EMUSE: Evolutionary Map of the Universe Search Engine

TL;DR

EMUSE is a multimodal search engine for radio sources in large astronomical datasets, utilizing fine-tuned foundation models to improve classification and retrieval of diverse radio galaxy morphologies.

Contribution

This work introduces EMUSE, a novel search engine that fine-tunes foundation models for multimodal radio source classification and retrieval in large-scale astronomical surveys.

Findings

Effective retrieval of radio sources with distinct morphological features

Demonstrated the model's ability to recognize various radio galaxy classes

Identified challenges in detecting rare or unseen sources

Abstract

We present EMUSE (Evolutionary Map of the Universe Search Engine), a tool designed for searching specific radio sources within the extensive datasets of the EMU (Evolutionary Map of the Universe) survey, with potential applications to other Big Data challenges in astronomy. Built on a multimodal approach to radio source classification and retrieval, EMUSE fine-tunes the OpenCLIP model on curated radio galaxy datasets. Leveraging the power of foundation models, our work integrates visual and textual embeddings to enable efficient and flexible searches within large radio astronomical datasets. We fine-tune OpenCLIP using a dataset of 2,900 radio galaxies, encompassing various morphological classes, including FR-I, FR-II, FR-x, R-type, and other rare and peculiar sources. The model is optimized using adapter-based fine-tuning, ensuring computational efficiency while capturing the unique characteristics of radio sources. The fine-tuned model is then deployed in EMUSE, allowing for seamless image- and text-based queries over the EMU survey dataset. Our results demonstrate the model's effectiveness in retrieving and classifying radio sources, particularly in recognizing distinct morphological features. However, challenges remain in identifying rare or previously unseen radio sources, highlighting the need for expanded datasets and continuous refinement. This study showcases the potential of multimodal machine learning in radio astronomy, paving the way for more scalable and accurate search tools in the field. The search engine is accessible at https://askap-emuse.streamlit.app/ and can be used locally by cloning the repository at https://github.com/Nikhel1/EMUSE.