Scalable Variational Learning for Noisy-OR Bayesian Networks with Normalizing Flows for Complex Cascading Disaster Systems

Scalable Variational Learning for Noisy-OR Bayesian Networks with Normalizing Flows for Complex Cascading Disaster Systems | 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 Scalable Variational Learning for Noisy-OR Bayesian Networks with Normalizing Flows for Complex Cascading Disaster Systems Xuechun Li, Susu Xu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5462482/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 11 You are reading this latest preprint version Abstract Sudden-onset disasters such as earthquakes often induce multiple cascading hazards and impacts, causing human and economic losses. While recent advances in remote sensing technologies provide valuable data for rapid hazard assessment, current methods face two fundamental limitations. First, the inherent causal relationship and co-location of disaster-induced hazards and impacts makes the decoupling of individual hazard or impact particularly challenging. Second, and critically for disaster response, existing methods cannot adapt to new information during the critical response period - they provide only static initial estimates despite the continuous influx of ground truth data from field reconnaissance. This inability to update and refine assessments in real-time severely limits their practical utility for emergency response, where understanding of the disaster's impact typically evolves significantly over time. Herein, we present online-DisasterVINF, a framework that uniquely addresses both limitations. We leverage Noisy-OR Bayesian networks, which are particularly suited for modeling how multiple hazards independently contribute to the observed impacts, combined with normalizing flows to provide a more expressive alternative to simple log-linear relationships. The framework is also capable of improving its estimation by incorporating ground truth data as it becomes available through post-disaster reconnaissance. We develop a novel variational inference approach that jointly approximates posteriors by leveraging complex causal relationships and remote sensing techniques. We evaluate our framework on multiple seismic events from diverse countries around the globe. Our results demonstrate that online-DisasterVINF significantly enhances estimation accuracy compared to existing methods, while our analysis shows the online updating mechanism substantially improves model performance as ground truth becomes available, underlining its adaptability for real-time disaster response. Earth and environmental sciences/Environmental sciences Earth and environmental sciences/Natural hazards Full Text Additional Declarations No competing interests reported. Supplementary Files NPJdisasterVINFsubmitsupplement.pdf Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 16 Jan, 2025 Reviews received at journal 16 Jan, 2025 Reviewers agreed at journal 06 Jan, 2025 Reviewers agreed at journal 02 Jan, 2025 Reviews received at journal 26 Nov, 2024 Reviewers agreed at journal 24 Nov, 2024 Reviewers agreed at journal 24 Nov, 2024 Reviewers invited by journal 21 Nov, 2024 Editor assigned by journal 21 Nov, 2024 Submission checks completed at journal 21 Nov, 2024 First submitted to journal 15 Nov, 2024 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-5462482","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":383155046,"identity":"5858810e-e65c-47d3-ac30-62619e8bd7b2","order_by":0,"name":"Xuechun Li","email":"","orcid":"","institution":"Johns Hopkins University","correspondingAuthor":false,"prefix":"","firstName":"Xuechun","middleName":"","lastName":"Li","suffix":""},{"id":383155047,"identity":"43630c5a-32e5-4bd1-8c7d-1ca69cfd04f1","order_by":1,"name":"Susu Xu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAqElEQVRIiWNgGAWjYPACG2YDEMVDgpY00rUcZiBei/yM9GfSvG3n2c0lEhgfvG0jQovBjRwzyZltt5ktZyQwG84lSotEDpvER6AWgxsJbEDriHSYRGLbOZAW9t9EaWG4kWAGtOUA2BZmorQYnHljbDnjXDKzwZmHzZJzzhHjsPb0h7d5yuySDY4nH/zwpowYh0FBMgMDYwMJ6oHAjjTlo2AUjIJRMKIAAOnIMkn3oEOtAAAAAElFTkSuQmCC","orcid":"","institution":"Johns Hopkins University","correspondingAuthor":true,"prefix":"","firstName":"Susu","middleName":"","lastName":"Xu","suffix":""}],"badges":[],"createdAt":"2024-11-15 18:53:07","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5462482/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5462482/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":70520532,"identity":"60ddbed1-c7f7-4d37-904b-f935f9c79b96","added_by":"auto","created_at":"2024-12-04 03:25:03","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":10251991,"visible":true,"origin":"","legend":"","description":"","filename":"NPJdisasterVINFsubmit.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5462482/v1_covered_80059267-42a1-40e8-b888-f330f2511895.pdf"},{"id":70519533,"identity":"81b67a88-e91b-4640-95a3-552ad660beee","added_by":"auto","created_at":"2024-12-04 03:16:59","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":44190073,"visible":true,"origin":"","legend":"","description":"","filename":"NPJdisasterVINFsubmitsupplement.