{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T02:45:41Z","timestamp":1775616341970,"version":"3.50.1"},"reference-count":61,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>In light of urbanization, climate change, and the escalation of extreme weather events, flood management is becoming more and more important. Improving community resilience and reducing flood risks require prompt decision-making and effective communication. This study investigates how flood management systems can incorporate Large Language Models (LLMs), especially those that use Retrieval-Augmented Generation (RAG) architectures. We suggest a multimodal framework that uses a Flood Knowledge Graph to aggregate data from various sources, such as social media, hydrological, and meteorological inputs. Although LLMs have the potential to be transformative, we also address important drawbacks like governance issues, hallucination risks, and a lack of physical modeling capabilities. When compared to text-only LLMs, the RAG system significantly improves the reliability of flood-related decision support by reducing factual inconsistency rates by more than 75%. Our suggested architecture includes expert validation and security layers to guarantee dependable, useful results, like flood-constrained evacuation route planning. In areas that are vulnerable to flooding, this strategy seeks to strengthen warning systems, enhance information sharing, and build resilient communities.<\/jats:p>","DOI":"10.3390\/a18110713","type":"journal-article","created":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T07:58:32Z","timestamp":1762934312000},"page":"713","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Improved Flood Management and Risk Communication Through Large Language Models"],"prefix":"10.3390","volume":"18","author":[{"given":"Divas","family":"Karimanzira","sequence":"first","affiliation":[{"name":"Fraunhofer Institute for Optronics, System Technique and Image Exploitation IOSB, Am Vogelherd 90, 98693 Ilmenau, Germany"}]},{"given":"Thomas","family":"Rauschenbach","sequence":"additional","affiliation":[{"name":"Fraunhofer Institute for Optronics, System Technique and Image Exploitation IOSB, Am Vogelherd 90, 98693 Ilmenau, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4932-9267","authenticated-orcid":false,"given":"Tobias","family":"Hellmund","sequence":"additional","affiliation":[{"name":"Fraunhofer Institute for Optronics, System Technique and Image Exploitation IOSB, Fraunhoferstra\u00dfe 1 76131 Karlsruhe, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0630-0779","authenticated-orcid":false,"given":"Linda","family":"Ritzau","sequence":"additional","affiliation":[{"name":"Fraunhofer Institute for Optronics, System Technique and Image Exploitation IOSB, Am Vogelherd 90, 98693 Ilmenau, Germany"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Kuhaneswaran, B., Sorwar, G., Alaei, A.R., and Tong, F. (2025). Evolution of data-driven flood forecasting: Trends, technologies, and gaps\u2014A systematic mapping study. Water, 17.","DOI":"10.3390\/w17152281"},{"key":"ref_2","unstructured":"World Bank Tokyo Development Learning Center (2025, August 25). Urban Flood Management in a Changing Climate: Global and Japanese Insights. Available online: https:\/\/www.worldbank.org."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/02626667.2013.857411","article-title":"Flood risk and climate change\u2014Global and regional perspectives","volume":"59","author":"Kundzewicz","year":"2014","journal-title":"Hydrol. Sci. J."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Vishwakarma, V., and Thawait, A.K. (2025). A review of flood estimation methods: Advancements and challenges. Flood Forecasting and Hydraulic Structures, Springer.","DOI":"10.1007\/978-981-97-9168-2_19"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Zhou, Q., Su, J., Arnbjerg-Nielsen, K., Ren, Y., Luo, J., Ye, Z., and Feng, J. (2021). A GIS-based hydrological modeling approach for rapid urban flood hazard assessment. Water, 13.","DOI":"10.3390\/w13111483"},{"key":"ref_6","first-page":"1","article-title":"Advancements and Challenges in Hydrological Modeling: A Comprehensive Review","volume":"Volume 410","author":"Pandey","year":"2025","journal-title":"Hydrology and Hydrologic Modelling"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.55670\/fpll.futech.1.1.1","article-title":"Application of machine learning in flood forecasting","volume":"1","author":"Bayat","year":"2022","journal-title":"Future Technol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"101873","DOI":"10.1016\/j.ejrh.2024.101873","article-title":"An interpretable hybrid deep learning model for flood forecasting based on Transformer and LSTM","volume":"54","author":"Li","year":"2024","journal-title":"J. Hydrol. Reg. Stud."