APPLICATION OF ARTIFICIAL NEURAL NETWORK FOR WATER QUALITY MANAGEMENT
I. Zaheer C.-G Bai · Lowland Technology International · 2003
A new artificial neural network based on decision-making approach for water quality management to control environmental pollution is presented. Previous research on water quality management problems has shown that traditional optimization techniques and an expert-system approach do not provide an educated solution comparing with decision making approach, which is related to the interpretation of data based on certain set of rules. Under such conditions, the Artificial Neural Network (ANN) learns the rule governing the decision-making through a series of experiments. In the present study, ANN was used to evaluate the relative effects of various pollution sources on the quality of river water. Using a back- propagation algorithm of a feed forward neural network, the relative effects of pollution sources were evaluated for strategic planning of water quality management. The case study for the Hanjiang River of China was selected to demonstrate the procedure and performance of a neural network-based approach for analysis and discussion. whose architecture and operation are inspired from our knowledge about biological neural cells (neurons) in the brain. A real neural network is a collection of neurons, the tiny cells that our brains are composed of. A network can consist of a few to a few billion neurons connected in an array of different methods. ANNs attempt to model these biological structures in terms of both their architecture and operation. Their function can be described either as mathematical computational models for non-linear function approximation, data classification, and clustering / non- parametric regression, or as a simulations of the behavior of a collection of model biological neurons in the human. Neural networks have provided a system that can reliably perform the decision-making in placing of the human brain and that can act as an alternative to expert systems for the few decades. In such a system, the rules governing the decision-making process related to data interpretation are learned either experimentally or by simulation using a complicated non-linear dynamic. The applications for