{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T13:18:33Z","timestamp":1785417513168,"version":"3.56.0"},"reference-count":27,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62263018"],"award-info":[{"award-number":["62263018"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"award":["62263018"],"award-info":[{"award-number":["62263018"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>To address the high non-stationarity of COVID-19 pandemic time-series data and the severe error accumulation issue in long-horizon forecasting, a spatiotemporal two-branch multi-step forecasting model named CFC-FLCA is proposed. This model integrates closed-form continuous-time neural networks (CFC), a hybrid decomposition strategy combining variational mode decomposition (VMD) and jump plus AM-FM mode decomposition (JMD), and a cross-attention (CA) mechanism. First, the VMD-JMD hybrid mode decomposition method is applied to preprocess raw new case sequences. By leveraging the complementary advantages of the two decomposition algorithms, non-stationary sequences are adaptively decomposed into high-frequency noise components and low-to-mid-frequency trend-periodic components, eliminating random disturbance interference at the data source. On this basis, a time\u2013frequency dual-branch feature extraction network is constructed. CFC provides ultra-long-range temporal dependency modeling capability; the time-domain branch adopts Legendre projection units (LPU) to extract robust temporal evolution features, while the frequency-domain branch employs frequency-enhanced units (FEU) to uncover latent periodic patterns that are difficult to capture using traditional time-domain methods. A cross-attention mechanism is introduced to dynamically learn the importance weights of time\u2013frequency-domain features, enabling the adaptive deep integration of complementary information and effectively mitigating error accumulation in long-horizon forecasting. Multi-step forecasting experiments are conducted on real-world COVID-19 datasets from Belgium, the Czech Republic, and Ireland, with comprehensive comparisons against mainstream time series forecasting models. The experimental results demonstrate that the CFC-FLCA model outperforms all comparison models across all evaluation metrics for all prediction horizons.<\/jats:p>","DOI":"10.3390\/a19070577","type":"journal-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T03:06:52Z","timestamp":1784084812000},"page":"577","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A VMD-JMD Hybrid Decomposition and CFC-FLCA Network for COVID-19 Multi-Step Epidemic Forecasting"],"prefix":"10.3390","volume":"19","author":[{"given":"Shike","family":"Chen","sequence":"first","affiliation":[{"name":"Faculty of Electric Power Engineering, Kunming University of Science and Technology, Kunming 650500, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guihong","family":"Bi","sequence":"additional","affiliation":[{"name":"Faculty of Electric Power Engineering, Kunming University of Science and Technology, Kunming 650500, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhong","family":"Li","sequence":"additional","affiliation":[{"name":"Faculty of Electric Power Engineering, Kunming University of Science and Technology, Kunming 650500, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Faculty of Electric Power Engineering, Kunming University of Science and Technology, Kunming 650500, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nan","family":"Yang","sequence":"additional","affiliation":[{"name":"Faculty of Electric Power Engineering, Kunming University of Science and Technology, Kunming 650500, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1677","DOI":"10.1056\/NEJMp2003762","article-title":"Responding to COVID-19\u2014A once-in-a-century pandemic?","volume":"382","author":"Gates","year":"2020","journal-title":"N. Engl. J. Med."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"141381","DOI":"10.1016\/j.jhazmat.2026.141381","article-title":"Temporal fusion transformer-based forecasting of COVID-19 infection trends using environmental indicators","volume":"512","author":"Portus","year":"2026","journal-title":"J. Hazard. Mater."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Shi, Y., Zhu, X., Zhu, X., Cheng, B., and Zhong, Y. (2025). Kalman filter-based epidemiological model for post-COVID-19 era surveillance and prediction. Sensors, 25.","DOI":"10.3390\/s25082507"},{"key":"ref_4","first-page":"49","article-title":"Review of COVID-19 propagation prediction methods","volume":"59","author":"Wang","year":"2023","journal-title":"Comput. Eng. Appl."},{"key":"ref_5","first-page":"7","article-title":"Review on infectious disease dynamics models and their applications in COVID-19 epidemic simulation and prediction","volume":"41","author":"Li","year":"2020","journal-title":"Chin. Med. Equip. J."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"109945","DOI":"10.1016\/j.asoc.2022.109945","article-title":"Temporal convolutional networks with RNN approach for chaotic time series prediction","volume":"133","author":"Dudukcu","year":"2023","journal-title":"Appl. Soft Comput."