{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T09:07:33Z","timestamp":1772096853953,"version":"3.50.1"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T00:00:00Z","timestamp":1772064000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T00:00:00Z","timestamp":1772064000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Technical Research Centre of Finland"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Geoinformatica"],"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    The forecasting of multi-hazards is a vital, though underinvestigated, area of disaster risk management. The traditional studies have mainly focused on single-hazard forecasting, thus leaving its utility in real-world and realistic scenarios. This study, in turn, presents a spatio-temporal multi-label classification model, a framework designed expressly to capture the complex interrelationships between a range of hazards. The methodological framework used disaster occurrence data from the Open Federal Emergency Management Agency (OpenFEMA) database and converted the raw records of disasters into a multi-label dataset. Pressure-level reanalysis data is extracted from Climate Data Store (CDS) based on the multi-hazard event. Spatial data is extracted in 25\n                    <jats:inline-formula>\n                      <jats:tex-math>$$\\times$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    59 grid format in different temporal dependencies (12\u00a0h, 8\u00a0h, 6\u00a0h) at the 850 hPa pressure level. The model architecture combines convolutional neural networks (CNNs) with spatial attention mechanisms and gated recurrent units (GRUs) that model the temporal sequences. This combination enables multi-hazard predictions by utilizing the spatial and temporal data. Experimental analysis reveals that the proposed model outperformed the baseline variants, i.e., 2D CNN, Convolutional Long Short-Term Memory (ConvLSTM), and Convolutional Gated Recurrent Unit (ConvGRU) without attention. The proposed model achieved per-class accuracy up to 0.8868, the subset accuracy is 0.55, and the Hamming loss up to 0.127, which are 3.88%, 13.59% and 21.12% performance improvements over the baseline models respectively. In addition, the use of various lead times and the fusion of multiple lead times (12\u00a0h+8\u00a0h+6\u00a0h) significantly improves the predictive capability. The proposed framework has high potential for disaster preparedness and early warning systems in the real world. It proposes a flexible and efficient method of dealing with the growing complexity of multi-hazard environments.\n                  <\/jats:p>","DOI":"10.1007\/s10707-026-00568-0","type":"journal-article","created":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T08:19:19Z","timestamp":1772093959000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep spatio-temporal learning for multi-hazard events: A ConvGRU multi-label classification approach"],"prefix":"10.1007","volume":"30","author":[{"given":"Syeda Zoupash","family":"Zahra","sequence":"first","affiliation":[]},{"given":"Najia","family":"Saher","sequence":"additional","affiliation":[]},{"given":"Kalim","family":"Sattar","sequence":"additional","affiliation":[]},{"given":"Malik Muhammad Saad","family":"Missen","sequence":"additional","affiliation":[]},{"given":"Rab Nawaz","family":"Bashir","sequence":"additional","affiliation":[]},{"given":"Muhammad","family":"Faheem","sequence":"additional","affiliation":[]},{"given":"Amjad","family":"Rehman","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,2,26]]},"reference":[{"key":"568_CR1","doi-asserted-by":"publisher","unstructured":"Gaillard JC, Texier P (2010) Religions, natural hazards, and disasters: An introduction. Religion 40(2): 81\u201384. https:\/\/doi.org\/10.1016\/j.religion.2009.12.001. Religions, Natural Hazards, and