Nor Azazi Zakaria

Genetic Programming to Predict Bridge Pier Scour

Bridge-pier scour is a significant problem for the safety of bridges. Extensive laboratory and field studies have been conducted examining the effect of relevant variables. This note presents an alternative to the conventional regression-based equations (HEC-18 and regression equation developed by the writers), in the form of artificial neural networks (ANNs) and genetic programming (GP). There had been 398 data sets of field measurements that were collected from published literature and were used to train the network or evolve the program. The developed network and evolved programs were validated by using the observations that were not involved in the training. The performance of GP was found more effective when compared to regression equations and ANNs in predicting the scour depth at bridge piers.

Flood risk mapping for Pari River incorporating sediment transport

Geographic Information Systems (GIS) are an efficient and interactive spatial decision support tool for flood risk analysis. This paper describes the development of ArcView GIS extension — namely AVHEC-6.avx — to integrate the HEC-6 hydraulic model within GIS environment. The extension was written in an Avenue Script language and Dialog Designer with a series of ‘point and click’ options. It has the capability of analyzing the computed water surface profiles generated from HEC-6 model and producing a related flood map for the Pari River in the ArcView GIS. The user-friendly menu interface guides the user to understand, visualize, build query, conduct repetitious and multiple analytical tasks with HEC-6 outputs. The flood risk model was tested using the hydraulic and hydrological data from the Pari River catchment area. The required sediment input parameters were obtained from field sampling. The results of this study clearly show that GIS provides an effective environment for flood risk analysis and mapping. The present study only concentrates on the flood risk within the boundary of the bunds.  2002 Elsevier Science Ltd. All rights reserved.

Gene expression programming for total bed material load estimation—a case study

This paper presents Gene-Expression Programming (GEP), which is an extension to the genetic programming (GP) approach to predict the total bed material load for three Malaysian rivers. The GEP is employed without any restriction to an extensive database compiled from measurements in the Muda, Langat, and Kurau rivers. The GEP approach demonstrated a superior performance compared to other traditional sediment load methods. The coefficient of determination, R(2) (=0.97) and the mean square error, MSE (=0.057) of the GEP method are higher than those of the traditional method. The performance of the GEP method demonstrates its predictive capability and the possibility of the generalization of the model to nonlinear problems for river engineering applications.

Genetic programming to predict ski-jump bucket spill-way scour

Researchers in the past had noticed that application of Artificial Neural Networks (ANN) in place of conventional statistics on the basis of data mining techniques predicts more accurate results in hydraulic predictions. Mostly these works pertained to applications of ANN. Recently, another tool of soft computing, namely, Genetic Programming (GP) has caught the attention of researchers in civil engineering computing. This article examines the usefulness of the GP based approach to predict the relative scour depth downstream of a common type of ski-jump bucket spillway. Actual field measurements were used to develop the GP model. The GP based estimations were found to be equally and more accurate than the ANN based ones, especially, when the underlying cause-effect relationship became more uncertain to model.

Bio-ecological drainage system (BIOECODS) for water quantity and quality control

Abstract Land use change in urbanizing watersheds can have a significant impact on hydrologic and hydraulic process as well a degradation of water quality on receiving waters. The Bio‐Ecological Drainage System (BIOECODS) consists of elements of storage, flow retarding and infiltration engineering. Swales, dry ponds, detention ponds and wetland are the main components of BIOECODS that function as flow attenuation and water quality treatment devices. The BIOECODS is a pilot project that meets the requirements of the Stormwater Management Manual for Malaysia and has been constructed at the Engineering Campus of the University Science Malaysia, Nibong Tebal, Penang. BIOECODS represents an alternative to the traditional hard engineering‐based drainage system to manage stormwater quantity and quality for urban areas. This article discusses how the BIOECODS could be implemented to control stormwater quantity from an urbanized area and reduce the water quality impact on the receiving water.

