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.
A. Pourhaghi; F. Radmanesh; A. Maleki
Abstract
Introduction : Sustainable development of groundwater resourcesrequires a proper assessment of available resources, understanding of system behavior and interaction between groundwater and surface water.In recent years, a Delfan plain (in Iran) is facing a sharp decline in groundwater levels due to increasing ...
Read More
Introduction : Sustainable development of groundwater resourcesrequires a proper assessment of available resources, understanding of system behavior and interaction between groundwater and surface water.In recent years, a Delfan plain (in Iran) is facing a sharp decline in groundwater levels due to increasing in population and exploitation of groundwater resources.In this study, using modflow model effect of drought and wet conditions on water table fluctuations of Delfan plain aquifer was evaluated.
Materials and Methods: Delfan plain is one of the Lorestan Plains (in Iran Country) and located in the north of the Lorestan Province, around the city ofNurabad (Delfan).Precipitation survey of the region shows that the average annual rainfall in the plains is 480 mm and aquifers of the region has 10 piezometric wells. Drawing of the groundwater hydrograph from 2004 to 2013 shows that the general trend of the groundwater level is downward, which represent decreasing in groundwater resources of the region. At the beginning of the modeling process using Modflow model, after gathering all the required information, conceptual model of the plain was generated. To preparing this model, various data such as topographic maps, geophysical data, logs of wells, pumping tests and observation wells data and flow data taken from exploitation wells was used. Water level data of October 2007 which has the lowest fluctuation was used for the calibration of steady state.In this step with model successive run, hydraulic conductivity is optimized. After model calibration in the steady state, do same in the unsteady state.Specific discharge was optimized at this step.After calibration in the unsteady state, model needs verification to be trusted.For this purpose, verification was done in November 2012 to November 2014.After calibration and validation of the model, the model was carried out under drought and wet conditions.Drought is one of the environmental disasters that its occurrence could bring the water challenges in the field of quality and quantity. Because of drought and lack of rainfall affect groundwater resources, soil moisture and river flow, used index called Standard Precipitation Index (SPI) to quantify the impact of rainfall in of 3, 6, 12, 24-month period.This index is calculated based on long-term statistics.
Results Discussion :In steady state, the model's sensitivity is studied according to changes in hydraulic conductivity value and discharge of pumping wells and in the unsteady state according to specific yield and other parameters was investigated. Based on this analysis in steady state, generally it can be said that the model is more sensitive to the exploitation wells. In unsteady state, the model is more sensitive to specific yield and hydraulic conductivity and other parameters are in the next level.With SPI reviewing of 120-months, it was seen that the plain in 1984 and 1993 has the lowest 120-month SPI with the value of -1.08 (with average precipitation value of 423 mm).For applying virtual wet period with 30-years precipitation reviewing, it was observed that years of 2001 and 2010 have the most 120-month SPI value with value of 1.86 (with average precipitation value of 587 mm).For applying the virtual wet conditions in the next step, the model was simulated with the rainfall data of 2001 and 2010.To decrease the water table drop, considering the amount of drop and water needs of the region, several runs were performed which ultimately results showed to offset the drop in these three exploitation areas, the discharge of exploitation wells must be reduce 20% that This strategy is able to reduce the average annual rate of water table drop for the next 10 years. Finally, after model’s run and piezometers drop, plain model was used to obtain groundwater balance.
Conclusion: The model implementation in drought and wet conditions shows that in these conditions the groundwater level decreases with the average of (-7.80m) and (-5.83m), respectively. which with the 20 % decrease of the discharge of the exploitation wells in these conditions, the level groundwater and aquifer balance improves.For the next ten years in the normal condition or present situation of exploitation, plain balance is -83.20 million cubic meters which by 20% reduction in wells exploitation, this water balance is predicted -41.20 million cubic meters for next 10 years.In the drought conditions Delfan aquifer water balance is predicted as -91.20 million cubic meters during ten years which by 20% reduction of wells exploitation this water balance increases to -49.20 million cubic meters.
