Skip to main content

Advertisement

ZPDSN: spatio-temporal meteorological forecasting with topological data analysis

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Meteorological forecasting is of paramount importance for safeguarding human life, mitigating natural disasters, and promoting economic development. However, achieving precise forecasts poses significant challenges owing to the complexities associated with feature representation in observed meteorological data and the dynamic spatio-temporal dependencies therein. Graph Neural Networks (GNNs) have gained prominence in addressing spatio-temporal forecasting challenges, owing to their ability to model non-Euclidean data structures and capture spatio-temporal dependencies. However, existing GNN-based methods lead to obscure of spatio-temporal patterns between nodes due to the over-smoothing problem. Worse still, important high-order structural information is lost during GNN propagation. Topological Data Analysis (TDA), a synthesis of mathematical analysis and machine learning methodologies that can mine the higher-order features present in the data itself, offers a novel perspective for addressing cross-domain spatio-temporal meteorological forecasting tasks. To leverage above problems more effectively and empower GNN with time-aware ability, a new spatio-temporal meteorological forecasting model with topological data analysis is proposed, called Zigzag Persistence with subgraph Decomposition and Supra-graph construction Network (ZPDSN), which can dynamically simulate meteorological data across the spatio-temporal domain. The adjacency matrix for the final spatial dimension is derived by treating the topological features captured via zigzag persistence as a high-order representation of the data, and by introducing subgraph decomposition and supra-graph construction mechanisms to better capture spatial-temporal correlations. ZPDSN outperforms other GNN-based models on four meteorological datasets, namely, temperature, cloud cover, humidity and surface wind component.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Algorithm 1
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data availability and access

The meteorological data that support this study are publicly available in github repository, https://github.com/pangeo-data/WeatherBench

References

  1. Kiran Kumar V, Ramesh K, Rakesh V (2023) Optimizing lstm and bi-lstm models for crop yield prediction and comparison of their performance with traditional machine learning techniques. Appl Intell 53(23):28291–28309. https://doi.org/10.1007/s10489-023-05005-5

    Article  MATH  Google Scholar 

  2. Hao Y, Wang Q, Ma T et al (2023) Energy allocation and task scheduling in edge devices based on forecast solar energy with meteorological information. J Parallel Distr Com 177:171–181. https://doi.org/10.1016/j.jpdc.2023.03.005

    Article  MATH  Google Scholar 

  3. Huang X, Jiang Y, Tang J (2023) Mapredrnn: multi-attention predictive rnn for traffic flow prediction by dynamic spatio-temporal data fusion. Appl Intell 53(16):19372–19383. https://doi.org/10.1007/s10489-023-04494-8

    Article  Google Scholar 

  4. Zhou H, Ma T, Rong H et al (2022) Mdmn: multi-task and domain adaptation based multi-modal network for early rumor detection. Expert Syst Appl 195:116517. https://doi.org/10.1016/j.eswa.2022.116517

    Article  Google Scholar 

  5. Zhang X, Jin Q, Yu T et al (2022) Multi-modal spatio-temporal meteorological forecasting with deep neural network. ISPRS J Photogramm Remote Sens 188:380–393. https://doi.org/10.1016/j.isprsjprs.2022.03.007

    Article  MATH  Google Scholar 

  6. Karevan Z, Suykens JA (2020) Transductive lstm for time-series prediction: an application to weather forecasting. Neural Netw 125:1–9. https://doi.org/10.1016/j.neunet.2019.12.030

    Article  Google Scholar 

  7. Fang X, Han S, Li J et al (2023) A fcm-xgboost-gru model for short-term photovoltaic power forecasting based on weather classification. In: 2023 5th Asia Energy and Electrical Engineering Symposium (AEEES), pp 1444–1449. https://doi.org/10.1109/AEEES56888.2023.10114292

  8. Wang X, Girshick R, Gupta A et al (2018) Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 7794–7803

  9. Ma T, Rong H, Hao Y et al (2022) A novel sentiment polarity detection framework for chinese. IEEE Trans Affective Comput 13(1):60–74. https://doi.org/10.1109/TAFFC.2019.2932061

    Article  MATH  Google Scholar 

  10. Lin H, Gao Z, Xu Y et al (2022) Conditional local convolution for spatio-temporal meteorological forecasting. Proc AAAI Conf Artif Intell 36(7):7470–7478. https://doi.org/10.1609/aaai.v36i7.20711

    Article  MATH  Google Scholar 

  11. Reichstein M, Camps-Valls G, Stevens B et al (2019) Deep learning and process understanding for data-driven earth system science. Nature 566(7743):195–204. https://doi.org/10.1038/s41586-019-0912-1

    Article  MATH  Google Scholar 

  12. Liang Y, Ouyang K, Wang Y et al (2023) Mixed-order relation-aware recurrent neural networks for spatio-temporal forecasting. IEEE Trans Knowl Data Eng 35(9):9254–9268. https://doi.org/10.1109/TKDE.2022.3222373

