AI Insight
Researchers developed a new method for discovering strong gravitational lenses using active learning and self-supervised machine learning, eliminating the need for simulated training data. Applied to 3.7 million galaxies from the Kilo-Degree Survey, the approach identified 140 high-quality lens candidates through iterative expert inspection of only 3,000 objects, with 81 being newly discovered systems. The method recovered approximately 22% of previously known lenses while finding a diverse population of candidates that complement traditional supervised learning approaches.
Why it matters
This technique could significantly improve the efficiency of finding rare gravitational lenses in upcoming large-scale astronomical surveys like Euclid, Roman, and the Rubin Observatory, reducing dependence on simulated datasets that may miss unusual or unexpected lens configurations. The human-in-the-loop approach enables discovery of diverse lens systems while requiring inspection of only a tiny fraction of available data.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Abstract: Strong gravitational lenses (SGLs) are rare systems whose discovery currently relies primarily on supervised machine learning methods trained on large simulated datasets. We present the first application of Astronomaly:PROTEGE to SGL discovery, demonstrating that a human-in-the-loop active learning framework can efficiently identify lenses in large imaging surveys without the need for simulated training data. We consider a sample of 3.7 million bright galaxies from the Kilo-Degree Survey (KiDS) DR4. Feature representations are extracted using a convolutional neural network pre-trained on the ImageNet dataset and subsequently fine-tuned on KiDS data using the self-supervised Bootstrap Your Own Latent (BYOL) framework. Within the embedding of these representations, the active learning loop of Astronomaly iteratively selects the most informative systems for expert inspection. A total of 3,000 objects are inspected across multiple rounds, yielding 34 high-quality (grade A/B) SGL candidates. On the basis that these systems occupy similar regions in the learned feature space, we expand this sample through nearest-neighbour similarity analysis. Including the active learning discoveries, we identify a total of 140 grade A/B candidates and more than 1,000 additional lower-confidence systems (grade C). Among the A/B candidates, 81 are newly identified, while approximately 22% of previously known grade A/B KiDS lenses are recovered. These results demonstrate strong potential for next-generation surveys such as Euclid, Roman, and Rubin’s Legacy Survey of Space and Time. With approximately 60% of the high-quality candidates newly reported, this approach complements supervised methods by reducing reliance on simulations and enabling the discovery of a diverse population of SGLs.