Euclid Computer Vision
Gravitational Lens Data Science
The Euclid space telescope from the European Space Agency (ESA) observes large areas of the sky with the goal of mapping the structure of the Universe, such as dark matter and dark energy. Within this data, strong gravitational lenses appear as distortions in galaxy images. Detecting and interpreting these systems is difficult, not only because they are rare, but also because their appearance depends strongly on how the data is processed and represented.
Euclid Computer Vision focuses on understanding these effects. The project explores how astronomical image data, color construction, scaling choices, and deep learning techniques influence both visual inspection and computational analysis. By combining data science, machine learning, image processing, and computer vision techniques, the project studies how different representations of Euclid data change what information becomes visible and usable.
Dive deeper
This semester, the project focused on turning earlier research and experiments into a more integrated Euclid Computer Vision software setup. The work included improving the image processing workflow, preparing Euclid-style data for analysis, experimenting with visual representations, and connecting machine learning classification to a backend pipeline.
The software combines preprocessing, model inference, and backend communication so that gravitational lens candidates can be analysed in a more structured way. Different parts of the project contributed to this, including data preparation, classification experiments, supervised model development, unsupervised exploration, generated data, transformation techniques, and backend integration.
The current system should be seen as a proof of concept that shows how Euclid image data can move through a technical workflow: from input data, to preprocessing and visualisation, to classification and software integration. Future work can expand this by adding more lens classes, improving the dataset, strengthening model reliability, and connecting the pipeline further to the full frontend or analysis environment.