Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 263

The DOI matches its Crossref record; 136 of the 136 references it cites were found in a registry or an index.

A comprehensive survey of deep learning for time series forecasting: architectural diversity and open challenges

Open access
Kim, Jongseon, Kim, Hyungjoon, Kim, HyunGi, Lee, Dongjun, Yoon, Sungroh·2025·Artificial Intelligence Review

Abstract

Time series forecasting is a critical task that provides key information for decision-making across various fields, such as economic planning, supply chain management, and medical diagnosis. After the use of traditional statistical methodologies and machine learning in the past, various fundamental deep learning architectures such as MLPs, CNNs, RNNs, and GNNs have been developed and applied to solve time series forecasting problems. However, the structural limitations caused by the inductive biases of each deep learning architecture constrained their performance. Transformer models, which excel at handling long-term dependencies, have become significant architectural components for time series forecasting. However, recent research has shown that alternatives such as simple linear layers can outperform Transformers. These findings have opened up new possibilities for using diverse architectures, ranging from fundamental deep learning models to emerging architectures and hybrid approaches. In this context of exploration into various models, the architectural modeling of time series forecasting has now entered a renaissance. This survey not only provides a historical context for time series forecasting but also offers comprehensive and timely analysis of the movement toward architectural diversification. By comparing and re-examining various deep learning models, we uncover new perspectives and present the latest trends in time series forecasting, including the emergence of hybrid models, diffusion models, Mamba models, and foundation models. By focusing on the inherent characteristics of time series data, we also address open challenges that have gained attention in time series forecasting, such as channel dependency, distribution shift, causality, and feature extraction. This survey explores vital elements that can enhance forecasting performance through diverse approaches. These contributions help lower entry barriers for newcomers by providing a systematic understanding of the diverse research areas in time series forecasting (TSF), while offering seasoned researchers broader perspectives and new opportunities through in-depth exploration of TSF challenges.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/s10462-025-11223-9

Cites

136 of 136 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 136 references

Research works printed but not linked: 157

  1. Achiam J, Adler S, Agarwal S, et al (2023) Gpt-4 technical report. Preprint at arXiv:2303.08774 · arXiv
  2. Ahmed DM, Hassan MM, Mstafa RJ (2022) A review on deep sequential models for forecasting time series data. Appl Comput Intell Soft Comput 1:6596397
  3. Alcaraz JL, Strodthoff N (2023) Diffusion-based time series imputation and forecasting with structured state space models. Transactions on Machine Learning Research https://openreview.net/forum?id=hHiIbk7ApW
  4. Ansari AF, Stella L, Turkmen AC, et al (2024) Chronos: Learning the language of time series. Transactions on Machine Learning Research https://openreview.net/forum?id=gerNCVqqtR, Expert Certification
  5. Bai S, Kolter JZ, Koltun V (2018) An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. Preprint at arXiv:1803.01271 · arXiv
  6. Barlin JN, Zhou Q, Clair CMS et al (2013) Classification and regression tree (cart) analysis of endometrial carcinoma: seeing the forest for the trees. Gynecol Oncol 130(3):452–456 · doi:10.1016/j.ygyno.2013.06.009
