COVID-19 Outbreak Prediction with Machine Learning

preprint OA: gold CC-BY-4.0
📄 Open PDF Full text JSON View at publisher

Abstract

Several outbreak prediction models for COVID-19 are being used by officials around the world to make informed-decisions and enforce relevant control measures. Among the standard models for COVID-19 global pandemic prediction, simple epidemiological and statistical models have received more attention by authorities, and they are popular in the media. Due to a high level of uncertainty and lack of essential data, standard models have shown low accuracy for long-term prediction. Although the literature includes several attempts to address this issue, the essential generalization and robustness abilities of existing models needs to be improved. This paper presents a comparative analysis of machine learning and soft computing models to predict the COVID-19 outbreak as an alternative to susceptible-infected-recovered (SIR) and susceptible-exposed-infectious-recovered (SEIR) models. Among a wide range of machine learning models investigated, two models showed promising results (i.e., multi-layered perceptron, MLP, and adaptive network-based fuzzy inference system, ANFIS). Based on the results reported here, and due to the highly complex nature of the COVID-19 outbreak and variation in its behavior from nation-to-nation, this study suggests machine learning as an effective tool to model the outbreak. This paper provides an initial benchmarking to demonstrate the potential of machine learning for future research. Paper further suggests that real novelty in outbreak prediction can be realized through integrating machine learning and SEIR models.
Full text 24,521 characters · extracted from preprint-html · click to expand
COVID-19 Outbreak Prediction with Machine Learning | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF COVID-19 Outbreak Prediction with Machine Learning Sina F. Ardabili , Amir Mosavi, Pedram Ghamisi, Filip Ferdinand, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-27130/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Several outbreak prediction models for COVID-19 are being used by officials around the world to make informed-decisions and enforce relevant control measures. Among the standard models for COVID-19 global pandemic prediction, simple epidemiological and statistical models have received more attention by authorities, and they are popular in the media. Due to a high level of uncertainty and lack of essential data, standard models have shown low accuracy for long-term prediction. Although the literature includes several attempts to address this issue, the essential generalization and robustness abilities of existing models needs to be improved. This paper presents a comparative analysis of machine learning and soft computing models to predict the COVID-19 outbreak as an alternative to susceptible-infected-recovered (SIR) and susceptible-exposed-infectious-recovered (SEIR) models. Among a wide range of machine learning models investigated, two models showed promising results (i.e., multi-layered perceptron, MLP, and adaptive network-based fuzzy inference system, ANFIS). Based on the results reported here, and due to the highly complex nature of the COVID-19 outbreak and variation in its behavior from nation-to-nation, this study suggests machine learning as an effective tool to model the outbreak. This paper provides an initial benchmarking to demonstrate the potential of machine learning for future research. Paper further suggests that real novelty in outbreak prediction can be realized through integrating machine learning and SEIR models. Health Economics & Outcomes Research Artificial Intelligence and Machine Learning COVID-19 Coronavirus disease Coronavirus SARS-CoV-2 model prediction machine learning Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Figure 8 Figure 9 Figure 10 Figure 11 Figure 12 Figure 13 Figure 14 Figure 15 Figure 16 Figure 17 Figure 18 Figure 19 Figure 20 Figure 21 Figure 22 Figure 23 Figure 24 Figure 25 Figure 26 Full Text Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-27130","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"","associatedPublications":[],"authors":[{"id":545223,"identity":"c20a473f-bfb2-484b-b919-dc5a4d5bc1c8","order_by":1,"name":"Sina F. Ardabili ","email":"","orcid":"","institution":"","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Sina","middleName":"F.","lastName":"Ardabili","suffix":""},{"id":545224,"identity":"a0eccea4-fd8f-4084-aede-cf1f32cf6bd1","order_by":2,"name":"Amir Mosavi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABDklEQVRIiWNgGAWjYFACxgYYo/FhA0MCRASCeAhqaTYkUgsCsElCtMB1YdfCP+1w2wfGHBt7/hnJbZUz29IYDG43NzB83HFYtr+B95gEFi0StxObZzBuS0uccSOx7ebGthwGgzsHGxhnnjlsPOMAXxo2LQxALQyM2w4nMJw52HbzwZkKBoMbie2/edsOJzYc4DHDpkUeqsVeHqilEKqlgRmkZT4OLQZQLYwbjje2MW6oyEFo2YBDiyFISyLQLxuPNzZLzqhI45EEagH6Jd1442EeYwssWuRupz9m+LjNxl7uMPvDjz0GyXJ8N9IfAEPMWnbe8R7DG1iDGQgSkNhIccGMS/0oGAWjYBSMAkIAAEWzblYWWcprAAAAAElFTkSuQmCC","orcid":"","institution":"","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Amir","middleName":"","lastName":"Mosavi","suffix":""},{"id":545225,"identity":"c7f715d4-cf48-4e37-89e8-a87df066cfa7","order_by":3,"name":"Pedram Ghamisi","email":"","orcid":"","institution":"","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Pedram","middleName":"","lastName":"Ghamisi","suffix":""},{"id":545226,"identity":"b2b24424-3fda-48e8-be19-6e313469a3bc","order_by":4,"name":"Filip Ferdinand","email":"","orcid":"","institution":"","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Filip","middleName":"","lastName":"Ferdinand","suffix":""},{"id":545227,"identity":"d71e5f85-c793-41e6-8115-187b689146b5","order_by":5,"name":"Annamaria R. Varkonyi-Koczy","email":"","orcid":"","institution":"","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Annamaria","middleName":"R.","lastName":"Varkonyi-Koczy","suffix":""},{"id":545228,"identity":"f8e41d89-40ce-4617-bdc9-23a4f1c40b57","order_by":6,"name":"Uwe Reuter","email":"","orcid":"","institution":"","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Uwe","middleName":"","lastName":"Reuter","suffix":""},{"id":545229,"identity":"d6f7632a-b143-4a9f-8bce-bd59f0b807a3","order_by":7,"name":"Timon Rabczuk","email":"","orcid":"","institution":"","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Timon","middleName":"","lastName":"Rabczuk","suffix":""},{"id":545230,"identity":"4ac1a900-7305-40dc-aa35-d9b5c152f75a","order_by":8,"name":"Peter M. Atkinson","email":"","orcid":"","institution":"","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Peter","middleName":"M.","lastName":"Atkinson","suffix":""}],"badges":[],"createdAt":"2020-05-04 17:28:31","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-27130/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-27130/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":1038892,"identity":"6cf0acc4-a371-4670-a7cf-920784df74cd","added_by":"auto","created_at":"2020-05-06 18:02:41","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":89878,"visible":true,"origin":"","legend":"Italy’s COVID-19 outbreak: the actual number of confirmed infections vs. epidemiological model.","description":"","filename":"fig1.png","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1/fig1.png"},{"id":1038894,"identity":"63fe0f53-4dc5-48b9-b6d8-bf2bf55f3745","added_by":"auto","created_at":"2020-05-06 18:02:42","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":135326,"visible":true,"origin":"","legend":"Cumulative number of cases for five countries during thirty days (https://www.worldometers.info/coronavirus/country)","description":"","filename":"fig2.png","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1/fig2.png"},{"id":1038895,"identity":"67b34aa2-7648-4d78-b076-f9df55a63fca","added_by":"auto","created_at":"2020-05-06 18:02:42","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":55697,"visible":true,"origin":"","legend":"GA algorithm","description":"","filename":"fig3.png","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1/fig3.png"},{"id":1038896,"identity":"6f9f49fd-f8be-4e68-94ce-4108a0dc9369","added_by":"auto","created_at":"2020-05-06 18:02:42","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":37131,"visible":true,"origin":"","legend":"GWO algorithm","description":"","filename":"fig4.png","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1/fig4.png"},{"id":1038897,"identity":"6b7ac235-bb71-4514-82b5-4fcabbd7c1b4","added_by":"auto","created_at":"2020-05-06 18:02:42","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":117235,"visible":true,"origin":"","legend":"Architecture of