PM_2.5 prediction model based on multivariate feature and frequency information enhancement

In order to improve the prediction accuracy of PM<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</inf>, a combined prediction model based on empirical mode decomposition, temporal convolutional network and frequency-enhanced gated attention was proposed. The eigenmode function of PM<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</inf> time series is obtained by empirical mode decomposition, and the sample entropy is calculated to distinguish the components of high-frequency, medium-frequency and low-frequency components. The component components are fed into the temporal convolutional network together with other relevant meteorological data to capture the local characteristics and long-term dependencies of the time series. The discrete cosine transform is used to convert the time-domain features extracted by the temporal convolutional network into the frequency domain, and the importance of different frequency components is dynamically evaluated through the attention mechanism. The experimental results show that the EMD-TCN-FEGA combined model is superior to the traditional model in PM<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</inf> concentration prediction, and has higher accuracy and generalization ability.