{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T09:57:40Z","timestamp":1776765460698,"version":"3.51.2"},"reference-count":73,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T00:00:00Z","timestamp":1764633600000},"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>Accurate predictions of earthquakes are crucial for disaster preparedness and risk mitigation. Conventional machine learning models like Random Forest, SVR, and XGBoost are frequently used for seismic forecasting; however, capturing the intricate spatiotemporal relationships in earthquake data remains a challenge. To overcome this issue, we propose SeismoQuakeGNN, a novel Graph Neural Network (GNN) and Transformer-based hybrid framework that integrates spatial and temporal learning for improved seismic forecasting. Unlike existing GNN-based models, SeismoQuakeGNN introduces an optimized spatial encoding mechanism to dynamically learn seismic interdependencies, coupled with a Transformer-driven attention module to capture long-range temporal correlations. Furthermore, initial experiments with XGBoost demonstrated its limitations in learning earthquake patterns, reinforcing the need for deep spatial\u2013temporal modeling. The new SeismoQuakeGNN method is capable of substantial and efficient data processing of relationships in both space and time, as well as providing superior transfer to different seismic areas, thereby qualifying as a dependable starting point to extensive earthquake forecasting and hazard evaluation.<\/jats:p>","DOI":"10.3389\/frai.2025.1690476","type":"journal-article","created":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T11:42:22Z","timestamp":1764675742000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["SeismoQuakeGNN: a hybrid framework for spatio-temporal earthquake prediction with transformer-enhanced models"],"prefix":"10.3389","volume":"8","author":[{"given":"Anny","family":"Leema","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ponnuraman","family":"Balakrishnan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gladys Gnana","family":"Kiruba","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ganesarathinam","family":"Rajarajan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stuti","family":"Goel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Prisha","family":"Aggarwal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,12,2]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"11713","DOI":"10.3390\/su151511713","article-title":"Early detection of earthquakes using IoT and cloud infrastructure: a survey","volume":"15","author":"Abdalzaher","year":"2023","journal-title":"Sustainability."},{"key":"ref2","first-page":"123","article-title":"Emerging technologies and supporting tools for predicting the intensity and potential damage of earthquakes","author":"Abdalzaher","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"2159","DOI":"10.3390\/rs16122159","article-title":"Employing machine learning for seismic intensity estimation using a single station for earthquake early warning","volume":"16","author":"Abdalzaher","year":"2024","journal-title":"Remote Sens."},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1061\/PPSCFX.SCENG-1292","article-title":"Machine-learning applications in structural response prediction","author":"Afshar","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"22744","DOI":"10.1038\/s41598-025-08526-w","article-title":"Data-driven assessment of corrosion in reinforced concrete structures embedded in clay dominated soils","volume":"15","author":"Ahmad","year":"","journal-title":"Sci. Rep."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"8191","DOI":"10.3390\/en14238191","article-title":"Evolution of temperature field around underground power cable for static and cyclic heating","volume":"14","author":"Ahmad","year":"2021","journal-title":"Energies"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.matpr.2019.06.404","article-title":"Experimental study of thermal performance of the backfill material around underground power cable under steady and cyclic thermal loading","volume":"17","author":"Ahmad","year":"2019","journal-title":"Mater Today Proc"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"7315","DOI":"10.1038\/s41598-025-91831-1","article-title":"Unveiling soil thermal behavior under ultra-high voltage power cable operations","volume":"15","author":"Ahmad","year":"","journal-title":"Sci. Rep."},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1109\/IATMSI60426.2024.10502770","volume-title":"Earthquake magnitude prediction using machine learning techniques","author":"Ahmed","year":"2024"},{"key":"ref10","first-page":"56","volume-title":"Machine learning-based seismic activity prediction","author":"Ajai","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"3539","DOI":"10.1016\/j.asr.2024.06.054","article-title":"Earthquake prediction using satellite data: advances and ahead challenges","volume":"74","author":"Akhoondzadeh","year":"2024","journal-title":"Adv. Space Res."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1905","DOI":"10.1029\/2019RS006931","article-title":"A machine learning-based detection of earthquake precursors using ionospheric data","volume":"55","author":"Akyol","year":"2020","journal-title":"Radio Sci."