Prepared by the Water Supply Engineering Technical Committee of the Infrastructure Council of the Environmental and Water Resources Institute of ASCE. This report examines the application of artificial neural network (ANN) technology to water supply engineering problems. Although ANN has rarely been used in in this area, those who have done so report findings that were beyond the capability of traditional statistical and mathematical modeling tools. This report describes the availability of diverse applications, along with the basics of neural network modeling, and summarizes the experiences of groups of researchers around the world who successfully demonstrated significant benefits from using ANN technology in water supply engineering. Topics include: Forecasting salinity levels in River Murray, South Australia; Predicting gastroenteritis rates and waterborne outbreaks; Modeling pH levels in a eutrophic Middle Loire River, France; and ANNs as function approximation tools replacing rigorous mathematical simulation models for analyzing water distribution networks.

R. S. GOVINDARAJU and ARAMACHANDRA RAO School of Civil Engineering Purdue University West Lafayette, IN. , USA Background and Motivation The basic notion of artificial neural networks (ANNs), as we understand them today, was perhaps first formalized by McCulloch and Pitts (1943) in their model of an artificial neuron. Research in this field remained somewhat dormant in the early years, perhaps because of the limited capabilities of this method and because there was no clear indication of its potential uses. However, interest in this area picked up momentum in a dramatic fashion with the works of Hopfield (1982) and Rumelhart et al. (1986). Not only did these studies place artificial neural networks on a firmer mathematical footing, but also opened the dOOf to a host of potential applications for this computational tool. Consequently, neural network computing has progressed rapidly along all fronts: theoretical development of different learning algorithms, computing capabilities, and applications to diverse areas from neurophysiology to the stock market. . Initial studies on artificial neural networks were prompted by adesire to have computers mimic human learning. As a result, the jargon associated with the technical literature on this subject is replete with expressions such as excitation and inhibition of neurons, strength of synaptic connections, learning rates, training, and network experience. ANNs have also been referred to as neurocomputers by people who want to preserve this analogy.

The textbook explorers the intersection of artificial intelligence (AI) and machine learning (ML) within water supply distribution systems offer comprehensive insights into cutting-edge applications. Covering fundamental concepts, these texts delve into the intricacies of data collection, preprocessing, and modeling specific to water networks. By utilizing AI and ML algorithms, this book elucidate how to optimize system performance, addressing challenges such as pressure management and leak detection. Decision support systems powered by AI play a pivotal role in forecasting demands and efficiently managing distribution networks. Through engaging case studies, readers gain valuable perspectives on real-world implementations, fostering a deeper understanding of the transformative potential of AI and ML in enhancing water supply infrastructure.

Engineers have attempted to solve water resources engineering problems with the help of empirical, regression-based and numerical models. Empirical models are not universal, nor are regression-based models. The numerical models are, on the other hand, physics-based but require substantial data measurement and parameter estimation. Hence, there is a need to employ models that are robust, user-friendly, and practical and that do not have the shortcomings of the existing methods. Artificial intelligence methods meet this need. Soft Computing in Water Resources Engineering introduces the basics of artificial neural networks (ANN), fuzzy logic (FL) and genetic algorithms (GA). It gives details on the feed forward back propagation algorithm and also introduces neuro-fuzzy modelling to readers. Artificial intelligence method applications covered in the book include predicting and forecasting floods, predicting suspended sediment, predicting event-based flow hydrographs and sedimentographs, locating seepage path in an earth-fill dam body, and the predicting dispersion coefficient in natural channels. The author also provides an analysis comparing the artificial intelligence models and contemporary non-artificial intelligence methods (empirical, numerical, regression, etc.). The ANN, FL, and GA are fairly new methods in water resources engineering. The first publications appeared in the early 1990s and quite a few studies followed in the early 2000s. Although these methods are currently widely known in journal publications, they are still very new for many scientific readers and they are totally new for students, especially undergraduates. Numerical methods were first taught at the graduate level but are now taught at the undergraduate level. There are already a few graduate courses developed on AI methods in engineering and included in the graduate curriculum of some universities. It is expected that these courses, too, will soon be taught at the undergraduate levels.

Artificial Neural Networks for Engineering Applications presents current trends for the solution of complex engineering problems that cannot be solved through conventional methods. The proposed methodologies can be applied to modeling, pattern recognition, classification, forecasting, estimation, and more. Readers will find different methodologies to solve various problems, including complex nonlinear systems, cellular computational networks, waste water treatment, attack detection on cyber-physical systems, control of UAVs, biomechanical and biomedical systems, time series forecasting, biofuels, and more. Besides the real-time implementations, the book contains all the theory required to use the proposed methodologies for different applications. Presents the current trends for the solution of complex engineering problems that cannot be solved through conventional methods Includes real-life scenarios where a wide range of artificial neural network architectures can be used to solve the problems encountered in engineering Contains all the theory required to use the proposed methodologies for different applications

Engineers have attempted to solve water resources engineering problems with the help of empirical, regression-based and numerical models. Empirical models are not universal, nor are regression-based models. The numerical models are, on the other hand, physics-based but require substantial data measurement and parameter estimation. Hence, there is a need to employ models that are robust, user-friendly, and practical and that do not have the shortcomings of the existing methods. Artificial intelligence methods meet this need. Soft Computing in Water Resources Engineering introduces the basics of artificial neural networks (ANN), fuzzy logic (FL) and genetic algorithms (GA). It gives details on the feed forward back propagation algorithm and also introduces neuro-fuzzy modelling to readers. Artificial intelligence method applications covered in the book include predicting and forecasting floods, predicting suspended sediment, predicting event-based flow hydrographs and sedimentographs, locating seepage path in an earth-fill dam body, and the predicting dispersion coefficient in natural channels. The author also provides an analysis comparing the artificial intelligence models and contemporary non-artificial intelligence methods (empirical, numerical, regression, etc.). The ANN, FL, and GA are fairly new methods in water resources engineering. The first publications appeared in the early 1990s and quite a few studies followed in the early 2000s. Although these methods are currently widely known in journal publications, they are still very new for many scientific readers and they are totally new for students, especially undergraduates. Numerical methods were first taught at the graduate level but are now taught at the undergraduate level. There are already a few graduate courses developed on AI methods in engineering and included in the graduate curriculum of some universities. It is expected that these courses, too, will soon be taught at the undergraduate levels.

A new Bayesian framework for training and selecting the complexity of artificial neural networks (ANNs) is developed in this thesis, based on Markov chain Monte Carlo (MCMC) techniques. The primary motivation of the research presented is the incorporation of uncertainty into ANNs used for water resources modelling, with emphasis placed on obtaining accurate results, while maintaining simplicity of implementation, which is considered to be of utmost importance for adoption of the framework by practitioners in this field. The real-world case studies used in this research, which involve salinity forecasting in the River Murray at Murray Bridge, South Australia, and the forecasting of cyanobacteria (Anabaena spp.) in the River Murray at Morgan, South Australia, are used to demonstrate the practical value of the Bayesian framework, particularly when extrapolation is required and when the available data are of poor quality.