Sanaa Mouzahir

Sanaa Mouzahir is a graduate student in computational science and engineering and mechanical engineering combining deep learning with rigorous probabilistic methods to improve coarse-grid simulations of fluid flows. Standard closure models are deterministic and provide no uncertainty estimates, limiting their reliability for mission-critical predictions. Sanaa generates training data through the MSEAS finite volume solver and implements stochastic boundary conditions via the Econometrics Toolbox with parallel execution through the Parallel Computing Toolbox. Her Deep Gaussian closure achieves calibrated uncertainty while gracefully degrading on out-of-distribution inputs. She processes hundreds of simulations efficiently using parallel workflows, reducing typical computation times by 60%. The framework seamlessly integrates MATLAB-based solvers with Python learning systems through the MATLAB Engine API, preserving numerical fidelity during long simulation rollouts. As a MathWorks Fellow, Sanaa will design multi-objective optimization frameworks using the Global Optimization Toolbox to balance accuracy against computational cost, as well as closure models of transient fluid dynamical systems. Her work opens new possibilities for reliable uncertainty quantification across ocean and environmental modeling applications.