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5462482/v1/e2bb1202b983b35410a4c5d8.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Scalable Variational Learning for Noisy-OR Bayesian Networks with Normalizing Flows for Complex Cascading Disaster Systems","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"npj-natural-hazards","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [npj Natural Hazards](https://www.nature.com/npjnathazards/)","snPcode":"44304","submissionUrl":"https://submission.springernature.com/new-submission/44304/3","title":"npj Natural Hazards","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-5462482/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5462482/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Sudden-onset disasters such as earthquakes often induce multiple cascading hazards and impacts, causing human and economic losses. While recent advances in remote sensing technologies provide valuable data for rapid hazard assessment, current methods face two fundamental limitations. First, the inherent causal relationship and co-location of disaster-induced hazards and impacts makes the decoupling of individual hazard or impact particularly challenging. Second, and critically for disaster response, existing methods cannot adapt to new information during the critical response period - they provide only static initial estimates despite the continuous influx of ground truth data from field reconnaissance. This inability to update and refine assessments in real-time severely limits their practical utility for emergency response, where understanding of the disaster's impact typically evolves significantly over time. Herein, we present online-DisasterVINF, a framework that uniquely addresses both limitations. We leverage Noisy-OR Bayesian networks, which are particularly suited for modeling how multiple hazards independently contribute to the observed impacts, combined with normalizing flows to provide a more expressive alternative to simple log-linear relationships. The framework is also capable of improving its estimation by incorporating ground truth data as it becomes available through post-disaster reconnaissance. We develop a novel variational inference approach that jointly approximates posteriors by leveraging complex causal relationships and remote sensing techniques. We evaluate our framework on multiple seismic events from diverse countries around the globe. Our results demonstrate that online-DisasterVINF significantly enhances estimation accuracy compared to existing methods, while our analysis shows the online updating mechanism substantially improves model performance as ground truth becomes available, underlining its adaptability for real-time disaster response.","manuscriptTitle":"Scalable Variational Learning for Noisy-OR Bayesian Networks with Normalizing Flows for Complex Cascading Disaster Systems","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-12-04 03:16:51","doi":"10.21203/rs.3.rs-5462482/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-01-17T02:27:51+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-01-16T21:51:54+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"96725262924987150012294715332709536226","date":"2025-01-06T14:54:09+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"107331263004927725532983515060503165131","date":"2025-01-02T17:45:03+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-11-27T04:20:50+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"145523798316981214755260190138972284949","date":"2024-11-24T09:15:17+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"124471025213487235227570522889033108114","date":"2024-11-24T09:09:12+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-11-21T13:47:08+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-11-21T13:44:33+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-11-21T13:32:43+00:00","index":"","fulltext":""},{"type":"submitted","content":"npj Natural Hazards","date":"2024-11-15T18:37:48+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"npj-natural-hazards","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [npj Natural Hazards](https://www.nature.com/npjnathazards/)","snPcode":"44304","submissionUrl":"https://submission.springernature.com/new-submission/44304/3","title":"npj Natural Hazards","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"cebeb082-9138-420b-8c32-aef3d31b05b5","owner":[],"postedDate":"December 4th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":40810218,"name":"Earth and environmental sciences/Environmental sciences"},{"id":40810219,"name":"Earth and environmental sciences/Natural hazards"}],"tags":[],"updatedAt":"2025-02-27T08:23:53+00:00","versionOfRecord":[],"versionCreatedAt":"2024-12-04 03:16:51","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5462482","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5462482","identity":"rs-5462482","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}