The key topics of my recent work include Uncertainty quantification for computer model experiments using deep learning and Gaussian processes. Spatial data analysis for for various fields of application including atmospheric science, hydrology, and genetics.

Synthetic data generation with incomplete survey data under informative sampling

Inverse Computer Model Calibration Approach with Conditional Variational Auto-encoder

Stick-Breaking Mixture Normalizing Flows with Component-Wise Tail Adaptation for Variational Inference

spaDesign: A Statistical Framework to Improve the Design of Sequencing-based Spatial Transcriptomics Experiments

Long-Term Historical Slowdown in Atlantic Meridional Overturning Circulation

Various-Neighbor Neural Network Emulator for Computer Models with Large Spatial Output

A Spatio-Temporal Dirichlet Process Mixture Model on Linear Networks for Crime Data

Computer Model Emulation and Calibration for Discrete Data

Protective effectiveness of SARS-CoV-2 infection risk among hybrid, vaccine, and infection-induced immunity against the omicron variant, K-SEROSMART

A History-Dependent Approach for Accurate Initial Condition Estimation in Epidemic Models

Interpretable Machine Learning and Criminological Theories: Global Evidence on Bullying Perpetration and Victimization (2001-2014)

Physics-driven dynamic interpolation with application to pollution satellite images

The joint local dependence Cholesky prior for bandwidth selection across multiple groups

Dynamic Interactions of COVID-19 Incidences, Mobility, and Social Distancing Policies in Seoul: A VAR Model Approach

Fast Computer Model Calibration using Annealed and Transformed Variational Inference

Bayesian Model Calibration and Sensitivity Analysis for Oscillating Biological Experiments

Assessing Predictability of Environmental Time Series with Statistical and Machine Learning Models

A Personalized Dose-Finding Algorithm Based on Adaptive Gaussian Process Regression

A Bayesian Convolutional Neural Network-based Generalized Linear Model

scLENS: Data-driven signal detection for unbiased scRNA-seq data analysis

Density Physics-Informed Neural Network reveals sources of cell heterogeneity in signal transduction

Nonparametric Predictive Model for Sparse and Irregular Longitudinal Data

A Spatio-Temporal Dirichlet Process Mixture Model for Coronavirus Disease-19

Imputing Missing Sleep Data from Wearables with Neural Networks in Real-World Settings

A Bayesian Multivariate Mixture Model for Spatial Transcriptomics Data

Remote Sensing-Enabled Machine Learning for River Water Quality Modeling Under Multidimensional Uncertainty

graph-GPA 2.0: improving multi-disease genetic analysis with integration of functional annotation data

Analysis of East Asia Wind Vectors Using Space–Time Cross-Covariance Models

Statistical Power Analysis for Designing Bulk, Single-Cell, and Spatial Transcriptomics Experiments: Review, Tutorial, and Perspectives

An illustration of model agnostic explainability methods applied to environmental data

Ice model calibration using semi-continuous spatial data

Computer Model Calibration with Time Series Data using Deep Learning and Quantile Regression

An interaction Neyman-Scott point process model for Coronavirus Disease-19

Enabling Dynamic Emulation of High-Dimensional Model Outputs: Demonstration for Mexico City Groundwater Management

Fast and accurate learned multiresolution dynamical downscaling for precipitation

Note: A new approach to the modeling of spatially dependent and heterogeneous geographical regions

High-fidelity hurricane surge forecasting using emulation and sequential experiments

Diagnosing added value of convection-permitting regional models using precipitation event identification and tracking

A regularized spatial market segmentation method with Dirichlet process Gaussian mixture prior

Computer model calibration based on image warping metrics: an application for sea ice deformation

A novel method to test non-exclusive hypotheses applied to Arctic ice projections from dependent models

Bayesian pollution source identification via an inverse physics model

Stilt: easy emulation of AR(1) computer model output in multidimensional parameter space

Monthly Rainfall-Runoff Modeling at Watershed Scale: A Comparative Study of Data-Driven and Theory-Driven Approaches

Statistics and the Future of the Antarctic Ice Sheet

Changes in spatio-temporal precipitation patterns in changing climate conditions

Improving ice sheet model calibration using paleoclimate and modern data

An option pricing model using high frequency data

Large ensemble modeling of last deglacial retreat of the West Antarctic Ice Sheet: Comparison of simple and advanced statistical techniques

Calibrating an ice sheet model using high-dimensional binary spatial data

A composite likelihood approach to computer model calibration with high-dimensional spatial data

Fast dimension-reduced climate model calibration and the effect of data aggregation

Probabilistic calibration of a Greenland Ice Sheet model using spatially-resolved synthetic observations: toward projections of ice mass loss with uncertainties

What is the effect of unresolved internal climate variability on climate sensitivity estimates?

