{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T19:03:04Z","timestamp":1791486184608,"version":"4.3.4"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1014846","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T00:00:00Z","timestamp":1791417600000}}],"reference-count":26,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T00:00:00Z","timestamp":1790726400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Institute of Health","award":["5R01AI102939"],"award-info":[{"award-number":["5R01AI102939"]}]},{"name":"National Institute of Health","award":["5R01AI102939"],"award-info":[{"award-number":["5R01AI102939"]}]},{"DOI":"10.13039\/100025287","name":"Center for Forecasting and Outbreak Analytics","doi-asserted-by":"publisher","award":["CDC-RFA-FT-23-0069"],"award-info":[{"award-number":["CDC-RFA-FT-23-0069"]}],"id":[{"id":"10.13039\/100025287","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100025287","name":"Center for Forecasting and Outbreak Analytics","doi-asserted-by":"publisher","award":["CDC-RFA-FT-23-0069"],"award-info":[{"award-number":["CDC-RFA-FT-23-0069"]}],"id":[{"id":"10.13039\/100025287","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Forecasting infectious disease incidence can provide important information to guide public health planning, yet it is difficult because epidemic dynamics are complex. Current mechanistic and statistical approaches often struggle to capture multimodal uncertainty or emergent trends. Influpaint adapts denoising diffusion probabilistic models to epidemic forecasting. By encoding influenza seasons as spatiotemporal images in which pixel intensity represents incidence, Influpaint learns a rich distribution of disease dynamics from a hybrid dataset of surveillance and simulated trajectories. Forecasting is formulated as a conditional generation (inpainting) task from partial observations. We show that Influpaint generates realistic, diverse epidemic trajectories and achieves forecast accuracy that is competitive with leading ensemble methods in retrospective evaluation. In real-time evaluation during the 2022\u20132025 U.S. CDC FluSight challenges, performance improved substantially across seasons, with highly accurate but somewhat overconfident projections in 2024\u20132025. The best performance was achieved with a training dataset containing 30% surveillance and 70% simulated trajectories. These results show that diffusion models can capture important spatiotemporal structure in influenza dynamics and provide a flexible framework for probabilistic infectious disease forecasting.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1014846","type":"journal-article","created":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T17:41:36Z","timestamp":1790790096000},"page":"e1014846","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Generative diffusion models for spatiotemporal influenza forecasting"],"prefix":"10.1371","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2677-6574","authenticated-orcid":true,"given":"Joseph","family":"Lemaitre","sequence":"first","affiliation":[{"name":"Gillings School of Global Public Health, University of North Carolina at Chapel Hill","place":["Chapel Hill, North Carolina, United States of America"],"department":["Department of Epidemiology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Justin","family":"Lessler","sequence":"additional","affiliation":[{"name":"Gillings School of Global Public Health, University of North Carolina at Chapel Hill","place":["Chapel Hill, North Carolina, United States of America"],"department":["Department of Epidemiology"]},{"name":"Johns Hopkins Bloomberg School of Public Health","place":["Baltimore, Maryland, United States of America"],"department":["Department of Epidemiology"]},{"name":"Carolina Population Center, University of North Carolina at Chapel Hill","place":["Chapel Hill, North Carolina, United States of America"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,30]]},"reference":[{"issue":"1","key":"pcbi.1014846.ref001","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1214\/18-BA1117","article-title":"Dynamic Bayesian Influenza Forecasting in the United States with Hierarchical Discrepancy (with Discussion)","volume":"14","author":"D Osthus","year":"2019","journal-title":"Bayesian Anal"},{"key":"pcbi.1014846.ref002","first-page":"6840","article-title":"Denoising Diffusion Probabilistic Models.","volume-title":"Advances in Neural Information Processing Systems","author":"J Ho","year":"2020"},{"key":"pcbi.1014846.ref003","first-page":"8780","article-title":"Diffusion Models Beat GANs on Image Synthesis.","volume-title":"Advances in Neural Information Processing Systems","author":"P Dhariwal","year":"2021"},{"key":"pcbi.1014846.ref004","doi-asserted-by":"crossref","first-page":"100810","DOI":"10.1016\/j.epidem.2024.100810","article-title":"Flusion: Integrating multiple data sources for accurate influenza predictions","volume":"50","author":"EL Ray","year":"2025","journal-title":"Epidemics"},{"key":"pcbi.1014846.ref005","doi-asserted-by":"crossref","first-page":"100877","DOI":"10.1016\/j.epidem.2025.100877","article-title":"Machine learning-based short-term forecasting of COVID-19 hospital admissions using routine hospital patient data","volume":"54","author":"MS Wohlfender","year":"2026","journal-title":"Epidemics"},{"issue":"8051","key":"pcbi.1014846.ref006","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1038\/s41586-024-08564-w","article-title":"Artificial intelligence for modelling infectious disease epidemics","volume":"638","author":"MUG Kraemer","year":"2025","journal-title":"Nature"},{"key":"pcbi.1014846.ref007","first-page":"41164","article-title":"Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models.","volume-title":"Proceedings of the 40th International Conference on Machine Learning. vol. 202 of Proceedings of Machine Learning