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"50982","DOI":"10.1109\/ACCESS.2021.3065939","article-title":"Designing deep-based learning flood forecast model with ConvLSTM hybrid algorithm","volume":"9","author":"Moishin","year":"2021","journal-title":"IEEE Access"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Acikara, T., Xia, B., Yigitcanlar, T., and Hon, C. (2023). Contribution of social media analytics to disaster response effectiveness: A systematic review of the literature. Sustainability, 15.","DOI":"10.3390\/su15118860"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Yahyazadeh Shourabi, K., Niksokhan, M.H., and Nikoo, M.R. (2025). Enhancing flood frequency predictions under climate change and uncertainty using machine learning model fusion and wavelet transform. Earth Syst. Environ.","DOI":"10.1007\/s41748-025-00859-w"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"494","DOI":"10.3390\/jcp4030024","article-title":"Data privacy and ethical considerations in database management","volume":"4","author":"Pina","year":"2024","journal-title":"J. Cybersecur. Priv."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Lin, C.A. (2023). Flood risk management via risk communication, cognitive appraisal, collective efficacy, and community action. Sustainability, 15.","DOI":"10.3390\/su151914191"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Ye, F., Wang, Y., Xu, D., Zhang, X., and Jin, G. (2024). Designing a knowledge graph system for digital twin to assess urban flood risk. Web and Big Data, Springer.","DOI":"10.1007\/978-981-97-2303-4_13"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zajac, M., Kulawiak, C., Li, S., Erickson, C., Hubbell, N., and Gong, J. (2025). Unifying flood-risk communication: Empowering community leaders through AI-enhanced, contextualized storytelling. Hydrology, 12.","DOI":"10.3390\/hydrology12080204"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1007\/s42979-021-00971-4","article-title":"Multi-source multimodal data and deep learning for disaster response: A systematic review","volume":"3","author":"Algiriyage","year":"2022","journal-title":"SN Comput. Sci."},{"key":"ref_17","first-page":"5185","article-title":"Climbing towards NLU: On meaning, form, and understanding in the age of data","volume":"2020","author":"Bender","year":"2020","journal-title":"ACL Anthol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"5685","DOI":"10.1007\/s00146-025-02312-y","article-title":"Artificial intelligence in governance: Recent trends, risks, challenges, innovative frameworks, and future directions","volume":"40","author":"Ghosh","year":"2025","journal-title":"AI Soc."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"3005","DOI":"10.1007\/s10462-022-10246-w","article-title":"Human-in-the-loop machine learning: A state of the art","volume":"56","year":"2023","journal-title":"Artif. Intell. Rev."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Abdel-Mooty, M.N., El-Dakhakhni, W., and Coulibaly, P. (2022). Data-driven community flood resilience prediction. Water, 14.","DOI":"10.3390\/w14132120"},{"key":"ref_21","unstructured":"Xie, Y., Jiang, B., Mallick, T., Bergerson, J.D., Hutchison, J.K., Verner, D.R., Branham, J., Alexander, M.R., Ross, R.B., and Feng, Y. (2025). A RAG-based multi-agent LLM system for natural hazard resilience and adaptation. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"5235","DOI":"10.1007\/s13042-025-02570-8","article-title":"REMFLOW: RAG-enhanced multi-factor rainfall flooding warning in sponge airports via large language model","volume":"16","author":"Wang","year":"2025","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"ref_23","unstructured":"Bhatti, M. (2024). Using Large Language Models for Early Flood Analysis: A Case Study. [Master\u2019s Thesis, Lappeenranta\u2013Lahti University of Technology]. Available online: https:\/\/lutpub.lut.fi\/bitstream\/handle\/10024\/167888\/mastersthesis%20bhatti%20maaz.pdf."},{"key":"ref_24","unstructured":"Barantiev, D., Mastronunzio, M., Paris, S., Proietti, C., and Santini, M. (2025, August 25). Pilot Cyclogenesis Monitoring in GDACS (Global Disaster Alert and Coordination System). Available online: https:\/\/www.preventionweb.net\/media\/108040\/download?startDownload=20251111."