Wind Speed Forecasting Using Recurrent Neural Networks and Long Short Term Memory

Abstract

Wind is a natural phenomenon that plays an essential role in various aspects of human life, including the spread of pests in plants. This variable is right for regions often hit by strong winds. The development of machine learning technology now makes predictions of wind speed to anticipate future impacts. This study proposes wind speed predictions using Recurrent Neural Network (RNN) with Long Short Term Memory (LSTM). The data used was obtained from the Nganjuk Meteorology and Geophysics Agency (BMKG), East Java from 2008 to 2017. The results showed that the use of the Adam model could provide 92.7% accuracy for training data and 91.6% for new data.