Participants

Participants
(alphabetically listed; last updated 8/6/2024)

Ishfaq Aziz, University of Illinois Urbana-Champaign
Poster: PHYSICS-INFORMED MACHINE LEARNING FOR EM WAVE PROPAGATION AND MATERIAL PROPERTY ESTIMATION
Bahador Bahmani, Johns Hopkins University
RESOLUTION INDEPENDENT NEURAL OPERATOR (RINO)
Prasanna Balaprakash, Oak Ridge National Laboratory
SCALABLE AUTOMATED DEEP ENSEMBLE FOR UNCERTAINTY QUANTIFICATION IN SCIENTIFIC MACHINE LEARNING
Alejandro Becerra, Tufts University

   AN END-TO-END FRAMEWORK FOR SURROGATES OF HYBRID PROPELLANTS

Christophe Bonneville, Sandia National Laboratories

   Poster: ACCELERATING PHASE FIELD SIMULATIONS THROUGH TIME EXTRAPOLATION WITH ADAPTIVE FOURIER NEURAL OPERATORS AND U-NETS
Ramin Bostanabad, University of California, Irvine

  GAUSSIAN PROCESSES: FROM TOPOLOGY OPTIMIZATION TO OPERATOR LEARNING

Tan Bui-Thanh, The University of Texas at Austin

LEARN2SOLVE: A MODEL-CONSTRAINED TANGENT APPROACH FOR SUPERSONIC FLOWS

Dibyajyoti Chakraborty, Pennsylvania State University

    Poster: TURBULENCE MODELING FOR LARGE-EDDY SIMULATIONS USING MACHINE LEARNING
Promit Chakroborty, Johns Hopkins University

   Poster: EFFICIENT RARE EVENT SIMULATION USING AN EXPLAINABLE ACTIVE LEARNING AND MULTIFIDELITY SURROGATE MODELING FRAMEWORK
Krishnanunni Chandradath Girija, The University of Texas at Austin

   Poster: APPROACHES FOR DEEP NEURAL ARCHITECTURE ADAPTATION
Agnimitra Dasgupta, University of Southern California

   SOLVING INVERSE PROBLEMS IN MECHANICS USING CONDITIONAL SCORE-BASED DIFFUSION MODELS
Marta D’Elia, Pasteur Labs & Stanford University
SCIENTIFIC MACHINE LEARNING IN INDUSTRIAL SETTINGS
Som Dhulipala, Idaho National Laboratory

   Poster: MOOSE STOCHASTIC TOOLS FOR PARALLELIZED INVERSE/FORWARD UNCERTAINTY QUANTIFICATION, MULTI-OUTPUT SURROGATE MODELING, ACTIVE LEARNING, AND MULTIFIDELITY MODELING
Pan Du, University of Notre Dame

   CONFILD: CONDITIONAL NEURAL FIELD LATENT DIFFUSION MODEL GENERATING SPATIOTEMPORAL TURBULENCE
Poster: AI-ENABLED RAPID IMAGE-BASED HEMODYNAMIC MODELING WITH QUANTIFIED UNCERTAINTY

Danial Faghihi, University at Buffalo

   STRATEGIC DISCOVERY AND RELIABILITY ASSESSMENT OF DEEP LEARNING SURROGATE MODELS
Ionut Farcas, Virginia Tech

   DISTRIBUTED COMPUTING FOR PHYSICS-BASED DATA-DRIVEN REDUCED MODELING AT SCALE
Charbel Farhat, Stanford University
A NONPARAMETRIC PROBABILISTIC APPROACH FOR MODELING AND QUANTIFYING MODEL-FORM UNCERTAINTY IN CFD WITH TURBULENCE MODELING
Leonardo Ferreira Guilhoto, University of Pennsylvania

   Poster: COMPOSITE BAYESIAN OPTIMIZATION IN FUNCTION SPACES USING NEON - NEURAL EPISTEMIC OPERATOR NETWORKS

Krishna Garikipati, University of Southern California
INFERENCE OF FOKKER-PLANCK EQUATIONS FOR THE DYNAMICS OF POPULATIONS
Georgios Georgalis, Tufts University

   Poster: MULTISCALE EMULATORS AND UQ OF BOUNDARY OUTPUTS FOR COUPLED REACTING FLOWS
Roger Ghanem, University of Southern California
PHYSICS EXTRACTION PODS (PEP): AN EVOLUTION OF THE RVE
Haiwen Guan, The Pennsylvania State University

    Poster: LUCIE: A LIGHTWEIGHT UNCOUPLED CLIMATE EMULATOR WITH LONG-TERM STABILITY AND PHYSICAL CONSISTENCY FOR O(1000)-MEMBER ENSEMBLES
Ashwini Gupta, Johns Hopkins University

   Poster: DEEP LEARNING FOR MICROSTRUCTURE-RESOLVED MULTISCALE MODELING, OPTIMIZATION AND UNCERTAINTY QUANTIFICATION
Joseph Hart, Sandia National Laboratories

   Poster: HYPER-DIFFERENTIAL SENSITIVITY ANALYSIS WITH RESPECT TO MODEL DISCREPANCY
Amanda Howard, Pacific Northwest National Laboratory
MORE OF A GOOD(?) THING: UNCERTAINTY PROPAGATION THROUGH MULTIFIDELITY DEEP OPERATOR NETWORKS
Xun Huan, University of Michigan

   Poster: BAYESIAN FOKKER-PLANCK-BASED INVERSE REFORCEMENT LEARNING
Birendra Jha, University of Southern California

