Wind direction forecasting with artificial neural networks and support vector machines. (15th March 2015)

• Record Type: Journal Article
• Authors: Tagliaferri, F.; Viola, I.M.; Flay, R.G.J.
• Is Part Of: Ocean engineering. Volume 97(2015)
• Page Start: 65
• Page End: 73
• Publication Date: 2015-03-15
• Subjects: Wind forecast -- Support vector machines -- Artificial neural networks -- Sailing yacht -- Race -- Tactics; Ocean engineering -- Periodicals; Ocean engineering; Periodicals; 620.4162
• DOI: 10.1016/j.oceaneng.2014.12.026
• Languages: English
• ISSNs: 0029-8018

Abstract

Abstract: We propose two methods for short term forecasting of wind direction with the aim to provide input for tactic decisions during yacht races. The wind direction measured in the past minutes is used as input and the wind direction for the next two minutes constitutes the output. The two methods are based on artificial neural networks (ANN) and support vector machines (SVM), respectively. For both methods we optimise the length of the moving average that we use to pre-process the input data, the length of the input vector and, for the ANN only, the number of neurons of each layer. The forecast is evaluated by looking at the mean absolute error and at a mean effectiveness index, which assesses the percentage of times that the forecast is accurate enough to predict the correct tactical choice in a sailing yacht race. The ANN forecast based on the ensemble average of ten networks shows a larger mean absolute error and a similar mean effectiveness index than the SVM forecast. However, we showed that the ANN forecast accuracy increases significantly with the size of the ensemble. Therefore increasing the computational power, it can lead to a better forecast. Abstract : Author-Highlights: We propose a novel method for the forecast of the wind direction for yacht races. For the first time ANN and SVM are used for wind direction forecast. The effects of the key ANN and SVM parameters on the forecast accuracy are shown. We found that ANN can allow a more accurate forecast than SVM for yacht racing tactic but with higher computational requirements.