Riverflow/River Stage Prediction for Military Applications Using Artificial Neural Network Modeling

Abstract

Artificial Neural Networks (ANNs) were successfully applied to two different scale watershed systems for riverflow and stage prediction. It is a powerful and easy-to-use operational tool for addressing two of the most difficult temporal and spatial forecasting and prediction problems: nonlinearity and time-delay. In the lower portions of the Mississippi River, riverflow characteristics at Memphis, TN, can be predicted with a high degree of accuracy from two upstream gauges, even without rainfall data and tributary flow data. Less accurate results were obtained for the Sava River daily flow study, due mainly to the limited length of available data sets. The ANN model performance was excellent for 40 years monthly mean data set for the Sava River. With two upstream sets available, the model can accurately predict the downstream monthly flow. The study indicated that once a good data set is available, it can provide quick and accurate prediction for desired locations, such as the bridge site for military operation. The best performance of an ANN for flow prediction heavily depends on not only the length of the data sets but also whether the most significant patterns were included in the process.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 01, 2000
Accession Number
ADA382991

Entities

People

  • Bernard B. Hsieh
  • Charles L. Bartos

Organizations

  • Engineer Research and Development Center

Tags

Communities of Interest

  • Human Systems

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Artificial Intelligence Software
  • Cognitive Science
  • Computer Programming
  • Computer Programs
  • Computer Science
  • Computers
  • Data Sets
  • Drainage Basins
  • Information Science
  • Military Applications
  • Military Operations
  • Mississippi River
  • Neural Networks
  • Nonlinear Dynamics
  • Spreadsheet Software
  • United States

Readers

  • Computational Modeling and Simulation
  • Hydraulic Engineering.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks