Bulent Tutmez

Modelling electrical conductivity of groundwater using an adaptive neuro-fuzzy inference system

Electrical conductivity is an important indicator for water quality assessment. Since the composition of mineral salts affects the electrical conductivity of groundwater, it is important to understand the relationships between mineral salt composition and electrical conductivity. In this present paper, we develop an adaptive neuro-fuzzy inference system (ANFIS) model for groundwater electrical conductivity based on the concentration of positively charged ions in water. It is shown that the ANFIS model outperforms more traditional methods of modelling electrical conductivity based on the total solids dissolved in the water, even though ANFIS uses less information. Additionally, the fuzzy rules in the ANFIS model provide a categorization of ground water samples in a manner that is consistent with the current understanding of geophysical processes.

Spatial estimation model of porosity

This paper addresses a spatial estimation model which uses fuzzy clustering algorithm and assesses the aquifer porosity based on point cumulative semimadogram (PCSM) measure. In order to obtain the estimated porosity values, the model employs standard regional dependence function (SRDF) which provides weights for different regional locations depending on the distances from the reference site. The proposed methodology has three stages: (1) structure identification; (2) spatial dependence measure; and (3) interpolation. The model has been tested using a real data set which was taken from an aquifer in Turkey. The performance evaluations indicate that the new methodology can be applied in geological based domains.

Comparing two data driven interpolation methods for modeling nitrate distribution in aquifer

Abstract As a soluble compound in water, nitrate could easily pass through soil to the groundwater. In recent decades, nitrate pollution of groundwater has been increased mainly as a result of excessive application of fertilizers in agricultural areas. Appraisal of nitrate distribution in aquifers is not a new problem but it is still unsolved. This paper compares the performances of two modeling approaches such as geostatistical (kriging) and soft (fuzzy) computing in spatial interpolation of nitrate concentration in groundwater. For this purpose, the groundwater samples are collected from springs and wells in Mersin–Tarsus Aquifer to be considered. The estimation models are established based on data driven modeling concept. The results and performance evaluations indicate that the estimation capacity of the fuzzy model is higher than that of the kriging model.

Local spatial regression models : a comparative analysis on soil contamination

Spatial data analysis focuses on both attribute and locational information. Local analyses deal with differences across space whereas global analyses deal with similarities across space. This paper addresses an experimental comparative study to analyse the spatial data by some weighted local regression models. Five local regression models have been developed and their estimation capacities have been evaluated. The experimental studies showed that integration of objective function based fuzzy clustering to geostatistics provides some accurate and general models structures. In particular, the estimation performance of the model established by combining the extended fuzzy clustering algorithm and standard regional dependence function is higher than that of the other regression models. Finally, it could be suggested that the hybrid regression models developed by combining soft computing and geostatistics could be used in spatial data analysis.

Use of hybrid intelligent computing in mineral resources evaluation

Mineral resources are a formal quantification of naturally occurring materials. Estimation of resource parameters such as grade and thickness may be carried out using different methodologies. In this paper, a soft methodology, which is artificial neural network (ANN) based fuzzy modelling is presented for grade estimation and its stages are demonstrated. The neuro-fuzzy method uses preliminary clustering and finally estimates the ore grades based on radial basis neural network and interpolation. Two case studies designed for both simulated and real data sets indicate that the approach is relatively accurate and flexible. In addition, the method is suitable for modelling via limited number of data. The results and performance comparisons with conventional methods show that the computing method is efficient. 2009 Elsevier B.V. All rights reserved.

Trend Analysis for the Projection of Energy-Related Carbon Dioxide Emissions

Carbon dioxide is one of the most foremost greenhouse gases in the atmosphere. Carbon dioxide emission is very crucial for both health and environment. Trend analysis approach was employed for modeling world total carbon dioxide emissions from the consumption of coal and all fossil fuels (petroleum, flaring of natural gas, natural gas, and coal). The results obtained from the analyses showed that the models can be used for CO2 emission projections into the future planning.

Regression Kriging Analysis for Longitudinal Dispersion Coefficient

Prediction of longitudinal dispersion coefficient (LDC) is still a novel topic for both environmental and water sciences due to its practical importance. In this study, the appraisal of LDC is considered as a spatial modelling problem and the analyses are carried out by regression kriging. Since LDC prediction includes some geometrical (spatial) parameters, the analyses have been performed such that it takes spatial variability of data into account. The modelling procedure consists of two stages. In the first stage, spatial variables are analyzed via multi-linear regression technique and deterministic relationships are identified. In the second stage, based on the spatial auto-correlations of the residuals, the regression-based kriging procedure is applied. The capacity and accuracy level of the method has been compared with former models. As a consequence, the applications revealed that analyzing hydraulic and geometrical parameters with spatially correlated errors is a convenient approach for evaluating LDC in a hydrological system.

Evaluating geo-environmental variables using a clustering based areal model

Global regression models do not accurately reflect the spatial heterogeneity which characterises most geo-environmental variables. In analysing the relationships between such variables, an approach is required which allows the model parameters to vary spatially. This paper proposes a new framework for exploring local relationships between geo-environmental variables. The method is based on extended objective function based fuzzy clustering with the environmental parameters estimated through on a locally weighted regression analysis. The case studies and prediction evaluations show that the fuzzy algorithm yields well-fitted models and accurate predictions. In addition to an increased accuracy of prediction relative to the widely-used geographically weighted regression (GWR), the proposed algorithm provides the search radius (bandwidth) and weights for local estimation directly from the data. The results suggest that the method could be employed effectively in tackling real world kernel-based modelling problems.

Measurement uncertainty analysis for compressive loading-based ultrasonic wave propagation

Abstract As a non-destructive test, the ultrasonic pulse velocity measure is one of the convenient tools suggested to estimate elasticity and strength properties of rocks. Since the experimental procedure and identification process cover various uncertainty sources, an extensive measurement uncertainty analysis is required to determine the variations in the testing procedure and measurement. As a generally accepted document for the measurement uncertainty, the ‘Guide to expression of uncertainty in measurement (GUM)’ recommends Taylor and Monte Carlo methods to evaluate the measurement uncertainties. In this study, both random and systematic uncertainties encountered in ultrasonic wave propagation are analysed and appraised. Starting from the conventional methods recommended in GUM and further approaches proposed previously, a copula-based evaluation procedure is proposed in order to improve the consideration of dependencies in the measurement data.

Hybrid least-squares regression modelling using confidence bonds

One of the questions regarding bridging of soft computing and statistical methods is the (re-)use of information between the two approaches. In this context, we consider in this paper whether statistical confidence bounds can be used in the hybrid fuzzy least squares regression problem. By using the confidence limits as the spreads of the fuzzy numbers, uncertainty estimates for the fuzzy model can be provided. Experiments have been conducted in the paper, both on regression coefficients and the predicted responses of regression models. The findings show that the use of the confidence intervals as the widths of memberships gives successful results and opens new possibilities in system modeling and analysis.