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

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.