    Article  MATH  Google Scholar 

  13. Guo S, Lin Y, Wan H et al (2022) Learning dynamics and heterogeneity of spatial-temporal graph data for traffic forecasting. IEEE Trans Knowl Data Eng 34(11):5415–5428. https://doi.org/10.1109/TKDE.2021.3056502

    Article  MATH  Google Scholar 

  14. Chen Y, Segovia I, Gel YR (2021) Z-gcnets: time zigzags at graph convolutional networks for time series forecasting. In: Meila M, Zhang T (eds) Proceedings of the 38th international conference on machine learning, proceedings of machine learning research, vol 139. PMLR, pp 1684–1694

  15. Ning Y, Kazemi H, Tahmasebi P (2022) A comparative machine learning study for time series oil production forecasting: arima, lstm, and prophet. Comput Geosci-uk 164:105126. https://doi.org/10.1016/j.cageo.2022.105126

    Article  MATH  Google Scholar 

  16. Ohashi O, Torgo L (2012) Wind speed forecasting using spatio-temporal indicators. In: ECAI 2012, vol 242. IOS Press, pp 975–980. https://doi.org/10.3233/978-1-61499-098-7-975

  17. Yu R, Cheng D, Liu Y (2015) Accelerated online low rank tensor learning for multivariate spatiotemporal streams. In: Bach F, Blei D (eds) Proceedings of the 32nd international conference on machine learning, proceedings of machine learning research, vol 37. PMLR, pp 238–247

  18. Pfeifer PE, Deutsch SJ (1980) A starima model-building procedure with application to description and regional forecasting. Trans Inst Br Geogr 5(3):330–349

    Article  MATH  Google Scholar 

  19. Asaly S, Gottlieb LA, Reuveni Y (2021) Using support vector machine (svm) and ionospheric total electron content (tec) data for solar flare predictions. IEEE J Sel Topics Appl Earth Observ Remote Sens 14:1469–1481. https://doi.org/10.1109/JSTARS.2020.3044470

    Article  MATH  Google Scholar 

  20. Hill AJ, Herman GR, Schumacher RS (2020) Forecasting severe weather with random forests. Mon Weather Rev 148(5):2135–2161. https://doi.org/10.1175/MWR-D-19-0344.1

    Article  MATH  Google Scholar 

  21. Chattopadhyay A, Hassanzadeh P, Pasha S (2020) Predicting clustered weather patterns: a test case for applications of convolutional neural networks to spatio-temporal climate data. Sci Rep 10(1):1317. https://doi.org/10.1038/s41598-020-57897-9

    Article  MATH  Google Scholar 

  22. Wang S, Cao J, Yu PS (2022) Deep learning for spatio-temporal data mining: a survey. IEEE Trans Knowl Data Eng 34(8):3681–3700. https://doi.org/10.1109/TKDE.2020.3025580

    Article  MATH  Google Scholar 

  23. Shi X, Chen Z, Wang H et al (2015) Convolutional lstm network: a machine learning approach for precipitation nowcasting. In: Cortes C, Lawrence N, Lee D et al (eds) Advances in neural information processing systems, vol 28. Curran Associates Inc

    MATH  Google Scholar 

  24. Wang Y, Wu H, Zhang J et al (2023) Predrnn: a recurrent neural network for spatiotemporal predictive learning. IEEE Trans Pattern Anal Mach Intell 45(2):2208–2225. https://doi.org/10.1109/TPAMI.2022.3165153

    Article  MATH  Google Scholar 

  25. Ma Z, Zhang H, Liu J (2022) Preciplstm: a meteorological spatiotemporal lstm for precipitation nowcasting. IEEE Trans Geosci Remote Sens 60:1–8. https://doi.org/10.1109/TGRS.2022.3198222

    Article  MATH  Google Scholar 

  26. Ma M, Xie P, Teng F et al (2023) Histgnn: hierarchical spatio-temporal graph neural network for weather forecasting. Inf Sci 648:119580. https://doi.org/10.1016/j.ins.2023.119580

    Article  MATH  Google Scholar 

  27. Balti H, Abbes AB, Sang Y et al (2023) Spatio-temporal heterogeneous graph using multivariate earth observation time series: application for drought forecasting. Comput Geosci-uk 179:105435. https://doi.org/10.1016/j.cageo.2023.105435

    Article  MATH  Google Scholar 

  28. Chazal F, Michel B (2021) An introduction to topological data analysis: fundamental and practical aspects for data scientists. Front Artif Intell 4:108. https://doi.org/10.3389/frai.2021.667963

    Article  MATH  Google Scholar 

  29. Tauzin G, Lupo U, Tunstall L et al (2021) giotto-tda:: a topological data analysis toolkit for machine learning and data exploration. J Mach Learn Res 22(39):1–6

