Highly infectious diseases like COVID-19 have affected millions worldwide, with transmission clearly linked to crowd mobility. However, research on the predictive power of city-level mobility remains limited. Most existing forecasting methods focus on state or national level, making it difficult for policymakers to quickly respond to emerging threats. To address this gap, we propose the Inner-Inter City Learner (IIL) for short- and mid-term COVID-19 case predictions at the city level, based on the correlation between human interaction and new cases. IIL consists of two key components: an inter-city transmission learner and an inner-city propagation learner. The first uses city mobility graphs and graph neural networks to learn how transmission in one city is influenced by others. The second, leveraging the highly contagious nature of the virus, captures key features of COVID-19 spread within cities. To overcome limited inner-city mobility data, we apply model-agnostic meta-learning to transfer common features across cities. We conduct various experiments and compare our methods with the state-of-art baselines. The results show the superiority of our method across various forecast horizons.
ChimmulaVKRZhangL. Time series forecasting of COVID-19 transmission in canada using lstm networks. Chaos Solit Fract2020; 135: 109864.
2.
AlakkariKSubhiAAAlkattanH, et al.Forecasting COVID-19 infection using encoder-decoder lstm and attention lstm algorithms. J Intell Syst Int Things2023; 8: 2.
3.
Al-RashediAAl-HageryMA. Deep learning algorithms for forecasting COVID-19 cases in saudi arabia. Appl Sci2023; 13: 1816.
4.
MilneGJXieSPoklepovichD, et al.A modelling analysis of the effectiveness of second wave COVID-19 response strategies in australia. Sci Rep2021; 11: 11958.
5.
LiXPatelVDuanL, et al.Real-time epidemiology and acute care need monitoring and forecasting for COVID-19 via bayesian sequential monte carlo-leveraged transmission models. Int J Environ Res Public Health2024; 21: 193.
6.
ChangSWilsonMLLewisB, et al.Supporting COVID-19 policy response with large-scale mobility-based modeling. In: Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining, 2021, pp.2632–2642.
7.
Soriano-PañosDCotaWFerreiraSC, et al.Modeling communicable diseases, human mobility, and epidemics: A review. Ann Phys2022; 534: 2100482.
8.
KapoorABenXLiuL, et al.Examining COVID-19 forecasting using spatio-temporal graph neural networks. arXiv preprint arXiv:200703113, 2020.
9.
PanagopoulosGNikolentzosGVazirgiannisM. Transfer graph neural networks for pandemic forecasting. In: Proceedings of the AAAI conference on artificial intelligence, Vol. 35, 2021, pp.4838–4845.
10.
EfimovDUshirobiraR. On an interval prediction of COVID-19 development based on a seir epidemic model. Annu Rev Control2021; 51: 477–487.
11.
HeSPengYSunK. Seir modeling of the COVID-19 and its dynamics. Nonlinear Dyn2020; 101: 1667–1680.
12.
LorchLKremerHTrouleauW, et al.Quantifying the effects of contact tracing, testing, and containment measures in the presence of infection hotspots. ACM Trans Spatial Alg Syst2022; 8: 1–28.
13.
YangZZengZWangK, et al.Modified seir and ai prediction of the epidemics trend of COVID-19 in china under public health interventions. J Thorac Dis2020; 12: 165.
14.
RodríguezAMuralidharNAdhikariB, et al.Steering a historical disease forecasting model under a pandemic: Case of flu and COVID-19. In: Proceedings of the AAAI conference on artificial intelligence, Vol. 35, 2021, pp.4855–4863.
15.
KufelT, et al.Arima-based forecasting of the dynamics of confirmed COVID-19 cases for selected european countries. Equilib Quart J Econ Econ Policy2020; 15: 181–204.
16.
OspinaRGondimJALeivaV, et al.An overview of forecast analysis with arima models during the COVID-19 pandemic: Methodology and case study in brazil. Mathematics2023; 11: 3069.
17.
Ala’rajMMajdalawiehMNizamuddinN. Modeling and forecasting of COVID-19 using a hybrid dynamic model based on seird with arima corrections. Infect Dis Modell2021; 6: 98–111.
18.
ZgFangSqYangalLv Cx et. Application of a data-driven xgboost model for the prediction of COVID-19 in the usa: a time-series study. BMJ Open2022; 12: e056685.
19.
DuanYMaoYGuoY, et al.COVID-19 propagation prediction model using improved grey wolf optimization algorithms in combination with xgboost and bagging-integrated learning. Mathem Probl Eng2022; 2022: 1314459.
20.
ZhouLZhaoCLiuN, et al.Improved lstm-based deep learning model for COVID-19 prediction using optimized approach. Eng Appl Artif Intell2023; 122: 106157.
21.
AdigaAWangLHurtB, et al.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, 2021, pp.2505–2513.
22.
WathoreRRawlekarSAnjumS, et al.Improving performance of deep learning predictive models for COVID-19 by incorporating environmental parameters. Gondw Res2023; 114: 69–77.
23.
SongYChenHSongX, et al.Stg-net: A COVID-19 prediction network based on multivariate spatio-temporal information. Biomed Signal Process Control2023; 84: 104735.
24.
DengSWangSRangwalaH, et al.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, 2020.
25.
GaoJSharmaRQianC, et al.Stan: spatio-temporal attention network for pandemic prediction using real-world evidence. J Am Med Inform Assoc2021; 28: 733–743.
26.
PuXZhuJWuY, et al.Dynamic adaptive spatio–temporal graph network for COVID-19 forecasting. CAAI Trans on Intell Technol2024; 9: 769–786.
27.
La GattaVMoscatoVPostiglioneM, et al.An epidemiological neural network exploiting dynamic graph structured data applied to the COVID-19 outbreak. IEEE Trans Big Data2020; 7: 45–55.
28.
XiaoCZhouJHuangJ, et al.C-watcher: A framework for early detection of high-risk neighborhoods ahead of COVID-19 outbreak. In: Proceedings of the AAAI conference on artificial intelligence, Vol. 35, 2021, pp.4892–4900.
29.
SchwabeAPerssonJFeuerriegelS. Predicting COVID-19 spread from large-scale mobility data. In: Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining, 2021, pp.3531–3539.
GravesAJaitlyN. Towards end-to-end speech recognition with recurrent neural networks. In: International conference on machine learning, 2014, pp.1764–1772. PMLR.
32.
FinnCAbbeelPLevineS. Model-agnostic meta-learning for fast adaptation of deep networks. In: International conference on machine learning, 2017, pp.1126–1135. PMLR.
33.
KangYGaoSLiangY, et al.Multiscale dynamic human mobility flow dataset in the us during the COVID-19 epidemic. Sci Data2020; 7: 390.
34.
VillanuevaIConesaDCatalàM, et al.Country-report pattern corrections of new cases allow accurate 2-week predictions of COVID-19 evolution with the gompertz model. Sci Rep2024; 14: 10775.
