Alarms Without Smoke: Predicting and Addressing False Alarms in Urban Fire Services

Shitian Zhang and Huanfa Chen

No 9pg5n_v1, SocArXiv from Center for Open Science

Abstract: False fire alarms waste essential resources and prevent fire services from responding to real fires in time. While previous research has mainly focused on improving hardware accuracy, the spatial and temporal patterns of false alarms remain largely unexplored. This study analyses 15 years of historical fire incident data from the West Midlands Fire Service, UK. The data reveal that attending false alarms accounts for 34% of total mobilisation time. Given this significant potential for resource savings, we applied machine learning to predict an alarm’s validity at the point of dispatch. Our proposed model achieves an accuracy of 86.0% and only misses 2.1% of real incidents. This study introduces a new geospatial perspective to mitigate the impact of false alarms. Furthermore, the model can be integrated into existing fire service policies to enhance public safety and urban resilience.

Date: 2026-05-20
References: Add references at CitEc
Citations:

Downloads: (external link)
https://osf.io/download/6a0de3b892b305aff22c3ce7/

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:osf:socarx:9pg5n_v1

DOI: 10.31219/osf.io/9pg5n_v1

Access Statistics for this paper

More papers in SocArXiv from Center for Open Science
Bibliographic data for series maintained by OSF ().