A history-dependent approach for accurate initial condition estimation in epidemic models

Dynamic interactions of COVID-19 incidences, mobility, and social distancing policies in seoul: A VAR model approach

scLENS: data-driven signal detection for unbiased scRNA-seq data analysis

Stilt: Easy Emulation of Time Series AR(1) Computer Model Output in Multidimensional Parameter Space

A 3-D hybrid ice-sheet model is applied to the last deglacial retreat of the West Antarctic Ice Sheet over the last  ∼  20 000 yr. A large ensemble of 625 model runs is used to calibrate the model to modern and geologic data, including reconstructed grounding lines, relative sea-level records, elevation–age data and uplift rates, with an aggregate score computed for each run that measures overall model–data misfit. Two types of statistical methods are used to analyze the large-ensemble results: simple averaging weighted by the aggregate score, and more advanced Bayesian techniques involving Gaussian process-based emulation and calibration, and Markov chain Monte Carlo. The analyses provide sea-level-rise envelopes with well-defined parametric uncertainty bounds, but the simple averaging method only provides robust results with full-factorial parameter sampling in the large ensemble. Results for best-fit parameter ranges and envelopes of equivalent sea-level rise with the simple averaging method agree well with the more advanced techniques. Best-fit parameter ranges confirm earlier values expected from prior model tuning, including large basal sliding coefficients on modern ocean beds.

Large ensemble modeling of the last deglacial retreat of the West Antarctic Ice Sheet: comparison of simple and advanced statistical techniques

A composite likelihood approach to computer model calibration using high-dimensional spatial data

How will the climate system respond to anthropogenic forcings? One approach to this question relies on climate model projections. Current climate projections are considerably uncertain. Characterizing and, if possible, reducing this uncertainty is an area of ongoing research. We consider the problem of making projections of the North Atlantic meridional overturning circulation (AMOC). Uncertainties about climate model parameters play a key role in uncertainties in AMOC projections. When the observational data and the climate model output are high-dimensional spatial data sets, the data are typically aggregated due to computational constraints. The effects of aggregation are unclear because statistically rigorous approaches for model parameter inference have been infeasible for high-resolution data. Here we develop a flexible and computationally efficient approach using principal components and basis expansions to study the effect of spatial data aggregation on parametric and projection uncertainties. Our Bayesian reduced-dimensional calibration approach allows us to study the effect of complicated error structures and data-model discrepancies on our ability to learn about climate model parameters from high-dimensional data. Considering high-dimensional spatial observations reduces the effect of deep uncertainty associated with prior specifications for the data-model discrepancy. Also, using the unaggregated data results in sharper projections based on our climate model. Our computationally efficient approach may be widely applicable to a variety of high-dimensional computer model calibration problems.

Probabilistic calibration of a Greenland Ice Sheet model using spatially resolved synthetic observations: toward projections of ice mass loss with uncertainties

Won Chang

Professor

Won Chang's Research Group

교수님 소개

장원

연구실 소개

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

Synthetic data generation with incomplete survey data under informative sampling

Inverse Computer Model Calibration Approach with Conditional Variational Auto-encoder

Stick-Breaking Mixture Normalizing Flows with Component-Wise Tail Adaptation for Variational Inference

연구실 보유 특허

대학별 입시끈

우리 연구실 모집

교수님 소개

장원

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

Synthetic data generation with incomplete survey data under informative sampling

Inverse Computer Model Calibration Approach with Conditional Variational Auto-encoder

Stick-Breaking Mixture Normalizing Flows with Component-Wise Tail Adaptation for Variational Inference

연구실 보유 특허

최근 3년간 연구실적 높은 연구실

대학별 입시끈

우리 연구실 모집