Wind speed prediction of unmanned sailboat based on CNN and LSTM hybrid neural network

Wind speed is a key factor for unmanned sailboats, and accurate prediction of wind speed is of great significance to the safety and performance of unmanned sailboats. In this study, a novel hybrid neural network scheme based on convolutional neural network (CNN) and long short-term memory (LSTM) is proposed for multi-step wind speed prediction. The scheme consists of two parts: a data processing module and a model module. We improved the grid search method to determine the selection of learning rate and input length hyperparameters. Simulations were performed on three different data sets and four types of other benchmark models were developed for comparison with the CNN-LSTM, such as recurrent neural network (RNN) and LSTM model, etc. The forecasts are evaluated by looking at the mean absolute error (MAE), root mean squared error (RMSE), correlation coefficient (CC) and R squared (R2). The evaluation metrics showed that the MAE and RMSE of CNN-LSTM are lower than the other benchmark models most of the time, while both CC and R2 are higher than the other models, which means the CNN-LSTM performs better accuracy and stability. It is accurate enough to provide a reliable wind input to the unmanned sailboat control system.