Neural posterior inference with state-space models for calibrating ice sheet simulators

TL;DR

This paper introduces a neural posterior approximation method within a state-space framework to efficiently calibrate ice sheet models, improving parameter and state estimation accuracy for better sea level rise projections.

Contribution

It presents a novel neural network-based approach for calibrating high-dimensional ice sheet model parameters using observational data within a state-space model.

Findings

The method outperforms the current state-of-the-art ensemble Kalman filter in parameter and state estimation accuracy.

Application to Thwaites Glacier demonstrates practical effectiveness in real-world scenarios.

Simulation results confirm improved calibration accuracy over existing methods.

Abstract

Ice sheet models are routinely used to quantify and project an ice sheet's contribution to sea level rise. In order for an ice sheet model to generate realistic projections, its parameters must first be calibrated using observational data; this is challenging due to the nonlinearity of the model equations, the high dimensionality of the underlying parameters, and limited data availability for validation. This study leverages the emerging field of neural posterior approximation for efficiently calibrating ice sheet model parameters and boundary conditions. We make use of a one-dimensional (flowline) Shallow-Shelf Approximation model in a state-space framework. A neural network is trained to infer the underlying parameters, namely the bedrock elevation and basal friction coefficient along the flowline, based on observations of ice velocity and ice surface elevation. Samples from the approximate posterior distribution of the parameters are then used within an ensemble Kalman filter to infer latent model states, namely the ice thickness along the flowline. We show through a simulation study that our approach yields more accurate estimates of the parameters and states than a state-augmented ensemble Kalman filter, which is the current state-of-the-art. We apply our approach to infer the bed elevation and basal friction along a flowline in Thwaites Glacier, Antarctica.