   Poster: QUANTIFICATION OF WELL LOCATION AND PERMEABILITY UNCERTAINTIES IN GEOLOGIC CO2 STORAGE USING ENSEMBLE NEURAL OPERATOR PROXIES
Teeratorn Kadeethum, Sandia National Laboratories

   PROBABILISTIC INTERPRETATION OF IMPROVED NEURAL OPERATORS FOR LARGE-SCALE GEOLOGICAL CARBON STORAGE
Yannis Kevrekidis, Johns Hopkins University
ON SAMPLING THE THINGS THAT DO NOT MATTER
Wesley Lao, University of Texas at Austin

   Poster:  A SCIENTIFIC MACHINE LEARNING APPROACH FOR BRIDGING TWO- AND THREE-DIMENSIONAL FLOWS
Xin-Yang Liu, University of Notre Dame

   Poster: INTEGRATING PDE OPERATORS INTO NEURAL NETWORK ARCHITECTURE IN A MULTI-RESOLUTION MANNER FOR SPATIOTEMPORAL PREDICTION
Simon Mak, Duke University

   LOCAL TRANSFER LEARNING GAUSSIAN PROCESSES FOR COST-EFFICIENT SURROGATE MODELING OF EXPENSIVE COMPUTER SIMULATORS
Zachariah Malik, University of Colorado Boulder

   Poster: IMPROVING ENKF FOR NON-GAUSSIAN SYSTEMS WITH GENERATIVE MACHINE LEARNING
Youssef Marzouk, Massachusetts Institute of Technology
Romit Maulik, Pennsylvania State University & Argonne National Laboratory
INTERPRETABLE FINE-TUNING AND ERROR INDICATION FOR GRAPH NEURAL NETWORK SURROGATE MODELS
Kathryn Maupin, Sandia National Laboratories

   Poster: BAYESIAN OPTIMAL DESIGN OF PULSED POWER EXPERIMENTS
Habib Najm, Sandia National Laboratories
APPROXIMATE BAYESIAN MODEL CALIBRATION WITH SUMMARY STATISTICS

Cole Nockolds, The University of Texas at Austin

         Poster: SIMULATING STIFF SYSTEMS WITH A LINEAR PARAMETERIZED LATENT SPACE
Audrey Olivier, University of Southern California
EMBEDDING PHYSICS-DRIVEN UNCERTAINTY IN NEURAL NETWORKS WITH ANCHORED ENSEMBLES
Georgios Pasparakis, Johns Hopkins University

   Poster: BAYESIAN NEURAL NETWORKS FOR PREDICTING UNCERTAINTY IN FULL-FIELD MATERIAL RESPONSE
Abani Patra, Tufts University
LANDSLIDES AND ROCKETS: DATA, ML AND UQ FOR COUPLED MULTISCALE PHYSICS
Russell Philley, The University of Texas at Austin

   Poster: MODEL-CONSTRAINED UNCERTAINTY QUANTIFICATION FOR SCIENTIFIC DEEP LEARNING OF INVERSE PROBLEMS
Elizabeth Qian, Georgia Institute of Technology
MULTIFIDELITY LINEAR REGRESSION FOR SCIENTIFIC MACHINE LEARNING FROM SCARCE DATA
Weilun Qiu, University of Pennsylvania

   Poster: A MACHINE-LEARNING BASED STRATEGY TO DISCOVER INTERNAL VARIABLES FROM DATA
Fernando Rochinha, Universidade Federal do Rio de Janeiro

   BAYESIAN FULL WAVE INVERSION USING DEEP PRIORS
Khachik Sargsyan, Sandia National Laboratories
EMBEDDED FRAMEWORK FOR MODEL ERROR QUANTIFICATION AND PROPAGATION
Toryn Schafer, Texas A&M University

   MACHINE LEARNING DATA-DRIVEN CLOSURE MODELS
Himanshu Sharma, Johns Hopkins University

   Poster: A PHYSICS-CONSTRAINED POLYNOMIAL CHAOS FRAMEWORK FOR DATA-DRIVEN MODELING AND UNCERTAINTY QUANTIFICATION
Jim Stewart, Sandia National Laboratories
SCIENTIFIC MACHINE LEARNING AT SANDIA: A SPOTLIGHT
Pranv Sunil, Rutgers University

   Poster: USING FINITE ELEMENT PHYSICS-INFORMED NEURAL NETWORKS FOR SURROGATE MODELING
Jouni Susiluoto, Jet Propulsion Laboratory, California Institute of Technology
UNCERTAINTY QUANTIFICATION FOR PARTIAL FORWARD MODEL EMULATION IN EARTH REMOTE SENSING
Guoxiang Tong, University of Notre Dame

   Poster: ANALYZING CARDIOVASCULAR MODEL IDENTIFIABILITY WITH DEEP GENERATIVE NETWORKS
Chi (April) Tran, University of Colorado Boulder
WEAK-FORM LATENT SPACE DYNAMICS IDENTIFICATION WITH UQ
Nathaniel Trask, University of Pennsylvania
A DATA-DRIVEN EXTERIOR CALCULUS FOR PROBABILISTIC DIGITAL TWINS
Noah Wade, Naval Research Laboratory

   DEVELOPMENT AND EVALUATION OF AN ONLINE WEIGHT-BALANCING TRAINING METHODOLOGY TO IMPROVE NEURAL NETWORK TRAINING FOR UNCERTAINTY PROPATION
Ruda Zhang, University of Houston
STOCHASTIC SUBSPACE VIA PROBABILISTIC PCA TO CHARACTERIZE AND CORRECT MODEL ERROR