Abstract
Infectious disease forecasting has been a key focus and proved to be crucial in controlling epidemic. A recent trend is to develop forecasting models based on graph neural networks (GNNs). However, existing GNN-based methods suffer from two key limitations: (1) current models broaden receptive fields by scaling the depth of GNNs, which is insufficient to preserve the semantics of long-range connectivity between distant but epidemic related areas. (2) Previous approaches model epidemics within single spatial scale, while ignoring the multi-scale epidemic patterns derived from different scales. To address these deficiencies, we devise the Multi-scale Spatio-temporal Graph Neural Network (MSGNN) based on an innovative multi-scale view. To be specific, in the proposed MSGNN model, we first devise a novel graph learning module, which directly captures long-range connectivity from trans-regional epidemic signals and integrates them into a multi-scale graph. Based on the learned multi-scale graph, we utilize a newly designed graph convolution module to exploit multi-scale epidemic patterns. This module allows us to facilitate multi-scale epidemic modeling by mining both scale-shared and scale-specific patterns. Experimental results on forecasting new cases of COVID-19 in United State demonstrate the superiority of our method over state-of-arts. Further analyses and visualization also show that MSGNN offers not only accurate, but also robust and interpretable forecasting result. Code is available at https://github.com/JashinKorone/MSGNN.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10618-024-01035-w/MediaObjects/10618_2024_1035_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10618-024-01035-w/MediaObjects/10618_2024_1035_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10618-024-01035-w/MediaObjects/10618_2024_1035_Figa_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10618-024-01035-w/MediaObjects/10618_2024_1035_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10618-024-01035-w/MediaObjects/10618_2024_1035_Fig4_HTML.png)
Similar content being viewed by others
Notes
https://covid19forecasthub.org.
https://github.com/CSSEGISandData/COVID-19.
https://covid19forecasthub.org/eval-reports/#Incident_Case_Forecasts_(state)
https://covid19forecasthub.org/eval-reports/#Incident_Case_Forecasts_(county)
https://zoltardata.com/project/44.
References
Adiga A, Wang L, Hurt B et al. (2021) All models are useful: Bayesian ensembling for robust high resolution covid-19 forecasting. In: Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining. Association for Computing Machinery, New York, NY, USA, KDD ’21, pp 2505–2513. https://doi.org/10.1145/3447548.3467197
Arik S, Li CL, Yoon J et al. (2020) Interpretable sequence learning for covid-19 forecasting. In: Larochelle H, Ranzato M, Hadsell R et al. (eds) Advances in neural information processing systems, vol 33. Curran Associates Inc, New York, pp 18807–18818
Cao D, Wang Y, Duan J et al. (2020) Spectral temporal graph neural network for multivariate time-series forecasting. In: Larochelle H, Ranzato M, Hadsell R et al. (eds) Advances in neural information processing systems, vol 33. Curran Associates Inc, New York, pp 17766–17778
Ceylan Z (2020) Estimation of covid-19 prevalence in Italy, Spain, and France. Sci Total Environ 729(138):817. https://doi.org/10.1016/j.scitotenv.2020.138817
Chang S, Wilson ML, Lewis B et al. (2021) Supporting covid-19 policy response with large-scale mobility-based modeling. In: Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining. Association for Computing Machinery, New York, NY, USA, KDD ’21, pp 2632–2642. https://doi.org/10.1145/3447548.3467182,
Chen T, Guestrin C (2016) Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. Association for Computing Machinery, New York, NY, USA, KDD ’16, pp 785–794. https://doi.org/10.1145/2939672.2939785,
Chen D, Lin Y, Li W et al. (2020) Measuring and relieving the over-smoothing problem for graph neural networks from the topological view. In: The thirty-fourth AAAI conference on artificial intelligence, AAAI 2020, The thirty-second innovative applications of artificial intelligence conference, IAAI 2020, The Tenth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2020, New York, NY, USA, February 7–12, 2020. AAAI Press, pp 3438–3445. https://aaai.org/ojs/index.php/AAAI/article/view/5747
