{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T21:52:34Z","timestamp":1793483554441,"version":"4.5.0"},"reference-count":80,"publisher":"The Royal Society","issue":"232","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/royalsociety.org\/-\/media\/journals\/author\/Licence-to-Publish-20062019-final.pdf"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/royalsociety.org\/journals\/ethics-policies\/data-sharing-mining\/"}],"funder":[{"name":"NIH"},{"name":"NSF SCH"}],"content-domain":{"domain":["royalsocietypublishing.org"],"crossmark-restriction":true},"short-container-title":["J. R. Soc. Interface."],"published-print":{"date-parts":[[2025,11]]},"abstract":"<jats:p>Accurate forecasting of contagious illnesses has become increasingly important to public health policymaking and better prediction could prevent the loss of millions of lives. To better prepare for future pandemics, it is essential to improve forecasting methods and capabilities. In this work, we implement physics-informed neural networks (PINNs), a popular tool in the area of scientific machine learning, to perform infectious disease forecasting. The used PINNs model incorporates dynamical systems representations of disease transmission into the loss function, thereby assimilating epidemiological theory and data using neural networks. Our approach is designed to prevent model overfitting, which often occurs when training deep-learning models with observation data alone. In addition, we use an additional sub-network to account for mobility, cumulative vaccine doses and other covariates that influence the transmission rate, a key parameter in the compartmental model. To demonstrate the capability of the proposed model, we examine the performance of the model using state-level COVID-19 data in California. Our simulation results show that predictions of the PINNs model on the number of cases, deaths and hospitalizations are consistent with existing benchmarks. In particular, the PINNs model outperforms naive baseline forecasts and various sequence deep-learning models, such as recurrent neural networks, long short-term memory networks, gated recurrent units and transformer models. We also show that the performance of the PINNs model is comparable with that of a sophisticated Gaussian infection state forecasting model that combines the compartmental model, a data observation model and a regression model for inferring parameters in the compartmental model. Nonetheless, the PINNs model offers a simpler structure and is easier to implement. In summary, we perform a systematic study of the predictive capability of the PINNs model in forecasting the dynamics of infectious diseases and our results showcase the potential of the proposed model as an efficient computational tool to enhance the current capacity of infectious disease forecasting.<\/jats:p>","DOI":"10.1098\/rsif.2025.0379","type":"journal-article","created":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T00:05:47Z","timestamp":1764115547000},"update-policy":"https:\/\/doi.org\/10.1098\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["Physics-informed deep learning for infectious disease forecasting"],"prefix":"10.1098","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9596-8432","authenticated-orcid":true,"given":"Ying","family":"Qian","sequence":"first","affiliation":[{"name":"School of Chemical, Materials, and Biomedical Engineering, University of Georgia","place":["Athens, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8243-9234","authenticated-orcid":true,"given":"Kui","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Chemical, Materials, and Biomedical Engineering, University of Georgia","place":["Athens, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric","family":"Marty","sequence":"additional","affiliation":[{"name":"Odum School of Ecology and Center for the Ecology of Infectious Diseases, University of Georgia","place":["Athens, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Avranil","family":"Basu","sequence":"additional","affiliation":[{"name":"Odum School of Ecology and Center for the Ecology of Infectious Diseases, University of Georgia","place":["Athens, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4748-683X","authenticated-orcid":true,"given":"Eamon B.","family":"O'Dea","sequence":"additional","affiliation":[{"name":"Odum