Vittoria De Pellegrini πŸŽ“

Vittoria De Pellegrini

(she/her)

PhD Student, Earth Science & Engineering

King Abdullah University of Science and Technology (KAUST)

DeepWave Research Consortium

Professional Summary

Italian-Brazilian PhD student at KAUST and Doctoral Researcher with the DeepWave Consortium, building machine- and deep-learning workflows for subsurface reservoir characterization. I focus on deep generative AI, especially video diffusion models, to model multi-phase subsurface fluid-flow dynamics. My workflows rely on CUDA-aware, reproducible CPU/GPU pipelines running at scale on the KAUST IBEX Supercomputing cluster.

Education

Doctor of Philosophy in Earth Science and Engineering

King Abdullah University of Science and Technology (KAUST)

Master of Science in Petroleum Engineering

Politecnico di Torino

Bachelor of Science in Civil Engineering

Universita degli Studi di Padova

Interests

Deep Learning Deep Generative Modeling Generative AI Video Diffusion Models Petrophysics & Well-Logging GCS
Conference Publications

Peer-reviewed submissions where I present diffusion modeling for COβ‚‚ workflows.

Paper Publications

In-depth technical papers and proceedings that capture the experiments behind DeepWave.

Thesis

My Master’s thesis exploring supervised machine learning for well-log prediction.

Experience

  1. Doctoral Researcher

    DeepWave Research Consortium, KAUST
    Build deep generative models for multi-phase subsurface fluid-flow dynamics. Design latent conditional diffusion and progressive video diffusion models tailored to CO2 sequestration simulations. Run large-scale CUDA-aware training and inference experiments on the KAUST IBEX supercomputing cluster.
  2. Graduate Researcher

    Politecnico di Torino
    Developed supervised machine learning workflows for conventional and advanced well-log prediction. Applied the models to PETROBRAS datasets from the Sao Francisco and Santos basins in Brazil.
  3. Geophysics Intern

    Aramco Overseas Company B.V.
    Built a 3D multi-physics synthetic model for a Saudi geothermal site and generated surface wave dispersion curves. Produced synthetic seismograms to support seismic imaging workflows. Recognized with the Aramco Certificate in Seismic Modeling (see download below).

Education

  1. Doctor of Philosophy in Earth Science and Engineering

    King Abdullah University of Science and Technology (KAUST)
    GPA 3.89 (expected 2027)
  2. Master of Science in Petroleum Engineering

    Politecnico di Torino
    Grade 108/110; thesis on supervised machine learning models for well-log prediction applied to Brazilian basins.
  3. Bachelor of Science in Civil Engineering

    Universita degli Studi di Padova
    Grade 110/110
Projects

Featured work and collaborations.

Pandas featured image

Pandas

Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures.

Read more
PyTorch featured image

PyTorch

PyTorch is a Python package that provides tensor computation (like NumPy) with strong GPU acceleration.

Read more
scikit-learn featured image

scikit-learn

scikit-learn is a Python module for machine learning built on top of SciPy and is distributed under the 3-Clause BSD license.

Read more