{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T10:35:39Z","timestamp":1771929339932,"version":"3.50.1"},"reference-count":53,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T00:00:00Z","timestamp":1770595200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>\n                    Insufficient human capacity to manage flood risk, limited technical support, weak integrated planning processes, and institutional distortions further exacerbate these challenges. In this paper, we propose a multimodal AI fusion framework combining the power of Long-Short Term Memory (LSTM) and Graph Neural Networks (GNN) to model both temporal dynamics and spatial dependencies within streams of urban data. The architecture also includes a dynamic Resilience Scoring Index (RSI) that enables online anomaly detection and situational-awareness-based decision-making. Edge-AI processing units power instant sensor data intake, and decision dashboards deliver understandable city insights to make life easier for you. The method was thoroughly evaluated in three different cities: Singapore (rich in data), Chennai (with a paucity of data), and Rotterdam (resilience modeled) as a benchmark to understand the generalizability of the approach. The results consistently show that the LSTM+GNN hybrid model performs better than ARIMA, Random Forest, and unimodal deep networks, with a statistically significant improvement in F1 score (\n                    <jats:italic>p<\/jats:italic>\n                    \u202f&amp;lt;\u202f0.05), and incurs only marginal performance degradation under noisy and incomplete data scenarios. Our work contributes to Sustainable Development Goal 9 (SDG-9) by creating scalable, evidence-based solutions for infrastructure planning and disaster risk reduction, providing a replicable framework for global smart city resilience initiatives.\n                  <\/jats:p>","DOI":"10.3389\/frai.2025.1612431","type":"journal-article","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T07:29:48Z","timestamp":1770622188000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal AI fusion for infrastructure resilience: real-time urban analytics framework aligned with SDG-9"],"prefix":"10.3389","volume":"8","author":[{"given":"N. S.","family":"Kalyan Chakravarthi","sequence":"first","affiliation":[{"name":"Institute of Computer Science and Digital Innovation, UCSI University, 1 Jalan UCSI, UCSI Heights (Taman Connaught), Cheras","place":["Kuala Lumpur, Malaysia"]}]},{"given":"S.","family":"Jafar Ali Ibrahim","sequence":"additional","affiliation":[{"name":"Institute of Computer Science and Digital Innovation, UCSI University, 1 Jalan UCSI, UCSI Heights (Taman Connaught), Cheras","place":["Kuala Lumpur, Malaysia"]}]},{"given":"Raenu","family":"Kolandaisamy","sequence":"additional","affiliation":[{"name":"Institute of Computer Science and Digital Innovation, UCSI University, 1 Jalan UCSI, UCSI Heights (Taman Connaught), Cheras","place":["Kuala Lumpur, Malaysia"]}]},{"given":"M.","family":"Parveena","sequence":"additional","affiliation":[{"name":"Center of Sustainable Development, QIS College of Engineering and Technology","place":["Ongole, Andhra Pradesh, India"]}]},{"given":"Madhala","family":"Srenevasulu","sequence":"additional","affiliation":[{"name":"Center of Sustainable Development, QIS College of Engineering and Technology","place":["Ongole, Andhra Pradesh, India"]}]},{"given":"G.","family":"Sivaprasad","sequence":"additional","affiliation":[{"name":"Center of Sustainable Development, QIS College of Engineering and Technology","place":["Ongole, Andhra Pradesh, India"]}]}],"member":"1965","published-online":{"date-parts":[[2026,2,9]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1177\/14759217241239041","article-title":"An integrated deep neural network model for structural health monitoring using multisensor time-series data with 1D CNN and LSTM","volume":"24","author":"Ahmadzadeh","year":"2024","journal-title":"Struct. Health Monit."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1016\/j.aej.2024.12.078","article-title":"Integration of digital mapping technologies in urban development through sustainable and resilient infrastructure towards realizing SDG 9 achievement\u2013a systematic review","volume":"116","author":"Ahmed","year":"2025","journal-title":"Sustain. Cities Dev."},{"key":"ref3","author":"Al Marzooqi","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1520","DOI":"10.1109\/ACCESS.2018.2887023","article-title":"Energy consumption prediction for buildings using evolutionary deep learning","volume":"7","author":"Almalaq","year":"2018","journal-title":"Energies"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"625","DOI":"10.47709\/brilliance.v4i2.4889","article-title":"Smart infrastructure for urban mobility: considering artificial intelligence in predictive maintenance","volume":"4","author":"Alqasi","year":"2024","journal-title":"Brilliance Artif. Intell. Res"},{"key":"ref6","first-page":"369","article-title":"AI for smart disaster resilience among communities","volume-title":"Intelligent systems modeling and simulation III","author":"Amirulikhsan","year":"2024"},{"key":"ref7","first-page":"578","article-title":"Multi-criteria aspects of AI readiness in the perspective of human-centered design, resilience and sustainable development goals","volume":"27","author":"Apolinarski","year":"2024","journal-title":"Eur. Res. Stud. J."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"100387","DOI":"10.1016\/j.crm.2021.100387","article-title":"Digital technologies that could strengthen critical infrastructure climate resilience","volume":"35","author":"Argyroudis","year":"2022","journal-title":"Clim. Risk Manag."