Chen L, Xu J, Wu B et al. (2021) Group-aware graph neural network for nationwide city air quality forecasting. ar**v preprint ar**v:2108.12238
Costa GS, Cota W, Ferreira SC (2020) Outbreak diversity in epidemic waves propagating through distinct geographical scales. Phys Rev Res 2(043):306. https://doi.org/10.1103/PhysRevResearch.2.043306
Deng S, Wang S, Rangwala H et al. (2020) Cola-gnn: Cross-location attention based graph neural networks for long-term ili prediction. In: Proceedings of the 29th ACM international conference on information & knowledge management. Association for Computing Machinery, New York, NY, USA, CIKM ’20, pp 245–254. https://doi.org/10.1145/3340531.3411975
Derr T, Ma Y, Fan W et al. (2020) Epidemic graph convolutional network. In: Proceedings of the 13th international conference on web search and data mining. Association for Computing Machinery, New York, NY, USA, WSDM ’20, pp 160–168. https://doi.org/10.1145/3336191.3371807
Du Y, Ding N (2023) A systematic review of multi-scale spatio-temporal crime prediction methods. ISPRS Int J Geo Inf 12(6):209
Dubey B, Patra A, Srivastava PK et al. (2013) Modeling and analysis of an SEIR model with different types of nonlinear treatment rates. J Biol Syst 21(03):1350,023. https://doi.org/10.1142/S021833901350023X,
Fang X, Huang J, Wang F et al. (2020) Constgat: Contextual spatial-temporal graph attention network for travel time estimation at Baidu maps. In: Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining. Association for Computing Machinery, New York, NY, USA, KDD ’20, pp 2697–2705. https://doi.org/10.1145/3394486.3403320,
Feng X, Guo J, Qin B et al. (2017) Effective deep memory networks for distant supervised relation extraction. In: Proceedings of the 26th international joint conference on artificial intelligence. AAAI Press, IJCAI’17, pp 4002–4008
Fritz C, Dorigatti E, Rügamer D (2022) Combining graph neural networks and spatio-temporal disease models to improve the prediction of weekly covid-19 cases in Germany. Sci Rep 1:2. https://doi.org/10.1038/s41598-022-07757-5
Gao J, Sharma R, Qian C et al. (2021) Stan: spatio-temporal attention network for pandemic prediction using real-world evidence. J Am Med Inform Assoc 28(4):733–743
Ge L, Wu K, Zeng Y et al. (2022) Multi-scale spatiotemporal graph convolution network for air quality prediction. Appl Intell 51:3491
Guo K, Hu Y, Sun Y et al. (2021) Hierarchical graph convolution network for traffic forecasting. In: Proceedings of the AAAI conference on artificial intelligence, vol 35, no 1, pp 151–159. https://doi.org/10.1609/aaai.v35i1.16088
He S, Peng Y, Sun K (2020) SEIR modeling of the covid-19 and its dynamics. Nonlinear Dyn 101:1667–1680. https://doi.org/10.1038/s41598-022-07757-5
Jagpreet C, Turgay A, Benjamin L et al. (2022) Covid-19 simulator—covid19sim-simulator. Retrived on Sep 2022 https://covid19sim.org
** D, Yu Z, Huo C et al. (2021) Universal graph convolutional networks. In: Ranzato M, Beygelzimer A, Dauphin Y et al. (eds) Advances in neural information processing systems, vol 34. Curran Associates, Inc., pp 10,654–10,664. https://proceedings.neurips.cc/paper/2021/file/5857d68cd9280bc98d079fa912fd6740-Paper.pdf
** G, Liang Y, Fang Y et al. (2023a) Spatio-temporal graph neural networks for predictive learning in urban computing: a survey. ar**v preprint ar**v:2303.14483
** G, Liu L, Li F et al. (2023b) Spatio-temporal graph neural point process for traffic congestion event prediction. Proceedings of the AAAI Conference on Artificial Intelligence 37(12):14,268–14,276. https://doi.org/10.1609/aaai.v37i12.26669
Kapoor A, Ben X, Liu L et al. (2020) Examining covid-19 forecasting using spatio-temporal graph neural networks. ar**v preprint ar**v:2007.03113
Kara A (2021) Multi-step influenza outbreak forecasting using deep LSTM network and genetic algorithm. Expert Syst Appl 180(115):153. https://doi.org/10.1016/j.eswa.2021.115153