Disasters","DOI":"10.1016\/j.religion.2009.12.001"},{"issue":"3","key":"568_CR2","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1016\/j.geosus.2021.09.001","volume":"2","author":"P Cui","year":"2021","unstructured":"Cui P, Peng J, Shi P, Tang H, Ouyang C, Zou Q, Liu L, Li C, Lei Y (2021) Scientific challenges of research on natural hazards and disaster risk. Geograph Sustain 2(3):216\u2013223. https:\/\/doi.org\/10.1016\/j.geosus.2021.09.001","journal-title":"Geograph Sustain"},{"key":"568_CR3","doi-asserted-by":"publisher","first-page":"169120","DOI":"10.1016\/j.scitotenv.2023.169120","volume":"912","author":"R Lee","year":"2024","unstructured":"Lee R, White CJ, Adnan MSG, Douglas J, Mahecha MD, O\u2019Loughlin FE, Patelli E, Ramos AM, Roberts MJ, Martius O, Tubaldi E, van den Hurk B, Ward PJ, Zscheischler J (2024) Reclassifying historical disasters: From single to multi-hazards. Sci Total Environ 912:169120. https:\/\/doi.org\/10.1016\/j.scitotenv.2023.169120","journal-title":"Sci Total Environ"},{"issue":"2","key":"568_CR4","first-page":"79","volume":"3","author":"L Eshrati","year":"2015","unstructured":"Eshrati L, Mahmoudzadeh A, Taghvaei M (2015) Multi hazards risk assessment, a new methodology. Intern J Health Syst Disast Manag 3(2):79\u201379","journal-title":"Intern J Health Syst Disast Manag"},{"key":"568_CR5","first-page":"3","volume":"2010","author":"M Davies","year":"2010","unstructured":"Davies M, Bowman E, White D (2010) Physical modelling of natural hazards. Physical Modelling Geotechn ICPMG 2010:3\u201322","journal-title":"Physical Modelling Geotechn ICPMG"},{"issue":"2","key":"568_CR6","doi-asserted-by":"publisher","first-page":"283","DOI":"10.5194\/nhess-7-283-2007","volume":"7","author":"J Douglas","year":"2007","unstructured":"Douglas J (2007) Physical vulnerability modelling in natural hazard risk assessment. Nat Hazard 7(2):283\u2013288. https:\/\/doi.org\/10.5194\/nhess-7-283-2007","journal-title":"Nat Hazard"},{"key":"568_CR7","doi-asserted-by":"publisher","first-page":"103338","DOI":"10.1016\/j.ijdrr.2022.103338","volume":"84","author":"LT Jenkins","year":"2023","unstructured":"Jenkins LT, Creed MJ, Tarbali K, Muthusamy M, Trogrli\u0107 R, Phillips JC, Watson CS, Sinclair HD, Galasso C, McCloskey J (2023) Physics-based simulations of multiple natural hazards for risk-sensitive planning and decision making in expanding urban regions. Intern J Disast Risk Reduct 84:103338. https:\/\/doi.org\/10.1016\/j.ijdrr.2022.103338","journal-title":"Intern J Disast Risk Reduct"},{"issue":"6","key":"568_CR8","doi-asserted-by":"publisher","first-page":"853","DOI":"10.5194\/nhess-5-853-2005","volume":"5","author":"A Brenning","year":"2005","unstructured":"Brenning A (2005) Spatial prediction models for landslide hazards: review, comparison and evaluation. Nat Hazard 5(6):853\u2013862. https:\/\/doi.org\/10.5194\/nhess-5-853-2005","journal-title":"Nat Hazard"},{"key":"568_CR9","doi-asserted-by":"publisher","unstructured":"Steyerberg EW (2019) Statistical Models for Prediction, pp 59\u201393. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-030-16399-0_4","DOI":"10.1007\/978-3-030-16399-0_4"},{"issue":"3","key":"568_CR10","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1007\/s11069-005-5182-6","volume":"37","author":"S Beguer\u00eda","year":"2006","unstructured":"Beguer\u00eda S (2006) Validation and evaluation of predictive models in hazard assessment and risk management. Nat Hazards 37(3):315\u2013329","journal-title":"Nat Hazards"},{"issue":"3","key":"568_CR11","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1023\/B:NHAZ.0000007172.62651.2b","volume":"30","author":"C-JF Chung","year":"2003","unstructured":"Chung C-JF, Fabbri AG (2003) Validation of spatial prediction models for landslide hazard mapping. Nat Hazards 30(3):451\u2013472","journal-title":"Nat