Ali Najah

Water quality prediction model utilizing integrated wavelet-ANFIS model with cross-validation

This paper discusses the accuracy performance of training, validation and prediction of monthly water quality parameters utilizing Adaptive Neuro-Fuzzy Inference System (ANFIS). This model was used to analyse the historical data that were generated through continuous monitoring stations of water quality parameters (i.e. the dependent variable) of Johor River in order to imitate their secondary attribute (i.e. the independent variable). Nevertheless, the data arising from the monitoring stations and experiment might be polluted by noise signals owing to systematic and random errors. This noisy data often made the predicted task relatively difficult. Thus, in order to compensate for this augmented noise, the primary objective of this study was to develop a technique that could enhance the accuracy of water quality prediction (WQP). Therefore, this study proposed an augmented wavelet de-noising technique with Neuro-Fuzzy Inference System (WDT-ANFIS) based on the data fusion module for WQP. The efficiency of the modules was examined to predict critical parameters that were affected by the urbanization surrounding the river. The parameters were investigated in terms of the following: the electrical conductivity (COND), the total dissolved solids (TDSs) and turbidity (TURB). The results showed that the optimum level of accuracy was achieved by making the length of cross-validation equal one-fifth of the data records. Moreover, the WDT-ANFIS module outperformed the ANFIS module with significant improvement in predicting accuracy. This result indicated that the proposed approach was basically an attractive alternative, offering a relatively fast algorithm with good theoretical properties to de-noise and predict the water quality parameters. This new technique would be valuable to assist decision-makers in reporting the status of water quality, as well as investigating spatial and temporal changes.

Performance of ANFIS versus MLP-NN dissolved oxygen prediction models in water quality monitoring

We discuss the accuracy and performance of the adaptive neuro-fuzzy inference system (ANFIS) in training and prediction of dissolved oxygen (DO) concentrations. The model was used to analyze historical data generated through continuous monitoring of water quality parameters at several stations on the Johor River to predict DO concentrations. Four water quality parameters were selected for ANFIS modeling, including temperature, pH, nitrate (NO3) concentration, and ammoniacal nitrogen concentration (NH3-NL). Sensitivity analysis was performed to evaluate the effects of the input parameters. The inputs with the greatest effect were those related to oxygen content (NO3) or oxygen demand (NH3-NL). Temperature was the parameter with the least effect, whereas pH provided the lowest contribution to the proposed model. To evaluate the performance of the model, three statistical indices were used: the coefficient of determination (R2), the mean absolute prediction error, and the correlation coefficient. The performance of the ANFIS model was compared with an artificial neural network model. The ANFIS model was capable of providing greater accuracy, particularly in the case of extreme events.

Application of artificial neural networks for water quality prediction

The term “water quality” is used to describe the condition of water, including its chemical, physical, and biological characteristics. Modeling water quality parameters is a very important aspect in the analysis of any aquatic systems. Prediction of surface water quality is required for proper management of the river basin so that adequate measure can be taken to keep pollution within permissible limits. Accurate prediction of future phenomena is the life blood of optimal water resources management. The artificial neural network is a new technique with a flexible mathematical structure that is capable of identifying complex non-linear relationships between input and output data when compared to other classical modeling techniques. Johor River Basin located in Johor state, Malaysia, which is significantly degrading due to human activities and development along the river. Accordingly, it is very important to implement and adopt a water quality prediction model that can provide a powerful tool to implement better water resource management. Several modeling methods have been applied in this research including: linear regression models (LRM), multilayer perceptron neural networks and radial basis function neural networks (RBF-NN). The results showed that the use of neural networks and more specifically RBF-NN models can describe the behavior of water quality parameters more accurately than linear regression models. In addition, we observed that the RBF finds a solution faster than the MLP and is the most accurate and most reliable tool in terms of processing large amounts of non-linear, non-parametric data.

Optimized Neural Network Prediction Model for Potential Evapotranspiration Utilizing Ensemble Procedure

Potential evapotranspiration (ETo) is an essential hydrologic parameter for having better understanding for hydrologic cycle in certain catchment area. In addition, ETo is vital for calculating the agricultural demand. In fact, Penman-Monteith (PM) method is considered as reference method for estimating (ETo), however, this method required a lot of data to be used which is not usually available in many catchment areas. Furthermore, there are several efforts that have been performed as competitor to reach accurate estimation of (ETo) when there is lack of data to utilize (PM) method, but still required numerous research. Recently, methods based on Artificial Intelligence (AI) have been suggested to provide reliable prediction model for several application in engineering and especially for hydrological process. However, time series prediction based on Artificial Neural Network (ANN) learning algorithms is fundamentally difficult and faces problem. One of the major shortcomings is that the ANN model experiences over-fitting problem during training session and also occurs when a neural network loses its generalization. In this research a modification for the classical Multi Layer Preceptron- Artificial Neural Network (MLP-ANN) modeling namely; Ensemble Neural Network (ENN) is proposed and applied for predicting daily ETo. The proposed model applied at two different region with two different climatic conditions, Rasht city located north part of Iran and Johor Bahru City, Johor, Malaysia using maximum and minimum daily temperature collected from 1975 to 2005. The result showed that the ENN outperformed the classical MLP-ANN method and successfully predict daily ETo utilizing maximum and minimum temperature only with satisfactory level of accuracy. In addition, the proposed model could achieve accuracy level better than the traditional competitor methods for ETo.

