Accurate climate projections at high spatial resolution are essential for assessing the potential of solar energy systems. Global Climate Models (GCMs), while robust at large scales, lack the granularity needed for local energy planning. Downscaling techniques bridge this gap by refining coarse climate outputs to finer resolutions.

This internship will explore and compare two distinct approaches of downscaling techniques in a perfect model approach framework:

• CDFt (Cumulative Distribution Function transform): A statistical method that adjusts climate model outputs based on observed distributions.
• Vision Transformer (ViT): A deep learning architecture based on transformer.

This internship is in collaboration with The « Centre Européen de Recherche et de Formation Avancée en Calcul Scientifique » (Cerfacs).

As a Comparative study of statistical and AI-based downscaling methods for climate projections in solar energy M/F trainee, your missions will be :

• Implement and evaluate CDFt and a Vision Transformer-based model for downscaling temperature and solar radiation projections.
• Apply both methods to selected regions with high solar energy potential.
• Assess performance based on metrics such as bias, RMSE, correlation, and energy-relevant indicators (e.g., solar irradiance variability).
• Explore the interpretability and computational efficiency of each method.

You will evolve within a team of experienced professionals and with a tutor-coach, the reference for your future profession. Individualized support will help you develop your autonomy and lead you to your diploma!

Are you currently enrolled in an engineering school or a Master’s program and looking for a 6-month end-of-studies internship starting in February 2026?

Do you have knowledge in climate science, machine learning, or applied mathematics?
Are you proficient in Python and familiar with libraries such as TensorFlow or PyTorch?
Do you know how to work with climate data formats like NetCDF?
Experience with statistical downscaling techniques and/or deep learning architectures is a strong asset.
Are you passionate about renewable energy and climate impact assessment?
Professional proficiency in English is essential for this position. Strong writing skills will be a plus.

So don't wait any longer, apply to join our team!

This offer is for a full-time, contractual internship; alternating internships are not possible.

To apply, please attach a CV + covering letter (your internship dates must be indicated).

Cette offre concerne un stage conventionné à temp plein, les stages alternés ne sont possibles.
 Pour postuler, merci de joindre un CV + lettre de motivation (vos dates de stage doivent être indiquées).