Comparison of Artificial Neural Network and Regression Models in the Prediction of Urban Stormwater Quality
Abstract:Urban stormwater quality is influenced by many interrelated processes. However, the site-specific nature of these complex processes makes stormwater quality difficult to predict using physically based process models. This has resulted in the need for more empirical techniques. In this study, artificial neural networks (ANN) were used to model urban stormwater quality. A total of 5 different constituents were analyzed—chemical oxygen demand, lead, suspended solids, total Kjeldahl nitrogen, and total phosphorus. Input variables were selected using stepwise linear regression models, calibrated on logarithmically transformed data. Artificial neural networks models were then developed and compared with the regression models. The results from the analyses indicate that multiple linear regression models were more applicable for predicting urban stormwater quality than ANN models.
Document Type: Research Article
Publication date: 2008-01-01
More about this publication?
- Water Environment Research (WER) is published monthly, including an annual Literature Review. A subscription to WER includes access to the latest content back to 1992, as well as access to fast track articles. An individual subscription is valid for 12 months from month of purchase.
Water Environment Research (WER) publishes peer-reviewed research papers, research notes, state-of-the-art and critical reviews on original, fundamental and applied research in all scientific and technical areas related to water quality, pollution control, and management. An annual Literature Review provides a review of published books and articles on water quality topics from the previous year. Published as: Sewage Works Journal, 1928 - 1949; Sewage and Industrial Wastes, 1950 - 1959; Journal Water Pollution Control Federation, 1959 - Oct 1989; Research Journal Water Pollution Control Federation, Nov 1989 - 1991; Water Environment Research, 1992 - present.
- Editorial Board
- Information for Authors
- Submit a Paper
- Subscribe to this Title
- Membership Information
- Information for Advertisers
- WEF Bookstore
- Ingenta Connect is not responsible for the content or availability of external websites