SR-7/98-99 : Applications of artificial neural networks in surface water hydrology

Abstract

An Artificial Neural Network (ANN) is a computational method inspired by the studies of the brain and nervous system in biological organisms. ANN represent highly idealised mathematical models of our present understanding of such complex systems. One of the characteristics of the neural networks is their ability to learn. A neural network is not programmed like a conventional computer program, but is presented with examples of the patterns, observations and concepts, or any type of data which it is supposed to learn. Through the process of learning (also called training) the neural network organises itself to develop an internal set of features, that it uses to classify information or data. Due to its massively parallel processing architecture the ANN is capable of efficiently handling complex computations, thus making it the most preferred technique today for high speed processing of huge data. These characteristics render ANNs to be very suitable tools for handling various hydrological modelling problems. In surface water hydrology the possible usages of ANNs have only recently begun to be investigated.

This status report reviews some of the important applications of ANNs in surface water hydrology, highlighting their advantages and limitations. The review also covers the basic aspects of ANNs, i.e., various ANN architectures and various ANN learning algorithms.

This status report has been prepared by Smt. Archana Sarkar, Scientist 'B' under the guidance of Shri R.D. Singh, Scientist 'F' and Shri R. Mehrotra, Scientist 'E'.