Scalable Modular Deep Learning Framework for Earthquake Early Warning Systems

Abstract

Earthquake Early Warning Systems (EEWS) require fast, reliable, and scalable processing of seismic data to deliver timely alerts and reduce disaster impacts. This study presents a modular deep learning–based EEWS framework that introduces a latency-aware, event-driven processing pipeline for real-time seismic data handling. The proposed architecture restructures the EEWS workflow into decoupled modules that communicate asynchronously via Kafka topics, enabling efficient data streaming and scalable processing. A standardized ingestion mechanism converts raw seismic traces into uniform JSON messages, ensuring interoperability and reducing preprocessing overhead. In addition, parallel data ingestion combined with topic-based message partitioning allows concurrent processing of waveform streams, improving throughput under high data rates. The framework integrates Docker-based containerization, multiprocessing, NGINX load balancing, and WebSocket communication to support flexible deployment and low-latency alert dissemination. Experimental results demonstrate reduced end-to-end latency and improved resource efficiency across multiple deployment scenarios. These findings highlight the effectiveness of pipeline-level optimization in supporting reliable and scalable real-time EEWS applications.

References

[1] Liu M, Tan YJ. Evaluating the performance of machine-learning-based phase pickers when applied to ocean bottom seismic data: Blanco oceanic transform fault as a case study. arXiv preprint arXiv:2410.18041. 2024 Oct 23.

[2] Tunç S, Tunç B, Çaka D, Budakoğlu E. An Overview of Traditional and Next-Generation Earthquake Early Warning Systems. J Adv Res Nat Appl Sci. 2024;10(3):747–760. https://doi.org/10.28979/jarnas.1481067

[3] Zhang M, Liu M, Feng T, Wang R, Zhu W. LOC-FLOW: An End-to-End Machine Learning-Based High-Precision Earthquake Location Workflow. Seismol Res Lett. 2022;93(5):2426–2438. https://doi.org/10.1785/0220220019

[4] Zhu W, Hou AB, Yang R, Datta A, Mousavi SM, Ellsworth WL, Beroza GC. QuakeFlow: a scalable machine-learning-based earthquake monitoring workflow with cloud computing. Geophys J Int. 2022;232(1):684–693. https://doi.org/10.1093/gji/ggac355

[5] Carvalho L, Mohammadigheymasi H, Crocker P, Tavakolizadeh N, Moradichaleshtori Y, Fernandes R. Application of the pair-input deep learning model for seismicity reassessment in Cameroon. Acta Geophys. 2024. https://doi.org/10.1007/s11600-024-01475-4

[6] Nikitha V, Praveen PP. Cloud-Enabled Scalable Framework for Deploying Machine Learning Models in Modern Healthcare Environments. In: 2026 International Conference on Electronics and Renewable Systems (ICEARS). 2026; p. 1423–8. https://doi.org/10.1109/ICEARS67481.2026.11416608

[7] Abdalzaher MS, Krichen M, Yiltas-Kaplan D, Ben Dhaou I, Adoni WYH. Early Detection of Earthquakes Using IoT and Cloud Infrastructure: A Survey. Sustainability. 2023;15(15):11713. https://doi.org/10.3390/su151511713

[8] Qin G, Juan M, Rui MH. IoT-Based Intelligent Power Supply Management Using Ensemble Learning for Seismic Observation Stations. Informatica. 2025;49(8). https://doi.org/10.31449/inf.v49i8.6502

[9] Aziz ZA, Abdulqader DN, Sallow AB, Omer KH. Python Parallel Processing and Multiprocessing: A Review. Acad J Nawroz Univ. 2021;10(3):345–54. https://doi.org/10.25007/ajnu.v10n3a1145

[10] Yao Y, Jin H, Shah AD, Han S, Hu Z, Ran Y, Stripelis D, Xu Z, Avestimehr S, He C. ScaleLLM: A Resource-Frugal LLM Serving Framework by Optimizing End-to-End Efficiency. arXiv preprint arXiv:2408.00008. 2024.