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksus.2011.05.002","article-title":"Earthquake magnitude prediction using artificial neural network in northern Red Sea area","author":"Alarifi","year":"2012","journal-title":"J. King Saud Univ. Sci."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"012002","DOI":"10.1088\/1742-6596\/1951\/1\/012057","article-title":"Application to earthquake early warning system","volume":"1811","author":"Apriani","year":"2021","journal-title":"J. Phys. Conf. Ser."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1451","DOI":"10.1080\/13632469.2017.1387184","article-title":"Application of hybrid models combining support vector regressors and RNNs for earthquake forecasting","volume":"22","author":"Asim","year":"2018","journal-title":"J. Earthq. Eng."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1007\/s11069-016-2579-3","article-title":"Earthquake magnitude prediction in Hindukush region using machine learning techniques","volume":"85","author":"Asim","year":"2016","journal-title":"Nat. Hazards"},{"key":"ref17","first-page":"243","article-title":"Earthquake magnitude prediction in Hindukush region using hybrid machine learning models","volume":"1148","author":"Asim","year":"2020","journal-title":"Adv. Intell. Syst. Comput."},{"key":"ref18","doi-asserted-by":"crossref","first-page":"57553","DOI":"10.1109\/ACCESS.2021.3071400","article-title":"Attention-based bi-directional long-short term memory network for earthquake prediction","volume":"9","author":"Banna","year":"2021","journal-title":"IEEE Access"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"192880","DOI":"10.1109\/ACCESS.2020.3029859","article-title":"Application of artificial intelligence in predicting earthquakes: state-of-the-art and future challenges","volume":"8","author":"Banna","year":"2020","journal-title":"IEEE Access"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"105856","DOI":"10.1016\/j.engappai.2023.105856","article-title":"Artificial intelligence-based real-time earthquake prediction","volume":"123","author":"Bhatia","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref21","article-title":"Improving earthquake prediction with artificial intelligence and machine learning","volume-title":"NASA gateways to blue skies competition","year":"2024"},{"key":"ref22","first-page":"54","article-title":"Earthquake prediction in Turkey: a comparative study of deep learning and ARIMA methods","volume":"82","author":"\u00c7ekim","year":"2023","journal-title":"Environ. Earth Sci."},{"key":"ref23","first-page":"120","article-title":"Prediction of earthquake magnitudes using machine learning techniques: a case study from India","volume-title":"Springer lecture notes in computer science","author":"Chittora","year":""},{"key":"ref24","first-page":"67","article-title":"Experimental analysis of earthquake prediction using machine learning classifiers","author":"Chittora","year":""},{"key":"ref25","first-page":"12","article-title":"Comparative analysis of machine learning techniques for earthquake magnitude prediction","volume":"11","author":"Debnath","year":"2020","journal-title":"J. Appl. Earth Observ. Geoinf."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.soildyn.2017.02.015","article-title":"ANN models for ground motion prediction in seismic analysis","volume":"100","author":"Dhanya","year":"2017","journal-title":"Soil Dyn. Earthq. Eng."},{"key":"ref27","first-page":"1","article-title":"Comparative analysis of machine learning models for earthquake prediction","volume":"13","author":"Dikmen","year":"2024","journal-title":"IJIREM"},{"key":"ref28","first-page":"105627","article-title":"Prediction of spectral accelerations of aftershock ground motion with deep learning method","volume":"141","author":"Ding","year":"2021","journal-title":"Soil Dyn. Earthq. Eng."},{"key":"ref30","first-page":"25","article-title":"Machine learning methods for earthquake prediction: A survey","volume-title":"Proceedings of the Fourth Conference on Software Engineering and Information Management (SEIM 2019)","author":"Galkina","year":"2019"},{"key":"ref31","first-page":"323","article-title":"Deep learning for earthquake prediction: an overview and analysis of predictive models","volume-title":"Proceedings of the international conference on artificial intelligence applications and innovations (AIAI)","author":"Gonz\u00e1lez","year":"2019"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1785\/BSSA0340040185","article-title":"Frequency of earthquakes in California","volume":"34","author":"Gutenberg","year":"1954","journal-title":"Bull. Seismol. Soc. Am."},{"key":"ref33","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1186\/s40623-024-02005-8","article-title":"Real-time earthquake magnitude estimation via a deep-learning, multiple-seismometer-based method using heterogeneous multimodalities","volume":"76","author":"Hou","year":"2024","journal-title":"Earth Planets Space"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"1393","DOI":"10.3390\/buildings14051393","article-title":"Applying machine learning to earthquake engineering: a scientometric analysis of world research","volume":"14","author":"Hu","year":"2024","journal-title":"Buildings."