two and three months in the test section, have a better performance than other models and also in addition to predicting power, this model has a high speed in terms of training and testing speed than other models.
Adele Alijanpour Shalmani; Alireza Vaezi; Mahmoudreza Tabatabaei
Abstract
Analysis of suspended sediment load data in rivers is the basis for understanding the trend of erosion and sediment in the management and planning of soil and water resources. Due to lack of access to daily suspended sediment loading data with direct measurement, it is important to use methods for modeling ...
Read More
Analysis of suspended sediment load data in rivers is the basis for understanding the trend of erosion and sediment in the management and planning of soil and water resources. Due to lack of access to daily suspended sediment loading data with direct measurement, it is important to use methods for modeling and estimating it in watersheds. One of the best methods used in this field is the use of artificial neural networks. To evaluate daily suspended sediment load, Sira hydrometric station was studied in Karaj River watershed. The number of data used in this study included 624 information records of 31 years (1981–2011) statistical period .Input data to the artificial neural network models included instantaneous flow discharge, average daily flow discharge, average daily flow discharge with a delay of three days, average daily precipitation and average daily precipitation with a delay of three days. Output data to models was daily suspended sediment load. In this research, gamma test and genetic algorithm were used to obtain optimal variables and best combination of variables for entering the model. Then, these combinations with some combination of test and error variables were entered to artificial neural network models. The self-organizing map neural network was used for data clustering and all data were divided into three homogeneous groups: 70 percentage training data, 15 percentage validation data and 15 percentage test data. Then, the combination of variables entered to neural network models with activation functions log sigmoid and tangent sigmoid. The results showed that the neural networks using the optimal variable combinations in comparison with manual combinations have a more accurate estimate for suspended sediment load. In all combinations of inputs to neural network models, a model with tangent sigmoid activation function, with input variables combination including, instantaneous flow discharge (Q), average daily flow discharge (Qi), average daily flow discharge for two day ago (Qi-2), average daily flow discharge for three day ago (Qi-3), average daily precipitation (Pi), average daily precipitation for two day ago (Pi-2) and average daily precipitation for three day ago (Pi-3), was the best model for estimating daily suspended sediment load. This model has the lowest of error (MAE=500.05 (ton/day), RMSE=1995.33(ton/day) and Erel=7%), the highest accuracy (R2=0.96), the highest performance model (NSE=0.96) and has the lowest general standard deviation (GSD=0.97) compared to other models. Also, this model is the best combination with the most influential input variables derived from gamma test and genetic algorithm for estimating SSL.
Saeed Farzin; Hamid Mirhashemi; Hamed Abbasi; Zohreh Maryanaji; Payam Khosravinia
Abstract
In this study, long-term memory and dynamic behavior of daily flow time-series of Khorramabad River, which its basin is mountainous and has urban land use, is investigated by Hurst exponent. The Hurst exponent of runoff signal of Khorramabad River during 1991-2014 period was obtained as 0.8. This value ...
Read More
In this study, long-term memory and dynamic behavior of daily flow time-series of Khorramabad River, which its basin is mountainous and has urban land use, is investigated by Hurst exponent. The Hurst exponent of runoff signal of Khorramabad River during 1991-2014 period was obtained as 0.8. This value shows long-term memory and nonlinear, dynamic signal of this river’s runoff. By applying neural network and wavelet transforms, the rainfall-runoff time-series of this river was simulated. In this respect, by taking the time-series of rainfall and rainfall-runoff as input to the artificial neural network and wavelet-neural network hybrid, four models including: 1) rainfall, neural network, 2) rainfall-runoff, neural network, 3) rainfall, wavelet-neural network and 4) rainfall-runoff, wavelet-neural network were developed. In the hybrid models of wavelet-neural network, time-series of rainfall and runoff were decomposed to high-frequency and low-frequency sub-signals. Results of evaluating the accuracy and efficiency of the four models showed that the wavelet–neural network model correctly simulated the runoff behavior with the best efficiency at 99% confidence level. Comparison of the results of wavelet–neural network model to the neural network model, using Morgan-Granger-Newbold, showed significant superiority of the first model. Also, results of evaluating signal error of the four implemented models, using two tests of Von-Neumann and Buishand test, showed that there is a significant substitution point in the signal error of the neural network model and signal of rainfall-runoff model. Therefore, existence of very different monthly and periodical fluctuations in 1991-1998 and 1999-2014 in the behavior of rainfall-runoff leads to reduction of efficiency and precision coefficient of neural network model. While, in the hybrid model of wavelet-neural network, allocation of relative weight to each sub-signal, has effectively reduced the short-term, average and long-term fluctuations in modeling error.
