Emulating satellite drag from large simulation experiments
From MaRDI portal
Abstract: Obtaining accurate estimates of satellite drag coefficients in low Earth orbit is a crucial component in positioning and collision avoidance. Simulators can produce accurate estimates, but their computational expense is much too large for real-time application. A pilot study showed that Gaussian process (GP) surrogate models could accurately emulate simulations. However, cubic runtime for training GPs means that they could only be applied to a narrow range of input configurations to achieve the desired level of accuracy. In this paper we show how extensions to the local approximate Gaussian Process (laGP) method allow accurate full-scale emulation. The new methodological contributions, which involve a multi-level global/local modeling approach, and a set-wise approach to local subset selection, are shown to perform well in benchmark and synthetic data settings. We conclude by demonstrating that our method achieves the desired level of accuracy, besting simpler viable (i.e., computationally tractable) global and local modeling approaches, when trained on seventy thousand core hours of drag simulations for two real-world satellites: the Hubble space telescope (HST) and the gravity recovery and climate experiment (GRACE).
Recommendations
- Locally induced Gaussian processes for large-scale simulation experiments
- Computer emulation with nonstationary Gaussian processes
- Scaled Vecchia approximation for fast computer-model emulation
- Faster Kriging: facing high-dimensional simulators
- Exploiting Variance Reduction Potential in Local Gaussian Process Search
Cites work
- A Full Scale Approximation of Covariance Functions for Large Spatial Data Sets
- A Limited Memory Algorithm for Bound Constrained Optimization
- An overview of composite likelihood methods
- Bayesian Design and Analysis of Computer Experiments: Use of Derivatives in Surface Prediction
- Design and analysis of computer experiments. With comments and a rejoinder by the authors
- Efficient emulators of computer experiments using compactly supported correlation functions, with an application to cosmology
- Full scale multi-output Gaussian process emulator with nonseparable auto-covariance functions
- scientific article; zbMATH DE number 52492 (Why is no real title available?)
- Inconsistent Estimation and Asymptotically Equal Interpolations in Model-Based Geostatistics
- Interpolation of spatial data. Some theory for kriging
- Kinetic models for gas-surface interactions
- Massively parallel approximate Gaussian process regression
- Objective Bayesian Analysis of Spatially Correlated Data
- Parallel partial Gaussian process emulation for computer models with massive output
- Robust Gaussian stochastic process emulation
- Strictly Proper Scoring Rules, Prediction, and Estimation
- The design and analysis of computer experiments.
Cited in
(17)- Locally induced Gaussian processes for large-scale simulation experiments
- Large-scale local surrogate modeling of stochastic simulation experiments
- Managing spherical proof masses in drag-free satellites with application to the LISA experiment
- Gaussian Process Prediction using Design-Based Subsampling
- Statistical Tests for Cross-Validation of Kriging Models
- Scaled Vecchia approximation for fast computer-model emulation
- Faster Kriging: facing high-dimensional simulators
- A Clustered Gaussian Process Model for Computer Experiments
- Sensitivity Prewarping for Local Surrogate Modeling
- Active Learning for Deep Gaussian Process Surrogates
- ProSpar-GP: Scalable Gaussian Process Modeling with Massive Nonstationary Datasets
- Sparse inverse Cholesky factorization of dense kernel matrices by greedy conditional selection
- Precision aggregated local models
- A comparison of Gaussian processes and neural networks for computer model emulation and calibration
- Active Sampling: A Machine-Learning-Assisted Framework for Finite Population Inference with Optimal Subsamples
- Monotonic warpings for additive and deep Gaussian processes
- Vecchia-approximated Deep Gaussian Processes for Computer Experiments
This page was built for publication: Emulating satellite drag from large simulation experiments
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5237174)