Research","author":"G Zhang","year":"2023"},{"issue":"2","key":"pcbi.1014846.ref008","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1008618","article-title":"Evaluating epidemic forecasts in an interval format","volume":"17","author":"J Bracher","year":"2021","journal-title":"PLoS Comput Biol"},{"key":"pcbi.1014846.ref009","doi-asserted-by":"crossref","first-page":"100753","DOI":"10.1016\/j.epidem.2024.100753","article-title":"flepiMoP: The evolution of a flexible infectious disease modeling pipeline during the COVID-19 pandemic","volume":"47","author":"JC Lemaitre","year":"2024","journal-title":"Epidemics"},{"key":"pcbi.1014846.ref010","doi-asserted-by":"crossref","first-page":"100738","DOI":"10.1016\/j.epidem.2023.100738","article-title":"The US COVID-19 and Influenza Scenario Modeling Hubs: Delivering long-term projections to guide policy","volume":"46","author":"SL Loo","year":"2024","journal-title":"Epidemics"},{"issue":"1","key":"pcbi.1014846.ref011","doi-asserted-by":"crossref","first-page":"6289","DOI":"10.1038\/s41467-024-50601-9","article-title":"Evaluation of FluSight influenza forecasting in the 2021-22 and 2022-23 seasons with a new target laboratory-confirmed influenza hospitalizations","volume":"15","author":"SM Mathis","year":"2024","journal-title":"Nat Commun"},{"issue":"6677","key":"pcbi.1014846.ref012","doi-asserted-by":"crossref","first-page":"1416","DOI":"10.1126\/science.adi2336","article-title":"Learning skillful medium-range global weather forecasting","volume":"382","author":"R Lam","year":"2023","journal-title":"Science"},{"issue":"8044","key":"pcbi.1014846.ref013","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1038\/s41586-024-08252-9","article-title":"Probabilistic weather forecasting with machine learning","volume":"637","author":"I Price","year":"2025","journal-title":"Nature"},{"key":"pcbi.1014846.ref014","unstructured":"Rout L, Parulekar A, Caramanis C, Shakkottai S. A Theoretical Justification for Image Inpainting using Denoising Diffusion Probabilistic Models. arXiv. ArXiv:2302.01217 [cs, math, stat]. 2023. Available from: http:\/\/arxiv.org\/abs\/2302.01217"},{"issue":"10","key":"pcbi.1014846.ref015","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1010598","article-title":"A deep learning approach to real-time HIV outbreak detection using genetic data","volume":"18","author":"MD Kupperman","year":"2022","journal-title":"PLoS Comput Biol"},{"key":"pcbi.1014846.ref016","article-title":"ImageNet Classification with Deep Convolutional Neural Networks.","volume-title":"Advances in Neural Information Processing Systems. vol. 25","author":"A Krizhevsky","year":"2012"},{"key":"pcbi.1014846.ref017","first-page":"234","article-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation.","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015. vol. 9351 of Lecture Notes in Computer Science","author":"O Ronneberger","year":"2015"},{"key":"pcbi.1014846.ref018","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep Residual Learning for Image Recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016. p. 770\u20138.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"3","key":"pcbi.1014846.ref019","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1007\/s11263-019-01198-w","article-title":"Group normalization","volume":"128","author":"Y Wu","year":"2020","journal-title":"Int J Comput Vis"},{"key":"pcbi.1014846.ref020","article-title":"Attention is All You Need.","volume-title":"Advances in Neural Information Processing Systems","author":"A Vaswani","year":"2017"},{"key":"pcbi.1014846.ref021","doi-asserted-by":"crossref","unstructured":"Liu Z, Mao H, Wu C-Y, Feichtenhofer C, Darrell T, Xie S. A ConvNet for the 2020s. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2022. p. 11976\u201386.","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"pcbi.1014846.ref022","doi-asserted-by":"crossref","unstructured":"Lugmayr A, Danelljan M, Romero A, Yu F, Timofte R, Van Gool L. RePaint: Inpainting using Denoising Diffusion Probabilistic Models. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2022. p. 11461\u201371.","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"pcbi.1014846.ref023","unstructured":"Song J, Meng C, Ermon S. Denoising Diffusion Implicit Models. In: International Conference on Learning Representations. 2021. Available from: https:\/\/openreview.net\/forum?id=St1giarCHLP"},{"key":"pcbi.1014846.ref024","doi-asserted-by":"crossref","DOI":"10.1038\/s44360-026-00145-7","article-title":"A Software Platform for Collaborative Infectious Disease Modeling","author":"Consortium of Infectious Disease Modeling Hubs","year":"2026","journal-title":"Nat Health"},{"key":"pcbi.1014846.ref025","unstructured":"Bosse NI, Gruson H, Cori A, van Leeuwen E, Funk S, Abbott S. Evaluating Forecasts with scoringutils in R. arXiv. ArXiv:2205.07090 [stat]. 2024. Available from: http:\/\/arxiv.org\/abs\/2205.07090"},{"key":"pcbi.1014846.ref026","unstructured":"Farrow DC, Brooks LC, Tibshirani RJ, Rosenfeld R. Delphi Epidata API. 2015. Available from: https:\/\/github.com\/cmu-delphi\/delphi-epidata"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1014846","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T00:00:00Z","timestamp":1791417600000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014846","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T18:00:00Z","timestamp":1791482400000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014846"}},"subtitle":[],"editor":[{"given":"Michiel","family":"van Boven","sequence":"first","affiliation":[{"name":"University Medical Center Utrecht","place":["NETHERLANDS, KINGDOM OF THE"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,30]]},"references-count":26,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,30]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1014846","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,30]]}}}