BiLSTM-RiskNet: Domain-Guided Explainable Deep Learning for Multi-Class Climate Risk Prediction from Hourly Weather Data

BiLSTM-RiskNet: Domain-Guided Explainable Deep Learning for Multi-Class Climate Risk Prediction from Hourly Weather Data | 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 Research Article BiLSTM-RiskNet: Domain-Guided Explainable Deep Learning for Multi-Class Climate Risk Prediction from Hourly Weather Data Anzim Hasan Nabil, MD Mahmudul Alom Sifat, Sadia Akter Sarika, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7793347/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 Precise and transparent forecasting of climate risk levels remains a formidable task in disaster preparedness because most current approaches either utilize static rule-based thresholds or do not tackle temporal trends in weather observations. These approaches typically prioritize the accuracy of predictions at the expense of interpretability and are thus unsuitable in high-stakes early-warning systems. To fill such gaps, this paper presents BiLSTM-RiskNet, a new domain-knowledge-guided and explainable deep learning approach for climate risk classification (low, medium, high) from raw hourly weather time series. Compared to existing research, the model employs physics-constrained automated labeling according to authoritative meteorological guidelines like NOAA Heat Index, Saffir–Simpson wind scale, and WMO barometric pressure criteria to provide semantically meaningful supervision in place of random thresholds. A Bidirectional LSTM is used on 24-hour rolling sequences to identify forward and backward temporal trends, so the model is better able to identify changing risk patterns than fixed or unidirectional methods. To address deep learning's black-box issue, explainable AI techniques are incorporated: LIME supplies local, instance-level interpretation, and SHAP supplies global feature attribution. These descriptions corroborate the model's reasoning to be theoretically rooted in climatological theory, e.g., extreme heat, humidity, and low pressure forming a part of the factors that contribute towards risky conditions. Equipped with a stratified, city-conscious dataset of more than three million hourly observations, BiLSTM-RiskNet achieves 95.23% accuracy with F1-scores of 0.98 (low), 0.72 (medium), and 0.92 (high) surpassing traditional machine learning and deep learning baselines. This synthesis of physics-based labeling, temporal deep learning, and open post-hoc explainability is a solid and reliable paradigm for real-time operational deployment, and represents an important milestone in AI-based climate risk reduction and disaster resilience. Climate Risk Prediction Sequential Deep Learning Bidirectional LSTM Domain-Guided Labeling LIME Interpretability SHAP Early Warning System Full Text Additional Declarations No competing interests reported. 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-7793347","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":525545121,"identity":"421583a5-b705-4b88-b189-cc265a7279a1","order_by":0,"name":"Anzim Hasan Nabil","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4UlEQVRIiWNgGAWjYHCChAMg0oCZufEBkObhI0ELY7MBSAsb0XYZMDC2SYAYBLXwz254eOgGwx15c3bGtsqvOXYybAzMDx/dwKNF4s6BhMM5DM8MdzYztt2W3ZYMdBibsXEOPmtuJIC0HGbccBioRXIbM1ALD5s0Pi3yUC32IC3FktvqCWsxgGpJBGlh/LjtMGEthmAtBoeTgX5plmbcdpyHjZmAX+Ru5CR/zqk4bLud//DBjz+3Vdvzszc/fIzX+ww8CaBIAQNmHjCJVzkIsB+AMxl/EFQ9CkbBKBgFIxEAAKBXSnZFzayuAAAAAElFTkSuQmCC","orcid":"","institution":"Govt. Science College, Tejgaon","correspondingAuthor":true,"prefix":"","firstName":"Anzim","middleName":"Hasan","lastName":"Nabil","suffix":""},{"id":525545125,"identity":"bc5930b5-a09e-4587-8535-aa1f0df932d0","order_by":1,"name":"MD Mahmudul Alom Sifat","email":"","orcid":"","institution":"DR. Mahbubur Rahman Mollah College","correspondingAuthor":false,"prefix":"","firstName":"MD","middleName":"Mahmudul Alom","lastName":"Sifat","suffix":""},{"id":525545126,"identity":"c957f599-70c9-484e-a4f1-ec149c737fc3","order_by":2,"name":"Sadia Akter Sarika","email":"","orcid":"","institution":"Monipur High School and College","correspondingAuthor":false,"prefix":"","firstName":"Sadia","middleName":"Akter","lastName":"Sarika","suffix":""},{"id":525545128,"identity":"4d757056-f7b5-42ea-9506-e1121102480f","order_by":3,"name":"Taiyeba Tasnim","email":"","orcid":"","institution":"Viqarunnisa Noon School and College","correspondingAuthor":false,"prefix":"","firstName":"Taiyeba","middleName":"","lastName":"Tasnim","suffix":""},{"id":525545129,"identity":"4638f87e-4e2a-4623-85b5-93058d4f21bc","order_by":4,"name":"Arnab Nandi Eshan","email":"","orcid":"","institution":"Govt. Ananda Mohan College","correspondingAuthor":false,"prefix":"","firstName":"Arnab","middleName":"Nandi","lastName":"Eshan","suffix":""},{"id":525545130,"identity":"d102f059-0ee1-4f79-af40-6b45b0d328c3","order_by":5,"name":"Tauseef Ahmed Khan","email":"","orcid":"","institution":"Dhaka Residential Model