Artificial Intelligence-Driven Fire Detection, Monitoring, and Spread Prediction

Dear Colleagues,

With rapid urbanization, as well as climate change exacerbating fire risks, both structural fires in buildings and wildfires in wildland–urban interfaces (WUIs) are posing growing threats to human safety, infrastructure integrity, and ecosystems. Structural fires—occurring in residential buildings, underground spaces (such as tunnels and cable trenches), public venues (e.g., shopping malls, stations), and industrial facilities—often involve confined environments, complex fuel loads, limited ventilation, rapid smoke propagation, and high evacuation difficulties, leading to severe casualties and economic losses. Traditional fire detection and monitoring methods, reliant on point sensors, manual patrols, or basic threshold-based systems, frequently suffer from delayed response, high false alarm rates, poor performance in low-visibility or harsh conditions, and limited predictive capability for dynamic spread. The integration of artificial intelligence (AI)—encompassing deep learning, computer vision, multi-sensor fusion, predictive modeling, and real-time analytics—offers transformative potential for early and accurate fire detection, continuous monitoring of fire dynamics, and reliable prediction of spread trajectories in these challenging scenarios, thereby enabling faster alerting, optimized firefighting strategies, improved evacuation guidance, and reduced overall fire impacts.

This Special Issue aims to present cutting-edge research and advancements in Artificial Intelligence-Driven Fire Detection, Monitoring, and Spread Prediction, with an emphasis on structural fires in buildings and wildfires at the wildland–urban interface, fully aligning with the scope of the Fire journal, which encompasses fire science, detection technologies, fire dynamics, risk assessment, and intelligent management approaches in diverse fire environments.

High-quality original contributions are invited, and potential topics include, but are not limited to, the following:

• AI-based early fire and smoke detection in residential buildings, public spaces, and industrial facilities using fixed cameras, IoT sensors, or edge computing devices;
• Deep learning models (e.g., YOLO variants, CNN-Transformer hybrids) for real-time flame/smoke recognition and false alarm reduction in confined or indoor environments;
• AI-driven fire detection and behavior analysis in underground spaces, including road/rail tunnels, cable trenches, and metro systems, addressing challenges like airflow, low light, and rapid smoke layering;
• Multi-modal data fusion (thermal imaging, video, gas sensors, environmental data) enhanced by machine learning for accurate monitoring and anomaly detection in complex building structures;
• Predictive modeling of fire spread and heat release in structural fires using physics-informed AI, graph neural networks, or generative models tailored to compartment fire scenarios;
• AI techniques for wildfire detection, monitoring, and spread forecasting specifically in wildland–urban interface (WUI) zones, incorporating ember transport, vegetation–fuel–building interactions, and community-level risk mapping;
• Real-time AI decision support systems for fire suppression strategy optimization, resource allocation, and evacuation planning in building fires and WUI wildfire events;
• Robustness evaluation, case studies, and comparative analyses of AI models in realistic scenarios involving residential/industrial fires, tunnel fires, and WUI fire transitions;
• Integration of AI with digital twins or simulation tools for proactive fire risk assessment and scenario forecasting in high-risk built and interface environments.

Dr. Chunxiang Liu
Prof. Dr. Zihe Gao
Dr. Mehdi Jangi
Prof. Dr. Ping Huang
Dr. Bo Li
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Fire is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• fire detection 
• deep learning 
• smoke recognition 
• fire spread prediction 
• tunnel fire 
• wildland–urban interface 
• industrial fires 
• building fires 
• pool fires