Design flood estimates have traditionally been based on records of past events. However, there is a need for a method of estimating peak flows without these records. The Estimated Parameter Flood Forecasting Model (EPFFM) has been developed to provide such a method for small water resource projects based on a 200 year or less design flood. This "user friendly" computer model calculates the expected peak flow and its standard deviation from low, probable, and high estimates of thirteen user supplied parameters. These parameters describe physical characteristics of the drainage basin, infiltration rates, and rainstorm characteristics. The standard deviation provides a measure of reliability and is used to produce an 80% confidence interval on peak flows. The thesis briefly reviews existing flow estimation techniques and then describes the development of EPFFM. This includes descriptions of the Chicago method of rainfall hyetograph synthesis, Horton's infiltration equation, inflow by time-area method, Muskingum routing equation, and an approximate method of estimating the variance of multivariate equations since these are all used by EPFFM to model the physical and mathematical processes involved. Two examples are included to demonstrate EPFFM's ability to estimate a confidence interval, and compare these with recorded peak flows. / Applied Science, Faculty of / Civil Engineering, Department of / Graduate

system model and computational methodology have been developed which evaluate the worth of flood forecast - response systems in reducing the economic damage caused by floods. The efficiencies of the forecast system, the response system, and the overall system may be individually obtained and compared. In this report the case study of Milton, Pennsylvania, was extended and further case studies were performed including a large residential section of Victoria, Texas, and all the residences in Columbus, Mississippi. These locations show better forecast and response efficiencies than obtained for Milton, Pennsylvania. The difference is attributed to longer forecast lead times at Columbus and Victoria. Sensitivity analyses were run at all three locations. These show the effects of many system factors, such as the time required to produce, disseminate and respond to a forecast, on the efficiency of the system. The forecast efficiency improves significantly as these times are reduced. Further analysis of the response system based on human factors involved has led to the development of a simulation model of the process by which the floodplain dweller determines the appropriate response to a flood warning. Investigation of ways to extend the methodology to evaluate regions lacking the detailed data used for the case studies has indicated more problems than answers. Extrapolation based on overall system efficiency related to published regional and national flood damage estimates was used to provide an approximate value of the flood forecast - response system for two regions and for the nation.A listing of simplicities and approximations which make computations tractable but which may affect accuracy is given. Finally, an evaluation of the work accomplished for this project and suggestions for the constructive use of the flood forecast -response system model and computational procedures is given.

Note:

M.Ing. (Electrical and Electronic Engineering Science) / Scientific workflows (SWFs) and artificial neural networks (ANNs) have attracted the attention of researchers in many fields and have been used to solve a variety of problems. Examples of these are (a) the use of scientific workflows for the sensor web in the hydrology domain and (b), the use of ANNs for the prediction of a number of water resource variables such as rainfall, flow, water level and various other water quality variables. ANNs have proved to be a powerful tool for prediction when compared with statistical methods. The aims of this research are to develop ANNs that act as predictive models for water resources and to deploy these models as predictive tools in a scientific workflow environment. While there are guidelines in the literature relating to the factors affecting network performance, there is no standard approach that is universally accepted for determining the optimum architecture of a neural network for a given problem. The parameters of a neural network and for the learning algorithm have a major effect on the performance of the neural network. We consider various recurrent and feed-forward neural network architectures for predicting changes in the water levels of dams. We explore various' hidden layer dimensions in learning the characteristics of the training data using the back propagation learning algorithm. Trained networks are deployed as predictive model in a scientific workflows environment called VisTrails. ': We review and discuss the use of SWFs and ANNs in the hydrology domain with emphasis on the development of neural network architecture that will give the best predictions for water resources. A number of architectures are employed to examine the best accurate predictive network for historical rainfall data. The findings of training experiments are promising in terms of the use of ANNs as a water resources predictive tool. Experimental results showed how the architecture of a neural network impacts on its predictive performance. This study shows that the number of hidden nodes is important factor for the improvement of the quality of the predictions.

published_or_final_version / Civil Engineering / Master / Master of Philosophy

No description available.

No description available.

No description available.

M.Comm. / The availability of large amounts of information and increases in computing power have facilitated the use of more sophisticated and effective technologies to analyse financial markets. The use of neural networks for financial time series forecasting has recently received increased attention. Neural networks are good at pattern recognition, generalisation and trend prediction. They can learn to predict next week's Dow Jones or flaws in concrete. Traditional methods used to analyse financial markets include technical and fundamental analysis. These methods have inherent shortcomings, which include bad timing of trading signals generated, and non-continuous data on which analysis is based. The purpose of the study was to create a tool with which to forecast financial time series on the Johannesburg Stock Exchange (JSE). The forecasted time series information was used to generate trading signals. A study of the building blocks of neural networks was done before the neural network was designed. The design of the neural network included data choice, data collection, calculations, data pre-processing and the determination of neural network parameters. The neural network was trained and tested with information from the financial sector of the JSE. The neural network was trained to predict share prices 4 days in advance with a Multiple Layer Feedforward Network (MLFN). The mean square error on the test set was 0.000930, with all test data values scaled between 0.1 - 0.9 and a sample size of 160. The prediction results were tested with a trading system, which generated a trade yielding 20 % return in 22 days. The neural network generated excellent results by predicting prices in advance. This enables better timing of trades and efficient use of capital. However, it was found that the price movement on the test set within the 4-day prediction period seldom exceeded the cost of trades, resulting in only one trade over a 5-month period for one security. This should not be a problem if all securities on the JSE are analysed for profitable trades. An additional neural network could also be designed to predict price movements further ahead, say 8 days, to assist the 4-day prediction

No description available.