Haitham Abdulmohsin Afan

ANN Based Sediment Prediction Model Utilizing Different Input Scenarios

Modeling sediment load is a significant factor in water resources engineering as it affects directly the design and management of water resources. In this study, artificial neural networks (ANNs) are employed to estimate the daily sediment load. Two different ANN algorithms, the feed forward neural network (FFNN) and radial basis function (RBF) have been used for this purpose. The neural networks are trained and tested using daily sediment and flow data from Rantau Panjang station on Johor River. The results show that combining flow data with sediment load data gives an accurate model to predict sediment load. The comparison of the results indicate that the FFNN model has superior performance than the RB model in estimating daily sediment load.

RBFNN versus FFNN for daily river flow forecasting at Johor River, Malaysia

Abstract Streamflow forecasting can have a significant economic impact, as this can help in water resources management and in providing protection from water scarcities and possible flood damage. Artificial neural network (ANN) had been successfully used as a tool to model various nonlinear relations, and the method is appropriate for modeling the complex nature of hydrological systems. They are relatively fast and flexible and are able to extract the relation between the inputs and outputs of a process without knowledge of the underlying physics. In this study, two types of ANN, namely feed-forward back-propagation neural network (FFNN) and radial basis function neural network (RBFNN), have been examined. Those models were developed for daily streamflow forecasting at Johor River, Malaysia, for the period (1999–2008). Comprehensive comparison analyses were carried out to evaluate the performance of the proposed static neural networks. The results demonstrate that RBFNN model is superior to the FFNN forecasting model, and RBFNN can be successfully applied and provides high accuracy and reliability for daily streamflow forecasting.

Application of artificial intelligence (AI) techniques in water quality index prediction: a case study in tropical region, Malaysia

The management of river water quality is one the most significant environmental challenges. Water quality index (WQI) describes several water quality variables at a certain aquatic environment and time. Classically, WQI is commonly computed using the traditional methods which involved lengthy computation, consume timing and occasionally associated with accidental errors during subindex calculation. Thus, providing an accurate prediction model for WQI is highly required. Recently, the artificial neural networks (ANNs) have been examined for similar prediction applications and exhibited a remarkable ability to capture the nonlinearity pattern between predictors and predictand. In the current research, two different ANN algorithms, namely radial basis function neural network (RBFNN) and back propagation neural networks models, have been applied to examine and mimic the relationship of WQI with the water quality variables in a tropical environment (Malaysia). The input variables categorized into two different architectures and have been inspected. In addition, comprehensive analysis for the performance evaluation and the sensitivity analysis of the variables have been conducted. The results achieved are positively promising with high performance accuracy belonging to RBFNN model for both scenarios. Furthermore, the proposed approach offers an effective alternative to compute and predict WQI, to the fact that WQI manual calculation methods involved lengthy computations, transformations, use of various subindex formulae for each value of the constituent water quality variables, and consuming time.

Optimized River Stream-Flow Forecasting Model Utilizing High-Order Response Surface Method

Accurate and reliable stream-flow forecasting has a key role in water resources planning and management. Most recently, soft computing approaches have become progressively prevalent in modelling hydrological variables and most specifically stream-flows. This is due to their ability to capture the non-linearity and non-stationarity characteristics of the hydrological variables with minimum information requirements. Despite this, they present several challenges in the modelling architecture, as there is a need to establish a suitable pre-processing method for the stream-flow data and an appropriate optimization model has to be integrated in order re-adjust the weights and biases associated with the model structure. On top of that, artificial intelligent models require “trial and error” procedures in order to be properly tuned (number of hidden layers, number of neurons within the hidden layers and the type of the transfer function). However, soft computing approach experienced several problems while calibration such as over-fitting. In this research, the Response Surface Method (RSM) is improved based on high-order polynomial functions for forecasting the river stream-flow namely; High-Order Response Surface (HORS) method. Several higher orders have been examined, second, third, fourth and fifth polynomial functions in order to figure out the best fit that able to mimic the pattern of stream-flow. In order to demonstrate the effectiveness of the proposed model, monthly stream-flow time series data located in Aswan High Dam (AHD) has been examined. A detailed analysis of the overall statistical indicators revealed that the proposed method showed outstanding performance for monthly stream-flow forecasting at AHD. It could be concluded that the fifth order polynomial function outperforms the other orders of the polynomial functions especially with May model who achieved minimum MAE 0.12, NRMSE 0.07, MSE 0.03 and maximum SF and R2 (0.97, 0.99) respectively.

Heavy metal monitoring, analysis and prediction in lakes and rivers: state of the art

Several research efforts have been conducted to monitor and analyze the impact of environmental factors on the heavy metal concentrations and physicochemical properties of water bodies (lakes and rivers) in different countries worldwide. This article provides a general overview of the previous works that have been completed in monitoring and analyzing heavy metals. The intention of this review is to introduce the historical studies to distinguish and understand the previous challenges faced by researchers in analyzing heavy metal accumulation. In addition, this review introduces a survey on the importance of time increment sampling (monthly and/or seasonally) to comprehend and determine the rate of change of different parameters on a monthly and seasonal basis. Furthermore, suggestions are made for future research to achieve more understandable figures on heavy metal accumulation by considering climate conditions. Thus, the intent of the current study is the provision of reliable models for predicting future heavy metal accumulation in water bodies in different climates and pollution conditions so that water management can be achieved using intelligent proactive strategies and artificial neural network (ANN) techniques.

Artificial intelligence and geo-statistical models for stream-flow forecasting in ungauged stations: state of the art

Developing an accurate model for discharge estimation techniques of the ungauged river basin is a crucial challenge in water resource management especially in under-development regions. This article is a thorough review of the historical improvement stages of this topic to understand previous challenges that faced researchers, the shortfalls of methods and techniques, how researchers prevailed and what deficiencies still require solutions. This revision focuses on data-driven approaches and GIS-based methods that have improved the accuracy of estimation of hydrological variables, considering their advantages and disadvantages. Past studies used artificial intelligence and geo-statistical methods to forecast the runoff at ungauged river basins, and mapping the spatial distribution has been considered in this study. A recommendation for future research on the potential of a hybrid model utilizing both approaches is proposed and described.

Influence of bed deposit in the prediction of incipient sediment motion in sewers using artificial neural networks

ABSTRACT This study investigates the performance of artificial neural networks in predicting the incipient sediment motion in sewers. Two neural network algorithms, i.e. feed forward neural network (FFNN) and radial basis function (RBF), were employed to estimate the critical velocity over varying sediment thickness, median grain size and water depth. Empirical data from five studies were fed into the models and the performance of each model was scrutinized based on three performance criteria. Prediction from FFNN was found to give higher accuracy than values obtained from RBF. Analysis was also extended to observe the correlation between the predicted critical velocity with calculated critical velocity using five empirical equations developed using non-linear regression analysis. Prediction by FFNN proved to have the highest accuracy compared to the RBF and the values obtained through empirical equations described in this study.