Mass religious events are very problematic with the extreme density of the crowd, environmental destruction, and
social stress. Although data-driven models have been extensively applied to predict such risks, they tend to be less semantically
integrated and explainable. This paper proposes an ontology-based framework to model and infer multidimensional stress
conditions during mega religious events, using the MahaKumbh as a case study.The framework integrates forecasted crowd,
environmental, and social indicators into a formal ontology developed using Web Ontology Language (OWL). Semantic Web
Rule Language (SWRL) rules are used to classify the stress levels and make inferences of high-risk events, using logical
reasoning. It is based on the MahaKumbh 2025 case study, which shows that the proposed approach can be used to infer the
categories of stresses and high-risk events without manual labeling.The findings emphasize the fact that ontology-based
reasoning offers understandable, explainable, and reusable knowledge representations that enhance conventional predictive
models. The suggested framework provides a decision-support tool that is powerful to the planners and policymakers engaged
in the organization of religious meetings of a high scale.
[1] Verma, R. (2025). Security and Surveillance at Large Religious Gatherings: Crowd Management Strategies for the 2025
MahaKumbhMela. Synergy:International Journal of Multidisciplinary Studies, 2(3), 47-57.
[2] Singh, S., Shaloo, K., Sinha, S., Kumar, P., &Nath, B. (2025). Delivering emergency care at the religious mass gathering of
India: an amalgamation of technology and spirituality—an institutional experience of managing pilgrims at
MahakumbhPrayagraj. Frontiers in Public Health, 13, 1695241.
[3] Flambard, V., Benamrouz-Vanneste, S., &Karami, A. B. (2023). Current Trends and Future Prospects on Smart and
Sustainable Cities. Smart Cities.
[4] Gu, K., Liu, H., Liu, J., Yu, X., Shi, T., &Qiao, J. (2022). Air pollution prediction in mass rallies with a new temporally
weighted sample-based multitask learner. IEEE Transactions on Instrumentation and Measurement, 71, 1-15.
[5] Stănescu, G., &Oprea, S. V. (2025). Recent Trends and Insights in Semantic Web and Ontology-Driven Knowledge
Representation Across Disciplines Using Topic Modeling. Electronics, 14(7), 1313.
[6] Yang, X., Sun, X., & Tang, L. (2024). Multifactor Mathematical Modeling and Analysis of the Impact of Extreme Climate on
Geological Disasters. Water, 16(15), 2211.
[7] De Nicola, A., &Villani, M. L. (2025). Actionable Semantic Patterns in the Crisis Management Lifecycle: The TERMINUS
Ontology. Smart Cities, 8(5), 179.
[8] Kushwah, G., & Singh, P. (2026). Forecasting and quantifying event-induced stress during the PrayagrajMahaKumbh using
machine learning and a composite event stress index. International Research Journal of Innovations in Engineering and
Technology (IRJIET), 10(1), 113–122. https://doi.org/10.47001/IRJIET/2026.101013.
[9] AdvaitaSen. (2025). MahaKumbh Complete Dataset. Kaggle. Available at:
https://www.kaggle.com/datasets/advaitasen/mahakumbh-complete-dataset?resource=download (accessed 6 June 2026).
[10] Jiang, S., & Cao, X. (2025). Rule Inferring for Engineering Quality Risk Management Based on Ontology in Housing
Construction. Sustainability, 17(4), 1643.
[11] Liu, R., & Fischer, M. (2026). Ontology-Based Modeling and Reasoning for Construction Field Context. Journal of
Management in Engineering, 42(1), 04025059.
