Bayesian Calibration with Functional Outputs Using Elastic Partial Matching
Abstract
Calibrating a simulation model involves estimating its parameters by comparing model outputs with experimental data, so that simulation results faithfully reproduce the experimental observations. When the outputs are functions of time, there are multiple ways to quantify the discrepancy between experimental and simulated curves. A recent approach based on elastic functional data analysis decomposes a functional output into two components: a function temporally aligned to a template, and the corresponding warping function. This decomposition splits the problem into two independent calibration tasks, thereby addressing functional misalignment. However, it assumes that experimental and simulated curves share the same temporal support, an assumption often violated in practice when initial or end times are themselves uncertain or depend on the calibration parameters. In this work, we reinterpret the decomposition step as an approximation to a more general Bayesian calibration problem that incorporates an error term on the time axis. This perspective allows us to naturally extend the framework to a broader family of time warpings with varying initial or end times, using partial elastic alignment. We illustrate the method on a synthetic test case, comparing it with existing Bayesian calibration methods and demonstrating improved surrogate performance and error modeling. We then apply the proposed approach to the calibration of an equation of state (a thermodynamic equation relating the state variables of a material).
Related
- Elastic Multi-Fidelity Bayesian Model Calibration
- Native Probability Outputs for Clinical Triage: An Evaluation of Calibration and Decision Accuracy
- A Hilbert-Valued Functional Decomposition Framework for Explaining Time-Dependent Outputs
- Active learning strategy for excursion-set confidence regions of functional simulator outputs
- Generalized Posterior Calibration via Infinitesimal-Jackknife Variance Matching
BibTeX
@misc{casteras2026bayesian,
title = {{Bayesian Calibration with Functional Outputs Using Elastic Partial Matching}},
author = {Paul Casteras and Julien Bect and Josselin Garnier and Gwenaël Salin},
howpublished = {HAL},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.24676},
eprint = {2609.24676},
archivePrefix = {arXiv},
url = {https://centralesupelec.hal.science/hal-05750576v1},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Bayesian Calibration with Functional Outputs Using Elastic Partial Matching
AU - Paul Casteras
AU - Julien Bect
AU - Josselin Garnier
AU - Gwenaël Salin
PY - 2026
DA - 2026/09/18
PB - HAL
DO - 10.48550/arxiv.2609.24676
UR - https://centralesupelec.hal.science/hal-05750576v1
AB - Calibrating a simulation model involves estimating its parameters by comparing model outputs with experimental data, so that simulation results faithfully reproduce the experimental observations. When the outputs are functions of time, there are multiple ways to quantify the discrepancy between experimental and simulated curves. A recent approach based on elastic functional data analysis decomposes a functional output into two components: a function temporally aligned to a template, and the corresponding warping function. This decomposition splits the problem into two independent calibration tasks, thereby addressing functional misalignment. However, it assumes that experimental and simulated curves share the same temporal support, an assumption often violated in practice when initial or end times are themselves uncertain or depend on the calibration parameters. In this work, we reinterpret the decomposition step as an approximation to a more general Bayesian calibration problem that incorporates an error term on the time axis. This perspective allows us to naturally extend the framework to a broader family of time warpings with varying initial or end times, using partial elastic alignment. We illustrate the method on a synthetic test case, comparing it with existing Bayesian calibration methods and demonstrating improved surrogate performance and error modeling. We then apply the proposed approach to the calibration of an equation of state (a thermodynamic equation relating the state variables of a material).
ER -