Kargas N, Qian C, Sidiropoulos ND et al. (2021) Stelar: Spatio-temporal tensor factorization with latent epidemiological regularization. Proceedings of the AAAI Conference on Artificial Intelligence 35(6):4830–4837. https://doi.org/10.1609/aaai.v35i6.16615, https://ojs.aaai.org/index.php/AAAI/article/view/16615
Kipf TN, Welling M (2017a) Semi-supervised classification with graph convolutional networks. In: 5th International conference on learning representations, ICLR 2017, Toulon, France, April 24–26, 2017, Conference Track Proceedings. OpenReview.net. https://openreview.net/forum?id=SJU4ayYgl
Kipf TN, Welling M (2017b) Semi-supervised classification with graph convolutional networks. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24–26, 2017, Conference Track Proceedings. OpenReview.net. https://openreview.net/forum?id=SJU4ayYgl
Li Z, Huang C, **a L et al. (2022) Spatial-temporal hypergraph self-supervised learning for crime prediction. In: 2022 IEEE 38th international conference on data engineering (ICDE), pp 2984–2996. https://doi.org/10.1109/ICDE53745.2022.00269
Lin H, Bai R, Jia W et al. (2020) Preserving dynamic attention for long-term spatial-temporal prediction. In: Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining. Association for Computing Machinery, New York, NY, USA, KDD ’20, pp 36–46. https://doi.org/10.1145/3394486.3403046
López L, Rodó X (2021) A modified seir model to predict the covid-19 outbreak in spain and italy: Simulating control scenarios and multi-scale epidemics. Results in Physics 21(103):746
Maleki M, Mahmoudi MR, Wraith D et al. (2020) Time series modelling to forecast the confirmed and recovered cases of covid-19. Travel Med Infect Dis 37(101):742. https://doi.org/10.1016/j.tmaid.2020.101742
Montero-Manso P, Athanasopoulos G, Hyndman RJ et al. (2020) Fforma: Feature-based forecast model averaging. Int J Forecast 36(1):86–92. https://doi.org/10.1016/j.ijforecast.2019.02.011
Mussumeci E, Codeço Coelho F (2020) Large-scale multivariate forecasting models for dengue—LSTM versus random forest regression. Spatial Spatio-temporal Epidemiol 35(100):372
O’Dea E (2022) Ceid-walk. Retrived on Sep 2022 https://github.com/e3bo/random-walks
Oreshkin BN, Carpov D, Chapados N et al. (2020) N-BEATS: neural basis expansion analysis for interpretable time series forecasting. In: 8th international conference on learning representations, ICLR 2020, Addis Ababa, Ethiopia, April 26–30, 2020. OpenReview.net. https://openreview.net/forum?id=r1ecqn4YwB
Panaggio MJ, Rainwater-Lovett K, Nicholas PJ et al. (2022) Gecko: A time-series model for covid-19 hospital admission forecasting. Epidemics 39(100):580. https://doi.org/10.1016/j.epidem.2022.100580
Panagopoulos G, Nikolentzos G, Vazirgiannis M (2021) Transfer graph neural networks for pandemic forecasting. Proceedings of the AAAI Conference on Artificial Intelligence 35(6):4838–4845. https://doi.org/10.1609/aaai.v35i6.16616
Qian Z, Alaa AM, van der Schaar M (2020) When and how to lift the lockdown? global covid-19 scenario analysis and policy assessment using compartmental Gaussian processes. In: Larochelle H, Ranzato M, Hadsell R et al. (eds) Advances in neural information processing systems, vol 33. Curran Associates, Inc., pp 10,729–10,740
Ray EL, Wattanachit N, Niemi J et al. (2020) Ensemble forecasts of coronavirus disease 2019 (covid-19) in the us. MedR**v, pp 2020–08
Rodríguez A, Muralidhar N, Adhikari B et al. (2021) Steering a historical disease forecasting model under a pandemic: Case of flu and covid-19. Proceedings of the AAAI Conference on Artificial Intelligence 35(6):4855–4863. https://doi.org/10.1609/aaai.v35i6.16618
Shahid F, Zameer A, Muneeb M (2020) Predictions for covid-19 with deep learning models of LSTM, GRU and Bi-LSTM. Chaos, Solitons Fractals 140(110):212. https://doi.org/10.1016/j.chaos.2020.110212
Shuvo SB, Molokwu BC, Kobti Z (2020) Simulating the impact of hospital capacity and social isolation to minimize the propagation of infectious diseases. In: Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining. Association for Computing Machinery, New York, NY, USA, KDD ’20, pp 3451–3457. https://doi.org/10.1145/3394486.3412859
