hadi ansari; safar marofi
Abstract
Introduction: Snow water equivalent (SWE) provides important information for water resources management and recently has attracted the attention of many researchers using remote sensing. Remote sensing presents a possibility for observation of snow characteristics, like water equivalent, over larger ...
Read More
Introduction: Snow water equivalent (SWE) provides important information for water resources management and recently has attracted the attention of many researchers using remote sensing. Remote sensing presents a possibility for observation of snow characteristics, like water equivalent, over larger areas. Validation of remote sensing data of snow water equivalent (SWE) has always been an important issue for the researchers. Previous studies have assessed the global SWE data. Although it has been tried by using large-scale models of the world to estimate SWE, but regional effects such as snow density, topography and local meteorological conditions may lead to uncertainty.
Materials and Methods: The Northwestern Iran was selected as the study area in this research. Reasons for choosing this area are being mountainous with much snowfall. Also this region compared to the other parts of Iran, has more dense snow survey stations. In this study the AMSR-E sensor data and Global Land Data Assimilation System (GLDAS) was used to estimate SWE in the basins of the northwestern Iran. After processing AMSR-E sensor data and GLDAS model with related software, SWE was estimated in the snow survey stations and evaluated with observed data. To specify the snow density effect on SWE data in AMSR-E sensor from the snow density data, the stations were used. To determine the accuracy of estimation of SWE at different heights, snow survey stations is arranged by considering height and were divided into four height classes that contain enough observational data to evaluate computational data in each height class. To verify SWE obtained estimations in the stations, Root Mean Square Error (RMSE) and Pearson correlation coefficient (r) assessment criteria were used. After evaluating, the SWE data of AMSR-E sensor and GLDAS model for the GLDAS model monthly data to estimate SWE was used for the period 2000 to 2015. With calculating average annual SWE from monthly data, SWE trend changes in mentioned period, the moving averages graphs 3, 5 and 7-year-old was drawn.
Results and Discussion: According to the obtained results, SWE computational data with observational data had significant correlation at the 1% level. Using in situ snow densities, the correlation coefficient between AMSR-E and situ SWE increased from 0.27 to 0.55. The results showed that the best estimation of SWE is in the stations, which have the height of 1,350 to 1600 meters. Also with increasing altitude, the estimation accuracy is significantly reduced. In most years maximum of the SWE was obtained in January and February and in the period of June to September, the area was out of snow storage. According to the average annual SWE and moving averages graphs 3, 5 and 7-years old, the SWE of Northwestern Iran basins in period 2015-2001 has a reducing trend.
Conclusions: In the regions like the Northwestern Iran mountainous where snowfall constitutes a significant fraction of total precipitation, the snowpack delays the resulting runoff into the time of year where water demand is greater. So measurement of snow on the ground has been an important component of hydrologic forecasting for a century. Various remotely sensed snow data have been widely utilized for cold regions to explore the relationships between snow distribution, river discharge, and climate change. The accuracy of remotely sensed snow products should be well understood and incorporated in any investigations using such data. The main objective of the present study was to quantitatively compare the AMSR-E and GLDAS model for an understudied region of the earth. AMSR-E global SWE data and GLDAS data were compared by situ SWE measurements performed in the snow courses. The results showed that the snow density is an effective factor in derived algorithm for the SWE AMSR-E data. Also with increasing height, precision of the estimation significantly decreased. The determination of SWE from satellite imagery in progress updated with new learning. The obtained results from passive microwave in smooth terrain are promising, but involvement of different mechanisms become more complicated as the terrain gets more complex. Nevertheless, it is believed that if the above discussions are taken into account, AMSR-E would provide valuable SWE information even for a mountainous region like Northwestern Iran. It is also hoped that this study would be a starting point in the water scarce, developing Iran to plan and use the limited supply in a suitable manner.
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.