MLP","description":"","filename":"fig5.png","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1/fig5.png"},{"id":1038898,"identity":"9b7f1751-a010-4bf0-9a79-5f8677952683","added_by":"auto","created_at":"2020-05-06 18:02:42","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":102708,"visible":true,"origin":"","legend":"ANFIS architecture","description":"","filename":"fig6.png","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1/fig6.png"},{"id":1038899,"identity":"8464607e-3692-4ce2-bcae-16ea56d5f0ce","added_by":"auto","created_at":"2020-05-06 18:02:42","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":103130,"visible":true,"origin":"","legend":"Fitness graph for China fitted by GWO","description":"","filename":"fig7.png","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1/fig7.png"},{"id":1038900,"identity":"e93f9a3d-e37c-41d9-be77-443cbf4b641a","added_by":"auto","created_at":"2020-05-06 18:02:42","extension":"png","order_by":8,"title":"Figure 8","display":"","copyAsset":false,"role":"figure","size":107197,"visible":true,"origin":"","legend":"Set of models for Italy fitted by GWO","description":"","filename":"fig8.png","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1/fig8.png"},{"id":1038901,"identity":"66b74ab1-406b-4a0d-9158-954f83d433a0","added_by":"auto","created_at":"2020-05-06 18:02:43","extension":"png","order_by":9,"title":"Figure 9","display":"","copyAsset":false,"role":"figure","size":90512,"visible":true,"origin":"","legend":"Set of models for Iran fitted by GWO","description":"","filename":"fig9.png","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1/fig9.png"},{"id":1038902,"identity":"9d0aba09-42b9-4f13-a36c-bb08ec4facda","added_by":"auto","created_at":"2020-05-06 18:02:43","extension":"png","order_by":10,"title":"Figure 10","display":"","copyAsset":false,"role":"figure","size":100584,"visible":true,"origin":"","legend":"Set of models for Germany fitted by GWO","description":"","filename":"fig10.png","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1/fig10.png"},{"id":1038903,"identity":"17f88e9a-92fb-46df-b5b7-1d8ca6fe80e8","added_by":"auto","created_at":"2020-05-06 18:02:43","extension":"png","order_by":11,"title":"Figure 11","display":"","copyAsset":false,"role":"figure","size":107484,"visible":true,"origin":"","legend":"Set of models for USA fitted by GWO","description":"","filename":"fig11.png","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1/fig11.png"},{"id":1038904,"identity":"6becd828-dba9-46e6-8bae-6dac62e253e5","added_by":"auto","created_at":"2020-05-06 18:02:43","extension":"png","order_by":12,"title":"Figure 12","display":"","copyAsset":false,"role":"figure","size":98761,"visible":true,"origin":"","legend":"Set of models for Italy fitted by ML methods","description":"","filename":"fig12.png","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1/fig12.png"},{"id":1038905,"identity":"dad77cb9-dd31-4006-bbd4-62b4ec4ba1eb","added_by":"auto","created_at":"2020-05-06 18:02:43","extension":"png","order_by":13,"title":"Figure 13","display":"","copyAsset":false,"role":"figure","size":98678,"visible":true,"origin":"","legend":"Set of models for China fitted by ML methods","description":"","filename":"fig13.png","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1/fig13.png"},{"id":1038906,"identity":"12ab7db8-86eb-49be-8c1f-9efa632556d9","added_by":"auto","created_at":"2020-05-06 18:02:43","extension":"png","order_by":14,"title":"Figure 14","display":"","copyAsset":false,"role":"figure","size":112913,"visible":true,"origin":"","legend":"Set of models for Iran fitted by ML methods","description":"","filename":"fig14.png","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1/fig14.png"},{"id":1038907,"identity":"30b814e4-5b61-40f4-9cf7-a08d861e41eb","added_by":"auto","created_at":"2020-05-06 18:02:43","extension":"png","order_by":15,"title":"Figure 15","display":"","copyAsset":false,"role":"figure","size":88949,"visible":true,"origin":"","legend":"Set of models for Germany fitted by ML methods","description":"","filename":"fig15.png","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1/fig15.png"},{"id":1038908,"identity":"32248b1c-ccfa-4e41-8556-3578b895f9ab","added_by":"auto","created_at":"2020-05-06 18:02:43","extension":"png","order_by":16,"title":"Figure 16","display":"","copyAsset":false,"role":"figure","size":98266,"visible":true,"origin":"","legend":"Set of models for USA fitted by ML