What to expect
This thesis explores foundation models for sky imaging that learn shared, universal representations of atmospheric phenomena from large-scale data, rather than building separate models for individual tasks such as cloud classification or irradiance forecasting. It investigates approaches including multimodal and multi-task learning, spatiotemporal modeling, and physics-informed representations to capture cloud dynamics and physical consistency. The goal is to obtain robust, reusable atmospheric features that support physically consistent generative forecasting across diverse applications.
You will be part of a diverse and motivated team working on energy-transition topics and contributing to climate protection. Close collaboration with supervisors and colleagues will support you in exchanging ideas and solving challenges. You will gain hands-on experience in machine learning, software development, automated testing, version control and modern image-processing technologies. A particular highlight of the project is the opportunity to work in Almería, Spain, one of the sunniest locations in Europe.
Your tasks
* review existing approaches on vision foundation models
* prepare multi-modal datasets, aligning modalities and curating task-specific targets
* design and implement model architectures with shared latent space
* develop and implement self-supervised cross-modal and multi-task training strategies that incorporate physical constraints and temporal consistency
* evaluate representations across multiple downstream tasks and forecasting scenarios and compare them to existing approaches
* document methodology and results in a well-structured Master's thesis
Your profile
* You have a strong academic record in a master's program in computer science, physics, mathematics engineering or a related field.
* experience in Python and basic knowledge about machine learning
* the ability to work independently and collaborate in an international team
* prior experience in data analysis, computer vision and git versioning systems
* confident in speaking and writing English
If this sounds like an exciting opportunity for you, please apply by sending us a cover letter and your CV!