Emulation with uncertainty quantification of regional sea‐level change caused by the Antarctic Ice Sheet
Projecting regional sea‐level change under various climate‐change scenarios typically involves running forward simulations of the Earth's gravitational, rotational and deformational (GRD) response to ice‐mass change, which requires substantial computational cost if applied to probabilistic frameworks requiring thousands to millions of samples. Here we build emulators of regional sea‐level change at 27 coastal locations, due to the GRD effects associated with future Antarctic Ice Sheet mass change over the 21st century. The emulators are evaluated against a numerical sea‐level model applied to an ensemble of ice‐sheet model simulations of the Antarctic Ice Sheet through 2100. We build a physics‐based emulator using a recent sensitivity kernel approach and compare it to machine learning based emulators (neural network and conditional variational autoencoder methods). In order to quantify uncertainty, we derive well‐calibrated prediction intervals for regional sea‐level change via split‐conformal inference and linear regression, and show that Monte Carlo dropout does not yield well‐calibrated uncertainties in this instance. We also demonstrate substantial gains in computational efficiency using both the physics‐based emulator and neural networks in comparison to the numerical model for the complete regional sea‐level solution. Overall, we find the physics‐based emulator modestly outperforms the machine learning emulators for this problem.
Publications: Yoo et al.(2025). Emulation with uncertainty quantification of regional sea‐level change caused by the Antarctic Ice Sheet. Journal of Geophysical Research: Machine Learning and Computation, 2, e2024JH000349.
Wildfires can be devastating, causing significant damage to property, ecosystem disruption, and loss of life. Forecasting the evolution of wildfire boundaries is essential to real-time wildfire management. To this end, substantial attention in the wildifre literature has focused on the level set method, which effectively represents complicated boundaries and their change over time. Nevertheless, most of these approaches rely on a heavily-parameterized formulas for spread and fail to account for the uncertainty in the forecast. The rapid evolution of large wildfires and inhomogeneous environmental conditions across the domain of interest (e.g., varying land cover, fire-induced winds) give rise to a need for a model that enables efficient data-driven learning of fire spread and allows uncertainty quantification. Here, we present a novel hybrid model that nests an echo state network to learn nonlinear spatio-temporal evolving velocities (speed in the normal direction) within a physically-based level set model framework. This model is computationally efficient and includes calibrated uncertainty quantification. We show the forecasting performance of our model with simulations and two real data sets – the Haybress and Thomas megafires that started in California (USA) in 2017.
Publications: Yoo, M. and Wikle, C. K. (2023). Using echo state networks to inform physical models for fire front propagation, Spatial Statistics, 54, 100732, https://doi.org/10.1016/j.spasta.2023.100732
A massive wildfire could impact nature, humans, and society, causing catastrophic damage to property and human resources. Forecasting the wildfire front propagation is essential to prevent potential loss. Forecasting has multiple benefits, including firefighting efforts and saving lives in danger. The level set method has been widely used to analyze the change in surfaces, shapes, and boundaries. In particular, a signed distance function used in level set methods can readily be interpreted and represent complicated boundaries and their changes in time quite effectively. While there is substantial literature on the level set method in wildfire applications, these implementations have relied on a heavily-parametrized formula for a rate of spread. Also, they have less focused on uncertainty quantification for complex Spatio-temporal data. Here, we present a Bayesian Spatio-temporal dynamic model based on level sets, which can be utilized for predicting and forecasting the boundary of interest in the presence of uncertainty in data and lack of knowledge about the boundary velocity. We show the effectiveness of our method by applying it to the evolution of the firefront boundary of a classic megafire – the 2017-2018 Thomas fire in Southern California and the 2017 Haypress fire in California.
Publications: Yoo, M. and Wikle, C. K. (2024). A Bayesian Spatio-temporal Level Set Dynamic Model and Application to Fire Front Propagation, Annals of Applied Statistics, 18, 404-423, https://doi.org/10.1214/23-AOAS1794
As the patents of biological products expire, the generic of biological products, called biosimilar (or follow-on biologics), has received interest from the pharmaceutical industry and related areas. Since Biological products have different characteristics from chemical drugs, the existing method to test the similarity between the generic and reference drugs cannot be directly used for the biological product and biosimilar. Even though statistical tests to evaluate biosimilarity have been studied, the one for ordinal endpoints has not yet been proposed. In this study, we extend the existing method to ordinal endpoints.
Publications: Yoo, M. and Kim, D. (2019). Statistical tests for biosimilarity based on relative distance between follow-on biologics for ordinal endpoints, Communications for Statistical Applications and Methods, 27, 1-14, https://doi.org/10.29220/CSAM.2020.27.1.001