Umut Okkan

Prediction of unconfined compressive strength of carbonate rocks using artificial neural networks

The unconfined compressive strength (UCS) of intact rocks is an important geotechnical parameter for engineering applications. Determining UCS using standard laboratory tests is a difficult, expensive and time consuming task. This is particularly true for thinly bedded, highly fractured, foliated, highly porous and weak rocks. Consequently, prediction models become an attractive alternative for engineering geologists. The objective of study is to select the explanatory variables (predictors) from a subset of mineralogical and index properties of the samples, based on all possible regression technique, and to prepare a prediction model of UCS using artificial neural networks (ANN). As a result of all possible regression, the total porosity and P-wave velocity in the solid part of the sample were determined as the inputs for the Levenberg–Marquardt algorithm based ANN (LM-ANN). The performance of the LM-ANN model was compared with the multiple linear regression (REG) model. When training and testing results of the outputs of the LM-ANN and REG models were examined in terms of the favorite statistical criteria, which are the determination coefficient, adjusted determination coefficient, root mean square error and variance account factor, the results of LM-ANN model were more accurate. In addition to these statistical criteria, the non-parametric Mann–Whitney U test, as an alternative to the Student’s t test, was used for comparing the homogeneities of predicted values. When all the statistics had been investigated, it was seen that the LM-ANN that has been developed, was a successful tool which was capable of UCS prediction.

Application of Generalized Regression Neural Networks in Predicting the Unconfined Compressive Strength of Carbonate Rocks

Measuring unconfined compressive strength (UCS) using standard laboratory tests is a difficult, expensive, and time-consuming task, especially with highly fractured, highly porous, weak rock. This study aims to establish predictive models for the UCS of carbonate rocks formed in various facies and exposed in Tasonu Quarry, northeast Turkey. The objective is to effectively select the explanatory variables from among a subset of the dataset containing total porosity, effective porosity, slake durability index, and P-wave velocity in dry samples and in the solid part of samples. This was based on the adjusted determination coefficient and root-mean-square error values of different linear regression analysis combinations using all possible regression methods. A prediction model for UCS was prepared using generalized regression neural networks (GRNNs). GRNNs were preferred over feed-forward back-propagation algorithm-based neural networks because there is no problem of local minimums in GRNNs. In this study, as a result of all possible regression analyses, alternative combinations involving one, two, and three inputs were used. Through comparison of GRNN performance with that of feed-forward back-propagation algorithm-based neural networks, it is demonstrated that GRNN is a good potential candidate for prediction of the unconfined compressive strength of carbonate rocks. From an examination of other applications of UCS prediction models, it is apparent that the GRNN technique has not been used thus far in this field. This study provides a clear and practical summary of the possible impact of alternative neural network types in UCS prediction.

The combined use of wavelet transform and black box models in reservoir inflow modeling

Abstract In the study presented, different hybrid model approaches are proposed for reservoir inflow modeling from the meteorological data (monthly precipitation, one-month-ahead precipitation and monthly mean temperature data) by the combined use of discrete wavelet transform (DWT) and different black box techniques. Multiple linear regression (MLR), feed forward neural networks (FFNN) and least square support vector machines (LSSVM) were considered as the black box methods. In the modeling strategy, meteorological input data were decomposed into wavelet sub-time series at three resolution levels and ineffective sub-time series were eliminated by Mallows’ Cp based all possible regression method. As a result of all possible regression analyses, 2-months mode of time series of monthly temperature (D1_Tt), 8-months mode of time series (D3_Tt) of monthly temperature and approximation mode of time series (A3_Tt) of monthly temperature were eliminated. Remained effective sub-time series were used as the inputs of MLR, FFNN and LSSVM. When the performances of the training and testing periods were compared, it was observed that the DWTFFNN conjunction model has better results in terms of mean square errors (MSE) and determination coefficients (R2) statistics. The discrete wavelet transform approach also increased the accuracy of multiple linear regression and least squares support vector machines.

Evaluating climate change effects on runoff by statistical downscaling and hydrological model GR2M

The main purpose of this study is to evaluate the impacts of climate change on Izmir-Tahtali freshwater basin, which is located in the Aegean Region of Turkey. For this purpose, a developed strategy involving statistical downscaling and hydrological modeling is illustrated through its application to the basin. Prior to statistical downscaling of precipitation and temperature, the explanatory variables are obtained from National Centers for Environmental Prediction/National Center for Atmospheric Research reanalysis data set. All possible regression approach is used to establish the most parsimonious relationship between precipitation, temperature, and climatic variables. Selected predictors have been used in training of artificial neural networks-based downscaling models and the trained models with the obtained relationships have been operated to produce scenario precipitation and temperature from the simulations of third Generation Coupled Climate Model. Biases from downscaled outputs have been reduced after downscaling process. Finally, the corrected downscaled outputs have been transformed to runoff by means of a monthly parametric hydrological model GR2M to assess the probable impacts of temperature and precipitation changes on runoff. According to the A1B climate scenario results, statistically significant trends are foreseen for precipitation, temperature, and runoff in the study basin.

Relevance vector machines approach for long-term flow prediction

Over the past years, some artificial intelligence techniques like artificial neural networks have been widely used in the hydrological modeling studies. In spite of their some advantages, these techniques have some drawbacks including possibility of getting trapped in local minima, overtraining and subjectivity in the determining of model parameters. In the last few years, a new alternative kernel-based technique called a support vector machines (SVM) has been found to be popular in modeling studies due to its advantages over popular artificial intelligence techniques. In addition, the relevance vector machines (RVM) approach has been proposed to recast the main ideas behind SVM in a Bayesian context. The main purpose of this study is to examine the applicability and capability of the RVM on long-term flow prediction and to compare its performance with feed forward neural networks, SVM, and multiple linear regression models. Meteorological data (rainfall and temperature) and lagged data of rainfall were used in modeling application. Some mostly used statistical performance evaluation measures were considered to evaluate models. According to evaluations, RVM method provided an improvement in model performance as compared to other employed methods. In addition, it is an alternative way to popular soft computing methods for long-term flow prediction providing at least comparable efficiency.