Uploaded November 2025 | Updated November 2026, 1 day ago
Michael Shields is a professor in the Department of Civil and Systems Engineering and holds a secondary appointment in the Department of Materials Science and Engineering. He is also a fellow in the Hopkins Extreme Materials Institute and a member of the Data Science and AI Institute. He is currently the director of the Center on High-Throughput Materials Discovery for Extremes and a member of the leadership team for the Center on Artificial Intelligence for Materials in Extreme Environments. He also serves as the current chair of the Whiting School of Engineering Faculty Senate and is an Ivy+ Provost Leadership Fellow.
Description of "Navigating Uncertainty: Building Confidence in Science in the Age of AI":
As human beings, we are constantly dealing with uncertainty in our everyday lives. Each of us develops our own mechanisms to cope with it—some healthy and others less so. In science and engineering, we go to great lengths to be certain—to perform precise, detailed, and controlled analyses that lead to deterministic predictions. But, even in science and engineering, uncertainties cannot be avoided and can have profound impacts on the performance of engineering systems. These uncertainties are especially pervasive as artificial intelligence and machine learning are increasingly integrated into physics-based modeling, analysis, and design. This talk will introduce essential principles of uncertainty quantification, which underpin the “coping mechanisms” for uncertainty in engineering. It will then attempt to evaluate these coping mechanisms—identifying areas where we are effective in addressing uncertainty, pointing to areas where we have been less successful, and proposing solutions to improve our treatment of uncertainty and ultimately improving confidence in the performance of engineering systems. Applications will be shown for engineering systems, ranging from materials performance under extreme conditions to large-scale structural failures such as the Key Bridge—with a particular emphasis on the use of AI, ML, and data-driven methods to quantify uncertainty and the ability to quantify uncertainty in these AI/ML models themselves.
Michael Shields is a professor in the Department of Civil and Systems Engineering and holds a secondary appointment in the Department of Materials Science and Engineering. He is also a fellow in the Hopkins Extreme Materials Institute and a member of the Data Science and AI Institute. He is currently the director of the Center on High-Throughput Materials Discovery for Extremes and a member of the leadership team for the Center on Artificial Intelligence for Materials in Extreme Environments. He also serves as the current chair of the Whiting School of Engineering Faculty Senate and is an Ivy+ Provost Leadership Fellow.
Description of "Navigating Uncertainty: Building Confidence in Science in the Age of AI":
As human beings, we are constantly dealing with uncertainty in our everyday lives. Each of us develops our own mechanisms to cope with it—some healthy and others less so. In science and engineering, we go to great lengths to be certain—to perform precise, detailed, and controlled analyses that lead to deterministic predictions. But, even in science and engineering, uncertainties cannot be avoided and can have profound impacts on the performance of engineering systems. These uncertainties are especially pervasive as artificial intelligence and machine learning are increasingly integrated into physics-based modeling, analysis, and design. This talk will introduce essential principles of uncertainty quantification, which underpin the “coping mechanisms” for uncertainty in engineering. It will then attempt to evaluate these coping mechanisms—identifying areas where we are effective in addressing uncertainty, pointing to areas where we have been less successful, and proposing solutions to improve our treatment of uncertainty and ultimately improving confidence in the performance of engineering systems. Applications will be shown for engineering systems, ranging from materials performance under extreme conditions to large-scale structural failures such as the Key Bridge—with a particular emphasis on the use of AI, ML, and data-driven methods to quantify uncertainty and the ability to quantify uncertainty in these AI/ML models themselves.

