EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Hybrid Framework Integrating Traditional Models and Deep Learning for Multi-Scale Time Series Forecasting

Zihan Liu iD, Zijia Zhang, Weizhe Zhang

Entropy · 28.06.2025 · 27 (7) · 695

DOI: 10.3390/e27070695 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 28.06.2025. Verfasst von Zihan Liu und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Automation, Nanjing University of Information Science and Technology, 219 Ningliu Road, Nanjing 210044, China. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Time series forecasting is critical for decision-making in numerous domains, yet achieving high accuracy across both short-term and long-term horizons remains challenging. In this paper, we propose a general hybrid forecasting framework that integrates a traditional statistical model (ARIMA) with modern deep learning models (such as LSTM and Transformer). The core of our approach is a novel multi-scale prediction mechanism that combines the strengths of both model types to better capture short-range patterns and long-range dependencies. We design a dual-stage forecasting process, where a classical time series component first models transparent linear trends and seasonal patterns, and a deep neural network then learns complex nonlinear residuals and long-term contexts. The two outputs are fused through an adaptive mechanism to produce the final prediction. We evaluate the proposed framework on eight public datasets (electricity, exchange rate, weather, traffic, illness, ETTh1/2, and ETTm1/2) covering diverse domains and scales. The experimental results show that our hybrid method consistently outperforms stand-alone models (ARIMA, LSTM, and Transformer) and recent, specialized forecasters (Informer and Autoformer) in both short-horizon and long-horizon forecasts. An ablation study further demonstrates the contribution of each module in the framework. The proposed approach not only achieves state-of-the-art accuracy across varied time series but also offers improved interpretability and robustness, suggesting a promising direction for combining statistical and deep learning techniques in time series forecasting.

Schlagwörter

Stichwörter der Autor:innen

hybrid time series forecastingmulti-scale prediction mechanismstatistical–deep learning integration

Autor:innen und Institutionen

  • School of Automation, Nanjing University of Information Science and Technology, 219 Ningliu Road, Nanjing 210044, China.

ORCID-Profile: Zihan Liu

Zitieren

APA

Liu, Z., Zhang, Z., & Zhang, W. (2025). A Hybrid Framework Integrating Traditional Models and Deep Learning for Multi-Scale Time Series Forecasting. Entropy, 27(7), 695. https://doi.org/10.3390/e27070695

Vancouver

Liu Z, Zhang Z, Zhang W. A Hybrid Framework Integrating Traditional Models and Deep Learning for Multi-Scale Time Series Forecasting. Entropy. 2025;27(7):695. doi:10.3390/e27070695

BibTeX
@article{Liu2025,
  author = {Liu, Zihan and Zhang, Zijia and Zhang, Weizhe},
  title = {A Hybrid Framework Integrating Traditional Models and Deep Learning for Multi-Scale Time Series Forecasting},
  journal = {Entropy},
  year = {2025},
  volume = {27},
  number = {7},
  pages = {695},
  doi = {10.3390/e27070695}
}
Kostenlos starten →