School of Ecology and Center for the Ecology of Infectious Diseases, University of Georgia","place":["Athens, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2461-3015","authenticated-orcid":true,"given":"Xianqiao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Environmental, Civil Agricultural and Mechanical Engineering, College of Engineering, University of Georgia","place":["Athens, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1969-3778","authenticated-orcid":true,"given":"Spencer J.","family":"Fox","sequence":"additional","affiliation":[{"name":"Department of Epidemiology and Biostatistics, University of Georgia","place":["Athens, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7221-3801","authenticated-orcid":true,"given":"Pejman","family":"Rohani","sequence":"additional","affiliation":[{"name":"Odum School of Ecology and Center for the Ecology of Infectious Diseases, University of Georgia","place":["Athens, USA"]},{"name":"Department of Infectious Diseases, College of Veterinary Medicine, University of Georgia","place":["Athens, USA"]},{"name":"Center for Influenza Disease and Emergence Research, University of Georgia","place":["Athens, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4646-1235","authenticated-orcid":true,"given":"John M.","family":"Drake","sequence":"additional","affiliation":[{"name":"Odum School of Ecology and Center for the Ecology of Infectious Diseases, University of Georgia","place":["Athens, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"He","family":"Li","sequence":"additional","affiliation":[{"name":"School of Chemical, Materials, and Biomedical Engineering, University of Georgia","place":["Athens, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"175","published-online":{"date-parts":[[2025,11,26]]},"reference":[{"key":"e_1_3_9_2_2","doi-asserted-by":"publisher","DOI":"10.15585\/mmwr.mm7117e1"},{"key":"e_1_3_9_3_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature02759"},{"key":"e_1_3_9_4_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-022-04788-w"},{"key":"e_1_3_9_5_2","doi-asserted-by":"publisher","DOI":"10.1093\/cid\/ciab673"},{"key":"e_1_3_9_6_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12889-019-7966-8"},{"key":"e_1_3_9_7_2","article-title":"An accurate hierarchical model to forecast diverse seasonal infectious diseases","author":"Case BKM","year":"2025","unstructured":"Case BKM, Salcedo MV, Fox SJ. 2025 An accurate hierarchical model to forecast diverse seasonal infectious diseases. medRxiv. (doi:10.1101\/2025.03.03.25323259)","journal-title":"medRxiv."},{"key":"e_1_3_9_8_2","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198545996.001.0001"},{"key":"e_1_3_9_9_2","volume-title":"Modelling infectious diseases: in humans and animals","author":"Keeling MJ","year":"2008","unstructured":"Keeling MJ, Rohani P. 2008 Modelling infectious diseases: in humans and animals. Princeton, NJ: Princeton University Press. (doi:10.1515\/9781400841035)"},{"key":"e_1_3_9_10_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-78911-6_2"},{"key":"e_1_3_9_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4939-9828-9"},{"key":"e_1_3_9_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7612-3"},{"key":"e_1_3_9_13_2","doi-asserted-by":"publisher","DOI":"10.1111\/1469-0691.12308"},{"key":"e_1_3_9_14_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.0020174"},{"key":"e_1_3_9_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2020.12.001"},{"key":"e_1_3_9_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cnsns.2021.105764"},{"key":"e_1_3_9_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2020.109846"},{"key":"e_1_3_9_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/s42399-020-00330-z"},{"key":"e_1_3_9_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2020.110388"},{"key":"e_1_3_9_20_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-32159-6"},{"key":"e_1_3_9_21_2","doi-asserted-by":"publisher","DOI":"10.1126\/scitranslmed.aaj1748"},{"key":"e_1_3_9_22_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1508814112"},{"key":"e_1_3_9_23_2","doi-asserted-by":"publisher","DOI":"10.1098\/rsif.2021.0702"},{"key":"e_1_3_9_24_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1011610"},{"key":"e_1_3_9_25_2","article-title":"Real-time mechanistic