Proceedings of the Technical Conference on the Use of Microprocessors and Microcomputers in Operational Hydrology, Geneva, 4-5 September 1984, organized by the World Meteorological Organization

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.

Africa, the cradle of many old civilizations, is the second largest world continent, and the homeland of nearly one-eighth of the world population. Despite Africa’s richness in natural resources, the average income per person, after excluding a few countries, is the lowest all over the world, and the percentage of inhabitants infected with contagious diseases is the highest. Development of Africa to help accommodate the ever-increasing population and secure a reasonable living standard to all inhabitants, though an enormous challenge is extremely necessary. Water is the artery of life, without it all living creatures on earth cannot survive. As such, a thorough knowledge of the meteorological and hydrological processes influencing the yield and quality of the water resources, surface and subsurface, and their distribution and variability in time and space is unavoidable for the overall development of any part of the world. It is highly probable that the said knowledge is at present a top priority to Africa, a continent that has been for so long-and probably still-devastated by the endless ambitions of colonial powers not to forget the corruption and destruction practiced by the internal powers, at least in some countries. The present book “Hydrology and Water Resources of Africa” is written with the aim of bringing together in one volume a fair amount of knowledge any professional involved in hydrology and water resources of Africa needs to know.

Since the pioneering work of Shannon in the late 1940's on the development of the theory of entropy and the landmark contributions of Jaynes a decade later leading to the development of the principle of maximum entropy (POME), the concept of entropy has been increasingly applied in a wide spectrum of areas, including chemistry, electronics and communications engineering, data acquisition and storage and retreival, data monitoring network design, ecology, economics, environmental engineering, earth sciences, fluid mechanics, genetics, geology, geomorphology, geophysics, geotechnical engineering, hydraulics, hydrology, image processing, management sciences, operations research, pattern recognition and identification, photogrammetry, psychology, physics and quantum mechanics, reliability analysis, reservoir engineering, statistical mechanics, thermodynamics, topology, transportation engineering, turbulence modeling, and so on. New areas finding application of entropy have since continued to unfold. The entropy concept is indeed versatile and its applicability widespread. In the area of hydrology and water resources, a range of applications of entropy have been reported during the past three decades or so. This book focuses on parameter estimation using entropy for a number of distributions frequently used in hydrology. In the entropy-based parameter estimation the distribution parameters are expressed in terms of the given information, called constraints. Thus, the method lends itself to a physical interpretation of the parameters. Because the information to be specified usually constitutes sufficient statistics for the distribution under consideration, the entropy method provides a quantitative way to express the information contained in the distribution.