activity
20242026
collaborators
Showing 2025Show all

5 papers · 1 filter

stat.ML2025

Bifidelity Karhunen-Loève Expansion Surrogate with Active Learning for Random Fields

Aniket Jivani, Cosmin Safta, Beckett Y. Zhou +1

We present a bifidelity Karhunen-Loève expansion (KLE) surrogate model for field-valued quantities of interest (QoIs) under uncertain inputs. The approach combines the spectral ef…

cs.CE2025

Extrapolating Phase-Field Simulations in Space and Time with Purely Convolutional Architectures

Christophe Bonneville, Nathan Bieberdorf, Pieterjan Robbe +4

Phase-field models of liquid metal dealloying (LMD) can resolve rich microstructural dynamics but become intractable for large domains or long time horizons. We present a condition…

physics.comp-ph2025

A Comparison of Surrogate Constitutive Models for Viscoplastic Creep Simulation of HT-9 Steel

Pieterjan Robbe, Andre Ruybalid, Arun Hegde +4

Mechanistic microstructure-informed constitutive models for the mechanical response of polycrystals are a cornerstone of computational materials science. However, as these models b…

cs.LG2025

Uncertainty quantification of neural network models of evolving processes via Langevin sampling

Cosmin Safta, Reese E. Jones, Ravi G. Patel +4

We propose a scalable, approximate inference hypernetwork framework for a general model of history-dependent processes. The flexible data model is based on a neural ordinary differ…

stat.ML2025

Advancing calibration for stochastic agent-based models in epidemiology with Stein variational inference and Gaussian process surrogates

Connor Robertson, Cosmin Safta, Nicholson Collier +2

Accurate calibration of stochastic agent-based models (ABMs) in epidemiology is crucial to make them useful in public health policy decisions and interventions. Traditional calibra…