Teaching

Teaching is one of the most direct ways I can contribute to shaping the next generation of Earth scientists and data practitioners. My courses span a broad audience — from hundreds of undergraduates encountering planetary science for the first time, to small graduate seminars where students build fluency in numerical methods or modern AI workflows. I aim to make quantitative thinking accessible and to model the kind of intellectual curiosity I hope students carry with them long after the semester ends.

Current Courses

ES 2205  ·  Spring semesters
The Planets
General education natural science · 100–290 students

A general education course introducing the solar system to a broad undergraduate audience — most students are not science majors. Topics include orbital mechanics, the formation of the solar system, comparative planetary geology and atmospheres, the search for life, and humanity's robotic and crewed exploration of the solar system. I emphasize quantitative reasoning throughout, connecting physical principles to what we can observe and measure. The course consistently attracts 200–290 students per semester, and I work hard to keep it engaging at that scale.

Student evaluations: ~4.5–4.6 / 5.0
ES 5751  ·  Fall semesters (when offered)
Quantitative Reservoir Modeling
Graduate seminar · 10–15 students

A graduate seminar covering the physical and mathematical foundations of fluid flow through porous media, with applications to petroleum engineering and subsurface carbon storage. Topics include Darcy's law and its extensions, multiphase flow equations, rock and fluid properties, thermodynamic phase behavior, and numerical methods for reservoir simulation. Students implement core algorithms in MATLAB throughout the semester and complete a final project involving a custom flow simulation. This course is where I connect my research most directly to the classroom — several former students have gone on to work in reservoir simulation and computational hydrology.

Student evaluations: ~4.6–4.8 / 5.0
ES 5757  ·  Fall semesters
Artificial Intelligence in Earth Sciences
Graduate course · 11–20 students · first offered Fall 2022

I developed this course from scratch and first taught it in Fall 2022 as ES 5194. Redesigned for Fall 2025 following inputs from the NSF Cyber2A pedagogy workshop, the course now covers the full arc of modern machine learning in Earth and environmental science: from regression and classical ML to convolutional neural networks, vision transformers, and physics-informed neural networks. Each week pairs lecture with a hands-on Python lab using real Earth science datasets — satellite imagery, geophysical logs, and climate data. Students complete a final independent AI project and present their results to the group. The course has become a foundation for graduate students across Earth Sciences, Geography, and related programs who want to incorporate AI into their research.

Student evaluations: 4.8–5.0 / 5.0

Mentoring

Current PhD Students

  • 2020 – present
    Hsiao Jou (Amy) Hsu Deriving shallow-water bathymetry through AI-powered remote sensing (ICESat-2 + Sentinel-2 + PINNs)
  • 2026 – present
    Samir Pahari Research topic to be determined

Current MS Student

  • 2019 – present
    Satyaki Roy Chowdhury AI for coastal bathymetry; first author on IEEE/CVF WACV 2025 paper on Sentinel-2 bathymetry

PhD Graduates

  • 2020 – 2023
    Ziwei Li Deep learning from multispectral satellite imagery
  • 2017 – 2020
    William Eymold Evaluation of subsurface fluid migration using noble gas tracers and numerical modeling  ·  now: Postdoctoral Researcher, Sandia National Laboratory
  • 2016 – 2020
    Fengyang Xiong Desorption and adsorption of subsurface shale gas  ·  now: Postdoctoral Researcher, University of Oklahoma
  • 2014 – 2018
    Mohammad Amin Amooie Fluid mixing in multiphase and hydrodynamically unstable porous-media flows  ·  now: Senior Research Scientist, Center of Innovation for Flow through Porous Media, University of Wyoming

Postdoctoral Scholars

  • 2024 – 2025
    Petr Gális PhD, Czech Academy of Sciences, Prague  ·  natural hydrogen reservoir simulation
  • 2023 – 2024
    Sam Herreid PhD in Glaciology, Northumbria University, UK  ·  AI mapping of fairy circles for hydrogen prospecting
  • 2022 – 2024
    Saurabh Kaushik PhD, Academy of Scientific and Innovative Research (CSIO), Chandigarh, India  ·  satellite remote sensing and glaciology
  • 2021 – 2023
    Wei Ji Leong PhD, Victoria University of Wellington, New Zealand  ·  deep learning for water detection
  • 2019 – 2021
    Mengnan Li PhD, North Carolina State University  ·  reactive transport modeling  ·  now: Computational Scientist, Idaho National Laboratory
  • 2015 – 2017
    Mohamad Reza Soltanian PhD, Wright State University  ·  CO₂ sequestration and tracer transport  ·  now: Associate Professor of Geology, University of Cincinnati