Michael Shields

About

Michael Shields is a professor in the Department of Civil and Systems Engineering at Johns Hopkins University, with a secondary appointment in the Department of Materials Science and Engineering. He is a fellow in the Hopkins Extreme Materials Institute and a member of the Data Science and AI Institute. Shields serves as the director of the Center on High-Throughput Materials Discovery for Extremes and is part of the leadership team for the Center on Artificial Intelligence for Materials in Extreme Environments. His research focuses on uncertainty quantification for problems in computational mechanics and computational materials science, utilizing machine learning and stochastic methods to understand the effects of uncertainties and random variations on the performance of materials and structures. His work aims to improve the reliability of structures and materials during extreme events such as fires, earthquakes, high winds, shocks, blasts, and impacts, especially where computational efficiency is critical and system behavior is highly unpredictable. Shields’ group, known as the Shields Uncertainty Research Group (SURG), develops open-source software like UQPy to model uncertainty in physical and mathematical systems, employing approaches such as polynomial chaos expansions, Gaussian process regression, neural networks, and Monte Carlo methods. His research has been funded by multiple agencies including the NSF, Office of Naval Research, Army Research Laboratory, and…

Research topics

• Computer Science
• Machine Learning
• Artificial Intelligence
• Mathematics
• Algorithm
• Data Mining
• Physics
• Statistics
• Computational science
• Programming language

Selected publications

• Bayesian neural networks for uncertainty quantification in data-driven materials modeling

  Computer Methods in Applied Mechanics and Engineering · 2021 · 170 citations

  DOI

• Deep transfer operator learning for partial differential equations under conditional shift

  Nature Machine Intelligence · 2022 · 112 citations

  Transfer learning enables the transfer of knowledge gained while learning to perform one task (source) to a related but different task (target), hence addressing the expense of data acquisition and labelling, potential computational power limitations and dataset distribution mismatches. We propose a new transfer learning framework for task-specific learning (functional regression in partial differential equations) under conditional shift based on the deep operator network (DeepONet). Task-specif…

  DOI

• UQpy: A general purpose Python package and development environment for uncertainty quantification

  Journal of Computational Science · 2020 · 88 citations

  Senior authorCorresponding
  DOI

• Data-driven surrogates for high dimensional models using Gaussian process regression on the Grassmann manifold

  Computer Methods in Applied Mechanics and Engineering · 2020 · 55 citations

  Senior authorCorresponding
  DOI

• MANIFOLD LEARNING-BASED POLYNOMIAL CHAOS EXPANSIONS FOR HIGH-DIMENSIONAL SURROGATE MODELS

  International Journal for Uncertainty Quantification · 2022 · 39 citations

  Senior authorCorresponding

  In this work we introduce a manifold learning-based method for uncertainty quantification (UQ) in systems describing complex spatiotemporal processes. Our first objective is to identify the embedding of a set of high-dimensional data representing quantities of interest of the computational or analytical model. For this purpose, we employ Grassmannian diffusion maps, a two-step nonlinear dimension reduction technique which allows us to reduce the dimensionality of the data and identify meaningful…

  DOI

Recent grants

• Collaborative Research: Wind Tunnel Modeling of Higher-Order Turbulence and its Effects on Structural Loads and Response

  NSF · $319k · 2019–2024

• CAREER: Higher-Order Methods for Nonlinear Stochastic Structural Dynamics

  NSF · $500k · 2017–2023

• GOALI: Improving the Reliability of Aluminum Structures During Fire Through Computational Modeling

  NSF · $359k · 2014–2018

Frequent coauthors

• Joan L. Luft

  Michigan State University

  26 shared

• Dimitris G. Giovanis

  Johns Hopkins University

  23 shared

• Somayajulu L. N. Dhulipala

  20 shared

• Promit Chakroborty

  16 shared

• Katiana Kontolati

  Johns Hopkins University

  16 shared

• Yifeng Che

  13 shared

• George Deodatis

  12 shared

• Lori Graham‐Brady

  11 shared

Awards & honors

• 2025 Early Achievement Research Award from the International…
• Department of Energy Early Career Award
• NSF CAREER Award
• ONR Young Investigator Award
• IASSAR Early Achievement Award

Similar researchers at Johns Hopkins University

• Somnath Ghoshh-62
• James Guesth-37
• Jochen Muellerh-32