14 مرداد 1399
مريم بيات وركشي

مریم بیات ورکشی

مرتبه علمی: استادیار
نشانی: m.bayat.v@malayeru.ac.ir
تحصیلات: دکترای تخصصی / خاکشناسی-منابع آب
تلفن:
دانشکده: کشاورزی

مشخصات پژوهش

عنوان
Comparison of numerical model, neural intelligent and geostatistical in estimating groundwater table
نوع پژوهش مقاله ارائه شده
کلیدواژه‌ها
Numerical Model, CANFIS, Wavelet-ANN, geostatistical, Groundwater Table
سال
2017
پژوهشگران مریم بیات ورکشی

چکیده

Predicting groundwater levels are difficult and time consuming due its nonlinearity and complexity. Models provide groundwater managers and decision makers an efficient and low cost tool. The purpose of this study was to compare the numerical model, neural intelligent and geostatistical method to predict the groundwater table changes. The Hamedan – Bahar aquifer as one of the most important water sources in Hamedan province, Irna was studied. In this study, MODFLOW numerical code in GMS software, artificial neural network (ANN) and neural – fuzzy (CANFIS) method in NeuroSolution software, wavelet- neural method in MATLAB and geostatistical method in ArcGIS software were used. The results showed that the accuracy of methods in estimation of the groundwater table with the lowest Normal Root Mean Square Error (NRMSE) include Wavelet-ANN, CANFIS, geostatistical, ANN and numerical model, respectively. The NRMSE value in Wavelet-ANN method as optimization method was 0.11 % and in numerical model was 2.2 %. In addition, the correlation coefficients were 0.998 and 0.904, respectively. So, application of neural combination models, wavelet theory, in the estimation of groundwater table was the most suitable method compare to geostatistical and numerical model for selected aquifer.