Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences· 2021Q1· Review
Time-series forecasting with deep learning: a survey
- 1,668citations
- Q1SCImago
- 2021year
Short summary
This survey details deep learning architectures for time-series forecasting, covering encoder-decoder designs and hybrid models combining statistical and neural methods.
AI-generated from the title and abstract; the full text is not read.
Key points
- Surveys common encoder and decoder designs in deep learning for time-series forecasting.
- Explains how temporal information is incorporated into predictions by various models.
- Highlights recent developments in hybrid deep learning models combining statistical and neural approaches.
- Outlines deep learning's potential for decision support with time-series data.
AI-generated from the title and abstract; the full text is not read.
Abstract
Numerous deep learning architectures have been developed to accommodate the diversity of time-series datasets across different domains. In this article, we survey common encoder and decoder designs used in both one-step-ahead and multi-horizon time-series forecasting-describing how temporal information is incorporated into predictions by each model. Next, we highlight recent developments in hybrid deep learning models, which combine well-studied statistical models with neural network components to improve pure methods in either category. Lastly, we outline some ways in which deep learning can also facilitate decision support with time-series data. This article is part of the theme issue 'Machine learning for weather and climate modelling'.
The authors' abstract, as published at the source. Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences, 2021 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Signal Processing
Signal ProcessingComputer Science