},{"key":"ref_25","unstructured":"Masante, D., Barantiev, D., Destro, E., Mastronunzio, M., Paris, S., Proietti, C., Salvitti, V., and Santini, M. (2025, August 25). Multi-Hazard Early Warning System Global Disaster Alert and Coordination System (GDACS). Available online: https:\/\/www.gdacs.org\/documents\/2025\/GDACS_MHEWS_guide.pdf."},{"key":"ref_26","unstructured":"European Commission Joint Research Centre (2025, August 25). Europe Floods: New Tool to Estimate Water Depth and Extent. JRC News and Updates 2024, Available online: https:\/\/joint-research-centre.ec.europa.eu\/jrc-news-and-updates\/europe-floods-new-tool-estimate-water-depth-and-extent-2024-09-20_en."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Alobid, M., Chellai, F., and Sz\u0171cs, I. (2024). Trends and drivers of flood occurrence in Germany: A time series analysis of temperature, precipitation, and river discharge. Water, 16.","DOI":"10.3390\/w16182589"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Thieken, A.H., Kienzler, S., Kreibich, H., Kuhlicke, C., Kunz, M., M\u00fchr, B., M\u00fcller, M., Otto, A., Petrow, T., and Pisi, S. (2016). Review of the flood risk management system in Germany after the major flood in 2013. Ecol. Soc., 21, Available online: http:\/\/www.jstor.org\/stable\/26270411.","DOI":"10.5751\/ES-08547-210251"},{"key":"ref_29","unstructured":"Bundesamt f\u00fcr Kartographie und Geod\u00e4sie (BKG) (2025, May 23). Digitale Gel\u00e4ndemodelle. Retrieved 3 November 2025, Available online: https:\/\/www.d-copernicus.de\/programm\/netzwerk-und-kontakte\/fernerkundungsinstitute-firmen-in-deutschland\/bundesamt-fuer-kartographie-und-geodaesie-bkg\/."},{"key":"ref_30","unstructured":"Pottgiesser, T., Naumann, S., and M\u00fcller, A. (2025, May 23). Hydromorphologische Steckbriefe der Deutschen Flie\u00dfgew\u00e4ssertypen Umweltbundesamt 2025. Retrieved May 23, 2025. Available online: https:\/\/www.umweltbundesamt.de\/publikationen\/hydromorphologische-steckbriefe-der-deutschen."},{"key":"ref_31","unstructured":"European Environment Agency (2025, May 23). Urban Soil Sealing in Europe, Available online: https:\/\/www.eea.europa.eu\/articles\/urban-soil-sealing-in-europe."},{"key":"ref_32","unstructured":"Landesamt f\u00fcr Umwelt Rheinland-Pfalz (2025, August 25). Wassergefahrenkarten HQ100 und HQextrem, Available online: https:\/\/www.lfu.rlp.de."},{"key":"ref_33","unstructured":"Deutscher Wetterdienst (DWD) (2025, August 25). Niederschlagsradar und Unwetterwarnungen, Available online: https:\/\/www.dwd.de."},{"key":"ref_34","unstructured":"MeteoAlarm (2025, August 25). European Weather Alerts and Extreme Precipitation Indices. Available online: https:\/\/www.meteoalarm.org."},{"key":"ref_35","unstructured":"Copernicus Climate Change Service (2025, August 25). Climate Projections for Flood Risk in Europe, Available online: https:\/\/climate.copernicus.eu."},{"key":"ref_36","unstructured":"Statistisches Bundesamt (2025, August 25). Bev\u00f6lkerungsdichte und Vulnerable Gruppen in Hochwassergebieten, Available online: https:\/\/www.destatis.de."},{"key":"ref_37","unstructured":"Bundesamt f\u00fcr Bev\u00f6lkerungsschutz und Katastrophenhilfe (BBK) (2025, August 25). Kritische Infrastruktur in Deutschland, Available online: https:\/\/www.bbk.bund.de."},{"key":"ref_38","unstructured":"INSPIRE Directive (2025, August 25). Building Metadata Standards for Flood Risk Modeling, Available online: https:\/\/inspire.ec.europa.eu."},{"key":"ref_39","unstructured":"GDV\u2014Gesamtverband der Deutschen Versicherungswirtschaft (2025, August 25). Schadenshistorie und Versicherungsdaten bei Hochwasser. Available online: https:\/\/www.gdv.de."},{"key":"ref_40","unstructured":"German Water Partnership (2025, August 25). SCADA and IoT Integration in Water Infrastructure. Available online: https:\/\/germanwaterpartnership.de."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/10447318.2018.1427832","article-title":"Social Media in Crisis Management: An Evaluation and Analysis of Crisis Informatics Research","volume":"34","author":"Reuter","year":"2018","journal-title":"Int. J. Hum.-Comput. Interact."},{"key":"ref_42","unstructured":"KATWARN (2025, August 25). B\u00fcrgerwarnsysteme f\u00fcr Hochwasser und Unwetter. Available online: https:\/\/www.katwarn.de."},{"key":"ref_43","unstructured":"Bundesministerium des Innern (2025, August 25). Einsatzprotokolle und Beh\u00f6rdenberichte zur Flutkatastrophe 2021, Available online: https:\/\/www.bmi.bund.de."},{"key":"ref_44","unstructured":"European Parliament (2025, August 25). Directive 2007\/60\/EC on the Assessment and Management of Flood Risks, Available online: https:\/\/eur-lex.europa.eu."