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Monllor, P., Su, Z., Gabrielli, L., and Taltavull de La Paz, P. (2020). COVID-19 infection process in Italy and Spain: Are data talking? Evidence from ARMA and vector autoregression models. Front. Public Health, 8.","DOI":"10.3389\/fpubh.2020.550602"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"e25746","DOI":"10.1016\/j.heliyon.2024.e25746","article-title":"Random forest regression for prediction of COVID-19 daily cases and deaths in Turkey","volume":"10","year":"2024","journal-title":"Heliyon"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1467","DOI":"10.1016\/j.dsx.2020.07.045","article-title":"Prediction of new active cases of coronavirus disease (COVID-19) pandemic using multiple linear regression model","volume":"14","author":"Rath","year":"2020","journal-title":"Diabetes Metab. Syndr. Clin. Res. Rev."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"100085","DOI":"10.1016\/j.array.2021.100085","article-title":"Prediction of the number of COVID-19 confirmed cases based on K-means-LSTM","volume":"11","author":"Vadyala","year":"2021","journal-title":"Array"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"110212","DOI":"10.1016\/j.chaos.2020.110212","article-title":"Predictions for COVID-19 with deep learning models of LSTM, GRU and Bi-LSTM","volume":"140","author":"Shahid","year":"2020","journal-title":"Chaos Solit. Fractals"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.isatra.2020.12.057","article-title":"Transfer learning for COVID-19 cases and deaths forecast using LSTM network","volume":"124","author":"Gautam","year":"2022","journal-title":"ISA Trans."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"105560","DOI":"10.1016\/j.compbiomed.2022.105560","article-title":"A data-driven hybrid ensemble AI model for COVID-19 infection forecast using multiple neural networks and reinforced learning","volume":"146","author":"Jin","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zhang, C., and Sun, G.X. (2024). COVID-19 Spreading Prediction Model Based on a Multi-Head Self-Attention Mechanism. Res. Sq., 2024051234.","DOI":"10.21203\/rs.3.rs-4051560\/v1"},{"key":"ref_15","unstructured":"Samuelsson, H. (2024). Enhancing Skin Cancer Classification: A Hybrid Convolutional Neural Network and Closed-Form Continuous-Time Approach for Improved Accuracy and Efficiency. [Master\u2019s Thesis, KTH Royal Institute of Technology]."},{"key":"ref_16","unstructured":"Lechner, M., and Hasani, R. (2020, January 6\u20139). Learning long-term dependencies in irregularly-sampled time series. Proceedings of the 2020 IEEE 23rd International Conference on Information Fusion (FUSION), Virtual."},{"key":"ref_17","first-page":"1566727","article-title":"Prediction of COVID-19 in BRICS countries: An integrated deep learning model of CEEMDAN-R-ILSTM-Elman","volume":"2022","author":"Zhao","year":"2022","journal-title":"Comput. Math. Methods Med."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"617","DOI":"10.3390\/ijerph20010617","article-title":"A hybrid model for coronavirus disease 2019 forecasting based on ensemble empirical mode decomposition and deep learning","volume":"20","author":"Liu","year":"2023","journal-title":"Int. J. Environ. Res. Public Health"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"106674","DOI":"10.1016\/j.compbiomed.2023.106674","article-title":"A novel prediction model based on decomposition-integration and error correction for COVID-19 daily confirmed and death cases","volume":"156","author":"Yang","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"ref_20","unstructured":"Oan\u0103, I., Mih\u0103il\u0103-Pin\u021boiu, B.-E., and H\u00e2ncean, M.-G. (2023). COVID-19 Integrated Dataset: A Unique Blend of Social Dynamics and Weather Conditions, Zenodo. Version 2."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"105415","DOI":"10.1016\/j.cageo.2023.105415","article-title":"Land subsidence simulation based on extremely randomized trees combined with Monte Carlo algorithm","volume":"178","author":"Wang","year":"2023","journal-title":"Comput. Geosci."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1081","DOI":"10.1109\/TSP.2025.3535822","article-title":"Jump plus AM-FM mode decomposition","volume":"73","author":"Nazari","year":"2025","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1109\/TSP.2013.2288675","article-title":"Variational mode decomposition","volume":"62","author":"Dragomiretskiy","year":"2013","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2652","DOI":"10.1038\/s41598-021-81985-z","article-title":"Transmission dynamics and control measures of COVID-19 outbreak in China: A modelling study","volume":"11","author":"Zhang","year":"2021","journal-title":"Sci. Rep."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"992","DOI":"10.1038\/s42256-022-00556-7","article-title":"Closed-form continuous-time neural networks","volume":"4","author":"Hasani","year":"2022","journal-title":"Nat. Mach. Intell."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zhou, T., Ma, Z., Wang, X., Wen, Q., Sun, L., Yao, T., Yin, W., and Jin, R. (2022). FiLM: Frequency improved Legendre memory model for long-term time series forecasting. arXiv.","DOI":"10.52202\/068431-0921"},{"key":"ref_27","unstructured":"Gu, A., Dao, T., Ermon, S., Rudra, A., and R\u00e9, C. (2020). HiPPO: Recurrent memory with optimal polynomial projections. Advances in Neural Information Processing Systems 33 (NeurIPS 2020), Curran Associates."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/7\/577\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T03:16:26Z","timestamp":1784085386000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/7\/577"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,14]]},"references-count":27,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["a19070577"],"URL":"https:\/\/doi.org\/10.3390\/a19070577","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,14]]}}}