  7. Behrouz A, Santacatterina M, Zabih R (2024) Chimera: Effectively modeling multivariate time series with 2-dimensional state space models. In: The Thirty-eighth Annual Conference on Neural Information Processing Systems, https://openreview.net/forum?id=ncYGjx2vnE
  8. Beltagy I, Peters ME, Cohan A (2020) Longformer: The long-document transformer. Preprint at arXiv:2004.05150 · arXiv
  9. Bergsma S, Zeyl T, Guo L (2023) Sutranets: sub-series autoregressive networks for long-sequence, probabilistic forecasting. Adv Neural Inf Process Syst 36:30518–30533
  10. Box GE, Jenkins GM, Reinsel G et al (1970) Forecasting and control. Time Series. Analysis 3(75):1970
  11. Breiman L (1996) Bagging predictors. Mach Learning 24:123–140
  12. Brown T, Mann B, Ryder N et al (2020) Language models are few-shot learners. Adv Neural Inf Process Syst 33:1877–1901
  13. Cai W, Wang K, Wu H, et al (2024b) Forecastgrapher: Redefining multivariate time series forecasting with graph neural networks. Preprint at arXiv:2405.18036 · arXiv
  14. Cai X, Zhu Y, Wang X, et al (2024c) Mambats: Improved selective state space models for long-term time series forecasting. Preprint at arXiv:2405.16440 · arXiv
  15. Chang S, Zhang Y, Han W, et al (2017) Dilated recurrent neural networks. Adv Neural Inform Process Syst 30
  16. Chen Z, Ma M, Li T et al (2023) Long sequence time-series forecasting with deep learning: a survey. Inform Fusion 97:101819
  17. Chen K, Chen G, Xu D, et al (2021a) Nast: Non-autoregressive spatial-temporal transformer for time series forecasting. Preprint at arXiv:2102.05624 · arXiv
  18. Cheng X, Chen X, Li S, et al (2024c) Leveraging 2D information for long-term time series forecasting with vanilla transformers. Preprint at arXiv:2405.13810 · arXiv
  19. Cheng M, Yang J, Pan T, et al (2024b) Convtimenet: A deep hierarchical fully convolutional model for multivariate time series analysis. Preprint at arXiv:2403.01493 · arXiv
  20. Chen J, Lenssen JE, Feng A, et al (2024a) From similarity to superiority: Channel clustering for time series forecasting. In: The Thirty-eighth Annual Conference on Neural Information Processing Systems, https://openreview.net/forum?id=MDgn9aazo0
  21. Chen X, Li X, Liu B, et al (2024c) Biased temporal convolution graph network for time series forecasting with missing values. In: The Twelfth International Conference on Learning Representations
  22. Chen Y, Ren K, Wang Y, et al (2024d) Contiformer: Continuous-time transformer for irregular time series modeling. Adv Neural Inform Process Syst 36
  23. Chen P, ZHANG Y, Cheng Y, et al (2024b) Pathformer: Multi-scale transformers with adaptive pathways for time series forecasting. In: The Twelfth International Conference on Learning Representations, https://openreview.net/forum?id=lJkOCMP2aW
  24. Chicco D, Warrens MJ, Jurman G (2021) The coefficient of determination r-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. Peer J Comput Sci 7:e623
  25. Clark K, Luong MT, Le QV, et al (2020) Electra: Pre-training text encoders as discriminators rather than generators. In: International Conference on Learning Representations, https://openreview.net/forum?id=r1xMH1BtvB
  26. Crabbé J, Huynh N, Stanczuk JP, et al (2024) Time series diffusion in the frequency domain. In: Forty-first International Conference on Machine Learning, https://openreview.net/forum?id=W9GaJUVLCT
  27. Cryer JD (1986) Time series analysis, vol 286. Duxbury Press Boston
  28. Das A, Kong W, Sen R, et al (2024) A decoder-only foundation model for time-series forecasting. In: Forty-first International Conference on Machine Learning, https://openreview.net/forum?id=jn2iTJas6h
  29. Dimri T, Ahmad S, Sharif M (2020) Time series analysis of climate variables using seasonal ARIMA approach. J Earth Syst Sci 129:1–16 · doi:10.1007/s12040-020-01408-x
  30. Dosovitskiy A, Beyer L, Kolesnikov A, et al (2021) An image is worth 16x16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations, https://openreview.net/forum?id=YicbFdNTTy
