Euclid Quick Data Release (Q1). The Strong Lensing Discovery Engine E -- Ensemble classification of strong gravitational lenses: lessons for Data Release 1

TL;DR

This study combines machine learning and citizen science to identify strong gravitational lenses in Euclid data, achieving higher purity and completeness than individual methods, informing future large-scale surveys.

Contribution

It demonstrates that ensemble classification of lenses using machine learning and citizen science improves purity and completeness over individual classifiers in Euclid data.

Findings

Ensemble approach yields 52% purity and 50% completeness in lens identification.

Combining classifiers outperforms individual machine learning or citizen science methods.

Provides insights for managing large data volumes in future Euclid data releases.

Abstract

The Euclid Wide Survey (EWS) is expected to identify of order $100\,000$ galaxy-galaxy strong lenses across $14\,000$deg$^2$. The Euclid Quick Data Release (Q1) of $63.1$deg$^2$ Euclid images provides an excellent opportunity to test our lens-finding ability, and to verify the anticipated lens frequency in the EWS. Following the Q1 data release, eight machine learning networks from five teams were applied to approximately one million images. This was followed by a citizen science inspection of a subset of around $100\,000$ images, of which $65\%$ received high network scores, with the remainder randomly selected. The top scoring outputs were inspected by experts to establish confident (grade A), likely (grade B), possible (grade C), and unlikely lenses. In this paper we combine the citizen science and machine learning classifiers into an ensemble, demonstrating that a combined approach can produce a purer and more complete sample than the original individual classifiers. Using the expert-graded subset as ground truth, we find that this ensemble can provide a purity of $52\pm2\%$ (grade A/B lenses) with $50\%$ completeness (for context, due to the rarity of lenses a random classifier would have a purity of $0.05\%$). We discuss future lessons for the first major Euclid data release (DR1), where the big-data challenges will become more significant and will require analysing more than $\sim300$ million galaxies, and thus time investment of both experts and citizens must be carefully managed.