Mehmet Özger

Long Lead Time Drought Forecasting Using a Wavelet and Fuzzy Logic Combination Model: A Case Study in Texas

AbstractDrought forecasting is important for drought risk management. Considering the El Nino–Southern Oscillation (ENSO) variability and persistence in drought characteristics, this study developed a wavelet and fuzzy logic (WFL) combination model for long lead time drought forecasting. The idea of WFL is to separate each predictor and predictand into their frequency bands and then reconstruct the predictand series by using its predicted bands. The strongest-frequency bands of predictors and predictand were determined from the average wavelet spectra. Applying this combination model to the state of Texas, it was found that WFL had a significant improvement over the fuzzy logic model that did not use wavelet banding. Comparison with an artificial neural network (ANN) model and a coupled wavelet and ANN (WANN) model showed that WFL was more accurate for drought forecasting. Also, it should be noted that the ENSO variability is not a global precursor of drought. For this reason, prior to an application of s...

Determining turbulent flow friction coefficient using adaptive neuro-fuzzy computing technique

In the analysis of water distribution networks, the main required design parameters are the lengths, diameters, and friction coefficients of rough-pipes, as well as nodal demands and water levels in the reservoirs. Although some of these parameters such as the pipe lengths are precisely known and would remain the same at different points of the networks whereas some parameters such as the pipe diameters and friction coefficients would changed during the life of network and therefore they can be treated as imprecise information. The primary focus of this study is to investigate the accuracy of a fuzzy rule system approach to determine the relationship between pipe roughness, Reynolds number and friction factor because of the imprecise, insufficient, ambiguous and uncertain data available. A neuro-fuzzy approach was developed to relate the input (pipe roughness and Reynolds number) and output (friction coefficient) variables. The application of the proposed approach was performed for the data derived from the Moodys diagram. The performance of the proposed model was compared with respect to the conventional procedures using some statistic parameters for error estimation. The comparison test results reveal that through fuzzy rules and membership functions, the friction factor can be identified, precisely.

Comparison of fuzzy inference systems for streamflow prediction

Abstract A comparison of the Mamdani and the Takagi-Sugeno (TS) fuzzy inference systems is presented for predicting streamflow values. The TS fuzzy rule base uses linear functions of inputs to predict the output, whereas the Mamdani version of inference determines outputs through fuzzy sub-sets. A genetic algorithm-trained Mamdani system is applied for streamflow forecasting. All the uncertainties and model complications are treated in linguistic expressions in the form of IF—THEN statements. Fuzzy membership functions, rules and the type of defuzzification method are adjusted until the best correlation between measured and predicted values is reached. The two methods are then applied to flow predictions on the Euphrates River in Turkey, without employing exogenous variables such as rainfall. The advantages and disadvantages of the models are discussed using the case study. It is shown that the Mamdani type of fuzzy inference modelling outperforms the Takagi-Sugeno approach in terms of error criteria comparisons, but neither of the two outperforms a standard ARMA(2, 2) model.

Prediction of ocean wave energy from meteorological variables by fuzzy logic modeling

Research highlights? A new approach based on an expert system of fuzzy logic modeling was intoduced in ocean wave energy prediction. ? It is found that the fuzzy model for wave energy prediction performs better than classical approaches. ? By this proposed approach, it is possible to determine potential wave power in any area from meteorological measurements in the absence of spectral wave measurements. Ocean wave energy which is one of the promising renewable energy types has a direct relationship with the wave climate. The purpose of this study is to investigate the relationship between ocean wave energy and meteorological variables such as wind speed, air temperature, and sea temperature. It was shown that fuzzy logic modeling of these variables provides the possible non-linear relationship between them and consequently the wave energy can be predicted including the possible uncertainties in the system behavior. Compared to traditional approaches, fuzzy logic is more efficient in linking the multiple inputs to a single output in a non-linear manner. Here Takagi-Sugeno (TS) type fuzzy inference system was employed to predict wave energy amount from meteorological variables in the absence of wave records. For the application of the proposed approach the offshore stations located in the Pacific Ocean were used. The results were compared with the classical wave energy equation.

Association between Uncertainties in Meteorological Variables and Water-Resources Planning for the State of Texas

Because of the complexity and rapidly occurring changes in the dynamics of human demography and water demands, it is difficult to assess the future adequacy of limited freshwater resources. The planning of water resources largely depends on the meteorological variables (precipitation and evaporation) in terms of their distribution in space and time. Considering precipitation and evaporation as natural input and output without any human intervention for water-resources systems that can be perceived to represent the potential water-resources availability of an area, an uncertainty study was carried out for different water-resources regions in Texas. The entropy method was used for measuring the uncertainty in meteorological variables. It was observed that critical water-deficit regions based on meteorological variables are mostly located in the western part of Texas. The Mann-Kendall test was employed to understand the trend in precipitation, evaporation, and the meteorological excess index (MEI) in deficit...