  31. Dubey A, Jauhri A, Pandey A, et al (2024) The llama 3 herd of models. Preprint at arXiv:2407.21783 · arXiv
  32. Dudek G (2024) Stacking for probabilistic short-term load forecasting. In: International Conference on Computational Science, Springer, pp 3–18 · doi:10.1007/978-3-031-63751-3_1
  33. Ekambaram V, Jati A, Dayama P, et al (2024) Tiny time mixers (ttms): Fast pre-trained models for enhanced zero/few-shot forecasting of multivariate time series. CoRR
  34. Eldele E, Ragab M, Chen Z, et al (2024) Tslanet: Rethinking transformers for time series representation learning. International Conference on Machine Learning
  35. Fan X, Wu Y, Xu C, et al (2024b) MG-TSD: Multi-granularity time series diffusion models with guided learning process. In: The Twelfth International Conference on Learning Representations, https://openreview.net/forum?id=CZiY6OLktd
  36. Fan W, Yi K, Ye H, et al (2024a) Deep frequency derivative learning for non-stationary time series forecasting. IJCAI · doi:10.24963/ijcai.2024/436
  37. Feng R, Chen M, Song Y (2024) Learning traffic as videos: short-term traffic flow prediction using mixed-pointwise convolution and channel attention mechanism. Expert Syst Appl 240:122468
  38. García MV, Aznarte JL (2020) Shapley additive explanations for no2 forecasting. Eco Inform 56:101039
  39. Godahewa RW, Bergmeir C, Webb GI, et al (2021l) Monash time series forecasting archive. In: Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2), https://openreview.net/forum?id=wEc1mgAjU-
  40. Gong Z, Tang Y, Liang J (2023) Patchmixer: A patch-mixing architecture for long-term time series forecasting. Preprint at arXiv:2310.00655 · arXiv
  41. Gruver N, Finzi MA, Qiu S, et al (2023) Large language models are zero-shot time series forecasters. In: Thirty-seventh Conference on Neural Information Processing Systems, https://openreview.net/forum?id=md68e8iZK1
  42. Gu A, Johnson I, Goel K et al (2021) Combining recurrent, convolutional, and continuous-time models with linear state space layers. Adv Neural Inf Process Syst 34:572–585
  43. Gu A, Dao T (2024) Mamba: Linear-time sequence modeling with selective state spaces. In: First Conference on Language Modeling, https://openreview.net/forum?id=tEYskw1VY2
  44. Gu A, Goel K, Re C (2022) Efficiently modeling long sequences with structured state spaces. In: International Conference on Learning Representations, https://openreview.net/forum?id=uYLFoz1vlAC
  45. Han H, Park S, Min S et al (2023) Improving generalization performance of electrocardiogram classification models. Physiol Meas 44(5):054003
  46. Han L, Chen XY, Ye HJ, et al (2024) SOFTS: Efficient multivariate time series forecasting with series-core fusion. In: The Thirty-eighth Annual Conference on Neural Information Processing Systems, https://openreview.net/forum?id=89AUi5L1uA
  47. Hasson H, Maddix DC, Wang B, et al (2023) Theoretical guarantees of learning ensembling strategies with applications to time series forecasting. In: International Conference on Machine Learning, PMLR, pp 12616–12632
  48. Ho J, Jain A, Abbeel P (2020) Denoising diffusion probabilistic models. Adv Neural Inf Process Syst 33:6840–6851
  49. Hounie I, Porras-Valenzuela J, Ribeiro A (2024) Transformers with loss shaping constraints for long-term time series forecasting. In: Forty-first International Conference on Machine Learning
  50. Hou H, Yu FR (2024) Rwkv-ts: Beyond traditional recurrent neural network for time series tasks. Preprint at arXiv:2401.09093 · arXiv
  51. Huang S, Liu Y, Zhang F et al (2024) Crosswavenet: a dual-channel network with deep cross-decomposition for long-term time series forecasting. Expert Syst Appl 238:121642
  52. Hu Y, Liu P, Zhu P, et al (2024b) Adaptive multi-scale decomposition framework for time series forecasting. CoRR abs/2406.03751. https://doi.org/10.48550/arXiv.2406.03751 · arXiv · doi:10.48550/arxiv.2406.03751