bayesian forecasts of COVID-19 mortality","author":"Gibson GC","year":"2020","unstructured":"Gibson GC, Reich NG, Sheldon D. 2020 Real-time mechanistic bayesian forecasts of COVID-19 mortality. medRxiv. (doi:10.1101\/2020.12.22.20248736)","journal-title":"medRxiv"},{"key":"e_1_3_9_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210077"},{"key":"e_1_3_9_27_2","first-page":"2081","article-title":"Deep learning for few-shot white blood cell image classification and feature learning","volume":"11","author":"Deng Y","year":"2023","unstructured":"Deng Y, Li H. 2023 Deep learning for few-shot white blood cell image classification and feature learning. Comput. Methods Biomech. Biomed. Eng. 11, 2081\u20132091. (doi:10.1080\/21681163.2023.2219341)","journal-title":"Comput. Methods Biomech. Biomed. Eng."},{"key":"e_1_3_9_28_2","doi-asserted-by":"publisher","DOI":"10.3389\/fphy.2023.1259273"},{"key":"e_1_3_9_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107187"},{"key":"e_1_3_9_30_2","article-title":"Mathematical models for predicting COVID-19 pandemic: a review","volume":"1797","author":"Vytla V","year":"2021","unstructured":"Vytla V, Ramakuri SK, Peddi A, Kalyan Srinivas K, Nithish Ragav N. 2021 Mathematical models for predicting COVID-19 pandemic: a review. J. Phys. 1797, 012009. (doi:10.1088\/1742-6596\/1797\/1\/012009)","journal-title":"J. Phys."},{"key":"e_1_3_9_31_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42254-021-00314-5"},{"key":"e_1_3_9_32_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaw4741"},{"key":"e_1_3_9_33_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1922210117"},{"key":"e_1_3_9_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2025.113947"},{"key":"e_1_3_9_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2024.112918"},{"key":"e_1_3_9_36_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2023.116647"},{"key":"e_1_3_9_37_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2024.117479"},{"key":"e_1_3_9_38_2","doi-asserted-by":"publisher","DOI":"10.1137\/22M1518189"},{"key":"e_1_3_9_39_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2020.109913"},{"key":"e_1_3_9_40_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2020.113250"},{"key":"e_1_3_9_41_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2022.114823"},{"key":"e_1_3_9_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2021.110676"},{"key":"e_1_3_9_43_2","doi-asserted-by":"publisher","DOI":"10.1137\/19M1274067"},{"key":"e_1_3_9_44_2","doi-asserted-by":"publisher","DOI":"10.1007\/s44379-025-00015-1"},{"key":"e_1_3_9_45_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2018.10.045"},{"key":"e_1_3_9_46_2","doi-asserted-by":"publisher","DOI":"10.1167\/tvst.11.8.7"},{"key":"e_1_3_9_47_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106867"},{"key":"e_1_3_9_48_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ynexs.2024.100016"},{"key":"e_1_3_9_49_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00366-024-02003-0"},{"key":"e_1_3_9_50_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106732"},{"key":"e_1_3_9_51_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2100697118"},{"key":"e_1_3_9_52_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2022.115346"},{"key":"e_1_3_9_53_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2021.110754"},{"key":"e_1_3_9_54_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2020.113500"},{"key":"e_1_3_9_55_2","doi-asserted-by":"crossref","unstructured":"Zou Z Wang Z Karniadakis GE. 2025 Learning and discovering multiple solutions using physics-informed neural networks with random initialization and deep ensemble. (https:\/\/arxiv.org\/abs\/2503.06320)","DOI":"10.1098\/rspa.2025.0205"},{"key":"e_1_3_9_56_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2020.113547"},{"key":"e_1_3_9_57_2","doi-asserted-by":"publisher","DOI":"10.3390\/axioms11030121"},{"key":"e_1_3_9_58_2","unstructured":"Millevoi C. 2024 Physics-informed neural network in porous media and epidemiological applications. Doctoral thesis Universit\u00e0 degli Studi di Padova Italy."