CREST Students Present PhD Research Proposals on Urban Flood Prediction

Ali Haider
PhD Candidate, Civil Engineering, CCNY

Proposal Title: AI-Driven Multi-Sensor Modeling Framework for Urban Flood Prediction and Mapping in Data-Scarce Environments

Ali’s research sits at the forefront of remote sensing, machine learning, and urban resilience. His work aims to develop innovative, data-efficient approaches for understanding and predicting urban flood dynamics, particularly in regions where traditional ground-based observations are scarce or unavailable.

Shima Kamali
PhD Candidate, Civil Engineering, CCNY

Proposal Title: Integrative Urban Flood Modeling for New York City: Advancing LISFLOOD-FP and Surrogate Machine Learning for Real-Time Prediction

Shima’s research integrates high-resolution hydrodynamic modeling with surrogate machine-learning approaches to enhance urban flood prediction in New York City. Her work advances the LISFLOOD-FP model to better represent urban drainage processes and leverages data-driven surrogates to enable computationally efficient, near–real-time flood forecasting, supporting effective urban flood preparedness and decision-making.

Congratulations to Ali and Shima on successfully presenting their proposals! Their innovative research exemplifies CREST’s commitment to advancing resilient urban systems through cutting-edge science, technology, and data-driven solutions.