works on

From the 1 of 7 linked papers with an AI index.

activity
20242026
collaborators

7 papers

cs.LG2026

GeoQ: Geometry-Aware Conditional Quantile Error Estimation for Scientific Surrogate Models

Khoa Nguyen, Daniel Serino, Aviral Prakash +1

Neural-network surrogate models are increasingly used to accelerate scientific simulations, but their deployment in extrapolative and autoregressive settings requires input-depende…

physics.comp-ph2026

Structure-preserving variational neural fields: Uncertainty-quantified reduced-order modeling of nonlinear conservation laws

Aviral Prakash, Marc L. Klasky

The paper introduces a variational latent neural field framework that provides both uncertainty estimates and exact preservation of conservation laws for reduced-order models of no…

physics.flu-dyn2026

Discovery of Sparse Invariant Subgrid-Scale Closures via Dissipation-Controlled Training for Large Eddy Simulation on Anisotropic Grids

Samantha Friess, Aviral Prakash, John A. Evans

Neural networks offer highly expressive turbulence closures, yet their complexity obscures the physical mechanisms they aim to model, and their computational cost can limit their t…

physics.comp-ph2025

ECLEIRS: Exact conservation law embedded identification of reduced states for parameterized partial differential equations from sparse and noisy data

Aviral Prakash, Ben S. Southworth, Marc L. Klasky

Multi-query applications such as parameter estimation, uncertainty quantification and design optimization for parameterized PDE systems are expensive due to the high computational…

physics.comp-ph2024

Nonintrusive projection-based reduced order modeling using stable learned differential operators

Aviral Prakash, Yongjie Jessica Zhang

Nonintrusive projection-based reduced order models (ROMs) are essential for dynamics prediction in multi-query applications where access to the source of the underlying full order…

physics.flu-dyn2024

SNF-ROM: Projection-based nonlinear reduced order modeling with smooth neural fields

Vedant Puri, Aviral Prakash, Levent Burak Kara +1

Reduced order modeling lowers the computational cost of solving PDEs by learning a low-order spatial representation from data and dynamically evolving these representations using m…