Academic Credentials
  • Ph.D., Civil and Environmental Engineering, University of California, Berkeley, 2025
  • M.S., Structural Engineering, Stanford University, 2021
  • B.S., Civil Engineering, University of California, Berkeley, 2019
Professional Honors
  • Bakar Innovation Fellowship
  • Stanford School of Engineering Graduate Fellowship
  • John A. Blume Earthquake Engineering Research Assistantship
  • Tau Beta Pi Engineering Society
Professional Affiliations
  • American Society of Civil Engineers (ASCE) Member
  • Utility Engineering & Surveying Institute (UESI) Member
  • American Geophysical Union

Dr. Saw is a systems engineer specializing in infrastructure monitoring, performance-based engineering, and data science. Her expertise includes distributed fiber optic sensing technologies — particularly distributed acoustic sensing (DAS) — for continuous, real-time monitoring of civil and energy infrastructure systems. She has led projects applying these tools to monitor hydraulic fracturing operations, roadway vibration and activity, and whale vocalizations in Monterey Bay. She has also contributed to efforts detecting leaks and pressure surges in water pipelines, as well as assessing the structural health of wind turbines. Dr. Saw brings experience in earthquake source characterization, ground motion modeling and selection, and fragility and vulnerability modeling, contributing to probabilistic risk analyses spanning individual components to system-wide vulnerabilities. Her work integrates field sensor deployments with machine learning and deep learning approaches for feature extraction and signal classification, emphasizing reproducible, adaptive data workflows to inform infrastructure design, performance assessment, and operational decision-making.

Dr. Saw's doctoral research at the University of California, Berkeley culminated in the dissertation "Listening with Light: Distributed Acoustic Sensing for Event Detection, Characterization, and Classification." This research investigated how decisions made throughout the DAS data science lifecycle — ranging from study conceptualization and sensor deployment to domain-specific data analysis and signal characterization — impact the effectiveness of DAS-based monitoring systems. Through case studies on whale vocalizations, roadway activity, and hydraulic fracturing, Dr. Saw addressed challenges such as environmental noise, infrastructure heterogeneity, and labeling uncertainty, offering grounded guidance for applying DAS in complex, real-world environments.

As a Data Science Fellow at UC Berkeley's D-Lab, Dr. Saw supported the campus-wide research community by teaching workshops on data manipulation, cleaning, visualization, machine learning, and deep learning. This experience reflects her commitment to making advanced data science methods accessible and actionable across disciplines. In addition to her D-Lab role during her graduate studies, she also taught undergraduate and graduate students in a course on infrastructure sensing and modeling.