[11] Cara F, Cultrera G, Riccio G, et al. Temporary dense seismic network during the 2016 Central Italy seismic emergency for microzonation studies. Sci Data. 2019;6(1). https://doi.org/10.1038/s41597-019-0188-1

[12] Poulter AJ, Johnston SJ, Cox SJ. Using the MEAN stack to implement a RESTful service for an Internet of Things application. In: 2015 IEEE 2nd World Forum on Internet of Things (WF-IoT). 2015. p. 280–5. https://doi.org/10.1109/WF-IoT.2015.7389066

[13] Jamshidi P, Pahl C, Mendonça NC, Lewis J, Tilkov S. Microservices: The journey so far and challenges ahead. IEEE Software. 2018 May 4;35(3):24-35. https://doi.org/10.1109/MS.2018.2141039

[14] Hannousse A, Yahiouche S. Securing microservices and microservice architectures: A systematic mapping study. Computer Science Review. 2021 Aug 1;41:100415. https://doi.org/10.1016/j.cosrev.2021.100415

[15] Beyreuther M, Barsch R, Krischer L, Megies T, Behr Y, Wassermann J. ObsPy: A Python Toolbox for Seismology. Seismol Res Lett. 2010;81(3):530–533. https://doi.org/10.1785/gssrl.81.3.530

[16] Krischer L, Megies T, Barsch R, Beyreuther M, Lecocq T, Caudron C, Wassermann J. ObsPy: A Bridge for Seismology into the Scientific Python Ecosystem. Comput Sci Discov. 2015;8(1):014003. https://doi.org/10.1088/1749-4699/8/1/014003

[17] Megies T, Beyreuther M, Barsch R, Krischer L, Wassermann J. ObsPy - What can it do for data centers and observatories? Ann Geophys. 2011;54(1):47–58. https://doi.org/10.4401/ag-4838

[18] Martín C, Langendoerfer P, Zarrin PS, Díaz M, Rubio B. Kafka-ML: Connecting the data stream with ML/AI frameworks. Future Gener Comput Syst. 2022;126:15–33. https://doi.org/10.1016/j.future.2021.07.037

[19] Zhu W, Wang J, Chen Q, Beroza GC. Early Earthquake Warning Using Artificial Intelligence: Recent Advances and Challenges. Geophys J Int. 2022;229(1):19–35. https://doi.org/10.1093/gji/ggab473

[20] Syafrudin M, Alfian G, Fitriyani NL, Rhee J. Performance Analysis of IoT-Based Sensor, Big Data Processing, and Machine Learning Model for Real-Time Monitoring System in Automotive Manufacturing. Sensors. 2018;18(9):2946. https://doi.org/10.3390/s18092946

[21] Song J, Kook J. Mapping Server Collaboration Architecture Design with OpenVSLAM for Mobile Devices. Appl Sci. 2022;12(7). https://doi.org/10.3390/app12073653

[22] Ma L, Chi T. Performance Optimization in Apache Kafka for High-Throughput Event Processing. J Big Data. 2022;9(1):1–15. https://doi.org/10.1186/s40537-022-00646-6

[23] Raptis TP, Passarella A. Microservices Architecture Optimization for Real-Time Big Data Stream Analytics. Future Internet. 2022;14(11):333. https://doi.org/10.3390/fi14110333

[24] Alzubaidi A, Naz M, Zhang J, et al. Distributed Deep Learning with Apache Kafka and Kubernetes for Real-Time Data Streams. Appl Sci. 2023;13(2):803. https://doi.org/10.3390/app13020803

[25] Wibowo A, Heliani LS, Pratama C, et al. Deep learning for real-time P-wave detection: A case study in Indonesia’s earthquake early warning system. Appl Comput Geosci. 2024;24:100194. https://doi.org/10.1016/j.acags.2024.100194

