Robin Thibaut

Computational Geoscientist @ Zanskar Geothermal & Minerals

robin.jpeg

Computational geoscientist specializing in Bayesian uncertainty quantification for geothermal exploration. Develop Python-first workflows that integrate thermal simulation, geophysics, and well data to optimize drilling targets and quantify resource uncertainty.

Research Focus: Experimental design · Physics-informed ML · Subsurface characterization


Core Expertise

Programming & ML:

  • Python (NumPy, Pandas, scikit-learn, PyTorch, TensorFlow)
  • Uncertainty Quantification (Bayesian, BEL)
  • Experimental Design & Physics-informed ML
  • Time-series & Spatial Modeling

Geoscience Modeling:

  • Finite-element thermal simulation
  • MODFLOW, MT3DMS, MODPATH, ModelMuse
  • Geophysical Data Integration (CRTOMO, RES2DINV, ERT/IP)
  • SGeMs, Hydrologic & Groundwater Modeling

Data & Engineering:

  • SQL, Snowflake, Git, ETL/Data Engineering
  • Cloud (Google Cloud Platform), CI/CD
  • Scientific Visualization
  • Linux/macOS/Windows

Highlighted Publications


Open Source Software & Resources

Software Packages:

Datasets:



GitHub Stats

Robin's GitHub stats Top Languages

news

latest posts

selected publications

  1. Efficiency and heat transport processes of low-temperature aquifer thermal energy storage systems: new insights from global sensitivity analyses
    Luka Tas, Niels Hartog, Martin Bloemendal, and 5 more authors
    Geothermal Energy, Jan 2025
    Open access, published 07 January 2025
  2. sim_combined.png
    Comparing Well and Geophysical Data for Temperature Monitoring Within a Bayesian Experimental Design Framework
    \textbfRobin Thibaut, Nicolas Compaire, Nolwenn Lesparre, and 3 more authors
    Water Resources Research, Nov 2022
  3. whpa.png
    A new framework for experimental design using Bayesian Evidential Learning: The case of wellhead protection area
    \textbfRobin Thibaut, Eric Laloy, and Thomas Hermans
    Journal of Hydrology, Dec 2021