Time-series forecasting with deep learning: a survey
By Bryan Lim, Stefan Zohren. Philosophical Transactions of the Royal Society A, 2020
2,001 citations recorded by the source corpus.
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’.
Subfields: Management Science and Operations Research, Signal Processing, Time-Series & Forecasting
View Paper: https://arxiv.org/abs/2004.13408
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Management Science and Operations Research
In Signal Processing
In Time-Series & Forecasting
Citations in the corpus
- SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction (2021, background): “With the increasing data availability and computing power in recent years, it is shown that deep learning-based TSF techniques have the potential to achieve better forecasting accuracy than conventional approaches [24, 29].”
- Transformers in Time Series: A Survey (2022, background): “[Lim et al. , 2021] uses an LSTM network to encode positional embeddings, which can better exploit sequential ordering information in time series.”
- A Time Series is Worth 64 Words: Long-term Forecasting with Transformers (2022, background): “With the rapid growth of deep learning models, the number of research works has increased significantly on this topic (Bryan & Stefan, 2021; Torres et al., 2021; Lara-Ben ´ ıtez et al., 2021).”
- A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection (2023, background): “The analysis of time series not only provides insights into past trends but also facilitates a multitude of tasks such as forecasting [4], classification [5], anomaly detection [6], and data imputation [7].”
- TSMixer: An all-MLP Architecture for Time Series Forecasting (2023, methodology): “…have been proposed due to their capacity to capture both complex temporal patterns and cross-variate dependencies (Gamboa, 2017; Li et al., 2019; Wen et al., 2017; Zhou et al., 2021; Wu et al., 2021; Lim & Zohren, 2021; Liu et al., 2022a; Zhou et al., 2022b; Liu et al., 2022b; Zhou et al., 2022a) .”
- TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis (2022, background): “Because of its immense practical value, time series analysis has received great interest (Lim & Zohren, 2021).”
- Data Augmentation techniques in time series domain: a survey and taxonomy (2022, methodology): “Previous works were centred on a specific model or approximation, with works such as [16, 21, 22].”
- ModernTCN: A Modern Pure Convolution Structure for General Time Series Analysis (2024, background): “Because of the immense practical value, the past few years have witnessed the rapid development in time series analysis(Wen et al., 2022; Lim & Zohren, 2021).”
- Frequency-domain MLPs are More Effective Learners in Time Series Forecasting (2023, background): “…short-term forecasting and 6 benchmarks for long-term forecasting, which demonstrate our consistent superiority compared with state-of-the-art methods. based methods have been widely used in time series forecasting due to their capability of extracting nonlinear and complex correlations [25, 26].”