Asee peer logo

Predicting Primary Water Levels Using Back Propagation And General Regression Neural Networks

Download Paper |


2002 Annual Conference


Montreal, Canada

Publication Date

June 16, 2002

Start Date

June 16, 2002

End Date

June 19, 2002



Conference Session

Electrical and Computer Engineering Poster

Page Count


Page Numbers

7.929.1 - 7.929.10

Permanent URL

Download Count


Request a correction

Paper Authors

author page

Carlos Mendieta

author page

Carl Steidley

author page

Mario Garcia

Download Paper |

NOTE: The first page of text has been automatically extracted and included below in lieu of an abstract

Main Menu

Session 1532

Predicting Primary Water Levels Using Backpropagation and General Regression Neural Networks

Carlos Mendieta, Mario Garcia, Carl Steidley

Texas A&M University-Corpus Christi

Abstract This project applied two Artificial Neural Network models (Backpropagation and the General Regression Neural Network (GRNN)) to predict primary water levels at a single port on the Texas coast. The data for this project was provided by the Division of Nearshore Research and is collected hourly from several ports along the Texas coast. Important variables needed for making tide prediction were determined. The networks were then built, trained, and tested. The results obtained from each neural network are presented.

1.0 - Introduction

Tide prediction requires knowledge of a number of subjects. Oceanography, Meteorology, Mathematics, and Physics are a few of the major disciplines that are involved. Fortunately, applying Artificial Neural Networks (ANN) to the problem of tide prediction (or more specifically, primary water level prediction) reduces most of the work down to simple pattern recognition.

2.0 - Tidal Analysis

A study of tidal patterns and what affects them was needed to determine the ANN inputs 6. The primary tide generating forces are the gravitational pulls of celestial objects, namely the Sun and the Moon. Their movements cause large bodies of water to swell and recede according to their relative position to the earth and to each other. Though Newton’s Law of Gravitation does not directly describe this phenomenon, it can help explain it. Basically, the law states that the attraction between objects has a force proportional to their masses and inversely proportional to the square of the distances between the objects. Simply put, the closer the Sun or the Moon is to the earth, the greater the force of attraction. Now recall that one of the primary properties of any liquid is its viscosity. Ocean water has a very low resistance to flow. Tides are the direct response of the Sun and Moon's exertion of a force against the Earth's large bodies of water.

The Moon’s effects on the oceans are strongest at an interval of nearly two weeks. So, approximately twice a month, the Moon exerts the strongest gravitational pull on the Earth. Just after the full and new moon occur, tides generally have their greatest ranges from low to high water 1. The heights of those ranges are called spring tides while the lowest of the ranges are called neap tides. The figures 1 and 2 are helpful in visualizing the effects of the moon on the earth’s waters.

"Proceedings of the 2002 American Society for Engineering Education Annual Conference & Exposition Copyright © 2002, American Society for Engineering Education"

Main Menu

Mendieta, C., & Steidley, C., & Garcia, M. (2002, June), Predicting Primary Water Levels Using Back Propagation And General Regression Neural Networks Paper presented at 2002 Annual Conference, Montreal, Canada.

ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 2002 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference. - Last updated April 1, 2015