Smart City and Infrastructure Engineering

Background

Disasters—both natural and human-induced—continue to escalate in frequency, scale, and complexity, driven by climate change, rapid urbanization, infrastructure interdependencies, and global connectivity. These events result in substantial human, economic, and environmental losses, underscoring the urgent need to shift from reactive disaster response toward proactive, intelligence-driven disaster prevention and mitigation strategies.

Artificial Intelligence (AI) has emerged as a transformative enabler in addressing these challenges. Advances in machine learning, deep learning, computer vision, natural language processing, and predictive analytics enable the analysis of massive, heterogeneous data streams—including satellite imagery, sensor data, social media, weather models, and infrastructure telemetry—to detect early warning signals, assess vulnerabilities, and forecast disaster impacts with increasing accuracy. AI-powered models can support hazard prediction (e.g., floods, wildfires, earthquakes), optimize evacuation planning, enhance damage assessment, and enable adaptive resource allocation before and during disaster events.

Despite its potential, the adoption of AI in disaster prevention and mitigation remains uneven. Challenges include limited access to high-quality data, model interpretability, algorithmic bias, integration with legacy emergency management systems, cybersecurity risks, and the lack of operational frameworks that translate AI research into deployable solutions. Furthermore, many disaster-prone and underserved communities lack the technical capacity to leverage AI-driven tools effectively.

This symposium aims to bridge these gaps by providing a dedicated forum for researchers, practitioners, policymakers, and technologists to explore how AI can be responsibly designed, deployed, and governed for disaster prevention and mitigation. By emphasizing practical use cases, ethical considerations, and cross-sector collaboration, the symposium seeks to advance resilient, scalable, and inclusive AI-enabled approaches to disaster risk reduction across diverse hazard and geographic contexts.

Goal/Rationale

The primary goal of this symposium is to advance the effective and responsible use of Artificial Intelligence (AI) to enhance disaster prevention and mitigation across natural, technological, and human-induced hazard contexts. The symposium aims to move beyond theoretical discussions by fostering practical, interdisciplinary collaboration that translates AI research into deployable, real-world solutions for disaster risk reduction.

A key objective is to equip participants with a comprehensive understanding of how AI techniques—such as machine learning, deep learning, computer vision, geospatial analytics, and predictive modeling—can be applied to early warning systems, risk assessment, infrastructure monitoring, and impact forecasting. The symposium seeks to highlight successful case studies and emerging tools that demonstrate how AI can improve situational awareness, optimize resource allocation, and support data-driven decision-making before disasters occur.

Another goal is to address critical challenges associated with AI adoption in disaster contexts, including data quality and availability, model interpretability, bias and fairness, cybersecurity risks, and ethical and governance considerations. By engaging experts from academia, industry, emergency management, and public policy, the symposium will promote shared understanding of best practices for building trustworthy and resilient AI systems.

The symposium also aims to foster capacity building and knowledge transfer, particularly for practitioners and communities in disaster-prone or resource-constrained regions. Through guided discussions and collaborative sessions, participants will identify gaps, research opportunities, and actionable frameworks for integrating AI into disaster preparedness and mitigation planning.

Ultimately, the symposium seeks to catalyze sustained collaboration, inspire innovative AI-driven approaches, and contribute to the development of scalable, inclusive strategies that strengthen disaster resilience at local, regional, and global levels.

Scope

This symposium is designed to provide participants with a comprehensive and practical exploration of how Artificial Intelligence (AI) can be leveraged to support disaster prevention and mitigation efforts across diverse hazard domains. The scope of the symposium spans natural disasters (e.g., floods, wildfires, earthquakes, hurricanes), technological and industrial accidents, public health emergencies, and cyber-physical infrastructure disruptions. Emphasis is placed on pre-disaster risk reduction, early warning, preparedness, and mitigation rather than post-event response alone.

The symposium will cover a broad range of AI-driven techniques and applications, including predictive modeling, geospatial and satellite image analysis, sensor data fusion, anomaly detection, simulation and forecasting, and decision-support systems for emergency planning. Participants will engage with real-world case studies that illustrate how AI has been used to identify vulnerabilities, forecast impacts, prioritize mitigation actions, and improve resilience at community and infrastructure levels.

This symposium is intended for an interdisciplinary audience, including researchers, students, emergency management professionals, policymakers, infrastructure operators, urban planners, public health practitioners, and industry technologists. Participants are not expected to have advanced expertise in AI; introductory concepts will be provided where necessary, while advanced discussions will address system integration, scalability, ethics, and governance. Participants will benefit from interactive discussions, knowledge sharing, and guided exploration of best practices, challenges, and emerging research directions. By the end of the symposium, attendees will have a clearer understanding of AI’s capabilities and limitations in disaster prevention and mitigation, as well as actionable insights for applying AI-driven approaches within their own professional or research contexts.