Smyl S (2020) A hybrid method of exponential smoothing and recurrent neural networks for time series forecasting. Int J Forecast 36(1):75–85. https://doi.org/10.1016/j.ijforecast.2019.03.017
Srivastava A, Xu T, Prasanna VK (2020) Fast and accurate forecasting of covid-19 deaths using the sikj model. ar**v preprint ar**v:2007.05180
To T, Zhang K, Maguire B et al. (2021) Correlation of ambient temperature and covid-19 incidence in Canada. Sci Total Environ 750(141):484. https://doi.org/10.1016/j.scitotenv.2020.141484
Velickovic P, Cucurull G, Casanova A et al. (2018) Graph attention networks. In: 6th international conference on learning representations, ICLR 2018, Vancouver, BC, Canada, April 30–May 3, 2018, Conference Track Proceedings. OpenReview.net. https://openreview.net/forum?id=rJXMpikCZ
Wang L, Wang G, Gao L et al. (2020a) Spatiotemporal dynamics, nowcasting and forecasting of covid-19 in the United States. ar**v preprint ar**v:2004.14103
Wang P, Zheng X, Ai G et al. (2020b) Time series prediction for the epidemic trends of covid-19 using the improved LSTM deep learning method Case studies in Russia, Peru and Iran. Chaos, Solitons Fractals 140(110):214. https://doi.org/10.1016/j.chaos.2020.110214
Wang L, Adiga A, Chen J et al. (2022) Causalgnn: Causal-based graph neural networks for spatio-temporal epidemic forecasting. Proceedings of the AAAI Conference on Artificial Intelligence 36(11):12,191–12,199. https://doi.org/10.1609/aaai.v36i11.21479, https://ojs.aaai.org/index.php/AAAI/article/view/21479
Wu Z, Pan S, Long G et al. (2019) Graph wavenet for deep spatial-temporal graph modeling. In: Kraus S (ed) Proceedings of the twenty-eighth international joint conference on artificial intelligence. Association for the Advancement of Artificial Intelligence (AAAI), United States of America, pp 1907–1913. https://doi.org/10.24963/ijcai.2019/264. https://ijcai19.org/, https://www.ijcai.org/proceedings/2019/, international Joint Conference on Artificial Intelligence 2019, IJCAI 2019 ; Conference date: 10-08-2019 Through 16-08-2019
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. Association for Computing Machinery, New York, NY, USA, KDD ’20, pp 753–763. https://doi.org/10.1145/3394486.3403118
**e F, Zhang Z, Li L et al. (2023) Epignn: Exploring spatial transmission with graph neural network for regional epidemic forecasting. In: Amini MR, Canu S, Fischer A et al. (eds) Machine learning and knowledge discovery in databases. Springer, Cham, pp 469–485
Ye Y, Fan Y, Hou S et al. (2021) Community mitigation: a data-driven system for covid-19 risk assessment in a hierarchical manner. In: Proceedings of the 29th ACM international conference on information & knowledge management. Association for Computing Machinery, New York, NY, USA, CIKM ’20, pp 2909–2916. https://doi.org/10.1145/3340531.3412753
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
Zheng S, Gao Z, Cao W et al. (2021) Hierst: A unified hierarchical spatial-temporal framework for covid-19 trend forecasting. In: Proceedings of the 30th ACM international conference on information & knowledge management. Association for Computing Machinery, New York, NY, USA, CIKM ’21, pp 4383–4392. https://doi.org/10.1145/3459637.3481927,
Zhifeng G, Chaozhuo L, Wei C et al. (2022) Microsoft-deepstia. Retrived on Sep 2022. https://www.microsoft.com/en-us/ai/ai-for-health
Funding
This work was supported by National Key Research and Development Project (No. 2020AAA0106200), the National Nature Science Foundation of China under Grants (No.62325206, 619360005), Key Research and Development Program of Jiangsu Province under Grant BE2023016-4, and the Natural Science Foundation of Jiangsu Province under Grant BK20210595.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors have no Conflict of interest to declare that are relevant to the content of this article.
Additional information
Responsible editor: Aristides Gionis.
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.
About this article
Cite this article
Qiu, M., Tan, Z. & Bao, BK. MSGNN: Multi-scale Spatio-temporal Graph Neural Network for epidemic forecasting. Data Min Knowl Disc (2024). https://doi.org/10.1007/s10618-024-01035-w
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10618-024-01035-w