A predictive tool by fuzzy logic for outcome of patients with intracranial aneurysm

We aimed to investigate if the outcome of the patients with intracranial aneurysm could be predicted by fuzzy logic approach. Two hundred and forty two patients with the diagnosis of intracranial aneurysm were assessed retrospectively between January 2001 and December 2005. We recorded World Federation of Neurological Surgeons Scale (WFNSS), Fisher Scale and age at admission and Glasgow Outcome Score (GOS) at discharge from hospitalization for all the patients. We developed fuzzy sets by dividing WFNSS into four groups as good, fair, bad and very bad; age into three groups as young, middle and old; Fisher scale into three groups as few, moderate and large; outcome score into four groups as bad, fair, good and very good. We calculated the outcome of the patient with these sets by fuzzy model. Predicted outcome by fuzzy logic approach correlated with observed outcome scores of the patients (p>0, 05), including 95% confidence interval. We showed that outcome of the patients with aneurysm can be predicted by fuzzy logic approach, accurately.

Neuro-fuzzy approach for the spatial estimation of ocean wave characteristics

Real time applications of oceanographic data and statistical calculations for climatological studies suffer from missing data. To overcome this problem, spatial correlation of significant wave height from multiple stations is considered. Here significant wave height is taken as regionalized variable to establish a relationship through the use of fuzzy logic. There are other techniques in the literature to explore spatial dependency such as regression, Kriging and artificial neural networks. Spatial variability of wave characteristics is also important for ocean wave energy applications. It is shown that significant wave heights at the location of one buoy can be predicted using the neuro-fuzzy approach and the data from adjacent buoys. The proposed approach is compared with the multiple linear regression model which includes some restrictive assumptions. The implementation of the methodology is performed for the buoys located in the Gulf of Mexico.

Investigating the Multifractal Properties of Significant Wave Height Time Series Using a Wavelet-Based Approach

Singularities play a significant role in the characterization of time series. The temporal characteristics of fluctuating significant wave height time series are investigated in this study. The hourly time series from 24 stations located off the west coast of the United States are used for the analysis. The multifractal nature of these time series is unveiled by employing a wavelet-based method. The wavelet transform modulus maxima method is applied to obtain the multifractal spectra (singularity spectrum) of the significant wave height series. The multifractal spectra and their parameters such as peak, min and max Holder exponents, skewness coefficients, and support lengths are calculated. The peak Holder exponent ranged from 0.30 to 0.46 throughout the study area. Holder exponents that are less than 0.5 indicate that the time series exhibits an antipersistent random walk. The spatial variation of parameters is depicted through kriging maps. Different spatial variation patterns can be seen from the maps. It is clear that deep offshore stations have relatively higher Holder exponents than coastal areas. This change can be related to the wave generation mechanism, by way of physical interpretations. Since the stations located in the deep offshore can receive more swell waves than coastal zones and are open to large-scale storms, they may tend to be more persistent and have greater Holder exponents. Also, the type of the singularities occurring in deep offshore and in the coastal zones is assessed by considering the wave generating mechanisms.

Comparison of Discrete and Continuous Wavelet–Multilayer Perceptron Methods for Daily Precipitation Prediction

AbstractWavelet transforms are combined with predictive methods to develop prediction approaches so that the prediction accuracy can be improved in hydrologic predictions. Although the wavelet transform generates several subseries that show similar characteristics, the predictive method is used to develop the model using those subseries. There are several examples of these kinds of combined models, such as wavelet–multilayer perceptron (MP), wavelet fuzzy, wavelet autoregressive, and so forth. Generally, discrete wavelet transformation is used in combined models rather than continuous wavelet transform for unexplained reasons. As a result, in this study emphasis was placed on the comparison of the continuous wavelet–multilayer perceptron (CWT-MP) and discrete wavelet–multilayer perceptron (DWT-MP) models, which were also compared with the stand-alone MP model. Daily precipitation time series from two stations were used in the model development and comparison process. The current precipitation values were ...

Scaling Characteristics of Precipitation Data over Texas

The question addressed in this study was: do the number and magnitude of dry and wet spells occur in a scale invariant manner in the state of Texas or not? To answer this question, a large set of monthly precipitation data from 75 grid points spread across Texas was employed to investigate the spatial variability in the scaling properties of number and magnitude of dry and wet spells. No coherent regional differences were found. Using a power-law analysis, time-scale properties of dry and wet spells were examined, and power-law coefficients were related to the various truncation levels. A linear relationship was found between fractal dimensions of the numbers of dry and wet spells, whereas power-law coefficients of the magnitude remained constant for all truncation levels. Also, significant low-frequency patterns of precipitation were found when the wavelet transform was used. Generally, interannual cycles were found to be significant for the state of Texas. Low-frequency cycles had no distinguishable imp...