5 papers
Observation-Guided Neural Surrogate Learning for Scientific Simulation Emulation: A Single-Gauge Flood-Inundation Proof of Concept
Marzieh Alireza Mirhoseini
We present an observation-guided neural surrogate-learning framework for scientific simulation emulation, demonstrated on urban flood-inundation mapping. The framework combines LIS…
Learning Surrogate Rainfall-driven Inundation Models with Few Data
Marzieh Alireza Mirhoseini
Flood hazard assessment demands fast and accurate predictions. Hydrodynamic models are detailed but computationally intensive, making them impractical for quantifying uncertainty o…
Oja's plasticity rule overcomes several challenges of training neural networks under biological constraints
Navid Shervani-Tabar, Marzieh Alireza Mirhoseini, Robert Rosenbaum
Deep neural networks have achieved impressive performance through carefully engineered training strategies. Nonetheless, such methods lack parallels in biological neural circuits,…
Accelerated solutions of convection-dominated partial differential equations using implicit feature tracking and empirical quadrature
Marzieh Alireza Mirhoseini, Matthew J. Zahr
This work introduces an empirical quadrature-based hyperreduction procedure and greedy training algorithm to effectively reduce the computational cost of solving convection-dominat…
Model reduction of convection-dominated partial differential equations via optimization-based implicit feature tracking
Marzieh Alireza Mirhoseini, Matthew J. Zahr
This work introduces a new approach to reduce the computational cost of solving partial differential equations (PDEs) with convection-dominated solutions: model reduction with impl…