  53. Ilbert R, Odonnat A, Feofanov V, et al (2024) SAMformer: Unlocking the potential of transformers in time series forecasting with sharpness-aware minimization and channel-wise attention. In: Salakhutdinov R, Kolter Z, Heller K, et al (eds) Proceedings of the 41st International Conference on Machine Learning, Proceedings of Machine Learning Research, vol 235. PMLR, pp 20924–20954, https://proceedings.mlr.press/v235/ilbert24a.html
  54. Ioffe S, Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning, pmlr, pp 448–456
  55. Jia Y, Lin Y, Hao X, et al (2024) Witran: Water-wave information transmission and recurrent acceleration network for long-range time series forecasting. Adv Neural Inform Process Syst 36
  56. Jin M, Wang S, Ma L, et al (2024) Time-LLM: Time series forecasting by reprogramming large language models. In: International Conference on Learning Representations (ICLR)
  57. Jin M, Wen Q, Liang Y, et al (2023) Large models for time series and Spatio-temporal data: a survey and outlook. Preprint at arXiv:2310.10196 · arXiv
  58. Kang BG, Lee D, Kim H, et al (2024) Introducing spectral attention for long-range dependency in time series forecasting. Adv Neural Inform Process Syst
  59. Ke G, Meng Q, Finley T, et al (2017) LIGHTGBM: A highly efficient gradient boosting decision tree. Adv Neural Inform Process Syst 30
  60. Kim D, Baek JG (2022) Bagging ensemble-based novel data generation method for univariate time series forecasting. Expert Syst Appl 203:117366
  61. Kim T, Kim J, Tae Y, et al (2021) Reversible instance normalization for accurate time-series forecasting against distribution shift. In: International Conference on Learning Representations
  62. Kim D, Park J, Lee J, et al (2024) Are self-attentions effective for time series forecasting? In: The Thirty-eighth Annual Conference on Neural Information Processing Systems, https://openreview.net/forum?id=iN43sJoib7
  63. Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations, https://openreview.net/forum?id=SJU4ayYgl
  64. Kitaev N, Kaiser L, Levskaya A (2020) Reformer: The efficient transformer. In: International Conference on Learning Representations, https://openreview.net/forum?id=rkgNKkHtvB
  65. Kollovieh M, Ansari AF, Bohlke-Schneider M, et al (2024) Predict, refine, synthesize: Self-guiding diffusion models for probabilistic time series forecasting. Adv Neural Inform Process Syst 36
  66. Kong Z, Ping W, Huang J, et al (2021) Diffwave: A versatile diffusion model for audio synthesis. In: International Conference on Learning Representations, https://openreview.net/forum?id=a-xFK8Ymz5J
  67. Liang A, Jiang X, Sun Y, et al (2024a) Bi-mamba4ts: Bidirectional mamba for time series forecasting. Preprint at arXiv:2404.15772 · arXiv
  68. Liang D, Zhang H, Yuan D, et al (2024b) Minusformer: Improving time series forecasting by progressively learning residuals. Preprint at arXiv:2402.02332 · arXiv
  69. Li Y, Chen W, Hu X, et al (2024b) Transformer-modulated diffusion models for probabilistic multivariate time series forecasting. In: The Twelfth International Conference on Learning Representations, https://openreview.net/forum?id=qae04YACHs
  70. Li S, Jin X, Xuan Y, et al (2019) Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting. Adv Neural Inform Process Syst 32
  71. Li J, Li D, Savarese S, et al (2023) Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In: International conference on machine learning, PMLR, pp 19730–19742
  72. Lin K, Huang C (2022) Ensemble learning applications in multiple industries: a review. Inf Dyn Appl 1(1):44–58
  73. Lin S, Lin W, Wu W, et al (2024c) PETformer: Long-term time series forecasting via placeholder-enhanced transformer. https://openreview.net/forum?id=u3RJbzzBZj
  74. Li Z, Qin Y, Cheng X, et al (2024d) Ftmixer: Frequency and time domain representations fusion for time series modeling. Preprint at arXiv:2405.15256 · arXiv
