Optimizing machine learning methods to discover strong gravitational lenses in the deep lens survey

Machine learning models can greatly improve the search for strong gravitational lenses in imaging surveys by reducing the amount of human inspection required. In this work, we test the performance of supervised, semi-supervised, and unsupervised learning algorithms trained with the ResNetV2 neural network architecture on their ability to efficiently find strong gravitational lenses in the Deep Lens Survey (DLS). We use galaxy images from the survey, combined with simulated lensed sources, as labeled data in our training data sets. We find that models using semi-supervised learning along with data augmentations (transformations applied to an image during training, e.g. rotation) and Generative Adversarial Network (GAN) generated images yield the best performance. They offer 5 - 10 times better precision across all recall values compared to supervised algorithms. Applying the best performing models to the full 20 deg(2) DLS survey, we find 3 Grade-A lens candidates within the top 17 image predictions from the model. This increases to 9 Grade-A and 13 Grade-B candidates when 1 per cent (& SIM;2500 images) of the model predictions are visually inspected. This is & GSIM; 10 x the sky density of lens candidates compared to current shallower wide-area surveys (such as the Dark Energy Survey), indicating a trove of lenses awaiting discovery in upcoming deeper all-sky surveys. These results suggest that pipelines tasked with finding strong lens systems can be highly efficient, minimizing human effort. We additionally report spectroscopic confirmation of the lensing nature of two Grade-A candidates identified by our model, further validating our methods.

Automated summary

Machine learning models can significantly improve the search for strong gravitational lenses in imaging surveys. This study evaluates the performance of supervised, semi-supervised, and unsupervised learning algorithms trained with the ResNetV2 neural network architecture in finding strong gravitational lenses in the Deep Lens Survey. The results show that models using semi-supervised learning with data augmentations and GAN-generated images achieve the best performance.