Adaptive Temporal-Frequency Network for Time-Series Forecasting

A novel adaptive temporal-frequency network (ATFN), which is an end-to-end hybrid model incorporating deep learning networks and frequency patterns, is proposed for mid- and long-term time series forecasting. Within the framework of the ATFN, an augmented sequence to sequence model is used to learn the trend feature of complicated nonstationary time series, a frequency-domain block is used to capture dynamic and complicated periodic patterns of time series data, and a fully connected neural network is used to combine the trend and periodic features for producing a final forecast. An adaptive frequency mechanism consisting of phase adaption, frequency adaption, and amplitude adaption is designed for mapping the frequency spectrum of the current sliding window to that of the forecasting interval. The multilayer neural networks conduct a transformation similar to the inverse discrete Fourier transform for generating a periodic feature forecast. Synthetic data and real-world data with different periodic characteristics are used to evaluate the effectiveness of the proposed model. The experimental results indicate that the ATFN has promising performance and strong adaptability for long-term time-series forecasting.

Automated summary

This paper proposes a novel adaptive temporal-frequency network (ATFN) for mid- and long-term time series forecasting. The model combines deep learning networks and frequency patterns to learn the trend feature and capture dynamic periodic patterns of time series data. The experimental results demonstrate that the ATFN has promising performance and strong adaptability for long-term time-series forecasting.