Hazards"},{"key":"568_CR12","doi-asserted-by":"publisher","unstructured":"Tengtrairat N, Woo WL, Parathai P, Aryupong C, Jitsangiam P, Rinchumphu D (2021) Automated landslide-risk prediction using web gis and machine learning models. Sensors 21(13). https:\/\/doi.org\/10.3390\/s21134620","DOI":"10.3390\/s21134620"},{"issue":"1","key":"568_CR13","doi-asserted-by":"publisher","first-page":"1247","DOI":"10.1007\/s11069-021-04877-5","volume":"109","author":"H Ha","year":"2021","unstructured":"Ha H, Luu C, Bui QD, Pham D-H, Hoang T, Nguyen V-P, Vu MT, Pham BT (2021) Flash flood susceptibility prediction mapping for a road network using hybrid machine learning models. Nat Hazards 109(1):1247\u20131270. https:\/\/doi.org\/10.1007\/s11069-021-04877-5","journal-title":"Nat Hazards"},{"key":"568_CR14","doi-asserted-by":"publisher","unstructured":"Sattar K, Muhammad Saad Missen M, Saher N, Nawaz Bashir R, Zoupash Zahra S, Faheem M, Rehman Khan A (2025) Tropical cyclone intensity prediction using spatio-temporal data fusion. IEEE Access 13:70095\u201370104. https:\/\/doi.org\/10.1109\/ACCESS.2025.3561355","DOI":"10.1109\/ACCESS.2025.3561355"},{"key":"568_CR15","doi-asserted-by":"publisher","first-page":"124897","DOI":"10.1016\/j.eswa.2024.124897","volume":"255","author":"F Kazemi","year":"2024","unstructured":"Kazemi F, Asgarkhani N, Jankowski R (2024) Optimization-based stacked machine-learning method for seismic probability and risk assessment of reinforced concrete shear walls. Expert Syst Appl 255:124897. https:\/\/doi.org\/10.1016\/j.eswa.2024.124897","journal-title":"Expert Syst Appl"},{"issue":"9","key":"568_CR16","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1007\/s10064-022-02874-x","volume":"81","author":"AM Youssef","year":"2022","unstructured":"Youssef AM, Mahdi AM, Pourghasemi HR (2022) Landslides and flood multi-hazard assessment using machine learning techniques. Bull Eng Geol Env 81(9):370. https:\/\/doi.org\/10.1007\/s10064-022-02874-x","journal-title":"Bull Eng Geol Env"},{"issue":"1","key":"568_CR17","doi-asserted-by":"publisher","first-page":"13405","DOI":"10.1038\/s41598-023-40159-9","volume":"13","author":"T Zhang","year":"2023","unstructured":"Zhang T, Wang D, Lu Y (2023) Machine learning-enabled regional multi-hazards risk assessment considering social vulnerability. Sci Rep 13(1):13405. https:\/\/doi.org\/10.1038\/s41598-023-40159-9","journal-title":"Sci Rep"},{"key":"568_CR18","doi-asserted-by":"publisher","unstructured":"\u0160aki\u0107 Trogrli\u0107 R, Reiter K, Ciurean RL, Gottardo S, Torresan S, Daloz AS, Ma L, Padr\u00f3n Fumero N, Tatman S, Hochrainer-Stigler S, de Ruiter MC, Schlumberger J, Harris R, Garcia-Gonzalez S, Garc\u00eda-Vaquero M, Ar\u00e9valo TLF, Hernandez-Martin R, Mendoza-Jimenez J, Ferrario DM, Geurts D, Stuparu D, Tiggeloven T, Duncan MJ, Ward PJ (2024) Challenges in assessing and managing multi-hazard risks: A european stakeholders perspective. Environ Sci Policy 157:103774. https:\/\/doi.org\/10.1016\/j.envsci.2024.103774","DOI":"10.1016\/j.envsci.2024.103774"},{"key":"568_CR19","doi-asserted-by":"publisher","first-page":"116813","DOI":"10.1016\/j.jenvman.2022.116813","volume":"326","author":"MSG Adnan","year":"2023","unstructured":"Adnan MSG, Siam ZS, Kabir I, Kabir Z, Ahmed MR, Hassan QK, Rahman RM, Dewan A (2023) A novel framework for addressing uncertainties in machine learning-based geospatial approaches for flood prediction. J Environ Manage 326:116813. https:\/\/doi.org\/10.1016\/j.jenvman.2022.116813","journal-title":"J Environ Manage"},{"key":"568_CR20","doi-asserted-by":"publisher","unstructured":"Hayder IM, Al-Amiedy TA, Ghaban W, Saeed F, Nasser M, Al-Ali GA, Younis HA (2023) An intelligent early flood forecasting and prediction leveraging machine and deep learning algorithms with advanced alert system. Processes 