A Multistep Direct and Indirect Strategy for Predicting Wind Direction Based on the EMD-LSTM Model

For the wind speed prediction, many researchers have established prediction models based on machine learning methods, statistical and theoretical that is, direct methods. However, method cannot be widely used in direction because has strong randomness uncertainty. In order to solve this problem, paper proposed a method, indirect method. Specifically, is decomposed into crosswind alongwind considering correlation between direction. The are predicted long short-term memory (LSTM) model with empirical mode decomposition (EMD), then, value can calculated, realized. One-month monitoring data collected by structural health (SHM) system installed investigated bridge employed demonstrate effectiveness of for forecasting