Wavelet guided frequency-domain augmentation for robust time series forecasting

Time Series Forecasting (TSF) is essential across diverse domains, including finance, supply chain management, environmental monitoring, and healthcare, where reliable predictions support critical decision making. Despite recent progress in Deep Learning (DL) based forecasting, limited data availability and distributional variability often hinder model generalization. Data augmentation has emerged as an effective strategy to mitigate these challenges by increasing data diversity. Existing augmentation methods, such as frequency domain and wavelet based transformations, have shown effectiveness to some extent but struggle to maintain temporal coherence and consistency across varying prediction horizons. To address these limitations, this study proposes Wavelet-guided Frequency-based (WaveFreqAug), a novel hybrid augmentation method that integrates wavelet decomposition with adaptive frequency domain enhancement. The method operates on residual components to enrich spectral variability while preserving long-term temporal structures. Comprehensive experiments conducted on four benchmark datasets (ETTh1, ETTh2, ILI, and Weather) using six forecasting models demonstrate that WaveFreqAug outperforms both the unaugmented baseline, in which the same forecasting model is trained on the original data without any augmentation, and six State-of-the-Art (SOTA) augmentation methods applied to the same data, in the large majority of short- and long-term forecasting settings. These results highlight the robustness and generalizability of the proposed approach for improving deep learning based TSF.