Scientific machine learning (SciML) is an emerging discipline within data science that seeks to address domain-specic data challenges and extract insights from scientic data sets through innovative methodological solutions. SciML draws on tools from both machine learning and scientific computing to develop new methods for scalable, domain-aware, robust, reliable, and interpretable learning and data analysis, and will be critical in driving the next wave of data-driven scientific discovery in the physical and engineering sciences.

Like scientific computing, SciML is multidisciplinary and leverages expertise from applied and computational mathematics, computer science, and physical sciences.

Current research in the SciML group includes:

• Interpretable ML and explainable AI (XAI) for geophysical applications.
• Uncertainty quantification in ML-based climate emulators.
• Adaptive sampling for environmental monitoring (with URI).

Invited Talks (selected)

National Academies Committee on Solid Earth Geophysics Fall 2023 Meeting, hybrid (2023)

Women in Data Science: Data Science in Crisis Management. American University of Beirut, virtual (2023)

Symposium on Artificial Intelligence and Earthquake Engineering, EERI San Diego Chapter, hybrid (2022)

Seismological Society of America Annual Meeting: Machine Learning Plenary Panel, virtual (2021)

IRIS Distributed Acoustic Sensing Virtual Workshop and Tutorial, virtual (2020)

Congressional briefing on Machine Learning in Seismology, hosted by the Seismological Society of America, Washington D.C. (2019).

National Academies Committee on Seismology and Geodynamics Fall Meeting, Washington D.C. (2019)

Women in Data Science @ Stanford Earth Workshop, Stanford, CA (2019)

Machine Learning in Solid Earth Geoscience Conference, Santa Fe, NM (2019)

NeurIPS Workshop on Machine Learning for Geophysical and Geochemical Signals. Montreal, Canada (2018)

Seminars (selected)

2023: Sandia National Laboratory, Arizona State University

2022: University of Montana, University of Oslo

2021: MIT, Cornell University, University of Utah

2020: Michigan State University, University of Texas at Austin, Colorado School of Mines, University of British Columbia, UC Santa Barbara, Boston University, University of Delaware

pre-2020 (selected): Princeton University, UW-Seattle, Columbia University, Microsoft Research New England, Pontificia Universidad Católica de Chile, University of Tokyo, US Geological Survey, Sandia National Laboratory, Lawrence Livermore National Laboratory

Harvard Data Science Initiative Postdoctoral Fellowship, Harvard University (2018–20)

Student Leadership Award, ICME, Stanford University (2018)

Student Author Award, Geophysical Journal International (2018)

Student Presentation Award, Seismological Society of America (2016, 2017)

Senior Teaching Fellow, ICME, Stanford University (2016)

Short Course Instructor Award, ICME, Stanford University (2015)

Outstanding Student Paper Award, American Geophysical Union (2015)

Stanford Graduate Fellowship in Science and Engineering, Stanford University (2011–15)

Core Faculty, Brown Data Science Institute (DSI)

Faculty Affiliate, Institute at Brown for Environment and Society (IBES)

Scientific Artificial Intelligence Center (SciAI Center)

Current course

• EEPS 1720 / DATA 1720 - Tackling Climate Change with Machine Learning (Spring 2024 website)

Past courses

• EEPS-DATA 1340 (previously EEPS 1960D) - Machine Learning for the Earth and Environment (Spring 2023 website)
• DATA 1010 - Probability, Statistics and Machine Learning (Fall 2021 website)