  75. Liu Y, Wu H, Wang J et al (2022) Non-stationary transformers: exploring the stationarity in time series forecasting. Adv Neural Inf Process Syst 35:9881–9893
  76. Liu Z, Cheng M, Li Z, et al (2024e) Adaptive normalization for non-stationary time series forecasting: a temporal slice perspective. Adv Neural Inform Process Syst 36
  77. Liu Y, Hu T, Zhang H, et al (2024c) itransformer: Inverted transformers are effective for time series forecasting. In: The Twelfth International Conference on Learning Representations, https://openreview.net/forum?id=JePfAI8fah
  78. Liu J, Liu C, Woo G, et al (2024b) Unitst: Effectively modeling inter-series and intra-series dependencies for multivariate time series forecasting. Preprint at arXiv:2406.04975 · arXiv
  79. Liu Y, Li C, Wang J, et al (2024d) Koopa: Learning non-stationary time series dynamics with Koopman predictors. Adv Neural Inform Process Syst 36
  80. Liu H, Li C, Wu Q, et al (2024a) Visual instruction tuning. Adv Neural Inform Process Syst 36
  81. Liu S, Yu H, Liao C, et al (2021a) Pyraformer: Low-complexity pyramidal attention for long-range time series modeling and forecasting. In: International conference on learning representations
  82. Li Y, Yu R, Shahabi C, et al (2018) Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. In: International Conference on Learning Representations, https://openreview.net/forum?id=SJiHXGWAZ
  83. Lundberg SM, Lee SI (2017) A unified approach to interpreting model predictions. In: Guyon I, Luxburg UV, Bengio S, et al (eds) Advances in Neural Information Processing Systems, vol 30. Curran Associates, Inc., https://proceedings.neurips.cc/paper_files/paper/2017/file/8a20a8621978632d76c43dfd28b67767-Paper.pdf
  84. Luo D, Wang X (2024) Moderntcn: A modern pure convolution structure for general time series analysis. In: The Twelfth International Conference on Learning Representations
  85. McCracken MW, Ng S (2016) FRED-MD: a monthly database for macroeconomic research. J Business Econom Stat 34(4):574–589 · doi:10.1080/07350015.2015.1086655
  86. McLeod A, Gweon H (2013) Optimal deseasonalization for monthly and daily geophysical time series. J Environ Stat 4(11):1–11
  87. Meijer C, Chen LY (2024) The rise of diffusion models in time-series forecasting. Preprint at arXiv:2401.03006 · arXiv
  88. Nie Y, Nguyen NH, Sinthong P, et al (2023) A time series is worth 64 words: Long-term forecasting with transformers. In: The Eleventh International Conference on Learning Representations, https://openreview.net/forum?id=Jbdc0vTOcol
  89. Ni Z, Yu H, Liu S, et al (2024) Basisformer: Attention-based time series forecasting with learnable and interpretable basis. Adv Neural Inform Process Syst 36
  90. Oord Avd, Li Y, Vinyals O (2018) Representation learning with contrastive predictive coding. Preprint at arXiv:1807.03748 · arXiv
  91. Oreshkin BN, Carpov D, Chapados N, et al (2020) N-beats: Neural basis expansion analysis for interpretable time series forecasting. In: International Conference on Learning Representations, https://openreview.net/forum?id=r1ecqn4YwB
  92. Patro BN, Agneeswaran VS (2024a) Mamba-360: Survey of state space models as transformer alternative for long sequence modelling: Methods, applications, and challenges. Preprint at arXiv:2404.16112 · arXiv · doi:10.2139/ssrn.4930035
  93. Patro BN, Agneeswaran VS (2024b) Simba: Simplified mamba-based architecture for vision and multivariate time series. Preprint at arXiv:2403.15360 · arXiv
  94. Pearl J et al (2000) Models, reasoning and inference, vol 19. Cambridge University Press, Cambridge, p 3
  95. Qi S, Wen L, Li Y, et al (2024) Enhancing multivariate time series forecasting with mutual information-driven cross-variable and temporal modeling. Preprint at arXiv:2403.00869 · arXiv
  96. Quinlan JR (1986) Induction of decision trees. Mach learning 1:81–106