},{"key":"e_1_3_9_59_2","doi-asserted-by":"publisher","DOI":"10.3390\/epidemiologia2040033"},{"key":"e_1_3_9_60_2","doi-asserted-by":"publisher","DOI":"10.3934\/mbe.2023729"},{"key":"e_1_3_9_61_2","doi-asserted-by":"publisher","DOI":"10.3390\/v15081749"},{"key":"e_1_3_9_62_2","doi-asserted-by":"publisher","DOI":"10.1515\/cmb-2022-0001"},{"key":"e_1_3_9_63_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13662-022-03733-5"},{"key":"e_1_3_9_64_2","unstructured":"Shaier S Raissi M Seshaiyer P. 2021 Data-driven approaches for predicting spread of infectious diseases through DINNs: disease informed neural networks. (https:\/\/arxiv.org\/abs\/2110.05445)"},{"key":"e_1_3_9_65_2","doi-asserted-by":"publisher","DOI":"10.1615\/JMachLearnModelComput.2023047213"},{"key":"e_1_3_9_66_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1008618"},{"key":"e_1_3_9_67_2","article-title":"Ensemble forecasts of coronavirus disease 2019 (COVID-19) in the US","author":"Ray EL","year":"2020","unstructured":"Ray EL et al. 2020 Ensemble forecasts of coronavirus disease 2019 (COVID-19) in the US. medRxiv. (doi:10.1101\/2020.08.19.20177493)","journal-title":"medRxiv."},{"key":"e_1_3_9_68_2","doi-asserted-by":"publisher","DOI":"10.1016\/S1473-3099(20)30120-1"},{"key":"e_1_3_9_69_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2111452118"},{"key":"e_1_3_9_70_2","unstructured":"Google LLC. 2020 Google COVID-19 community mobility reports. See https:\/\/www.google.com\/covid19\/mobility\/."},{"key":"e_1_3_9_71_2","unstructured":"Kingma DP Ba J. 2014 Adam: a method for stochastic optimization. (https:\/\/arxiv.org\/abs\/1412.6980)"},{"key":"e_1_3_9_72_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2006.03.001"},{"key":"e_1_3_9_73_2","doi-asserted-by":"publisher","DOI":"10.4249\/scholarpedia.1888"},{"key":"e_1_3_9_74_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_9_75_2","doi-asserted-by":"publisher","DOI":"10.1109\/MWSCAS.2017.8053243"},{"key":"e_1_3_9_76_2","doi-asserted-by":"crossref","unstructured":"Ghojogh B Ghodsi A. 2020 Attention mechanism transformers BERT and GPT: tutorial and survey. OSF. (doi:10.31219\/osf.io\/m6gcn)","DOI":"10.31219\/osf.io\/m6gcn"},{"key":"e_1_3_9_77_2","first-page":"14453","article-title":"EINNs: epidemiologically-informed neural networks","volume":"37","author":"Rodr\u00edguez A","year":"2023","unstructured":"Rodr\u00edguez A, Cui J, Ramakrishnan N, Adhikari B, Prakash BA. 2023 EINNs: epidemiologically-informed neural networks. Proc. AAAI Conf. Artif. Intell. 37, 14453\u201314460. (doi:10.1609\/aaai.v37i12.26690)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"e_1_3_9_78_2","doi-asserted-by":"publisher","DOI":"10.15302\/J-QB-022-0281"},{"key":"e_1_3_9_79_2","article-title":"Neural networks for endemic measles dynamics: comparative analysis and integration with mechanistic models","author":"Madden WG","year":"2024","unstructured":"Madden WG, Jin W, Lopman B, Zufle A, Dalziel B, Metcalf CJE, Grenfell BT, Lau MSY. 2024 Neural networks for endemic measles dynamics: comparative analysis and integration with mechanistic models. medRxiv. (doi:10.1101\/2024.05.28.24307979)","journal-title":"medRxiv."},{"key":"e_1_3_9_80_2","unstructured":"Ying Q. 2025 Data & code. Physics-informed deep learning for infectious disease forecasting. Zenodo. (doi:10.5281\/zenodo.17196508)"},{"key":"e_1_3_9_81_2","doi-asserted-by":"publisher","DOI":"10.15585\/mmwr.mm7030e2"}],"container-title":["Journal of The Royal Society Interface"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/royalsocietypublishing.org\/doi\/pdf\/10.1098\/rsif.2025.0379","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/royalsocietypublishing.org\/doi\/full-xml\/10.1098\/rsif.2025.0379","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/royalsocietypublishing.org\/doi\/pdf\/10.1098\/rsif.2025.0379","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T00:05:59Z","timestamp":1764115559000},"score":1,"resource":{"primary":{"URL":"https:\/\/royalsocietypublishing.org\/doi\/10.1098\/rsif.2025.0379"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":80,"journal-issue":{"issue":"232","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["10.1098\/rsif.2025.0379"],"URL":"https:\/\/doi.org\/10.1098\/rsif.2025.0379","relation":{},"ISSN":["1742-5662"],"issn-type":[{"value":"1742-5662","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]},"assertion":[{"value":"2025-04-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-29","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-25","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"20250379"}}