CoRAL Lab at Virginia Tech

Compound flood hazard and Risk Assessment in Low-lying areas (CoRAL).

CoRAL_Logo.png

The CoRAL Lab integrates physics-informed and data-driven models to understand complex compound extreme dynamics in human and natural systems. We are interested in statistical analysis, hydrodynamic modeling, machine learning, remote sensing, and data collection using drones.

Vision:

The CoRAL Lab aims at enhancing the characterization, modeling, and prediction of compound extreme dynamics at different scales as well as their impacts on vulnerable communities to flooding.

We aim at providing actionable flood hazard maps, adaptation and planning strategies that integrate green infrastructure and risk-flood information through scenario-based simulations.

news

Jun 29, 2026 Our collaborative research on “Characterization of tropical cyclone surge evolution” has been accepted for publication in Coastal Engineering Journal. Congratulations to the team!
Jun 28, 2026 I am proud to share Sam’s last dance as a member of the CoRAL Lab. What a fantastic way to summarize his PhD journey with a perspective in collaboration with a giant in the machine learning field! Check our article “Towards Transferable Models for Efficient Spatiotemporal Flood Prediction Across Coastal-Estuarine Systems”.
Mar 30, 2026 Our collaborative research on “Towards a typology for hybrid compound flood modeling” has been accepted for publication in Hydrology and Earth System Sciences journal. Congratulations to the team!
Jan 29, 2026 Our collaborative research on “Evaluating the three-cornered hat method for hourly satellite precipitation fusion in hydrological forecasting: A case study in a Tropical Andean Basin” has been accepted for publication in the Journal of Hydrology: Regional Studies. Congratulations to the team!

latest posts

selected publications

  1. From local to regional compound flood mapping with deep learning and data fusion techniques
    David F Muñoz, Paul Muñoz, Hamed Moftakhari, and 1 more author
    Science of the Total Environment, 2021
  2. Quantifying cascading uncertainty in compound flood modeling with linked process-based and machine learning models
    David F Muñoz, Hamed Moftakhari, and Hamid Moradkhani
    Hydrology and Earth System Sciences, 2024
  3. Predicting the evolution of extreme water levels with long short-term memory station-based approximated models and transfer learning techniques
    Samuel Daramola, David F Muñoz, Paul Muñoz, and 2 more authors
    Water Resources Research, 2025
  4. Breaking down annual and tropical cyclone-induced nonlinear interactions in total water levels
    Md Shadman Sakib, David F Muñoz, and Thomas Wahl
    Advances in water resources, 2025
  5. A transferable deep learning framework to propagate extreme water levels from sparse tide-gauges across spatial domains
    Samuel Daramola, David F Muñoz, Md Shadman Sakib, and 2 more authors
    Expert Systems with Applications, 2025