College","correspondingAuthor":false,"prefix":"","firstName":"Tauseef","middleName":"Ahmed","lastName":"Khan","suffix":""}],"badges":[],"createdAt":"2025-10-06 17:23:25","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7793347/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7793347/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93257228,"identity":"ee4c7edb-c05b-4da3-8c9b-c6419b9f93b5","added_by":"auto","created_at":"2025-10-10 17:07:30","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2232718,"visible":true,"origin":"","legend":"","description":"","filename":"BiLSTMRiskNetDomainGuidedExplainableDeepLearningforMultiClassClimateRiskPredictionfromHourlyWeatherData.docx","url":"https://assets-eu.researchsquare.com/files/rs-7793347/v1/92ce0c7cb0ca0fb7cf61c4aa.docx"},{"id":93257227,"identity":"26cbbcb5-faa5-4e0f-b5e1-27f961afb85a","added_by":"auto","created_at":"2025-10-10 17:07:30","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8541,"visible":true,"origin":"","legend":"","description":"","filename":"c4695f8fea534a29a9e852f0ddb06fc9.json","url":"https://assets-eu.researchsquare.com/files/rs-7793347/v1/8839b19d4644d5355e712297.json"},{"id":93682012,"identity":"707ed94e-a5d9-4ca6-9d52-20695915d57f","added_by":"auto","created_at":"2025-10-16 12:30:30","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1276697,"visible":true,"origin":"","legend":"","description":"","filename":"BiLSTMRiskNetDomainGuidedExplainableDeepLearningforMultiClassClimateRiskPredictionfromHourlyWeatherData.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7793347/v1_covered_63138ec9-b09f-4933-85bb-d7a12adb2f85.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"BiLSTM-RiskNet: Domain-Guided Explainable Deep Learning for Multi-Class Climate Risk Prediction from Hourly Weather Data","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":true,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"Climate Risk Prediction, Sequential Deep Learning, Bidirectional LSTM, Domain-Guided Labeling, LIME Interpretability, SHAP, Early Warning System","lastPublishedDoi":"10.21203/rs.3.rs-7793347/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7793347/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Precise and transparent forecasting of climate risk levels remains a formidable task in disaster preparedness because most current approaches either utilize static rule-based thresholds or do not tackle temporal trends in weather observations. These approaches typically prioritize the accuracy of predictions at the expense of interpretability and are thus unsuitable in high-stakes early-warning systems. To fill such gaps, this paper presents BiLSTM-RiskNet, a new domain-knowledge-guided and explainable deep learning approach for climate risk classification (low, medium, high) from raw hourly weather time series. Compared to existing research, the model employs physics-constrained automated labeling according to authoritative meteorological guidelines like NOAA Heat Index, Saffir–Simpson wind scale, and WMO barometric pressure criteria to provide semantically meaningful supervision in place of random thresholds. A Bidirectional LSTM is used on 24-hour rolling sequences to identify forward and backward temporal trends, so the model is better able to identify changing risk patterns than fixed or unidirectional methods. To address deep learning's black-box issue, explainable AI techniques are incorporated: LIME supplies local, instance-level interpretation, and SHAP supplies global feature attribution. These descriptions corroborate the model's reasoning to be theoretically rooted in climatological theory, e.g., extreme heat, humidity, and low pressure forming a part of the factors that contribute towards risky conditions. Equipped with a stratified, city-conscious dataset of more than three million hourly observations, BiLSTM-RiskNet achieves 95.23% accuracy with F1-scores of 0.98 (low), 0.72 (medium), and 0.92 (high) surpassing traditional machine learning and deep learning baselines. This synthesis of physics-based labeling, temporal deep learning, and open post-hoc explainability is a solid and reliable paradigm for real-time operational deployment, and represents an important milestone in AI-based climate risk reduction and disaster resilience.","manuscriptTitle":"BiLSTM-RiskNet: Domain-Guided Explainable Deep Learning for Multi-Class Climate Risk Prediction from Hourly Weather Data","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-10 17:07:25","doi":"10.21203/rs.3.rs-7793347/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":"9acb06ca-be20-4ea5-a463-8bc8739d370f","owner":[],"postedDate":"October 10th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-10-15T14:53:16+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-10 17:07:25","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7793347","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7793347","identity":"rs-7793347","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}