},{"key":"ref_45","unstructured":"Th\u00fcringer Allgemeine (2025, August 25). Lokale Presseartikel zur Hochwasserlage in Ilmenau. Available online: https:\/\/www.thueringer-allgemeine.de."},{"key":"ref_46","unstructured":"European Language Grid (2025, August 25). Multilingual Datasets for Regional Disaster Modeling. Available online: https:\/\/www.european-language-grid.eu."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"518","DOI":"10.1515\/auto-2024-0033","article-title":"Probabilistic multi-step ahead streamflow forecast based on deep learning","volume":"72","author":"Karimanzira","year":"2024","journal-title":"at-Automatisierungstechnik"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"e2020WR028616","DOI":"10.1029\/2020WR028616","article-title":"Physical Instability of Individuals Exposed to Storm-Induced Coastal Flooding: Vulnerability of New Yorkers During Hurricane Sandy","volume":"57","author":"Wang","year":"2021","journal-title":"Water Resour. Res."},{"key":"ref_49","unstructured":"Neo4j: Neo4j, Inc (2025, October 25). Neo4j v5 Documentation. Available online: https:\/\/neo4j.com\/docs\/."},{"key":"ref_50","unstructured":"Prot\u00e9g\u00e9: Stanford University (2025, October 25). Prot\u00e9g\u00e9: The Open-Source Ontology Editor and Framework for Building Intelligent Systems. Available online: https:\/\/protege.stanford.edu\/."},{"key":"ref_51","unstructured":"Kafka: Apache Software Foundation (2025, October 25). Apache Kafka. Available online: https:\/\/kafka.apache.org\/."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"317","DOI":"10.4038\/cjs.v54i1.8286","article-title":"A review of river flood models: Methods and applications for forecasting and simulation","volume":"54","author":"Anuruddhika","year":"2025","journal-title":"Ceylon J. Sci."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"e2019WR025583","DOI":"10.1029\/2019WR025583","article-title":"Real-time flood forecasting based on a high-performance 2-D hydrodynamic model and numerical weather predictions","volume":"56","author":"Ming","year":"2020","journal-title":"Water Resour. Res."},{"key":"ref_54","unstructured":"Colverd, G., Darm, P., Silverberg, L., and Kasmanoff, N. (2023). FloodBrain: Flood disaster reporting by web-based retrieval augmented generation with an LLM. arXiv."},{"key":"ref_55","first-page":"195","article-title":"Retrieval-augmented generation: Trends, architectures, and use cases","volume":"10","author":"Rai","year":"2025","journal-title":"Int. J. Nov. Res. Dev."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Wang, X., Wang, Z., Gao, X., Zhang, F., Wu, Y., Xu, Z., Shi, T., Wang, Z., Li, S., and Qian, Q. Searching for best practices in retrieval-augmented generation. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing.","DOI":"10.18653\/v1\/2024.emnlp-main.981"},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1016\/j.jhydrol.2009.08.003","article-title":"Decomposition of the mean squared error and NSE performance criteria: Implications for improving hydrological modelling","volume":"377","author":"Gupta","year":"2009","journal-title":"J. Hydrol."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"4323","DOI":"10.5194\/hess-23-4323-2019","article-title":"Technical note: Inherent benchmark or not? Comparing Nash\u2013Sutcliffe and Kling\u2013Gupta efficiency scores","volume":"23","author":"Knoben","year":"2019","journal-title":"Hydrol. Earth Syst. Sci."},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Pouresmaeil, Y., Afroogh, S., and Jiao, J. Mapping out AI functions in intelligent disaster (mis)management and AI-caused disasters. arXiv, 2025.","DOI":"10.1007\/s00146-025-02423-6"},{"key":"ref_60","unstructured":"Luca, C. (2025, August 20). Ethical Considerations and Data Privacy in AI-Based Disaster Management. ResearchGate. Available online: https:\/\/www.researchgate.net\/publication\/390741074."},{"key":"ref_61","unstructured":"SIOP Committee for the Advancement of Professional Ethics (2025, August 20). AI Ethics Considerations Brief. Society for Industrial and Organizational Psychology. Available online: https:\/\/www.siop.org\/wp-content\/uploads\/2025\/07\/AI-ethics-considerations-brief.pdf."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/11\/713\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T07:59:40Z","timestamp":1762934380000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/11\/713"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,12]]},"references-count":61,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["a18110713"],"URL":"https:\/\/doi.org\/10.3390\/a18110713","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,12]]}}}