Time Series Forecasting using Diffusion Model in Case Water Quality of Chao Phraya River
Article Sidebar
Main Article Content
Abstract
Time series forecasting is a fundamental task for predicting future values in order to understand underlying behavior. Numerous forecasting models rely on learning patterns from historical observations. However, these models face limitations when time series data exhibit inherent uncertainty, multi-modality (i.e., multiple plausible outcomes), abrupt regime changes, or complex noise. Recently, an alternative solution has emerged in which models aim to approximate the distribution of possible future outcomes. One such solution is the use of Denoising Diffusion Probabilistic Models (Diffusion Models), which offer a promising framework by learning a generative process that models complex data distributions in a probabilistic and iterative manner. This capability enables the model to effectively capture uncertainty and multi-modality in time series forecasting. In this study, we implement a Diffusion Model for time series forecasting. We conduct an evaluation on a real-world case study involving water quality in the Chao Phraya River. The results demonstrate that the Diffusion Model outperforms classical techniques such as Long Short-Term Memory (LSTM) in time series forecasting.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Copyright @2021 Engineering Transactions
Faculty of Engineering and Technology
Mahanakorn University of Technology
References
J. L. Alcaraz and N. Strodthoff. Diffusion-based time series imputation and forecasting with structured state space models. Transactions on Machine Learn-ing Research, 2022.
M. Chen, S. Mei, J. Fan, and M.Wang. An overview of diffusion models: Applications, guided genera-tion, statistical rates and optimization. arXiv pre-print arXiv:2404.07771, 2024.
J. Ho, A. Jain, and P. Abbeel. Denoising diffusion probabilistic models. In Advances in Neural Information Processing Systems, volume 33, pp. 6840–6851, 2020.
M. Kollovieh, A. F. Ansari, M. Bohlke-Schneider, J. Zschiegner, H. Wang, and Y. B. Wang. Predict, refine, synthesize: Self-guiding diffusion models for probabilistic time series forecasting. In Advances in Neural Information Processing Systems, volume 36, pp. 28341–28364, 2023.
Y. Li, X. Lu, Y. Wang, and D. Dou. Generative time series forecasting with diffusion, denoise, and disentanglement. In Advances in Neural Information Processing Systems, pp. 23009–23022, 2022.
Y. Liang, H. Wen, Y. Nie, Y. Jiang, M. Jin, D. Song, S. Pan, and Q. Wen. Foundation models for time series analysis: A tutorial and survey. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 6555–6565, 2024.
H. Lim, M. Kim, S. Park, and N. Park. Regular time-series generation using SGM. arXiv preprint arXiv:2301.08518, 2023.
L. Lin, Z. Li, R. Li, X. Li, and J. Gao. Diffusion models for time-series applications: a survey. Frontiers of Information Technology & Electronic Engineering, 25(1):19–41, 2024.
Y. Liu, T. Ajanthan, H. Husain, and V. Nguyen. Self-supervision improves diffusion models for tabular data imputation. In Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, pp. 1513–1522, 2024.
C. Luo. Understanding diffusion models: A unified perspective.arXiv preprint arXiv:2208.11970, 2022.
C. Meijer and L. Y. Chen. The rise of diffusion models in time-series forecasting, arXiv preprint arXiv:2401.03006, 2024.
A. H. Murphy and R. L. Winkler. A general framework for forecast verification. Monthly Weather Review, 115(7):1330 – 1338, 1987.
A. Q. Nichol and P. Dhariwal. Improved denoising diffusion probabilistic models. In Proceedings of the 38th International Conference on Machine Learning, volume 139, pp. 8162–8171, 2021.
K. Rasul, C. Seward, I. Schuster, and R. Vollgraf. Autoregressive denoising diffusion models for multivariate probabilistic time series forecasting. In International Conference on Machine Learning, pp. 8857–8868, 2021.
J. Sohl-Dickstein, E. Weiss, N. Maheswaranathan, and S. Ganguli. Deep unsupervised learning using nonequilibrium thermodynamics. In Proceedings of the 32nd International Conference on Machine Learning, volume 37, pp. 2256–2265, 2015.
I. Sutskever, O. Vinyals, and Q. V. Le. Sequence to sequence learning with neural networks. In Advances in Neural Information Processing systems, volume 27, pp. 3104 – 3112, 2014.
Y. Tashiro, J. Song, Y. Song, and S. Ermon. CSDI: Conditional score-based diffusion models for probabilistic time series imputation. In Advances in Neural Information Processing Systems, volume 34, pp. 24804–24816, 2021.
V. T. Truong, L. B. Dang, and L. B. Le. Attacks and defenses for generative diffusion models: A comprehensive survey. ACM Comput. Surv., 57(8), 2025.
Q. Wen, T. Zhou, C. Zhang, W. Chen, Z. Ma, J. Yan, and L. Sun. Transformers in time series: a survey. In Proceedings of the 32nd International Joint Conference on Artificial Intelligence, 2023.
H. Wu, J. Xu, J. Wang, and M. Long. Autoformer: decomposition transformers with auto-correlation for long-term series forecasting. In Advances in Neural Information Processing systems, pp. 22419 – 22430, 2021.
L. Yang, Z. Zhang, Y. Song, S. Hong, R. Xu, Y. Zhao, W. Zhang, B. Cui, and M.-H. Yang. Diffusion models: A comprehensive survey of methods and applications. ACM Comput. Surv., 56(4), 2023.
H. Zhou, S. Zhang, J. Peng, S. Zhang, J. Li, H. Xiong, and W. Zhang. Informer: Beyond efficient transformer for long sequence time-series forecasting. In Proceedings of the AAAI Conference on Artificial Intelligence, 35(12):11106–11115, 2021.
T. Zhou, Z. Ma, Q. Wen, X. Wang, L. Sun, and R. Jin. FEDformer: Frequency enhanced decomposed transformer for long-term series forecasting. In Proceedings of the 39th International Conference on Machine Learning, volume 162, pp. 27268–27286, 2022.
