Dr Lea Dasallas: Breaking the wall of urban flood prediction
Participant in 2026 Falling Walls Lab Aotearoa New Zealand.
Dr Lea Dasallas
University of Canterbury
We aim to make flood predictions faster and more practical for early warning and evacuation. Current high-resolution hydrodynamic models are accurate and comprehensive but slow and computationally demanding, limiting their application for flood forecasting. We are developing a new approach to combine machine learning with physics-based models to deliver rapid, reliable flood-risk predictions that support safe transport mobility.
Lea Dasallas is a Postdoctoral Fellow in Civil and Environmental Engineering at the University of Canterbury, where she headed the stormwater flood modeling, flood-risk assessment and evacuation analysis for Wellington, New Zealand. Her background includes expertise in the analysis of extreme weather events, climate change adaptation, flood modeling, and disaster risk reduction. She had been working on flood-intervention options and how to mitigate flood disasters. Her PhD in Environmental Water Resource is from South Korea and her MSc in Meteorology is from the Philippines.