Time-series forecasting with deep learning: a survey
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'.- Publication:
-
Philosophical Transactions of the Royal Society of London Series A
- Pub Date:
- April 2021
- DOI:
- 10.1098/rsta.2020.0209
- arXiv:
- arXiv:2004.13408
- Bibcode:
- 2021RSPTA.37900209L
- Keywords:
-
- Statistics - Machine Learning;
- Computer Science - Machine Learning
- E-Print:
- Philosophical Transactions of the Royal Society A 2020