  97. Radford A, Kim JW, Hallacy C, et al (2021) Learning transferable visual models from natural language supervision. In: International conference on machine learning, PMLR, pp 8748–8763
  98. Ramesh A, Dhariwal P, Nichol A, et al (2022) Hierarchical text-conditional image generation with clip latent. Preprint at arXiv:2204.06125 1(2):3 · arXiv
  99. Rasul K, Ashok A, Williams AR, et al (2024) Lag-llama: Towards foundation models for probabilistic time series forecasting. Preprint at arXiv:2310.08278 · arXiv
  100. Rasul K, Seward C, Schuster I, et al (2021) Autoregressive denoising diffusion models for multivariate probabilistic time series forecasting. In: International Conference on Machine Learning, PMLR, pp 8857–8868
  101. Rossi E, Chamberlain B, Frasca F, et al (2020) Temporal graph networks for deep learning on dynamic graphs. In: ICML 2020 Workshop on Graph Representation Learning
  102. Saharia C, Chan W, Saxena S et al (2022) Photorealistic text-to-image diffusion models with deep language understanding. Adv Neural Inf Process Syst 35:36479–36494
  103. Shabani MA, Abdi AH, Meng L, et al (2023) Scaleformer: Iterative multi-scale refining transformers for time series forecasting. In: The Eleventh International Conference on Learning Representations, https://openreview.net/forum?id=sCrnllCtjoE
  104. Sharma N, Mangla M, Mohanty SN et al (2021) Employing stacked ensemble approach for time series forecasting. Int J Inf Technol 13:2075–2080
  105. Shen L, Chen W, Kwok J (2024) Multi-resolution diffusion models for time series forecasting. In: The Twelfth International Conference on Learning Representations
  106. Shen L, Kwok J (2023) Non-autoregressive conditional diffusion models for time series prediction. In: International Conference on Machine Learning, PMLR, pp 31016–31029
  107. Shi X, Chen Z, Wang H, et al (2015) Convolutional LSTM network: a machine learning approach for precipitation nowcasting. Adv Neural Inform Process Syst 28
  108. Shu Y, Lampos V (2024) Deformtime: Capturing variable dependencies with deformable attention for time series forecasting. Preprint at arXiv:2406.07438 · arXiv
  109. Smyl S, Oreshkin BN, Pełka P, et al (2024) Any-quantile probabilistic forecasting of short-term electricity demand. Preprint at arXiv:2404.17451 · arXiv · doi:10.2139/ssrn.4995513
  110. Sohl-Dickstein J, Weiss E, Maheswaranathan N, et al (2015) Deep unsupervised learning using nonequilibrium thermodynamics. In: International conference on machine learning, PMLR, pp 2256–2265
  111. Song Y, Ermon S (2019) Generative modeling by estimating gradients of the data distribution. Adv Neural Inform Process Syst 32
  112. Song Y, Sohl-Dickstein J, Kingma DP, et al (2021) Score-based generative modeling through stochastic differential equations. In: International Conference on Learning Representations, https://openreview.net/forum?id=PxTIG12RRHS
  113. Srivastava N, Hinton G, Krizhevsky A et al (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958
  114. Sui M, Zhang C, Zhou L et al (2024) An ensemble approach to stock price prediction using deep learning and time series models. 2024 IEEE 6th International Conference on Power. IEEE, Intelligent Computing and Systems (ICPICS), pp 793–797
  115. Sun Y, Xie Z, Chen D, et al (2024b) Hierarchical classification auxiliary network for time series forecasting. Preprint at arXiv:2405.18975 · arXiv
  116. Tang P, Zhang W (2024) PDMLP: Patch-based decomposed MLP for long-term time series forecastin. Preprint at arXiv:2405.13575 · arXiv
  117. Tashiro Y, Song J, Song Y et al (2021) CSDI: Conditional score-based diffusion models for probabilistic time series imputation. Adv Neural Inf Process Syst 34:24804–24816
  118. Touvron H, Martin L, Stone K, et al (2023) LLAMA 2: Open foundation and fine-tuned chat models. Preprint at arXiv:2307.09288 · arXiv
  119. Ulyanov D, Vedaldi A, Lempitsky V (2016) Instance normalization: The missing ingredient for fast stylization. Preprint at arXiv:1607.08022 · arXiv
