2024-07-10 –, Else (1.3)
Scientific machine learning methods that balance mechanist equations with data-driven inference provide novel surrogates that decompose global from local behaviors inherent to high-fidelity stochastic models. This novel approach to surrogate modeling is pioneering advancements in hierarchal calibration of agent-based models that preserve foundational scientific knowledge.
Machine-learned models are increasingly being used in lieu of, to complement, or as surrogates for classic computational models. The emerging field of scientific machine learning (SciML) seeks to fuse traditional mathematical modeling with advances in machine learning to handle challenges such as the implementation of numerical solvers, model-form error estimations, and the computational expense of high-fidelity models. SciML models balance mechanist equations with data-driven inference, resulting in computational models that preserve scientific knowledge while readily adapting to the unknown through data-driven discovery. These advancements are setting the foundation for which SciML is providing novel surrogates that decompose global and local behavior inherent to high fidelity stochastic models. This presentation will introduce neural network (NN) function approximations of model-form error to close the gap between ordinary differential equations (ODE) compartmental model to an epidemiological agent-based model (ABM). This universal differential equations surrogate to the ABM allows us to preserve the foundational ODE that represents the global disease dynamics and couples it the NN model-form errors that isolate function approximations for the local behaviors of the ABM. We will then further discussion on using this UDE surrogate to automate hierarchical calibration of ABMs where we decompose global parameter estimations from local parameter influence.
Erin C.S. Acquesta is a Mathematician and Principal Member of the Technical Staff with the Applied Information Sciences Center at Sandia National Laboratories. She received her MS and PhD from North Carolina State University in the field of applied mathematics. Her research areas of interest include scientific machine learning, uncertainty quantification, sensitivity analysis, and machine learning explainability; with an emphasis on providing credible, adaptive, and interpretable modeling capabilities for enhanced situational awareness in support of national security decision-making. Her primary domain area of expertise focuses on the mathematical properties of infectious disease models. As an area of professional service, she is a member of the ASME VVUQ standards committee, writing definitions for verification, validation, uncertainty quantification, and credibility for machine-learned models. She also volunteers her time for educational outreach as a mentor and head referee for the Albuquerque VEX VRC Robotics League and NM State VEX VRC Robotics Competitions.