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.isprsjprs.2017.11.011","article-title":"Beyond RGB: very high resolution urban remote sensing with multimodal deep networks","volume":"140","author":"Audebert","year":"2018","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref10","first-page":"1","article-title":"Artificial intelligence driven solutions for sustainable infrastructure development and management","volume":"2","author":"Balasubramanian","year":"2024","journal-title":"Int. J. Artif. Intell. Eng."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"116432","DOI":"10.1109\/ACCESS.2022.3217903","article-title":"Predicting the resilience of interdependent urban infrastructure systems","volume":"10","author":"Cassottana","year":"2022","journal-title":"IEEE Access"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1186\/s42055-024-00073-y","article-title":"Industry 5.0 and SDG 9: the synergy for sustainable transformation","volume":"7","author":"Costa","year":"2024","journal-title":"Sustain. Earth Rev."},{"key":"ref13","article-title":"Development of a new resilience evaluation framework for multi-component critical infrastructure","author":"Cui","year":"2024","journal-title":"IEEE Trans. Eng. Manag."},{"key":"ref14","author":"Dimitrovski","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"102804","DOI":"10.1016\/j.jag.2022.102804","article-title":"Joint deep learning to exploit OpenStreetMap and multimodal remote sensing data for detecting wastewater treatment plants","volume":"110","author":"Eatock","year":"2022","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref1001","first-page":"68","volume-title":"Nature","author":"Ehrlich","year":"2012"},{"key":"ref16","author":"Elbasha","year":"2025"},{"key":"ref17","article-title":"Using AI to analyze and predict for better urban mobility solutions: smart traffic management and better urban infrastructure","author":"Fatima","year":"2025","journal-title":"Smart Urban Syst."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"e14","DOI":"10.1017\/wat.2023.15","article-title":"Artificial intelligence: the foundation of tomorrow's urban water infrastructure\u2014a holistic view","volume":"1","author":"Fu","year":"2023","journal-title":"Cambridge Prisms Water"},{"key":"ref19","year":"2023"},{"key":"ref20","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s41742-024-00668-5","article-title":"A systematic review of AI approaches in the context of SDGs","volume":"19","author":"Greif","year":"2024","journal-title":"Int. J. Sustain. Dev."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1007\/s43621-024-00500-2","article-title":"AI-based engineering solutions for resilience of infrastructures against extreme rainfall events in arid regions: sustainability benefits","volume":"5","author":"Habib","year":"2024","journal-title":"Discov. Sustain."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"22181","DOI":"10.1038\/s41598-023-49296-7","article-title":"Multimodal urban air quality prediction and traffic analytics based on deep learning","volume":"13","author":"Hameed","year":"2023","journal-title":"Sci. Rep."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"104562","DOI":"10.1016\/j.scs.2023.104562","article-title":"Algorithmic urban planning for smart and sustainable development: a systematic literature review","volume":"94","author":"Heinrich","year":"2023","journal-title":"Sustain. Cities Soc."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"4340","DOI":"10.1109\/TGRS.2020.3016820","article-title":"More diverse is better: multimodal deep learning for remote-sensing imagery classification","volume":"59","author":"Hong","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"2779","DOI":"10.1007\/s12205-021-0565-0","article-title":"Integrating with LSTM network, a BIM-based visual warning management system for structural health monitoring","volume":"25","author":"Hou","year":"2021","journal-title":"KSCE J. Civ. Eng."},{"key":"ref27","article-title":"UrbanTransport","author":"Hussain","year":"2025","journal-title":"Urban Mobil. Syst."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"102926","DOI":"10.1016\/j.jag.2022.102926","article-title":"Deep learning in multi-modal remote sensing data fusion: a survey","volume":"112","author":"Li","year":"2022","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"61","DOI":"10.62030\/2024Julypaper4","article-title":"The emerging potential of artificial intelligence in urban and regional planning in the Indian context","volume":"2","author":"Marwaha","year":"2024","journal-title":"Int. J. Arts Archit. Des."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"1449404","DOI":"10.3389\/frsc.2024.1449404","article-title":"The role of machine learning in sustainable smart city development","volume":"6","author":"Mrabet","year":"2024","journal-title":"Sustain. Cities"},{"key":"ref31","first-page":"45","article-title":"A systematic review and future research directions","volume":"1","author":"Mujahid","year":"2024","journal-title":"J. Sustain. Econ."