    MathSciNet  MATH  Google Scholar 

  30. Carlsson G (2019) Persistent homology and applied homotopy theory. Handbook of homotopy theory, pp 297–330

  31. Jiang T, Huang M, Segovia-Dominguez I et al (2022) Learning space-time crop yield patterns with zigzag persistence-based lstm: toward more reliable digital agriculture insurance. In: Proceedings of the AAAI conference on artificial intelligence, pp 12538–12544. https://doi.org/10.1609/aaai.v36i11.21524

  32. Hoef LV, Adams H, King EJ et al (2023) A primer on topological data analysis to support image analysis tasks in environmental science. Artif Intell Earth Syst 2(1):e220039. https://doi.org/10.1175/AIES-D-22-0039.1

    Article  Google Scholar 

  33. Yan Z, Ma T, Gao L et al (2022) Neural approximation of graph topological features. In: Koyejo S, Mohamed S, Agarwal A et al (eds) Advances in neural information processing systems, vol 35. Curran Associates, Inc., pp 33357–33370

  34. Wasserman L (2018) Topological data analysis. Annu Rev Stat Appl 5(Volume 5, 2018):501–532. https://doi.org/10.1146/annurev-statistics-031017-100045

    Article  MathSciNet  MATH  Google Scholar 

  35. Carlsson G, De Silva V (2010) Zigzag persistence. Found Comput Math 10(4):367–405. https://doi.org/10.1007/s10208-010-9066-0

    Article  MathSciNet  MATH  Google Scholar 

  36. Kim W, Mémoli F, Smith Z (2020) Analysis of dynamic graphs and dynamic metric spaces via zigzag persistence. In: Topological data analysis: the abel symposium 2018. Springer, pp 371–389

  37. Bai L, Yao L, Li C et al (2020) Adaptive graph convolutional recurrent network for traffic forecasting. In: Proceedings of the 34th international conference on neural information processing systems. Curran Associates Inc., NIPS’20

  38. Adams H, Emerson T, Kirby M et al (2017) Persistence images: a stable vector representation of persistent homology. J Mach Learn Res 18(8):1–35

    MathSciNet  MATH  Google Scholar 

  39. Rasp S, Dueben PD, Scher S et al (2020) Weatherbench: a benchmark data set for data-driven weather forecasting. J Adv Model Earth Syst 12(11):e2020MS002203. https://doi.org/10.1029/2020MS002203

  40. Zhao L, Song Y, Zhang C et al (2020) T-gcn: a temporal graph convolutional network for traffic prediction. IEEE Trans Intell Transp Syst 21(9):3848–3858. https://doi.org/10.1109/TITS.2019.2935152

  41. Yu B, Yin H, Zhu Z (2018) Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. In: Proceedings of the 27th international joint conference on artificial intelligence. AAAI Press, IJCAI’18, pp 3634–3640

  42. Guo S, Lin Y, Feng N et al (2019) Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. In: Proceedings of the thirty-third AAAI conference on artificial intelligence, vol 33. AAAI Press, pp 922–929. https://doi.org/10.1609/aaai.v33i01.3301922

  43. Seo Y, Defferrard M, Vandergheynst P et al (2018) Structured sequence modeling with graph convolutional recurrent networks. In: Neural information processing. Springer, Springer International Publishing, pp 362–373

  44. Li Y, Yu R, Shahabi C et al (2017) Diffusion convolutional recurrent neural network: data-driven traffic forecasting. In: Proceedings of the international conference on learning representations, pp 1–16

  45. Wu Z, Pan S, Long G et al (2019) Graph wavenet for deep spatial-temporal graph modeling. In: Proceedings of the 28th international joint conference on artificial intelligence. AAAI Press, IJCAI’19, pp 1907–1913

  46. Wu Z, Pan S, Long G et al (2020) Connecting the dots: multivariate time series forecasting with graph neural networks. In: Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining, pp 753–763. https://doi.org/10.1145/3394486.3403118

Download references

Funding

This work is supported in part by the National Natural Science Foundation of China (No.62372243). This work is also supported in part by the National Natural Science Foundation of China (No.62102187, No.42175194), and in part by by STDF Egypt (No 43088).

Author information

Authors and Affiliations

Authors

Contributions

Tinghuai Ma and Yuming Su contributed to the conceptualization, methodology, formal analysis, investigation, and impelemention of the networks. Mohamed Magdy Abdel Wahab and Alaa Abd ELraouf Khalil contributed to the writing and provided useful support.

Corresponding author

Correspondence to Yuming Su.

Ethics declarations

Ethical and informed consent for data used

Not Applicable

Competing Interests

The authors have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ma, T., Su, Y., Abdel Wahab, M.M. et al. ZPDSN: spatio-temporal meteorological forecasting with topological data analysis. Appl Intell 55, 9 (2025). https://doi.org/10.1007/s10489-024-06053-1

Download citation

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s10489-024-06053-1

Keywords