Abstract
Introduction: Despite being helpful to explore and analyze large multidimensional datasets, visualization Techniques have been rarely considered in hydrology. One of the techniques is Pixel-Based (Raster-Based) graphs. Pixel-based graph is a graphing technique that maximizes displayed information using ...
Read More
Introduction: Despite being helpful to explore and analyze large multidimensional datasets, visualization Techniques have been rarely considered in hydrology. One of the techniques is Pixel-Based (Raster-Based) graphs. Pixel-based graph is a graphing technique that maximizes displayed information using a pixel or raster-based approach.
Materials and Methods: This study two types of raster-based graphs, including Raster-Hydrograph and Raster Hyetograph were evaluated, for Gamasiyab Karstic Spring located in Nahavand. The graphs were drawn by applying discharge and rainfall daily information of gamasiyab spring in 1969-2018. The MATLAB was employed to draw the graphs. To calculate the spring discharge, recorded data from Sang Sorakh and Variane Canal station were used. The data gathered for Sang Sorakh and Variane were recorded from 1969 and 2005, respectively. Thus, the spring discharge was the summation of both stations. The maximum, minimum and average discharge was, respectively, 37.97, 0.3 and 4 m3/s. It is important to note that the basin area is about 60 Km2.
Results and Discussion: By applying the graphs, six different phenomena were investigated:
Snowmelt: According to the raster hydrograph of the Gamasiyab spring, snowmelt occurs in the first 200 to 300 days of year (e.g. early April to late July). According to this graph, during the recent years, snowmelt period shortened. As of 2004, that the number of snowmelt days showed a considerable reduction as compared to the previous years. This issue has become more intense for the years after 2013 indicating a change in the spring discharge regime.
Drought: According to the raster hydrograph of the Gamasiyab spring, droughts were observed in 1998 and 1999.
Storm Flow: According to the raster hydrograph of the Gamasiyab spring, a storm flow was observed in the middle of April,1986. Storm flows were also observed in late February of 1986 and 2005, and the late March of 2016.
Dry Year: Dry Year is a year that the discharge is less than the average. 2008 and 2009 were the examples of dry years. In addition, 2014 was one-year low water.
Dry Month: Determine dry months are used for baseflow separation. In dry months, discharge is due to baseflow, and rainfall and snowmelt play a very small role in the discharge.
Monthly changes: Monthly changes happen when rapid changes in discharge are observed from one month to another. For example, the discharge regime suddenly changes from a dry to wet condition. According to the raster hydrograph of the Gamasiyab spring, the monthly changes in April and May, 2014 were observed. It was observed that the rainfall was almost equal to 0 in June to September. In the other words, rainfall period is from early November to early June. Maximum rainfall is in April and May.
Better results can be achieved by using both Raster Hydrograph and Raster Hyetograph. Discharge of Gamasiyab spring is affected by snowmelt and groundwater flow since late May to late September, and rainfall has no effect on spring discharge in this period. According to these graphs, it can be also concluded that springtime rainfall was impacted with one-month lag time. According to raster hydrograph, the minimum discharge occurs in October, however, the area receives rainfall during October based on raster Hyetograph. Therefore, the discharge increase in the November can be attributed to the precipitation falling during October.
Conclusion: Main benefits of this graphs are: 1. a way to view large datasets. 2. Quickly review and interpret. 3. Develop new types of products. 4. Cost and time efficiency. This method is able to show systematic error, missing data, outliers, comparison different places, potential new products. Results show that the snowmelt period in Gamasiyab spring decreased from 1969 to 2018. This period shortened from 100 to 30 days per year. The year of 2008 was the driest year during the statistical period of the spring, and a drought was also observed in 1998. According to raster hydrograph, the driest month was found to be October. Determining this month is very useful for base flow separation. One can conclude that these graphs including large amount of information, accelerate the processes of scanning and interpretation.
Abazar Solgi; Amir Pourhaghi; Heidar Zarei; Hadi Ansari
Abstract
Introduction: Chemical pollution of surface water is one of the serious issues that threaten the quality of water. This would be more important when the surface waters used for human drinking supply. One of the key parameters used to measure water pollution is BOD. Because many variables affect the water ...
Read More
Introduction: Chemical pollution of surface water is one of the serious issues that threaten the quality of water. This would be more important when the surface waters used for human drinking supply. One of the key parameters used to measure water pollution is BOD. Because many variables affect the water quality parameters and a complex nonlinear relationship between them is established conventional methods can not solve the problem of quality management of water resources. For years, the Artificial Intelligence methods were used for prediction of nonlinear time series and a good performance of them has been reported. Recently, the wavelet transform that is a signal processing method, has shown good performance in hydrological modeling and is widely used. Extensive research has been globally provided in use of Artificial Neural Network and Adaptive Neural Fuzzy Inference System models to forecast the BOD. But support vector machine has not yet been extensively studied. For this purpose, in this study the ability of support vector machine to predict the monthly BOD parameter based on the available data, temperature, river flow, DO and BOD was evaluated.
Materials and Methods: SVM was introduced in 1992 by Vapnik that was a Russian mathematician. This method has been built based on the statistical learning theory. In recent years the use of SVM, is highly taken into consideration. SVM was used in applications such as handwriting recognition, face recognition and has good results. Linear SVM is simplest type of SVM, consists of a hyperplane that dataset of positive and negative is separated with maximum distance. The suitable separator has maximum distance from every one of two dataset. So about this machine that its output groups label (here -1 to +1), the aim is to obtain the maximum distance between categories. This is interpreted to have a maximum margin. Wavelet transform is one of methods in the mathematical science that its main idea was given from Fourier transform that was introduced in the nineteenth-century. Overall, concept of wavelet transform for current theory was presented by Morlet and a team under the supervision of Alex Grossman at the Research Center for Theoretical Physics Marcel in France. After the parameters decomposition using wavelet analysis and using principal component analysis (PCA), the main components were determined. These components are then used as input to the support vector machine model to obtain a hybrid model of Wavelet-SVM (WSVM). For this study, a series of monthly of BOD in Karun River in Molasani station and auxiliary variables dissolved oxygen (DO), temperature and monthly river flow in a 13 years period (2002-2014) were used.
Results and Discussion: To run the SVM model, seven different combinations were evaluated. Combination 6 which was contained of 4 parameters including BOD, dissolved oxygen (DO), temperature and monthly river flow with a time lag have best performance. The best structure had RMSE equal to 0.0338 and the coefficient of determination equal to 0.84. For achieving the results of the WSVM, the wavelet transform and input parameters were decomposed to sub-signal, then this sub-signals were studied with Principal component analysis (PCA) method and important components were entered as inputs to SVM model to obtain the hybrid model WSVM. After numerous run this program in certain modes and compare them with each other, the results was obtained. One of the key points about the choice of the mother wavelet is the time series. So, the patterns of the mother wavelet functions that can better adapt to diagram curved of time series can do the mappings operation and therefore will have better results. In this study, according to different wavelet tests and according to the above note, four types of mother wavelet functions Haar, Db2, Db7 and Sym3 were selected.
Conclusions: Compare the results of the monthly modeling indicate that the use of wavelet transforms can increase the performance about 5%. Different structures and sensitivity analysis showed that the most important parameter which used in this study was parameter BOD, and then flow, DO and temperature were important. This means that the most effective BOD and temperature with minimum impact. Also between different kernels types, RBF kernel showed the best performance. So, combined wavelet with support vector machine is a new idea to predict BOD value in the Karun River.