},{"key":"ref32","first-page":"1","article-title":"MACeIP: a multimodal ambient context-enriched intelligence platform in smart cities","author":"Nguyen","year":"2024"},{"key":"ref33","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"208016","DOI":"10.1109\/ACCESS.2020.3034141","article-title":"A review of deep reinforcement learning for traffic signal control","volume":"8","author":"Rasheed","year":"2020","journal-title":"IEEE Access"},{"key":"ref1002","doi-asserted-by":"publisher","first-page":"805","DOI":"10.1038\/s41893-019-0352-9","article-title":"Six transformations to achieve the sustainable development goals","volume":"2","author":"Sachs","year":"2019","journal-title":"Nature sustainability,"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"3852","DOI":"10.3390\/rs16203852","article-title":"A review on deep learning for change detection through multimodal fusion of remote sensing images","volume":"16","author":"Saidi","year":"2024","journal-title":"Remote Sens"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"7639","DOI":"10.1109\/TVT.2022.3170733","article-title":"Deep learning at wireless edge on multimodal sensor data for vehicular network","volume":"71","author":"Salehi","year":"2022","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref37","first-page":"45","article-title":"AI and digital twin technology integration for smart infrastructure management on urban city landscape","volume":"1","author":"Setyadi","year":"2025","journal-title":"J. Smart Infrastruct. Manage."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"102485","DOI":"10.1016\/j.aei.2024.102485","article-title":"Using artificial intelligence in digital twin models for stormwater infrastructure systems in smart cities","volume":"61","author":"Sharifi","year":"2024","journal-title":"Adv. Eng. Inform."},{"key":"ref39","doi-asserted-by":"publisher","first-page":"104326","DOI":"10.1016\/j.jag.2024.104326","article-title":"Generate multimodal urban areas of interest from remote sensing imagery based on geographical prior","volume":"136","author":"Shi","year":"2025","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref40","doi-asserted-by":"publisher","first-page":"12119","DOI":"10.1080\/10106049.2022.2063411","article-title":"National level flood risk assessment based on GIS-aided hybridized deep neural network and fuzzy analytical hierarchy process models: a case study of Bangladesh","volume":"37","author":"Siam","year":"2022","journal-title":"Geocarto Int."},{"key":"ref41","first-page":"6","article-title":"Federated learning for envisage future trajectory smart transport system for climate sustainability and smart green planet","volume":"6","author":"Singh","year":"2023","journal-title":"Natl. J. Environ. Law"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/j.rse.2019.04.014","article-title":"A deep learning multimodal solution for urban land use understanding from the above and ground perspectives","volume":"228","author":"Srivastava","year":"2019","journal-title":"Remote Sens. Environ."},{"key":"ref43","doi-asserted-by":"publisher","first-page":"777","DOI":"10.5198\/jtlu.2021.1855","article-title":"Modelling urban spatial structure by deep learning with remote sensing: transportation spatial parameters in a multimodal way","volume":"14","author":"Stiller","year":"2022","journal-title":"J. Transp. Land Use"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"112339","DOI":"10.1016\/j.rse.2021.112339","article-title":"Multimodal deep learning from satellite and street-level imagery for measuring income, overcrowding, and environmental deprivation in urban areas","volume":"257","author":"Suel","year":"2021","journal-title":"Remote Sens. Environ."},{"key":"ref45","doi-asserted-by":"publisher","first-page":"2631","DOI":"10.1007\/s11069-020-04124-3","article-title":"To bring you artificial intelligence for disaster management","volume":"103","author":"Sun","year":"2020","journal-title":"Nat. Hazards"},{"key":"ref46","doi-asserted-by":"crossref","first-page":"387","DOI":"10.5194\/isprs-archives-XLVIII-M-1-2023-387-2023","article-title":"AI application for disaster risk management: challenges","volume":"48","author":"Velev","year":"2023","journal-title":"Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci."},{"key":"ref47","first-page":"385","article-title":"LSTM for a flood prediction model with context-based hydrology time series data","author":"Widiasari","year":"2018"},{"key":"ref48","doi-asserted-by":"publisher","first-page":"556","DOI":"10.3390\/buildings12050556","article-title":"Rethink on the identification of urban functional area: an approach based on multimodal deep learning fusing high-resolution remote sensing image and social perception data","volume":"12","author":"Xie","year":"2022","journal-title":"Buildings"},{"key":"ref49","doi-asserted-by":"publisher","first-page":"2988","DOI":"10.3390\/s20102988","article-title":"Can we create artificially intelligent cities to protect humanity from disasters?","volume":"20","author":"Yigitcanlar","year":"2020","journal-title":"Sustain. Cities Soc."},{"key":"ref50","doi-asserted-by":"publisher","first-page":"468","DOI":"10.3390\/ijgi12120468","article-title":"A multimodal data fusion framework based on deep learning for urban area function identification","volume":"12","author":"Yu","year":"2023","journal-title":"ISPRS Int. J. Geo Inf."},{"key":"ref51","doi-asserted-by":"publisher","first-page":"102606","DOI":"10.1016\/j.inffus.2024.102606","article-title":"Deep learning for cross-domain data fusion in urban computing: taxonomy, advances, and outlook","volume":"113","author":"Zou","year":"2025","journal-title":"Inf. Fusion"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1612431\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T09:55:02Z","timestamp":1771926902000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1612431\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,9]]},"references-count":53,"alternative-id":["10.3389\/frai.2025.1612431"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1612431","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,9]]},"article-number":"1612431"}}