  120. Van Den Oord A, Dieleman S, Zen H, et al (2016) Wavenet: a generative model for raw audio. Preprint at arXiv:1609.03499 12 · arXiv
  121. Vapnik V, Golowich S, Smola A (1996) Support vector method for function approximation, regression estimation and signal processing. Adv Neural Inform Process Syst 9
  122. Vaswani A, Shazeer N, Parmar N, et al (2017) Attention is all you need. Adv Neural Inform Process Syst 30
  123. Veličković P, Cucurull G, Casanova A, et al (2018) Graph attention networks. In: International Conference on Learning Representations, https://openreview.net/forum?id=rJXMpikCZ
  124. Wachter S, Mittelstadt B, Russell C (2017) Counterfactual explanations without opening the black box: Automated decisions and the GDPR. Harv JL Tech 31:841
  125. Wang Z, Ruan S, Huang T et al (2024) A lightweight multi-layer perceptron for efficient multivariate time series forecasting. Knowl-Based Syst 288:111463
  126. Wang Y, Wu H, Dong J, et al (2024c) Timexer: Empowering transformers for time series forecasting with exogenous variables. In: The Thirty-eighth Annual Conference on Neural Information Processing Systems, https://openreview.net/forum?id=INAeUQ04lT
  127. Wang S, Wu H, Shi X, et al (2024a) Timemixer: Decomposable multiscale mixing for time series forecasting. International Conference on Learning Representations
  128. Wang X, Zhou T, Wen Q, et al (2024b) Card: Channel aligned robust blend transformer for time series forecasting. In: The Twelfth International Conference on Learning Representations
  129. Wen R, Torkkola K, Narayanaswamy B, et al (2017) A multi-horizon quantile recurrent forecaster. Preprint at arXiv:1711.11053 · arXiv
  130. Woo G, Liu C, Kumar A, et al (2024) Unified training of universal time series forecasting transformers. In: Forty-first International Conference on Machine Learning
  131. Wu B, Wang L (2024) Two-stage decomposition and temporal fusion transformers for interpretable wind speed forecasting. Energy 288:129728
  132. Wu H, Xu J, Wang J et al (2021) Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. Adv Neural Inf Process Syst 34:22419–22430
  133. Wu B, Yu S, Peng L et al (2024) Interpretable wind speed forecasting with meteorological feature exploring and two-stage decomposition. Energy 294:130782
  134. Wu Z, Gong Y, Zhang A (2024b) Dtmamba: Dual twin mamba for time series forecasting. Preprint at arXiv:2405.07022 · arXiv
  135. Wu H, Hu T, Liu Y, et al (2023) Timesnet: Temporal 2d-variation modeling for general time series analysis. International Conference on Learning Representations
  136. Xiong Q, Tang K, Ma M, et al (2024) Tdt loss takes it all: Integrating temporal dependencies among targets into non-autoregressive time series forecasting. Preprint at arXiv:2406.04777 · arXiv
  137. Xu B, Sheng Y, Li P et al (2019) Causes and classification of EMD mode mixing. Vibroengineering Procedia 22:158–164 · doi:10.21595/vp.2018.20250
  138. Xu Z, Bian Y, Zhong J, et al (2024b) Beyond trend and periodicity: Guiding time series forecasting with textual cues. Preprint at arXiv:2405.13522 · arXiv
  139. Xu X, Chen Z, Xu D, et al (2022) Mixing signals: Data augmentation approach for deep learning based modulation recognition. Preprint at arXiv:2204.03737 · arXiv
  140. Xu X, Liang Y, Huang B, et al (2024a) Integrating mamba and transformer for long-short range time series forecasting. Preprint at arXiv:2404.14757 · arXiv
  141. Yang Y, Jin M, Wen H, et al (2024a) A survey on diffusion models for time series and Spatio-temporal data. Preprint at arXiv:2404.18886 · arXiv
  142. Yan T, Gong H, Yongping H, et al (2024) Probabilistic time series modeling with decomposable denoising diffusion model. In: Salakhutdinov R, Kolter Z, Heller K, et al (eds) Proceedings of the 41st International Conference on Machine Learning, Proceedings of Machine Learning Research, vol 235. PMLR, pp 55759–55777, https://proceedings.mlr.press/v235/yan24b.html
