Yaser Bageri; Esfandiar Abbas Novinpour; A Nadiri; Keiwan Naderi
Abstract
Most of the country's geographically area is located in dry and semi-dry zone with low rainfall. The growing population, the limitation of water resources and the prevalence of groundwater resources in most parts of the country requirement to accurate prediction of the amount of these resources due to ...
Read More
Most of the country's geographically area is located in dry and semi-dry zone with low rainfall. The growing population, the limitation of water resources and the prevalence of groundwater resources in most parts of the country requirement to accurate prediction of the amount of these resources due to the importance of these resources in optimal planning and management. In this research, in order to estimate the fluctuations of groundwater level in the Baruq aquifer, the artificial intelligence models including fuzzy, support vector machine and neural network models were used by the data of depth from 7 piezometers with long-term data of 14 years, as well as changes in temperature and precipitation in this period. Despite the inherent abilities of each models in predicting groundwater level, the heterogeneity of the study area prevented the high efficiency of these models. Therefore, SOM-AI modeling combined the self-organized maps (SOM) classification method and each model that is increased the efficiency of each composite model in different parts of the aquifer by dividing the study area into homogeneous regions. The results showed that the proposed method can be an effective method in the modeling of heterogeneous and even multi-layered aquifers.
S. Yusefzadeh; A. A. Nadiri
Abstract
Today Ground water is the main source of drinking, agriculture and other uses for humans. The demand for this critical and strategic natural resource increased with population growth and development of society. This increasing has been declining water resources and damage aquifers environment. Therefore, ...
Read More
Today Ground water is the main source of drinking, agriculture and other uses for humans. The demand for this critical and strategic natural resource increased with population growth and development of society. This increasing has been declining water resources and damage aquifers environment. Therefore, we need to manage aquifers and understanding the hydrogeological parameters to deal with the water crisis and prevent the distraction of aquifers. The one of most important parameter is hydraulic conductivity. Although, the ground water system is a complex system and estimation of hydrogeological parameters is associated with inherent uncertainty and also is costly and time consuming that usually done with classical methods such as laboratory tests, slug test, tracing test and pumping tests. So recently use artificial intelligence methods for estimation of hydraulic conductivity, reduced the uncertainty of this parameter and it adds up some accuracy. So that it can overcome on the shortcoming of classical methods. In this study, four artificial intelligence methods; mamdani fuzzy logic(MFL) system, sugeno fuzzy logic(SFL) system, Wavelet-neural network method and Least square support vector machine(LS-SVM) method were used as individual models to estimate the hydraulic conductivity by using of surface geophysical data in Maragheh-Bonab aquifer. Given that each these models based on their inherent properties, they presented good results in some parts of area. Therefore, for concurrent use of performance of all these models the nonlinear combination method as a supervised committee machine artificial intelligence (SCMAI) model were used to estimate the hydraulic conductivity in maragheh-bonab aquifer. The result of this model showed that this new combinational model has high performance than other single models that presented by using different evaluation criteria. Therefore, this model could also be used for estimation hydrogeological parameters in areas with high complexity. The SCMAI model was tested against 15 data. The RMSE and for SCMAI prediction were computed as 0.045 and 0.97, respectively. Comparing the error measure values with dose of individual models above, it is seen that SCMAI outperforms individual AI models with low RMSE and high values. This result implies that SCMAI model shows high performance for estimation the hydraulic conductivity values in the heterogeneous unconfined aquifer in Maragheh-Boanb plain.