},{"key":"ref35","doi-asserted-by":"publisher","first-page":"149","DOI":"10.14311\/NNW.2018.28.009","article-title":"Large earthquake magnitude prediction in Taiwan based on deep learning neural network","volume":"28","author":"Huang","year":"2018","journal-title":"Neural Netw. World"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"2248","DOI":"10.3390\/rs15092248","article-title":"Earthquake spatial probability and hazard estimation using various explainable AI (XAI) models at the Arabian peninsula","volume":"15","author":"Jena","year":"2023","journal-title":"Remote Sens"},{"key":"ref37","article-title":"An integrated approach for prediction of magnitude using machine learning","volume-title":"Proceedings of the 2024 ACM conference on knowledge discovery and data mining","author":"Joshi","year":"2024"},{"key":"ref38","article-title":"Earthquake magnitude prediction using deep learning for the horn of Africa","author":"Kassie","year":"2023","journal-title":"Soil Dyn. Earthq. Eng."},{"key":"ref39","first-page":"89","article-title":"Evaluating fine-tuned deep learning models for real-time earthquake prediction","volume":"12","author":"Kizilay","year":"2024","journal-title":"AI Civil Eng."},{"key":"ref40","doi-asserted-by":"publisher","first-page":"957","DOI":"10.1007\/s12145-024-01253-2","article-title":"A systematic review of Earthquake Early Warning (EEW) systems based on Artificial Intelligence","volume":"17","author":"Kolivand","year":"2024","journal-title":"Earth Science Informatics"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1186\/s40623-024-01982-0","article-title":"Applications of machine learning techniques to earthquake seismology","volume":"76","author":"Kubo","year":"2024","journal-title":"Earth Planets Space"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1186\/s40623-024-01982-0","article-title":"Recent advances in earthquake seismology using machine learning","volume":"76","author":"Kubo","year":"2024","journal-title":"Earth Planets Space"},{"key":"ref43","volume-title":"Deep learning for laboratory earthquake prediction and autoregressive forecasting of fault zone stress","author":"Laurentia","year":"2022"},{"key":"ref44","first-page":"131","article-title":"Earthquake prediction using deep learning with a dynamic loss function","volume":"13","author":"Li","year":"2020","journal-title":"Earth Sci. Inform."},{"key":"ref45","doi-asserted-by":"publisher","first-page":"1248","DOI":"10.1785\/0220190293","article-title":"Enhancing earthquake prediction accuracy through hybrid deep learning models: combining RNN and SVR techniques","volume":"91","author":"Li","year":"2020","journal-title":"Seismol. Res. Lett."},{"key":"ref46","doi-asserted-by":"crossref","DOI":"10.1109\/ICT-DM47966.2019.9032983","article-title":"Major earthquake event prediction using various machine learning algorithms","volume-title":"2019 6th international conference on information and communication technologies for disaster management (ICT-DM)","author":"Mallouhy","year":"2019"},{"key":"ref47","doi-asserted-by":"crossref","DOI":"10.1109\/ICT-DM47966.2019.9032983","article-title":"Major earthquake event prediction using various machine learning algorithms","volume-title":"2019 International conference on information and communication technologies for disaster management (ICT-DM)","author":"Mallouhy","year":"2019"},{"key":"ref49","author":"Mondol","year":""},{"key":"ref50","doi-asserted-by":"publisher","first-page":"6118","DOI":"10.1029\/2019GL083612","article-title":"Earthquake transformer: an attentive deep-learning model for simultaneous earthquake detection and phase picking","volume":"46","author":"Mousavi","year":"2019","journal-title":"Geophys. Res. Lett."},{"key":"ref51","doi-asserted-by":"crossref","first-page":"3952","DOI":"10.1038\/s41467-020-17591-w","article-title":"Earthquake transformer\u2014an attentive deep-learning model for simultaneous earthquake detection and phase picking","volume":"11","author":"Mousavi","year":"","journal-title":"Nat. Commun."},{"key":"ref52","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-020-67412-y","article-title":"CRED: a deep residual network of recurrent neural networks for earthquake signal detection","volume":"10","author":"Mousavi","year":"","journal-title":"Sci. Rep."},{"key":"ref53","doi-asserted-by":"publisher","first-page":"100163","DOI":"10.1016\/j.acags.2024.100163","article-title":"Machine learning technique in the north Zagros earthquake prediction","volume":"22","author":"Ommi","year":"2024","journal-title":"Appl. Comput. Geosci."},{"key":"ref54","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1142\/S0129065707000890","article-title":"Neural network models for earthquake magnitude prediction using multiple seismicity indicators","volume":"17","author":"Panakkat","year":"2007","journal-title":"Int. J. Neural Syst."},{"key":"ref55","doi-asserted-by":"publisher","first-page":"e1700578","DOI":"10.1126\/sciadv.1700578","article-title":"Convolutional neural network for earthquake detection and location","volume":"4","author":"Perol","year":"2018","journal-title":"Sci. Adv."