We develop scalable, AI-powered methods to generate, enhance, and validate datasets critical for urban resilience and infrastructure risk analysis. By leveraging machine learning, remote sensing, and generative models, we create high-quality, geospatially grounded datasets in data-scarce regions to support equitable and data-informed decision-making.
Investigating the risks associated with transitioning to renewable energy sources. This project involves quantitative financial risk assessment and scenario analysis to support sustainable energy policy and investment decisions.
We analyze the effects of heatwaves on public health and energy systems to develop adaptive strategies and decision-support tools. Our research aims to identify and address the risks heatwaves pose to vulnerable populations and critical infrastructure, enabling more effective management and mitigation of heatwave impacts.
We develop models to quantify damage caused by extreme events such as floods, earthquakes, and wildfires using satellite imagery, neural networks, large language models, and vision language models. Our innovative approach enables damage forecasting even in the absence of historical data. This capability provides stakeholders with valuable insights to proactively prepare for potential threats and mitigate risks associated with extreme events.
We analyze the socioeconomic impacts of extreme events in collaboration with stakeholders, with a focus on infrastructure interdependencies and equitable solutions. By understanding these interdependencies and identifying vulnerable communities, we aim to enhance the effectiveness of policy interventions and improve resilience across various cities.
We identify compound climate risks, focusing on physical hazards such as heavy precipitation and droughts. By analyzing various scenarios across different climate pathways, we quantify the associated risks and project their impacts. This includes evaluating potential effects on agricultural productivity and labor shortages, offering a comprehensive understanding of how these events might affect various sectors.
We create statistical, machine learning, and physics-based models to forecast and nowcast floods and assess their socioeconomic impacts. For instance, our rapid flood estimation model, GISSR, delivers real-time forecasts and nowcasts of flood events within seconds, facilitating prompt responses and effective risk management. Additionally, we employ statistical models to analyze the frequency and magnitude of hurricanes, providing valuable insights for preparedness and mitigation.
We develop decision-making frameworks and optimization algorithms to implement cost-effective and equitable measures against natural hazards, using hazard and demographic data. Our approach evaluates a variety of protective measures—such as seawalls, green infrastructure, and insurance, individually or in combination—across different times and locations to ensure optimal effectiveness.