methods","description":"","filename":"fig16.png","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1/fig16.png"},{"id":1038909,"identity":"c1c4969c-7514-42cc-ac72-52525d64aaed","added_by":"auto","created_at":"2020-05-06 18:02:43","extension":"png","order_by":17,"title":"Figure 17","display":"","copyAsset":false,"role":"figure","size":83675,"visible":true,"origin":"","legend":"Deviation from target value for models related to Italy","description":"","filename":"fig17.png","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1/fig17.png"},{"id":1038910,"identity":"d383855c-f7b0-456e-bb07-280a06904fe4","added_by":"auto","created_at":"2020-05-06 18:02:44","extension":"png","order_by":18,"title":"Figure 18","display":"","copyAsset":false,"role":"figure","size":97437,"visible":true,"origin":"","legend":"Deviation from target value for models related to China","description":"","filename":"fig18.png","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1/fig18.png"},{"id":1038911,"identity":"c8bf25e1-4bf8-4417-b4e5-b8c88bbffba9","added_by":"auto","created_at":"2020-05-06 18:02:44","extension":"png","order_by":19,"title":"Figure 19","display":"","copyAsset":false,"role":"figure","size":101906,"visible":true,"origin":"","legend":"Deviation from target value for models related to Iran","description":"","filename":"fig19.png","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1/fig19.png"},{"id":1038912,"identity":"8b9231f5-ebb0-433e-9a5a-1fbfe23f5308","added_by":"auto","created_at":"2020-05-06 18:02:44","extension":"png","order_by":20,"title":"Figure 20","display":"","copyAsset":false,"role":"figure","size":82263,"visible":true,"origin":"","legend":"Deviation from target value for models related to Germany","description":"","filename":"fig20.png","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1/fig20.png"},{"id":1038913,"identity":"b1a09d1f-8356-4821-83ae-4783db390371","added_by":"auto","created_at":"2020-05-06 18:02:44","extension":"png","order_by":21,"title":"Figure 21","display":"","copyAsset":false,"role":"figure","size":91187,"visible":true,"origin":"","legend":"Deviation from target value for models related to USA","description":"","filename":"fig21.png","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1/fig21.png"},{"id":1038914,"identity":"5c880583-3dc2-4280-b795-2fdc2b741429","added_by":"auto","created_at":"2020-05-06 18:02:44","extension":"png","order_by":22,"title":"Figure 22","display":"","copyAsset":false,"role":"figure","size":146969,"visible":true,"origin":"","legend":"The outbreak prediction for Italy through 75 days","description":"","filename":"fig22.png","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1/fig22.png"},{"id":1038915,"identity":"7d3dc058-5353-493d-877a-5c5ba88676f4","added_by":"auto","created_at":"2020-05-06 18:02:44","extension":"png","order_by":23,"title":"Figure 23","display":"","copyAsset":false,"role":"figure","size":130697,"visible":true,"origin":"","legend":"The outbreak prediction for China through 75 days","description":"","filename":"fig23.png","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1/fig23.png"},{"id":1038916,"identity":"e03fcbae-4be1-4841-b483-72a18dc18487","added_by":"auto","created_at":"2020-05-06 18:02:45","extension":"png","order_by":24,"title":"Figure 24","display":"","copyAsset":false,"role":"figure","size":141615,"visible":true,"origin":"","legend":"The outbreak prediction for Iran through 75 days","description":"","filename":"fig24.png","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1/fig24.png"},{"id":1038917,"identity":"60d5db3c-0586-4233-aa94-f6d46a6505d1","added_by":"auto","created_at":"2020-05-06 18:02:45","extension":"png","order_by":25,"title":"Figure 25","display":"","copyAsset":false,"role":"figure","size":127253,"visible":true,"origin":"","legend":"The outbreak prediction for Germany through 75 days","description":"","filename":"fig25.png","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1/fig25.png"},{"id":1038918,"identity":"eaf91b1c-5e33-4056-8049-021048ac2f68","added_by":"auto","created_at":"2020-05-06 18:02:45","extension":"png","order_by":26,"title":"Figure 26","display":"","copyAsset":false,"role":"figure","size":139990,"visible":true,"origin":"","legend":"The outbreak prediction for the USA through 75 days","description":"","filename":"fig26.png","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1/fig26.png"},{"id":1038927,"identity":"4d3c8574-1e5f-419e-afb6-8c2c66d22a6f","added_by":"auto","created_at":"2020-05-06 