CLOUD-AGNOSTIC INTELLIGENT MONITORING ARCHITECTURE FOR CLIMATE ANOMALIES IN EARLY WARNING SYSTEMS

Vasyl Lyashkevych, Yurii Marchuk, Petro Kulyk, Andrii Patynko, Taras Kerod

Abstract


Background. Climate-related hazards require early warning systems to combine heterogeneous environmental observations, detect anomalous spatiotemporal patterns, and disseminate warning signals to stakeholders. Existing solutions separate software architecture, anomaly-detection models, and decision logic to transform deviations into early signals.

Materials and Methods. The study develops a cloud-agnostic intelligent monitoring architecture for early warning systems, supported by ML-based anomaly identification and decision support. A hierarchical anomaly model is introduced for climate zones, areas, and regions. It evaluates four types of evidence: deviation from normal state, consistency with neighboring regions, consistency with parent area, and the influence of contextual factors. The method combines region-specific detector training, multi-component anomaly scoring, persistence-based warning confirmation, and CEP-based escalation. A synthetic spatiotemporal climate graph was used to compare the Robust Z-score statistical method, the Isolation Forest anomaly-detection algorithm, the One-Class Support Vector Machine method, and the proposed HCOIM-EWS method, where HCOIM-EWS denotes Hierarchical Context-Orchestrated Intelligent Monitoring for Early Warning Systems.

Results and Discussion. The proposed architecture integrates ML-based detector selection, region-specific training, hierarchical anomaly scoring, CEP-based warning logic, and notification distribution. In simulation, HCOIM-EWS achieved the lowest false-alarm count while maintaining comparable event-level recall. Compared with Robust Z-score, Isolation Forest, and One-Class SVM, the proposed method reduced false alarms by 55.0%, 22.6%, and 49.7%. The method is suitable for warning-oriented intelligent monitoring, where operational reliability and false-alarm reduction are as important as point-level sensitivity.

Conclusion. The proposed method extends anomaly detection in early warning systems from isolated local time-series analysis to hierarchical, context-aware, and event-driven intelligent monitoring. This confirms the technical feasibility of the architecture and justifies its use as a reusable template for climate-risk monitoring platforms.

Keywords: anomaly detection, early warning systems, intelligent monitoring, cloud-agnostic architecture, complex event processing, machine learning


Full Text:

PDF

References


[1] Rokhideh, M., Fearnley, C., & Budimir, M. (2025). Multi-hazard early warning systems in the Sendai Framework for disaster risk reduction: Achievements, gaps, and future directions. International Journal of Disaster Risk Science, 16, 103–116. https://doi.org/10.1007/s13753-025-00622-9

[2] Chandola, V., Banerjee, A., & Kumar, V. (2009). Anomaly detection: A survey. ACM Computing Surveys, 41(3), Article 15.
https://doi.org/10.1145/1541880.1541882

[3] Sgueglia, A., Di Sorbo, A., Visaggio, C. A., & Canfora, G. (2022). A systematic literature review of IoT time series anomaly detection solutions. Future Generation Computer Systems, 134, 170–186.
https://doi.org/10.1016/j.future.2022.04.005

[4] Camps-Valls, G., Fernández-Torres, M.-Á., Cohrs, K.-H., Höhl, A., Castelletti, A., Pacal, A., Robin, C., Martinuzzi, F., Papoutsis, I., Prapas, I., Pérez-Aracil, J., Weigel, K., Gonzalez-Calabuig, M., Reichstein, M., Rabel, M., Giuliani, M., Mahecha, M. D., Popescu, O.-I., Pellicer-Valero, O. J., ... Williams, T. (2025). Artificial intelligence for modeling and understanding extreme weather and climate events. Nature Communications, 16, Article 1919.
https://doi.org/10.1038/s41467-025-56573-8

[5] Spohn, T. K., Walsh, E., Horan, K., O’Donoghue, J., Charnecki, T., Haslam, M., & Gallagher, S. (2026). A machine learning approach using autoencoders to perform quality control on meteorological data. Environmental Data Science, 5, Article e1. https://doi.org/10.1017/eds.2026.10030

[6] Sun, H., Liu, Y., Zhang, Y., et al. (2025). A machine learning-based quality control algorithm for heavy rainfall observations. Remote Sensing, 17(24), Article 3976. https://doi.org/10.3390/rs17243976

