A Validation Study of Time Series Data Forecasting Using Neural Networks

Artificial Intelligence(AI) is a growing topic in Computer Science and has many uses in real world applications. One application is using Al, or more specifically Neural Networks to model data and predict outcomes. Neural Networks have been used in the past to predict weather changes, create facial recognition software , and to create self-driving cars. Our project is a validation study of, “Modeling Time Series Data With Deep Fourier Neural Networks” by Gashler and Ashmore, 2016. Here we show that a neural network can be trained to be an effective predictor of weather patterns in Alaska over several years. Our data suggests that dynamic parameter tuning can be an effective method to train a neural network to fit time series data. Our validation study focused on the original data set used by Gashler and Ashmore, which was a five-year period beginning in April of 2009. We feel this validation study is a good place to begin work on Artificial Intelligence. We have published our code on a public SWOSU Github repository to enable other researchers to use our code as a starting point. As computing resources and programming environments continue to improve, the value of forecasting will continue to increase. One may see this research as a way to improve familiarity with tools related to forecasting