Ph.D. Hydrologic Modeling and Scientific Machine Learning; Princeton University

Princeton, New Jersey, United States of America

Atmospheric Sciences (AS)
Hydrological Sciences (HS)
Natural Hazards (NH)

Full time

Student / Graduate / Internship

Master

21 December 2026

6 October 2026

I am seeking highly motivated Ph.D. students to join our research group in the Department of Civil and Environmental Engineering and the High Meadows Environmental Institute at Princeton University in Fall 2027. Research in the group focuses on advancing hydrologic prediction through improved process understanding, model development, and scientific machine learning approaches. Current opportunities center on the development of the Tiger-HLM modeling framework and span multiple areas of hydrology, Earth system science, and scientific machine learning.

Research in this area focuses on advancing large-scale hydrologic modeling through the development of improved process representations, parameterizations, and model formulations within Tiger-HLM. Research topics span both natural and human-influenced hydrologic systems. Of particular interest are applications in Arctic and cold-region environments, including permafrost, glaciers, seasonal snow, and ice processes, as well as human-water interactions such as irrigation and water withdrawals.

Additional interests include improving the representation of hydrologic processes and streamflow prediction in arid and water-limited regions. These diverse hydrologic settings provide opportunities to test and improve process representations and model formulations, while the broader goal is to advance hydrologic prediction across diverse hydroclimatic regimes and environmental conditions.

Research in this area focuses on the development and use of machine learning methods that are informed by physical principles and process-based models to improve hydrologic prediction, accelerate computation, and support process discovery. Topics include machine-learning emulators for Tiger-HLM (e.g., neural operators and transformers) and interpretable machine learning, including symbolic regression, for the discovery of new parameterizations, process representations, and model formulations that can be implemented and tested in Tiger-HLM.

The goal is to develop computationally efficient, scientifically interpretable, and physically consistent tools that advance hydrologic prediction and model development.

Candidates must have a degree in engineering, earth or environmental science, applied mathematics, computer science, physics, statistics, or a related discipline. Strong quantitative and computational skills are expected. Experience with hydrologic modeling, machine learning, scientific programming, numerical methods, and/or analysis of large geophysical datasets is particularly desirable.

Princeton University is an equal opportunity employer/affirmative action employer and all qualified applicants will receive consideration for employment without regard to age, race, color, religion, sex, sexual orientation, gender identity or expression, national origin, disability status, protected veteran status, or any other characteristic protected by law.