[7] Islam, M. M., Hasan, M., Mia, M. S., Masud, A. A., & Islam, A. R. M. T. (2025). Early warning systems in climate risk management: Roles and implementations in eradicating barriers and overcoming challenges. Natural Hazards Research, 5(3), 523–538. https://doi.org/10.1016/j.nhres.2025.01.007

[8] Chovanec, D., Kollár, B., Halúsková, B., Kubás, J., Pawęska, M., & Ristvej, J. (2025). A component-based approach to early warning systems: A theoretical model. Applied Sciences, 15(6), Article 3218.
https://doi.org/10.3390/app15063218

[9] Girotto, C. D., Piadeh, F., Bkhtiari, V., Behzadian, K., Chen, A. S., Campos, L. C., & Zolgharni, M. (2024). A critical review of digital technology innovations for early warning of water-related disease outbreaks associated with climatic hazards. International Journal of Disaster Risk Reduction, 100, Article 104151. https://doi.org/10.1016/j.ijdrr.2023.104151

[10] Zaharia, M., Xin, R. S., Wendell, P., Das, T., Armbrust, M., Dave, A., Meng, X., Rosen, J., Venkataraman, S., Franklin, M. J., Ghodsi, A., Gonzalez, J., Shenker, S., & Stoica, I. (2016). Apache Spark: A unified engine for big data processing. Communications of the ACM, 59(11), 56–65.
https://doi.org/10.1145/2934664

[11] Hutter, F., Kotthoff, L., & Vanschoren, J. (Eds.). (2019). Automated machine learning: Methods, systems, challenges. Springer.
https://doi.org/10.1007/978-3-030-05318-5

[12] Beck, H. E., McVicar, T. R., Vergopolan, N., Berg, A., & Wood, E. F. (2023). High-resolution (1 km) Köppen–Geiger maps for 1901–2099 based on constrained CMIP6 projections. Scientific Data, 10, Article 724.
https://doi.org/10.1038/s41597-023-02549-6

[13] García, J. A., Acero, F. J., Martínez-Pizarro, M., & Lara, M. (2024). A Bayesian hierarchical spatio-temporal model for summer extreme temperatures in Spain. Stochastic Environmental Research and Risk Assessment, 38(9), 3393–3410. https://doi.org/10.1007/s00477-024-02754-8

[14] Dereszynski, E. W., & Dietterich, T. G. (2011). Spatiotemporal models for data-anomaly detection in dynamic environmental monitoring campaigns. ACM Transactions on Sensor Networks, 8(1), Article 3. https://doi.org/10.1145/1993042.1993045

[15] Bâra, A., Văduva, A. G., & Oprea, S.-V. (2024). Anomaly detection in weather phenomena: News and numerical data-driven insights into climate change in Romania’s historical regions. International Journal of Computational Intelligence Systems, 17, Article 134.
https://doi.org/10.1007/s44196-024-00536-2

[16] Lyashkevych, V. Y. (2026). Intelligent monitoring as an information technology for context-aware decision-making strategy selection. Ukrainian Journal of Information Technology, 8(1), 39–50.
https://doi.org/10.23939/ujit2026.01.039

[17] Lyashkevych, V. Y. (2025). Sustainable optimization of consolidated data processing algorithms based on machine learning and genetic algorithms. Electronics and Information Technologies, 32, 39–54.
https://doi.org/10.30970/eli.32.3

[18] Gura, V., Ostrovska, O., & Lyashkevych, V. (2025). Scenario modelling and impact estimation of a local pollutant on the environment. Applied Computer Systems, 30(1), 195–201. https://doi.org/10.2478/acss-2025-0021

[19] Coughlan de Perez, E., Berse, K. B., Depante, L. A. C., Easton-Calabria, E., Evidente, E. P. R., Ezike, T., Heinrich, D., Jack, C., Lagmay, A. M. F. A., Lendelvo, S., Marunye, J., Maxwell, D. G., Murshed, S. B., Orach, C. G., Pinto, M., Poole, L. B., Rathod, K., Shampa, & Van Sant, C. (2022). Learning from the past in moving to the future: Invest in communication and response to weather early warnings to reduce death and damage. Climate Risk Management, 38, Article 100461. https://doi.org/10.1016/j.crm.2022.100461

[20] Sadiq, A.-A., Dougherty, R. B., Tyler, J., & Entress, R. (2023). Public alert and warning system literature review in the USA: Identifying research gaps and lessons for practice. Natural Hazards, 117(2), 1711–1744.
https://doi.org/10.1007/s11069-023-05926-x




DOI: http://dx.doi.org/10.30970/eli.34.4

Refbacks

  • There are currently no refbacks.