Sediment size characteristics of urban drains in Malaysian cities

Abstract The existing conventional drainage systems in cities throughout Malaysia have been built mainly to cater for the increase in surface runoff due to rapid development that occurs in the city borders. The drainage system is normally made up of open rigid concrete drain channels susceptible to maintenance problems such as sediment deposition, litter and utility pipes crossing. This paper highlights the results of surveys carried out to determine the sediment size characteristics in urban drains of five cities in Malaysia. A preliminary result from a sediment profile observation at Sungai Raja drainage system, Alor Setar is also described to establish the effect of drain size and slope on deposition trend.

Sungai Pahang digital flood mapping: 2007 flood

In this study, visits to areas in the subcatchments of Sungai Pahang, including Mentakab, Temerloh, Maran and Pekan, were made throughout the year 2009 to obtain information regarding inundation areas, flood depth, flow discharge and water levels relevant to the 2007 flood. Interviews with local people were also made to ascertain the true picture of the 2007 flood. Analyses of rainfall data, water level, flow discharge and river cross-sectional changes were carried out from data gathering. The development of a digital elevation model (DEM) was made from a combination of digital topographical maps and satellite images which were purchased from Jabatan Ukur dan Pemetaan Malaysia. This visually enhanced DEM was then used for the development of the actual extent of the 2007 flood in the study area. Several options of flood mitigation works are proposed to reduce the impact of a similar flood in the future based on the developed DEM.

Case Study: Flood Mitigation of the Muda River, Malaysia

The 2003 flood of the Muda River reached 1,340 m 3 /s at Ladang Victoria and adversely impacted 45,000 people in Malaysia. A flood control remediation plan proposed a levee height based on a 50-year discharge of 1,815 m 3 /s obtained from hydrologic models. This design discharge falls outside the 95% confidence intervals of the flood frequency analysis based on field measurements. Instream sand and gravel mining operations also caused excessive riverbed degradation, which largely off sets apparent benefits for flood control. Pumping stations have been systematically required at irrigation canal intakes. Several bridge piers have also been severely undermined and emergency abutment protection works were needed in several places. Instream sand and gravel mining activities should be replaced with offstream mining in the future. DOI: 10.1061/ASCEHY.1943-7900.0000163 CE Database subject headings: Floods; Hydrologic models; Hydraulic engineering; Gravel; Mining; Malaysia. Author keywords: Flood mitigation; Flood control; Hydrologic models; Hydraulic engineering; Gravel mining.

Discharge estimation for equatorial natural rivers with overbank flow

Abstract The estimation of discharge capacity in river channels is complicated by variations in geometry and boundary roughness. Estimating flood flows is particularly difficult because of compound cross‐sectional geometries and because of the difficulties of flow gauging. Results are presented of a field study including the stage‐discharge relationships and surface roughness in term of the Darcy‐Weisbach friction factor, fa for several frequently flooded equatorial natural rivers. Equations are presented giving the apparent shear force acting on the vertical interface between the main channel and floodplain. The resulted apparent friction factor, fa is shown to increase rapidly for low relative depth. A method for predicting the discharge of overbank flow of natural rivers is then presented, by means of a composite friction, fc , which represents the actual resistance to flow due to the averaged boundary shear force and the apparent shear force. Equations are also presented giving the composite friction factor from easily calculated parameters for overbank flow of natural rivers. The results obtained using the methods proposed show that a significant improvement has been achieved compare to the discharge obtained using traditional methods, with an averaged error of 2.7%.

Appraisal of soft computing techniques in prediction of total bed material load in tropical rivers

This paper evaluates the performance of three soft computing techniques, namely Gene-Expression Programming (GEP) (Zakaria et al 2010), Feed Forward Neural Networks (FFNN) (Ab Ghani et al 2011), and Adaptive Neuro-Fuzzy Inference System (ANFIS) in the prediction of total bed material load for three Malaysian rivers namely Kurau, Langat and Muda. The results of present study are very promising: FFNN (R2 = 0.958, RMSE = 0.0698), ANFIS (R2 = 0.648, RMSE = 6.654), and GEP (R2 = 0.97, RMSE = 0.057), which support the use of these intelligent techniques in the prediction of sediment loads in tropical rivers.