Scalable, Likelihood-Free Calibration of Ice-Sheet Models with Deep Diffusion Emulators and Feature Matching
Abstract
The Antarctic ice sheet is a major source of uncertainty in future sea-level projections, and physical simulators such as the PSU3D-ICE model are essential for studying its evolution. Calibrating them against observations is challenging: the simulator outputs and observed ice-thickness fields are high-dimensional, spatially dependent, and semi-continuous, with a large point mass at zero denoting ice-free regions. These features make conventional Gaussian-process emulation and likelihood-based calibration ill-suited and computationally infeasible at full resolution. We propose the sequential calibration method guided by a diffusion model and a Siamese network (SC-DS), a fully neural framework. For emulation, we develop a single conditional diffusion model that jointly generates the binary ice presence--absence pattern and the continuous thickness field, using global and local conditioning to represent how the input parameters shape the output. Because the emulator induces an intractable likelihood, our likelihood-free calibration replaces the hand-chosen distance and tolerance of approximate Bayesian computation with a probabilistic acceptance rule learned by an iteratively retrained Siamese network, together with a data--model discrepancy adjustment. Applied to the West Antarctic Ice Sheet, SC-DS matches the accuracy of state-of-the-art Gaussian-process calibration at a fraction of its computational cost and scales to the full-resolution domain, where existing methods become intractable.
Related
- Does Calibration Pick the Right Model? Likelihood Evidence from Income Risk
- Bayesian Graphical Models under Positivity Constraints: A Scalable Generalized Likelihood Approach
- Connecting Score Matching, Maximum Likelihood, and Expectation-Maximization in Mixed Linear Regression
- Few-Step Boltzmann Generators via Scalable Likelihood Flow Maps
- Fast and Scalable Multi-Agent Distribution Matching via Partitioned Optimal Transport
BibTeX
@misc{wi2026scalable,
title = {{Scalable, Likelihood-Free Calibration of Ice-Sheet Models with Deep Diffusion Emulators and Feature Matching}},
author = {Kanghyun Wi and Jaewoo Park and Saumya Bhatnagar and Won Chang},
howpublished = {arXiv},
year = {2026},
month = aug,
doi = {10.48550/arxiv.2608.29642},
eprint = {2608.29642},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.29642},
}
RIS
TY - UNPB
TI - Scalable, Likelihood-Free Calibration of Ice-Sheet Models with Deep Diffusion Emulators and Feature Matching
AU - Kanghyun Wi
AU - Jaewoo Park
AU - Saumya Bhatnagar
AU - Won Chang
PY - 2026
DA - 2026/08/30
PB - arXiv
DO - 10.48550/arxiv.2608.29642
UR - https://arxiv.org/abs/2608.29642
AB - The Antarctic ice sheet is a major source of uncertainty in future sea-level projections, and physical simulators such as the PSU3D-ICE model are essential for studying its evolution. Calibrating them against observations is challenging: the simulator outputs and observed ice-thickness fields are high-dimensional, spatially dependent, and semi-continuous, with a large point mass at zero denoting ice-free regions. These features make conventional Gaussian-process emulation and likelihood-based calibration ill-suited and computationally infeasible at full resolution. We propose the sequential calibration method guided by a diffusion model and a Siamese network (SC-DS), a fully neural framework. For emulation, we develop a single conditional diffusion model that jointly generates the binary ice presence--absence pattern and the continuous thickness field, using global and local conditioning to represent how the input parameters shape the output. Because the emulator induces an intractable likelihood, our likelihood-free calibration replaces the hand-chosen distance and tolerance of approximate Bayesian computation with a probabilistic acceptance rule learned by an iteratively retrained Siamese network, together with a data--model discrepancy adjustment. Applied to the West Antarctic Ice Sheet, SC-DS matches the accuracy of state-of-the-art Gaussian-process calibration at a fraction of its computational cost and scales to the full-resolution domain, where existing methods become intractable.
ER -