11(2). https:\/\/doi.org\/10.3390\/pr11020481","DOI":"10.3390\/pr11020481"},{"key":"568_CR21","doi-asserted-by":"publisher","first-page":"100917","DOI":"10.1016\/j.rsase.2022.100917","volume":"29","author":"S Saha","year":"2023","unstructured":"Saha S, Bera B, Shit PK, Bhattacharjee S, Sengupta N (2023) Prediction of forest fire susceptibility applying machine and deep learning algorithms for conservation priorities of forest resources. Remote Sens Appl Soc Environ 29:100917. https:\/\/doi.org\/10.1016\/j.rsase.2022.100917","journal-title":"Remote Sens Appl Soc Environ"},{"key":"568_CR22","doi-asserted-by":"publisher","unstructured":"Pang Y, Li Y, Feng Z, Feng Z, Zhao Z, Chen S, Zhang H (2022) Forest fire occurrence prediction in china based on machine learning methods. Remote Sens 14(21). https:\/\/doi.org\/10.3390\/rs14215546","DOI":"10.3390\/rs14215546"},{"key":"568_CR23","doi-asserted-by":"publisher","unstructured":"Sessa MF, Trapp RJ (2025) The prediction of potential tornado damage intensity using machine learning. Artif Intell Earth Syst 4(3). https:\/\/doi.org\/10.1175\/AIES-D-23-0113.1","DOI":"10.1175\/AIES-D-23-0113.1"},{"issue":"1","key":"568_CR24","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1038\/s41612-023-00420-4","volume":"6","author":"M Ayyad","year":"2023","unstructured":"Ayyad M, Hajj MR, Marsooli R (2023) Climate change impact on hurricane storm surge hazards in new york\/new jersey coastlines using machine-learning. npj Clim Atmosph Sci 6(1):88. https:\/\/doi.org\/10.1038\/s41612-023-00420-4","journal-title":"npj Clim Atmosph Sci"},{"key":"568_CR25","doi-asserted-by":"publisher","first-page":"123929","DOI":"10.1016\/j.jhydrol.2019.123929","volume":"577","author":"B Choubin","year":"2019","unstructured":"Choubin B, Borji M, Mosavi A, Sajedi-Hosseini F, Singh VP, Shamshirband S (2019) Snow avalanche hazard prediction using machine learning methods. J Hydrol 577:123929. https:\/\/doi.org\/10.1016\/j.jhydrol.2019.123929","journal-title":"J Hydrol"},{"issue":"4","key":"568_CR26","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1007\/s12040-023-02178-y","volume":"132","author":"A Ansari","year":"2023","unstructured":"Ansari A, Rao K, Jain A, Ansari A (2023) Formulation of multi-hazard damage prediction (mhdp) model for tunnelling projects in earthquake and landslide-prone regions: A novel approach with artificial neural networking (ann). J Earth Syst Sci 132(4):164. https:\/\/doi.org\/10.1007\/s12040-023-02178-y","journal-title":"J Earth Syst Sci"},{"issue":"1","key":"568_CR27","doi-asserted-by":"publisher","first-page":"14889","DOI":"10.1038\/s41598-021-94266-6","volume":"11","author":"S Pouyan","year":"2021","unstructured":"Pouyan S, Pourghasemi HR, Bordbar M, Rahmanian S, Clague JJ (2021) A multi-hazard map-based flooding, gully erosion, forest fires, and earthquakes in iran. Sci Rep 11(1):14889. https:\/\/doi.org\/10.1038\/s41598-021-94266-6","journal-title":"Sci Rep"},{"issue":"1","key":"568_CR28","doi-asserted-by":"publisher","first-page":"1451","DOI":"10.1038\/s41598-022-05364-y","volume":"12","author":"M Bordbar","year":"2022","unstructured":"Bordbar M, Aghamohammadi H, Pourghasemi HR, Azizi Z (2022) Multi-hazard spatial modeling via ensembles of machine learning and meta-heuristic techniques. Sci Rep 12(1):1451. https:\/\/doi.org\/10.1038\/s41598-022-05364-y","journal-title":"Sci Rep"},{"key":"568_CR29","doi-asserted-by":"publisher","unstructured":"Nachappa TG, Ghorbanzadeh O, Gholamnia K, Blaschke T (2020) Multi-hazard exposure mapping using machine learning for the state of salzburg, austria. Remote Sens 12(17). https:\/\/doi.org\/10.3390\/rs12172757","DOI":"10.3390\/rs12172757"},{"issue":"3","key":"568_CR30","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1007\/s11069-020-03927-8","volume":"102","author":"J Cao","year":"2020","unstructured":"Cao J, Zhang Z, Du J, Zhang