  143. Yang Y, Zhu Q, Chen J (2024b) Vcformer: Variable correlation transformer with inherent lagged correlation for multivariate time series forecasting. In: Larson K (ed) Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI-24. International Joint Conferences on Artificial Intelligence Organization, pp 5335–5343, https://doi.org/10.24963/ijcai.2024/590, (Main Track) · doi:10.24963/ijcai.2024/590
  144. Yan T, Zhang H, Zhou T, et al (2021) Scoregrad: Multivariate probabilistic time series forecasting with continuous energy-based generative models. Preprint at arXiv:2106.10121 · arXiv
  145. Ye J, Zhang W, Yi K, et al (2024) A survey of time series foundation models: Generalizing time series representation with large language mode. Preprint at arXiv:2405.02358 · arXiv
  146. Yi K, Zhang Q, Fan W, et al (2024) Frequency-domain mlps are more effective learners in time series forecasting. Adv Neural Inform Process Syst 36
  147. Yuan X, Qiao Y (2024) Diffusion-TS: Interpretable diffusion for general time series generation. In: The Twelfth International Conference on Learning Representations, https://openreview.net/forum?id=4h1apFjO99
  148. Zeng C, Liu Z, Zheng G, et al (2024) C-mamba: Channel correlation enhanced state space models for multivariate time series forecasting. Preprint at arXiv:2406.05316 · arXiv
  149. Zhang S, Chen Y, Xiao J et al (2021) Hybrid wind speed forecasting model based on multivariate data secondary decomposition approach and deep learning algorithm with attention mechanism. Renew Energy 174:688–704 · doi:10.1016/j.renene.2021.04.091
  150. Zhang Y, Ma L, Pal S, et al (2024e) Multi-resolution time-series transformer for long-term forecasting. In: International Conference on Artificial Intelligence and Statistics, PMLR, pp 4222–4230
  151. Zhang M, Sun Y, Liang F (2024c) Sparse deep learning for time series data: theory and applications. Adv Neural Inform Process Syst 36
  152. Zhang Y, Yan J (2023) Crossformer: Transformer utilizing cross-dimension dependency for multivariate time series forecasting. In: The eleventh international conference on learning representations
  153. Zhang K, Zou X, Tang Y (2024b) Caformer: Rethinking time series analysis from causal perspective. Preprint at arXiv:2403.08572 · arXiv
  154. Zhan T, He Y, Li Z, et al (2024) Time evidence fusion network: Multi-source view in long-term time series forecasting. Preprint at arXiv:2405.06419 · arXiv
  155. Zhao S, Ma T, Ermon S (2020) Individual calibration with randomized forecasting. In: International Conference on Machine Learning, PMLR, pp 11387–11397
  156. Zhou T, Ma Z, Wen Q, et al (2022) Fedformer: Frequency enhanced decomposed transformer for long-term series forecasting. In: International conference on machine learning, PMLR, pp 27268–27286
  157. Zhou T, Niu P, Wang X, et al (2023) One fits all: Power general time series analysis by pretrained LM. In: Thirty-seventh Conference on Neural Information Processing Systems, https://openreview.net/forum?id=gMS6FVZvmF

Metadata

Authors
Kim, J., Kim, H., Kim, H., Lee, D., & Yoon, S.
Venue
Artificial Intelligence Review
Published
2025-04-23
Volume
58
Issue
7
ISSN
  • 0269-2821 (ISSN-L)
  • 1573-7462
OpenAlex
W4409695029
Cited by
263
References
136
FWCI
128.56
Type
journal article
Language
en
Open access
hybrid
Licence

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: A comprehensive survey of deep learning for time series forecasting: architectural diversity and open challenges. https://app.cochat.ai/papers/10.1007/s10462-025-11223-9
The paper
Kim, J., Kim, H., Kim, H., Lee, D., & Yoon, S. (2025). A comprehensive survey of deep learning for time series forecasting: architectural diversity and open challenges. Artificial Intelligence Review. https://doi.org/10.1007/s10462-025-11223-9

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.