@article{22535,
  abstract     = {Flooding impacts are on the rise globally, and concentrated in urban areas. Currently, there are no operational systems to forecast flooding at spatial resolutions that can facilitate emergency preparedness and response actions mitigating flood impacts. We present a framework for real-time flood modeling and uncertainty quantification that combines the physics of fluid motion with advances in probabilistic methods. The framework overcomes the prohibitive computational demands of high-fidelity modeling in real-time by using a probabilistic learning method relying on surrogate models that are trained prior to a flood event. This shifts the overwhelming burden of computation to the trivial problem of data storage, and enables forecasting of both flood hazard and its uncertainty at scales that are vital for time-critical decision-making before and during extreme events. The framework has the potential to improve flood prediction and analysis and can be extended to other hazard assessments requiring intense high-fidelity computations in real-time.},
  author       = {Ivanov, Valeriy Y. and Xu, Donghui and Dwelle, M. Chase and Sargsyan, Khachik and Wright, Daniel B. and Katopodes, Nikolaos and Kim, Jongho and Tran, Vinh Ngoc and Warnock, April and Fatichi, Simone and Burlando, Paolo and Caporali, Enrica and Restrepo, Pedro and Sanders, Brett F. and Chaney, Molly M. and Nunes, Ana M. B. and Nardi, Fernando and Vivoni, Enrique R. and Istanbulluoglu, Erkan and Bisht, Gautam and Bras, Rafael L.},
  issn         = {1944-8007},
  journal      = {Geophysical Research Letters},
  number       = {20},
  publisher    = {American Geophysical Union},
  title        = {{Breaking down the computational barriers to real‐time urban flood forecasting}},
  doi          = {10.1029/2021gl093585},
  volume       = {48},
  year         = {2021},
}