Page Banner

United States Department of Agriculture

Agricultural Research Service

Title: Artificial Neural Networks in Hydrology Ii: Hydrologic Applications

Authors
item Govindaraju, R - PURDUE UNIV
item Rao, A - PURDUE UNIV
item Leib, David - KANSAS WATER OFFICE
item Najjar, Y - KANSAS WATER OFFICE
item Gupta, H - UNIV OF ARIZONA
item Hjelmfelt Jr, Allen

Submitted to: Journal Hydrologic Engineering
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: August 20, 1999
Publication Date: N/A

Interpretive Summary: In this second part of the final report of the American Society of Civil Engineers Task Committee on Application of Artificial Neural Networks in Hydrology the applications are described. These applications include rainfall, runoff modeling, streamflow prediction, precipitation forecasting, and reservoir operations. The task committee warns that the physics is locked up in the set of optimal weights and threshold values and is not revealed back to the user after training. Therefore, artificial neural networks cannot be considered a panacea for hydrologic problems, nor can they be viewed as replacements for other modeling techniques. This research will be of benefit to water resources engineers who will use it in analysis of the effects of improved practices on watershed responses to rainfall events.

Technical Abstract: This paper forms the second part of the series on application of artificial neural networks (ANNs) in hydrology. The role of ANN's in various branches of hydrology has been examined here. It is found that ANN's are robust tools for modeling many of the nonlinear hydrologic processes such as rainfall-runoff, stream flow, ground-water management, water quality simulation, and precipitation. After appropriate training, they are able to generate satisfactory results for many prediction problems in hydrology. A good physical understanding of the hydrologic process being modeled can help in selecting the input vector and designing a more efficient network. However, artificial neural networks tend to be very data intensive, and there appears to be no established methodology for design and successful implementation. For this emerging technique to find application in engineering practice, there are still some questions about this technique that must be further studied, and important aspects such as physical interpretation of ANN architecture, optimal training data set, adaptive learning, and extrapolation must be explored further. The merits and limitations of ANN applications have been discussed, and potential research avenues have been explored briefly.

Last Modified: 10/1/2014
Footer Content Back to Top of Page