hassan torabipodeh; ahmad godarzi; reza dehghani
Abstract
Simulation and evaluation of river sediment is one of the important issues in water resources management. Measuring the amount of sediment in conventional methods generally involves a lot of time and cost and sometimes does not have sufficient accuracy. In this study, a wavelet neural network was used ...
Read More
Simulation and evaluation of river sediment is one of the important issues in water resources management. Measuring the amount of sediment in conventional methods generally involves a lot of time and cost and sometimes does not have sufficient accuracy. In this study, a wavelet neural network was used to estimate the sediments of the Kashkan River in Lorestan Province, and its results were compared with conventional smart methods such as artificial neural network. Parameters of discharge, temperature, water soluble solids content and precipitation as input and sediment discharge were selected as output during the monthly statistical period (1984-2013). Correlation coefficient, root mean squared error, and Nash Sutcliff coefficient were used to evaluate and compare the performance of the models. Results showed that the combined structure has been able to provide acceptable results in estimating sediment yield using two intelligent methods. However, in terms of accuracy, the wavelet neural network model with the highest correlation coefficient (0.850), the lowest root mean square error (0.151 tonday-1), and the Nash-Sutcliff criterion (0.758) were prioritized in the validation stage. Results also showed that the wavelet neural network model has a high ability to estimate the minimum and maximum values.
Alireza Majidi; Gholamreza Lashkaripour; Ziaoddin Shoaei
Abstract
The swelling potential of fine-grained soils is one of effective parameters on soil mechanical behavior and erosion and fundamental data required for the design, construction and choosing construction materials. This paper presents a multi-layer perceptron (MLP) artificial neural network (ANN) model ...
Read More
The swelling potential of fine-grained soils is one of effective parameters on soil mechanical behavior and erosion and fundamental data required for the design, construction and choosing construction materials. This paper presents a multi-layer perceptron (MLP) artificial neural network (ANN) model to prediction of the swelling potential of marl soils. Marl soil is a fine-grained soil. The Levenberg-Marquadt learning algorithm was used to train the networks. Existing models prediction of soil swelling potential based on physical and soil index parameters. The present study considers the effects of chemical factors on the behavior and characteristics of fine-grained soils along with the common soil index parameters. The model used physicochemical and mechanical test results from 60 marl soil samples taken from marl formations in the Neogene basin in central Iran (Tehran, Qom and Saveh regions). The models were designed to use different input data sets and structures to determine which soil properties and ANN structures correlate well with the swelling potential parameter. Electrical conductivity (EC) of saturated soil was a new input parameter used in addition to the physical and soil index parameters that include the atterberg limit, activity, content of the clay and silt, initial of porosity ratio and dry density. Values of RMSE, R2 and MCE (evaluation criteria) related to the best model with the physical parameters LL, PI, A, M, C and Yd0 are respectively 0.89, 2.3, 0.84, and for the best model with the physical parameters LL, PI, M, C, Yd0 and EC are respectively 0.92, 1.7, and 0.91.The results of the evaluation criteria models show that inclusion of EC improved the accuracy of the model. It was found that the accuracy of the generalizations and estimations of the ANN models was further increased by clustering data before the data division stage by k-means method to Compared with hierarchical method.