An Approach Towards Developing a Dynamic GIS-Based Fire Risk Mapping Framework Integrating Multi-Criteria Decision Analysis and Real-Time Environmental Parameters: A Systematic Literature Review

This review has synthesised thirty-four peer-reviewed journal studies spanning forest, urban, industrial and transportation fire contexts to assess the current state of GIS, MCDA, machine learning, deep learning and IoT approaches to fire risk and fire hazard assessment. The evidence indicates a field in active but uneven development: GIS-based spatial overlay and MCDA weighting techniques have matured into interpretable, well-validated static risk-mapping methods; machine learning and deep learning have substantially advanced predictive accuracy and visual detection capability; and IoT architectures have demonstrated the technical feasibility of continuous environmental monitoring at the building scale. What remains largely unrealised across this literature is the integration of these strands into a single operational system capable of updating fire risk continuously, transparently and at a spatial scale useful for regional emergency management. The eleven gaps identified in this review — spanning dynamic updating, GIS-AI integration, IoT scalability, real-time weather use, uncertainty analysis, explainability, generalisation, dataset standardisation, validation rigor and decision-support readiness — are not attributable to any single research team’s oversight, but reflect the differing technological maturation paths of four methodological traditions that have so far developed largely in parallel. This review’s principal contribution is to make that fragmentation explicit through systematic thematic comparison, to formalise the underlying weighting and risk-aggregation logic through Eqs. (1)–(4) and to translate the resulting gaps into an approach towards a concrete, evidence-traceable conceptual framework for a dynamic GIS-MCDA-AI-IoT fire risk mapping system. This paper deliberately stops short of claiming to have developed or validated such a system: realising the proposed architecture empirically, including its implementation and validation against independent fire-occurrence and sensor data, is identified here as the logical next step for research in this area, including the authors’ own ongoing work.

[1]     A. Abdollahi and B. Pradhan, “Explainable artificial intelligence (XAI) for interpreting the contributing factors feed into the wildfire susceptibility prediction model,” Sci. Total Environ., vol. 879, p. 163004, 2023, doi: 10.1016/j.scitotenv.2023.163004. [2]     U. I. Abdullahi, W. Zhang, Y. Cao and G. Irankunda, “Integrating IoT technology for fire risk monitoring and assessment in residential building design,” Buildings, vol. 15, no. 8, p. 1346, 2025, doi: 10.3390/buildings15081346. [3]     M.-Y. Choi and S. Jun, “Fire risk assessment models using statistical machine learning and optimized risk indexing,” Appl. Sci., vol. 10, no. 12, p. 4199, 2020, doi: 10.3390/app10124199. [4]     U. Dampage, L. Bandaranayake, R. Wanasinghe, K. Kottahachchi and B. Jayasanka, “Forest fire detection system using wireless sensor networks and machine learning,” Sci. Rep., vol. 12, no. 1, p. 46, 2022, doi: 10.1038/s41598-021-03882-9. [5]     M. Dhakal, B. Bhatta, P. Lamichhane and A. Parajuli, “Synergistic approaches in forest fire risk mapping using fuzzy AHP and machine learning models in the Chure Tarai Madhesh Landscape (CTML) of Nepal,” Geomat. Nat. Hazards Risk, vol. 15, no. 1, 2024, doi: 10.1080/19475705.2024.2436540. [6]     J. Florath, J. Chanussot and S. Keller, “Utilizing volunteered geographic information for real-time analysis of fire hazards: Investigating the potential of Twitter data in assessing the impacted areas,” Fire, vol. 7, no. 1, p. 6, 2024, doi: 10.3390/fire7010006. [7]     Y. Hao, M. Li, J. Wang, X. Li and J. Chen, “A high-resolution spatial distribution-based integration machine learning algorithm for urban fire risk assessment: A case study in Chengdu, China,” ISPRS Int. J. Geo-Inf., vol. 12, no. 10, p. 404, 2023, doi: 10.3390/ijgi12100404. [8]     D. Huang, S. Lo, J. Chen, Z. Fu, Y. Zheng, L. Luo, Y. Zhuang, H. Cheng and L. Yang, “Mapping fire risk of passenger-carried fire load in metro system via floor field cellular automaton,” Reliab. Eng. Syst. Saf., 2025, doi: 10.1016/j.ress.2025.111428. [9]     M. C. Iban and O. Aksu, “SHAP-driven explainable artificial intelligence framework for wildfire susceptibility mapping using MODIS active fire pixels: An in-depth interpretation of contributing factors in Izmir, Türkiye,” Remote Sens., vol. 16, no. 15, p. 2842, 2024, doi: 10.3390/rs16152842. [10]   Y. Li, Y. Zeng, Z. Pan, et al., “Real-time forecast of high-resolution wildfire spread via fast cross-scale deep learning,” Eng. Environ., vol. 20, Art. 65, 2026, doi: 10.1007/s11783-026-2165-1.