Fire Danger Forecasting on an Hourly Basis via Weather Station-Based Machine Learning in the Sunshine Coast, Australia

Fire Danger Forecasting on an Hourly Basis via Weather Station-Based Machine Learning in the Sunshine Coast, Australia | 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 Article Fire Danger Forecasting on an Hourly Basis via Weather Station-Based Machine Learning in the Sunshine Coast, Australia Alberto Ardid, Andres Valencia, Antonhy Power, David Dempsey This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3857623/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 Sudden wildfire outbreaks can have devastating consequences, making accurate short-term forecasting crucial for timely evacuations and effective fire management strategies. Current systems, reliant on traditional methods and historical data, may not adequately capture the rapidly changing conditions leading to wildfires. This study introduces a novel machine learning-based approach for forecasting wildfire danger, tested on the Sunshine Coast of Australia. By analyzing real-time data from local weather stations, we aim to identify distinct weather patterns occurring hours to days before potential wildfires at high temporal resolution. Using 20 years of historical data, we trained machine learning models that achieved high accuracy in classifying pre-fire conditions and improve by 47% the overall performance compared to the classical forest fire danger index approach. The research also envisions extending this approach to other regions, overcoming data limitations for more effective global wildfire. This advancement addresses the immediate need for improved forecasting and sets the stage for more adaptable systems in the future. Earth and environmental sciences/Natural hazards Physical sciences/Mathematics and computing/Statistics Wildfires forecasting machine learning time series feature engineering. Full Text Additional Declarations No competing interests reported. Supplementary Files SIrev1101.pdf 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-3857623","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":267274577,"identity":"8f92e95b-ea7c-43d5-adfd-993ca4c680e3","order_by":0,"name":"Alberto Ardid","email":"data:image/png;base64,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","orcid":"","institution":"University of Canterbury","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Alberto","middleName":"","lastName":"Ardid","suffix":""},{"id":267274579,"identity":"ad7bcfcb-5133-4f50-afb6-5b9107a2c392","order_by":1,"name":"Andres Valencia","email":"","orcid":"","institution":"University of Canterbury","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Andres","middleName":"","lastName":"Valencia","suffix":""},{"id":267274580,"identity":"6f4b4c08-4021-408f-b6e9-4a985351add1","order_by":2,"name":"Antonhy Power","email":"","orcid":"","institution":"COVEY Associates Pty Ltd","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Antonhy","middleName":"","lastName":"Power","suffix":""},{"id":267274583,"identity":"61dfde81-d9d4-4470-8e25-eec65f282547","order_by":3,"name":"David Dempsey","email":"","orcid":"","institution":"University of Canterbury","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"David","middleName":"","lastName":"Dempsey","suffix":""}],"badges":[],"createdAt":"2024-01-12 16:44:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3857623/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3857623/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":55486631,"identity":"b88b8af2-6aa5-4b24-8114-e4708ff98572","added_by":"auto","created_at":"2024-04-29 06:13:44","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":962212,"visible":true,"origin":"","legend":"","description":"","filename":"maintext.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3857623/v1_covered_34b94b04-68b6-45ed-95ec-76c49e11a2df.pdf"},{"id":49657001,"identity":"189cb56f-1d68-42d3-8659-e0ff65516348","added_by":"auto","created_at":"2024-01-16 04:04:38","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":906296,"visible":true,"origin":"","legend":"","description":"","filename":"SIrev1101.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3857623/v1/f91fb30c42799139e68c1ab8.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Fire Danger Forecasting on an Hourly Basis via Weather Station-Based Machine Learning in the Sunshine Coast, Australia","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"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":"Wildfires forecasting, machine learning, time series feature engineering.","lastPublishedDoi":"10.21203/rs.3.rs-3857623/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3857623/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Sudden wildfire outbreaks can have devastating consequences, making accurate short-term forecasting crucial for timely evacuations and effective fire management strategies. Current systems, reliant on traditional methods and historical data, may not adequately capture the rapidly changing conditions leading to wildfires. This study introduces a novel machine learning-based approach for forecasting wildfire danger, tested on the Sunshine Coast of Australia. By analyzing real-time data from local weather stations, we aim to identify distinct weather patterns occurring hours to days before potential wildfires at high temporal resolution. Using 20 years of historical data, we trained machine learning models that achieved high accuracy in classifying pre-fire conditions and improve by 47% the overall performance compared to the classical forest fire danger index approach. The research also envisions extending this approach to other regions, overcoming data limitations for more effective global wildfire. This advancement addresses the immediate need for improved forecasting and sets the stage for more adaptable systems in the future.","manuscriptTitle":"Fire Danger Forecasting on an Hourly Basis via Weather Station-Based Machine Learning in the Sunshine Coast, Australia","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-01-16 04:04:33","doi":"10.21203/rs.3.rs-3857623/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":"28f38100-0c8a-493f-8632-c1efcb118221","owner":[],"postedDate":"January 16th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":28156636,"name":"Earth and environmental sciences/Natural hazards"},{"id":28156637,"name":"Physical sciences/Mathematics and computing/Statistics"}],"tags":[],"updatedAt":"2024-04-29T06:12:13+00:00","versionOfRecord":[],"versionCreatedAt":"2024-01-16 04:04:33","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3857623","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3857623","identity":"rs-3857623","version":["v1"]},"buildId":"cBFmMYwuxLRRLfASyISRj","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}