[26] Ma C, Chi Y. Evaluation test and improvement of load balancing algorithms of nginx. Ieee Access. 2022 Jan 26;10:14311-24. https://doi.org/10.1109/ACCESS.2022.3146422

[27] Kaviarasan R, Harikrishna P, Arulmurugan A. Load balancing in cloud environment using enhanced migration and adjustment operator based monarch butterfly optimization. Advances in Engineering Software. 2022 Jul 1;169:103128. https://doi.org/10.1016/j.advengsoft.2022.103128

[28] Kumar N, Sharma S, Dubey A, Devi K, Balusamy B. A Lightweight AI-Enabled Container Middleware for Edge Cloud Architectures. In: Integrating Cloud, Fog, and Edge Computing in Healthcare: Federated Learning and Blockchain Approaches: Harnessing Distributed Technologies for Enhanced Healthcare Delivery; 2026. p. 75–99. https://doi.org/10.1007/978-3-031-96265-3_6

[29] Bhavani GD, Chalapathi MM. Lightweight scalable deep learning framework for real time detection of potato leaf diseases. Scientific Reports. 2026;12. https://doi.org/10.1038/s41598-025-33423-7

[30] Abella V, Lastre JK, Pawana IW, Lee D, Kim B, You I. Benchmarking Deep Learning Architectures for Real-Time Intrusion Detection in Kubernetes-Orchestrated 5G Core Networks. Research Briefs on Information and Communication Technology Evolution. 2026;12:57–66. https://doi.org/10.64799/rebicte.V12.3

Authors

  • Satriawan Rasyid Purnama Department of Informatics, Universitas Diponegoro
  • Adi Wibowo Department of Informatics, Universitas Diponegoro
  • Arjuna Wahyu Kusuma Department of Informatics, Universitas Diponegoro
  • Liem Roy Marcelino Department of Informatics, Universitas Diponegoro
  • Indra Waspada Department of Informatics, Universitas Diponegoro
  • Cecep Pratama Department of Geodetic Engineering, Universitas Gadjah Mada
  • Leni Sophia Heliani Department of Geodetic Engineering, Universitas Gadjah Mada
  • David Prambudi Sahara Global Geophysics Research Group, Faculty of Mining and Petroleum Engineering, Institute of Technology Bandung
  • Sri Widiyantoro Global Geophysics Research Group, Faculty of Mining and Petroleum Engineering, Institute of Technology Bandung
  • Shindy Rosalia Global Geophysics Research Group, Faculty of Mining and Petroleum Engineering, Institute of Technology Bandung
  • Bondan Febriarta Faculty of Mining and Petroleum Engineering, Institute of Technology Bandung
  • Cahyo Adhi Hartanto Faculty of Computer Science, Universitas Indonesia

DOI:

https://doi.org/10.31449/inf.v50i15.14773

Keywords:

Earthquake Early Warning System, Deep Learning, Real-time Seismic Data Processing, Containerized Deployment, WebSocket-based Alert Dissemination

Downloads

Published

09/14/2026

Issue

Vol. 50 No. 15 (2026): Online-only issue

Section

Online-only

License

Authors retain copyright in their work. By submitting to and publishing with Informatica, authors grant the publisher (Slovene Society Informatika) the non-exclusive right to publish, reproduce, and distribute the article and to identify itself as the original publisher.

All articles are published under the Creative Commons Attribution license CC BY 3.0. Under this license, others may share and adapt the work for any purpose, provided appropriate credit is given and changes (if any) are indicated.

Authors may deposit and share the submitted version, accepted manuscript, and published version, provided the original publication in Informatica is properly cited.

How to Cite

Purnama, S. R., Wibowo, A., Kusuma, A. W., Marcelino, L. R., Waspada, I., Pratama, C., Heliani, L. S., Sahara, D. P., Widiyantoro, S., Rosalia, S., Febriarta, B., & Hartanto, C. A. (2026). Scalable Modular Deep Learning Framework for Earthquake Early Warning Systems. Informatica, 50(15). https://doi.org/10.31449/inf.v50i15.14773