},{"key":"ref56","doi-asserted-by":"publisher","first-page":"100075","DOI":"10.1016\/j.aiig.2024.100075","article-title":"The role of artificial intelligence and IoT in prediction of earthquakes: review","volume":"5","author":"Pwavodi","year":"","journal-title":"Artif. Intell. Geosci"},{"key":"ref57","first-page":"56","article-title":"The role of artificial intelligence and IoT in prediction","author":"Pwavodi","year":""},{"key":"ref58","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1007\/s12145-023-00991-z","article-title":"Machine learning for earthquake prediction: a systematic review of studies (2017\u20132021)","volume":"16","author":"Ridzwan","year":"2023","journal-title":"Earth Sci. Inform."},{"key":"ref59","doi-asserted-by":"crossref","DOI":"10.1007\/978-981-15-0886-8_53","article-title":"Dynamic lattice element modelling of cemented geomaterials","volume-title":"Advances in computer methods and geomechanics. Lecture notes in civil engineering","author":"Rizvi","year":"2020"},{"key":"ref60","doi-asserted-by":"publisher","first-page":"10169","DOI":"10.3390\/app142210169","article-title":"Earthquake prediction and alert system using IoT infrastructure and cloud-based environmental data analysis","volume":"14","author":"Rosca","year":"2024","journal-title":"Appl. Sci."},{"key":"ref61","first-page":"265","article-title":"Hybrid FPA-LS-SVM model for earthquake prediction using multiple seismic datasets","volume":"1148","author":"Salam","year":"2020","journal-title":"Adv. Intell. Syst. Comput."},{"key":"ref62","first-page":"123","article-title":"Deep learning-based earthquake catalog reveals the spatiotemporal characteristics of seismic activity","author":"Sun","year":"2024"},{"key":"ref63","first-page":"101","article-title":"Real-time earthquake prediction using recurrent neural networks and LSTM","volume-title":"Proceedings of the IEEE international conference on big data and machine learning (BDML)","author":"Suwal","year":"2021"},{"key":"ref64","first-page":"899","article-title":"Artificial intelligence in seismology: deep learning models for earthquake magnitude prediction","volume":"20","author":"Vasti","year":"2024","journal-title":"Nanotechnol. Percept."},{"key":"ref65","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proceedings of the 31st annual conference on neural information processing systems (NeurIPS)","author":"Vaswani","year":"2017"},{"key":"ref66","first-page":"56","article-title":"Optimization strategies for enhanced disaster management: a framework for earthquake forecasting","author":"Venkatanathan","year":"2024"},{"key":"ref67","doi-asserted-by":"publisher","first-page":"34567","DOI":"10.1109\/ACCESS.2021.3065281","article-title":"Combining seismic waveforms and topographical data for earthquake prediction using multi-modal learning","volume":"9","author":"Wang","year":"2021","journal-title":"IEEE Access"},{"key":"ref69","first-page":"317","article-title":"Performance of a low-cost earthquake early warning system (P-alert) and shake map production during the 2018 Mw 6.4 Hualien, Taiwan, earthquake","volume":"89","author":"Wu","year":"2018","journal-title":"Seismol. Res. Lett."},{"key":"ref70","author":"Xie","year":"2024"},{"key":"ref71","first-page":"237","article-title":"Satellite-based earthquake prediction using AdaBoost ensemble model","volume":"105","author":"Xiong","year":"2020","journal-title":"Nat. Hazards"},{"key":"ref72","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1007\/s11803-021-2027-6","article-title":"Deep learning for P-wave arrival picking in earthquake early warning","volume":"20","author":"Yanwei","year":"2021","journal-title":"Earthquake Eng. Eng. Vib."},{"key":"ref73","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1038\/s41598-024-76483-x","article-title":"Improving earthquake prediction accuracy in Los Angeles","volume":"14","author":"Yavas","year":"2024","journal-title":"Nat. Sci. Rep."},{"key":"ref74","doi-asserted-by":"publisher","first-page":"106663","DOI":"10.1016\/j.soildyn.2021.106663","article-title":"Spatiotemporally explicit earthquake prediction using deep neural network","volume":"144","author":"Yousefzadeh","year":"2021","journal-title":"Soil Dyn. Earthq. Eng."},{"key":"ref75","doi-asserted-by":"publisher","first-page":"1975","DOI":"10.1109\/TGRS.2019.2953794","article-title":"Modeling seismic activity using graph neural networks","volume":"58","author":"Zhang","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref76","doi-asserted-by":"publisher","first-page":"231","DOI":"10.14311\/NNW.2020.30.016","article-title":"Earthquake prediction model based on danger theory in artificial immunity","volume":"30","author":"Zhou","year":"2020","journal-title":"Neural Netw. World"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1690476\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T11:42:27Z","timestamp":1764675747000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1690476\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,2]]},"references-count":73,"alternative-id":["10.3389\/frai.2025.1690476"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1690476","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,2]]},"article-number":"1690476"}}