Multi-lead ahead prediction model of reference evapotranspiration utilizing ANN with ensemble procedure

Obtaining an accurate estimate of the reference evapotranspiration (ETo) can be difficult, especially when there is insufficient data to utilize the Penman–Monteith method. Artificial intelligence–based methods may provide reliable prediction models for several applications in engineering. However, time-series prediction based on artificial neural network (ANN) learning algorithms is fundamentally problematic. For example, the ANN model can experience over-fitting during training and, in consequence, lose its generalization. In this research, several over-fitting procedures have been augmented with the classical ANN model, are proposed. This model was applied to the prediction of the daily ETo at Rasht city, located in the north part of Iran, by using the minimum and maximum daily temperature of the region collected from 1975–1988. In addition, three different scenarios have been developed in order to achieve better prediction accuracy. The results showed that the proposed ENN model successfully predicted the daily ETo with a significant level of accuracy using only the maximum and minimum temperatures. The model also outperformed the classical ANN method. In addition, the proposed ENN compared with Hargreaves and Samani (Appl Eng Agric 1:96–99, 1985) (HGS) model and showed the ENN provides more accurate prediction for ETo. Furthermore, the proposed model could provide relatively good level of accuracy when examined for multi-lead predictions, which could not be afford by HGS model.

Amplified wavelet-ANFIS-based model for GPS/INS integration to enhance vehicular navigation system

Inertial navigation system (INS) relying on gyroscopes and accelerometers has been recently utilized in land vehicles. These INS sensors are integrated with Global Positioning System (GPS) to provide reliable positioning solutions in case of GPS outages that commonly occur in urban canyons. The major inadequacies of INS navigation sensors are the high noise level and the large bias instabilities that are stochastic in nature. The effects of these inadequacies manifest themselves as large position errors during GPS outages. Wavelet analysis is a signal processing method which is recently auspicious by many researchers due to its advantageous adaptation to non-stationary signals and able to perform analysis in both time and frequency domain over other signal processing methods such as the fast Fourier transform in some fields. This research proposes the utilization of wavelet de-nosing to improve the signal-to-noise ratio of each of the INS sensors. In addition, a neuro-fuzzy module is used to provide a reliable prediction of the vehicle position during GPS outages. The results from a road test experiment show the effectiveness of the proposed wavelet—neuro-fuzzy module.

Application of Neural Network for Scour and Air Entrainment Prediction

This research aims at introducing a system independent method for scour and air entrainment prediction utilizing Artificial Neural Network (ANN) based on previous experimental plunge pool scour tests for inclined circular jets. Furthermore, the current manuscript introduced a single ANN model to predict air entrainment devoid of pre-knowledge of the jet condition either smooth or rough jet. Regarding ANN applicability validation, its prediction results was compared to the earlier experimental results for three regression models; one for scour, and two air-models for a smooth and rough jet. The results from each model out of the three ANN models are proved more accurate than the corresponding pre-developed regression models. Relative error envelop of 5% was found to bound all the records for the prediction of air in both ANN models (smooth and rough). For the prediction of the scour, the ANN model was also better than the regression model with only two data records of 20% relative error.

Erratum to: Daily Forecasting of Dam Water Levels: Comparing a Support Vector Machine (SVM) Model With Adaptive Neuro Fuzzy Inference System (ANFIS) (Water Resour Manage, 10.1007/s11269-013-0382-4)

Reservoir planning and management are critical to the development of the hydrological field and necessary to Integrated Water Resources Management. The growth of forecasting models has resulted in an excellent model known as the Support Vector Machine (SVM). This model uses linearly separable patterns based on an optimal hyperplane, which are extended to non-linearly separable patterns by transforming the raw data to map into a new space. SVM can find a global optimal solution equipped with Kernel functions. These Kernel functions have high flexibility in the forecasting computation, enabling data to be mapped at a higher and infinite-dimensional space in an implicit manner. This paper presents a new solution to the expert system, using SVM to forecast the daily dam water level of the Klang gate. Four categories are identified to determine the best model: the input scenario, the type of SVM regression, the number of V-fold cross-validation and the time lag. The best input scenario employs both the rainfall R(t-i) and the dam water level L(t-i). Type 2 SVM regression is selected as the best regression type, and 5-fold cross-validation produces the most accurate results. The results are compared with those obtained using ANFIS: all the RMSE, MAE and MAPE values prove that SVM is a superior model to ANFIS. Finally, all the results are combined to determine the best time lag, resulting in R(t-2) L(t-2) for the best model with only 1.64 % error. Copyright Springer Science+Business Media Dordrecht 2013