L, Song Y, Sun G (2020) Multi-geohazards susceptibility mapping based on machine learning\u2014a case study in jiuzhaigou, china. Nat Hazards 102(3):851\u2013871. https:\/\/doi.org\/10.1007\/s11069-020-03927-8","journal-title":"Nat Hazards"},{"key":"568_CR31","doi-asserted-by":"publisher","unstructured":"Rocchi A, Chiozzi A, Nale M, Nikolic Z, Riguzzi F, Mantovan L, Gilli A, Benvenuti E (2022) A machine learning framework for multi-hazard risk assessment at the regional scale in earthquake and flood-prone areas. Appl Sci 12(2). https:\/\/doi.org\/10.3390\/app12020583","DOI":"10.3390\/app12020583"},{"key":"568_CR32","doi-asserted-by":"publisher","unstructured":"Ouma YO (2023) Omai L (2023) Flood susceptibility mapping using image-based 2d-cnn deep learning: Overview and case study application using multiparametric spatial data in data-scarce urban environments. Int J Intell Syst 1:5672401. https:\/\/doi.org\/10.1155\/2023\/5672401. https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2023\/5672401","DOI":"10.1155\/2023\/5672401"},{"issue":"3","key":"568_CR33","doi-asserted-by":"publisher","first-page":"1459","DOI":"10.1007\/s11053-023-10193-5","volume":"32","author":"F Chen","year":"2023","unstructured":"Chen F, Liang Z, Cao A (2023) Convlstm for predicting short-term spatiotemporal distribution of seismic risk induced by large-scale coal mining. Nat Resour Res 32(3):1459\u20131479","journal-title":"Nat Resour Res"},{"issue":"4","key":"568_CR34","doi-asserted-by":"publisher","first-page":"100494","DOI":"10.1016\/j.aosl.2024.100494","volume":"17","author":"M Zhou","year":"2024","unstructured":"Zhou M, Wu J, Chen M, Han L (2024) Comparative study on the performance of convlstm and convgru in classification problems\u2014taking early warning of short-duration heavy rainfall as an example. Atmosph Oceanic Sci Lett 17(4):100494","journal-title":"Atmosph Oceanic Sci Lett"}],"container-title":["GeoInformatica"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10707-026-00568-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10707-026-00568-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10707-026-00568-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T08:19:20Z","timestamp":1772093960000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10707-026-00568-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,26]]},"references-count":34,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["568"],"URL":"https:\/\/doi.org\/10.1007\/s10707-026-00568-0","relation":{},"ISSN":["1384-6175","1573-7624"],"issn-type":[{"value":"1384-6175","type":"print"},{"value":"1573-7624","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,26]]},"assertion":[{"value":"8 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 January 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 February 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 February 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The authors declare that generative AI tools were only used to aid in making minor grammatical corrections and language refinement during the manuscript preparation process. None of the generative AI tools were involved in data analysis, model development, experimental design, result generation, or interpretation of results. All scientific content, methodological choices and conclusions found in this paper are solely the work and responsibility of the authors.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Use of Generative AI"}},{"value":"This work of M. Faheem was supported in part by the VTT-Technical Research Centre of Finland. The authors are thankful for the support of the Data Analytics Laboratory (AIDA), College of Computer and Information Science (CCIS), Prince Sultan University, Riyadh, Saudi Arabia.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Acknowledgment"}}],"article-number":"8"}}