Ellyess Benmoufok

Research software engineer and applied scientist specialising in scientific Python, large-scale data pipelines, and simulation systems. PhD researcher at Imperial College London with strong experience in modular code design, reproducibility, and computational modelling. Proven ability to build maintainable open-source tools and integrate models into optimisation frameworks.

Education

PhD in Computational Science

Oct 2021 – Present

Imperial College London

  • Architected modular scientific Python frameworks for wind farm simulation.
  • Built scalable pipelines for large spatiotemporal datasets (ERA5).
  • Implemented clustering, bias correction, and validation algorithms.
  • Integrated simulation systems into PyPSA-based optimisation models.
  • Emphasised reproducibility, performance, and maintainability.

MSc in Applied Computational Science and Engineering

Oct 2019 – Oct 2020

Imperial College London

Distinction

  • Developed numerical and optimisation algorithms in Python and C++ for scientific computing applications.
  • Completed advanced coursework in dynamical systems, numerical methods, inversion, and parallel programming.
  • Co-authored research on generative adversarial networks (MOR-GANs) for multi-output regression in scientific data.
  • Built a foundation in high-performance and reproducible computational workflows.

BSc in Physics

Sep 2015 – Jun 2018

University of Surrey

First Class Honours

  • Built strong foundations in mathematical modelling, numerical analysis, and physical systems.
  • Applied computational techniques (including Fortran and Python) to scientific problem-solving.
  • Developed early interest in scientific computing and simulation-based research.

Experience

Graduate Teaching Assistant

Oct 2020 – Oct 2024

Imperial College London

  • Supported teaching of computational and numerical methods.
  • Helped students with Python, modelling, and scientific computing.

Data Science Intern

Jun 2021 – Sep 2021

Shell

  • Built machine learning models for energy analytics.
  • Processed large-scale geospatial and operational datasets.

App Developer

Dec 2020 – Mar 2021

Imperial College London

  • Built geospatial ML tools using Google Earth Engine.
  • Designed spatial analytics pipelines in JavaScript.

Publications

Geographic variability in reanalysis wind speed biases: A high-resolution bias correction approach for UK wind energy

Energy Conversion & Management · 2026

Wang, Y., Warder, S., Benmoufok, E.F., Wynn, A., Buxton, O.R.H., Staffell, I., & Piggott, M.D.

Energy Conversion and Management, 352, 121066.

Study further developing the multi-country high-resolution bias correction framework PyvWF.

View publication →

Improving wind power modelling through granular spatial and temporal bias correction of reanalysis data

Energy · 2024

Benmoufok, E.F., Warder, S., Zhu, E., Bhaskaran, B., Staffell, I., & Piggott, M.D.

Energy, 313, 133759.

Lead-author study developing a multi-country high-resolution bias correction framework for reanalysis-driven wind power modelling, PyVWF.

View publication →

Multi-Output Regression with Generative Adversarial Networks (MOR-GANs)

Applied Sciences · 2022

Phillips, T.R.F., Heaney, C.E.,Benmoufok, E., Li, Q., Hua, L., Porter, A.E., Chung, K.F., & Pain, C.C.

Applied Sciences, 12(18), 9209.

Co-authored study developing generative adversarial network (GAN) approaches for multi-output regression in scientific modelling applications.

View publication →

Technical Stack

Core Language: Python

Scientific Computing: NumPy · Pandas · Xarray · SciPy · Dask

Energy Systems & Optimisation: PyPSA · Atlite · Gurobi · Large-scale LP optimisation

Geospatial & Climate Data: GeoPandas · Shapely · Rasterio · ERA5 workflows

Workflow & Reproducibility: Snakemake · Conda · Git · GitHub

Visualisation & Reporting: Matplotlib · LaTeX

Beyond Research

Outside of computational energy modelling, I explore real-time audio-visual systems and creative coding. My work includes generative visual design using TouchDesigner and music production in Ableton Live, focusing on interactive and performance-driven workflows.

Selected Work

PyVWF: Python Virtual Wind Farm

Research Engineering

Methods for reducing systematic error in wind resource estimation pipelines, with emphasis on robust calibration and reproducible evaluation.

Open link ↗

Improving Wind Representation in PyPSA-Eur

Energy Systems

Scenario design and optimisation experiments for large-scale energy system planning using PyPSA-Eur and scientific Python tooling.

Open link ↗

OBK Gear Optimiser

Applied Optimisation

A practical optimisation interface translating formal models into clear decision support for iterative strategy tuning.

Open link ↗

Music Production and Sound Exploration

Creative Practice

Explorations in musical composition and sound design, blending technical precision with artistic expression.

Open link ↗