Functional Tensor Network Approximations for E3SM Land Model


The predictive performance of the Energy Exascale Earth System Model (E3SM) is challenged by the modeling choices for a large ensemble of physical processes. This results in a large number of uncertain parameters and computationally expensive numerical simulations. To overcome these challenges, we will focus on constructing surrogate models that exploit the model structure via low-rank functional tensor networks approximations. We will employ a variational inference approach to construct a probabilistic model that approximates the discrepancy between the surrogate and the original model predictions. We will focus on the land model component of E3SM and present results pertaining to global sensitivity analysis and model calibration at a regional scale.

Dec 13, 2021 12:00 AM — 12:00 AM
New Orleans, LA

I am contributing to the following presentations at this conference:

  • AKhachik Sargsyan, Daniel M Ricciuto, Cosmin Safta, Hit twice by the curse of dimensionality: spatio-temporal land model calibration using Karhunen-Loève and sparse polynomial chaos expansions
Cosmin Safta
Cosmin Safta
Distinguished Member of Technical Staff

My research interests include uncertainty quantification, machine learning, and statistics.