
Strengthening Risk and Disaster Resilience: Bridging Science, Technology, and Community for a Safer Future
Laboratory on Risk and Disaster Resilience Research
Associate Professor:LAM Chi Yung
E-mail:
[Research areas]
Risk and Disaster Management
[Keywords]
Risk, Disaster, Resilience, Analysis, Simulation
Skills and background we are looking for in prospective students
We welcome students with a strong academic background in engineering or science, as well as an interest in or experience with numerical and data analysis. Strong written and oral communication skills in English are also required.
What you can expect to learn in this laboratory
Our research focuses on the analysis, management, communication, and regulation of various types of risks in nature and society. In our laboratory, students are expected to understand the theories of risk and its management processes, as well as the integrated analytical techniques for addressing complex problems related to risks and disasters.
【Job category of graduates】 Civil service, consulting firm, railway/ transportation/ engineering company
Research outline
We are conducting research on frameworks and methodologies for risk prediction and disaster resilience. Focus areas include proactive management, resource optimization, and community-driven strategies, including (but not limited to):
Multimodal Risk Analysis Framework
We are studying a multimodal framework for risk analysis and prediction, integrating data from text, images, sensor readings, and historical records. By combining AI and machine learning models, this research aims to predict and mitigate risks in real-time across domains such as social infrastructure, socioeconomic systems, cybersecurity, and healthcare. The focus is on explainability, proactive management, and scenario simulation.
Integrated Disaster Resilience Framework
We are studying a disaster resilience framework that integrates real-time data from IoT sensors, satellite imagery, and social media to predict and enhance recovery efforts. By combining predictive analytics and community-based models, the framework aims to optimize resource allocation, improve emergency response, and foster adaptive strategies for resilient infrastructure and communities facing natural disasters.
Community-Based Disaster Risk Reduction
We are exploring the role of community-based risk reduction strategies in enhancing disaster resilience. The focus is on integrating multidisciplinary knowledge, participatory decision-making, and localized resource allocation to mitigate natural hazards. Case studies of successful initiatives are being investigated to assess their scalability and effectiveness in reducing vulnerabilities and fostering sustainable recovery. Emphasis is placed on empowering local stakeholders for long-term resilience.
Adaptive Decision Strategies for Uncertainty
We are examining the integration of scenario planning and game theory in decision-making for uncertain disaster risks. The focus is on how dynamic modeling and stakeholder collaboration can improve preparedness and resource allocation under uncertainty. Case studies are analyzed to assess how these methods enhanced adaptive strategies, reduced impacts, and fostered resilience in complex disaster scenarios, such as pandemics or cascading natural hazards.
Nature-Based Disaster Prediction Methods
We are investigating the use of natural indicators, such as animal behavior, plant growth patterns, and atmospheric changes, to predict natural disasters like earthquakes, tsunamis, and hurricanes. We combine traditional ecological knowledge with modern data analytics to develop predictive models. The goal is to create early-warning systems based on nature’s signals, enhancing disaster preparedness and response while preserving local knowledge.
Key publications
- LAM, C.Y., et al. (2025). An information network analysis approach to assessing the processes of issuing evacuation instructions: A study of evacuation cases in Japan. Journal of Risk Research. DOI: 10.1080/13669877.2025.2466537.
- LAM, C.Y., et al. (2025). Optimizing travel routes for medical services during evacuation: A network and shared mobility perspective. Progress in Disaster Science. DOI: 10.1016/j.pdisas.2025.100407.
- LAM, C.Y., et al. (2024). Topological network and fuzzy AHP modeling framework for the suitability analysis of evacuation shelters: A case study in Japan. International Journal of Disaster Risk Reduction. DOI: 10.1016/j.ijdrr.2024.104696.
Equipment
Advanced Analytical Software and Analyzers, High-Performance Computers
Teaching policy
Our laboratory encourages students to conduct advanced research while fostering creative thinking throughout the process.
[Website] URL : https://jaist.ac.jp/~cylam/lab/