The Disaster Analytics for Society Lab (DASL) is focused on using novel technologies and analytical methods to understand, model, and predict the impact of natural disasters on society, and develop tools to promote resilient cities. We combine methods from spatial statistics, risk / reliability analysis, machine learning, remote sensing and probabilistic modeling to develop information systems on pre-disaster risk, post-disaster impact and long-term disaster recovery. Our research has a particular focus on cities and urban regions as they represent extremes in terms of potential casualties and losses, and require more complex analyses due to their dynamics in terms of populations, infrastructure systems and networks. Beyond modeling and analysis, we investigate the communication of uncertainty as it relates to disaster risk, and the translation of resilience science into policy.
DASL is highly interdisciplinary and collaborative. Among these collaborators are the Stanford Urban Resilience Initiative, the World Bank, the Global Facility for Disaster Reduction and Recovery (GFDRR) Innovations Lab, Google, the Natural Capital Project, the Humanitarian OpenStreetMap Team, and others.
Main research interests include:
- Dynamic urban risk modeling and forecasting
- Quantitative models of resilience
- Big data analytics for rapid post-disaster impact assessment
- Data-driven models of urban vulnerability
- Transdisciplinary design research
- Nature-based risk-reduction solutions
After the Gorkha Earthquake - Damage Assessment In Nepal
Introduction to the Southeast Asia SEA-Level (SEA2) Program