.png){kind=icon}
.png){kind=icon}
Return
Emulating Simulation Experiments with Grounding Using a Two-Stage Classification-Regression Model
.png){kind=icon}
PRE
AI
DOI：10.1080/00401706.2026.2653566.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Computer models (simulators) are vital tools for investigating physical processes. Despite their utility, the prohibitive run-time of simulators hinders their direct application for uncertainty quantification. Gaussian process emulators (GPEs) have been used extensively to circumvent the cost of the simulator and are known to perform well on simulators with smooth, stationary output. In reality, many simulators violate these assumptions. Motivated by a finite element simulator, which models early stage oxidation of uranium in water vapor, we propose an adaptation of the GPE. Our adaptation is called the double emulator and is designed specifically for simulators that "ground" in a considerable volume of their input space. Grounding is the process by which a simulator attains its minimum and can result in violation of the stationarity and smoothness assumptions used in the conventional GPE. We perform numerical experiments comparing the performance of the GPE and double emulator on both the oxidation simulator and synthetic examples.
Keywords:
Computer experiment
Double emulator
Landing
Mixture model