BACK-PROPAGATION NEURAL NETWORK IN TIDAL-LEVEL FORECASTING

Reliability of tidal-level forecasting is essential for structure installation and human activities in the marine environment. This paper reports an application of the artificial neural network with backpropagation procedures for accurate forecast of tidal-level variations. Unlike the conventional harmonic analysis, this neural network model forecasts the time series of tidal levels directly using a learning process based on a set of previous data. Two sets of field data with diurnal and semidiurnal tide, respectively, were used to test the performance of the neural network model. Results indicate that the hourly tidal levels over a long duration can be efficiently predicted using only a very short-term hourly tidal record.

  • Availability:
  • Supplemental Notes:
    • This work is based on the project "Utilization of Coastal Zone" supported by the National Science Council, Taiwan, under Grant No. NSC87-2611-E-005-004.
  • Corporate Authors:

    American Society of Civil Engineers

    1801 Alexander Bell Drive
    Reston, VA  United States  20191-4400
  • Authors:
    • Tsai, C-P
    • Lee, T-L
  • Publication Date: 1999-7

Language

  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 00766165
  • Record Type: Publication
  • Contract Numbers: NSC87-2611-E-005-004
  • Files: TRIS
  • Created Date: Jul 12 1999 12:00AM