Multivariate long-term time series prediction based on the lifting wavelet transform
Chen Xu
Zhang Jianwei
Wang Shuyang
Jing Yongjun
Abstract：Objectives To address the challenge of effectively exploiting time-frequency information in multi-variate long-term time series prediction models,this study proposes a neural network model based on multi-level lifting wavelet transform(mLWTNet).Methods The proposed model first applies the lifting wavelet transform to decompose time series data from both time and frequency domains,followed by adaptive filter-ing of the resulting high-frequency subseries.Nonlinear features are extracted using an Elman neural net-work,while linear components are captured with an autoregressive integrated moving average(ARIMA)model.The outputs of the nonlinear and linear predictors are then fused through weighted integration to en-hance prediction accuracy.Results Experiments conducted on five publicly available real-world datasets demonstrate that mLWTNet achieves consistently superior performance—measured by mean squared error(MSE)and mean absolute error(MAE)—across various prediction horizons,outperforming five state-of-the-art models including FEDformer,InParformer,and WaveForM.On average,mLWTNet improves MSE and MAE by approximately 7.15%and 2.43%,respectively,compared with the second-best method.Con-clusions By leveraging lifting wavelet transform and hierarchical reconstruction-based prediction,the pro-posed model effectively utilizes the time-frequency characteristics of time series data,significantly improv-ing forecasting accuracy.
Keywords：long-term time series predictiontime series decompositionlifting wavelet transformadaptive filteringElman neural network
Publication Date：2025-07-31
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：8( 66-73 )