In this paper, classification of a large hydrochemical data set from Varamin plain is done by using fuzzy c-means (FCM) and hierarchical cluster analysis (HCA) clustering techniques. Then its application to hydrochemical facies delineation is discussed. Groundwater samp More
In this paper, classification of a large hydrochemical data set from Varamin plain is done by using fuzzy c-means (FCM) and hierarchical cluster analysis (HCA) clustering techniques. Then its application to hydrochemical facies delineation is discussed. Groundwater samples were grouped into three classes according to the optimum number of the classes and fuzziness exponent by using the fuzzy c-mean. The data set includes 90 deep and moderate deep well samples from groundwater data set and 9 hydrochemical variables were used. Results from both FCM and HCA clustering produced cluster centers that can be used to identify the physical and chemical processes creating the variations in the water chemistries. The optimum cluster in FCM method determined by optimization function, but in HCA method by trial and error. The FCM method is potentially useful in establishing hydrochemical facies distribution and may provide a better tool than HCA for clustering large data sets when overlapping or continuous clusters exist. Plotting the cluster membership value contours on a map demonstrated the existence of three spatially continuous, well-defined clusters of groundwater samples. The results showed that the FCM method is more sound for investigating threshold data rather than HCA method (that represents sharp and abrupt variations).
Manuscript profile
One of the main concerns in the aquifers adjacent to oil facilities is the leakage of LNAPLs. Since remediation processes costly and time consuming, so the first step in these systems is determining design goals. Often the most important goal of these systems is to maxi More
One of the main concerns in the aquifers adjacent to oil facilities is the leakage of LNAPLs. Since remediation processes costly and time consuming, so the first step in these systems is determining design goals. Often the most important goal of these systems is to maximize pollutant removal and minimize the cost. Identifying the thickness of LNAPL and its fluctuations can determine the type of recovery method and thus can be effective on the amount of removal and the cost of the implementation. In this study, three methods of gene expression programming (GEP), adaptive neuro-fuzzy inference system (ANFIS) and multivariate linear regression (MLR) were used to estimate and predict the LNAPL level. Input variables are groundwater level elevation and discharge rate of LNAPL and the output variable is the LNAPL level elevation. The results of the three models were analyzed by statistical parameters and it was determined that GEP technique has better results and could be used successfully in predicting LNAPL level fluctuations in recovery processes. Also, the GEP model provides an equation for predicting the LNAPL level that can be used in the field to predict the elevation of the LNAPL level.
Manuscript profile