18:02:57","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2369855,"visible":true,"origin":"","legend":"","description":"","filename":"COVIDArxive.pdf","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1_stamped.pdf"},{"id":1038893,"identity":"7e5dfdae-6074-445c-93c9-351edb310347","added_by":"auto","created_at":"2020-05-06 18:02:42","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2022664,"visible":true,"origin":"","legend":"","description":"","filename":"COVIDArxive.pdf","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1/COVIDArxive.pdf"},{"id":13501906,"identity":"b35aaa3a-45fd-4f4c-b86e-7a42c6daf70a","added_by":"auto","created_at":"2021-09-16 23:12:32","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2795885,"visible":true,"origin":"","legend":"","description":"","filename":"COVIDArxive.pdf","url":"https://assets-eu.researchsquare.com/files/rs-27130/v1_covered.pdf"}],"financialInterests":"","formattedTitle":"\u003cp\u003eCOVID-19 Outbreak Prediction with Machine Learning\u003c/p\u003e","fulltext":[{"header":"Full Text","content":"\u003cp\u003eThis preprint is available for \u003ca href='/article/rs-27130/latest.pdf' target='_blank'\u003edownload as a PDF\u003c/a\u003e.\u003c/p\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"COVID-19, Coronavirus disease, Coronavirus, SARS-CoV-2, model, prediction, machine learning","lastPublishedDoi":"10.21203/rs.3.rs-27130/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-27130/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eSeveral\u003cstrong\u003e \u003c/strong\u003eoutbreak prediction models for COVID-19 are being used by officials around the world to make informed-decisions and enforce relevant control measures. Among the standard models for COVID-19 global pandemic prediction, simple epidemiological and statistical models have received more attention by authorities, and they are popular in the media. Due to a high level of uncertainty and lack of essential data, standard models have shown low accuracy for long-term prediction. Although the literature includes several attempts to address this issue, the essential generalization and robustness abilities of existing models needs to be improved. This paper presents a comparative analysis of machine learning and soft computing models to predict the COVID-19 outbreak as an alternative to susceptible-infected-recovered (SIR) and susceptible-exposed-infectious-recovered (SEIR) models. Among a wide range of machine learning models investigated, two models showed promising results (i.e., multi-layered perceptron, MLP, and adaptive network-based fuzzy inference system, ANFIS). Based on the results reported here, and due to the highly complex nature of the COVID-19 outbreak and variation in its behavior from nation-to-nation, this study suggests machine learning as an effective tool to model the outbreak. This paper provides an initial benchmarking to demonstrate the potential of machine learning for future research. Paper further suggests that real novelty in outbreak prediction can be realized through integrating machine learning and SEIR models. \u0026nbsp;\u0026nbsp;\u003c/p\u003e","manuscriptTitle":"COVID-19 Outbreak Prediction with Machine Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2020-05-06 18:02:15","doi":"10.21203/rs.3.rs-27130/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"02f24ba1-a245-42dc-9243-4637258fb2c6","owner":[],"postedDate":"May 6th, 2020","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":93472,"name":"Health Economics \u0026 Outcomes Research"},{"id":93473,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2020-05-06T18:02:15+00:00","versionOfRecord":[],"versionCreatedAt":"2020-05-06 18:02:15","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-27130","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-27130","identity":"rs-27130","version":["v1"]},"buildId":"ehx78VzkSd0WSzXnipQa-","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. The paper's references may be in our DB but unresolved to ``paper_id`` (resolution happens at ingest when the cited DOI matches a row we already have). Run the cross-source citation reconcile pass to retry.

Source provenance

europepmc
last seen: 2026-05-19T01:45:01.086888+00:00
unpaywall
last seen: 2026-05-21T05:10:58.409756+00:00
License: CC-BY-4.0