# CMU DeepLens: Deep Learning For Automatic Image-based Galaxy-Galaxy Strong Lens Finding

## TL;DR

CMU DeepLens is a deep learning-based automated method for identifying galaxy-galaxy strong gravitational lenses in large survey data, achieving high completeness and reliability on simulated LSST-like images.

## Contribution

The paper introduces CMU DeepLens, a fully automated deep learning approach trained on realistic simulations for efficient galaxy-galaxy lens detection.

## Key findings

- Achieves 90% completeness at 99% rejection rate for certain lens parameters.
- Requires realistic complex simulations for effective training.
- Code is publicly available for community use.

## Abstract

Galaxy-scale strong gravitational lensing is not only a valuable probe of the dark matter distribution of massive galaxies, but can also provide valuable cosmological constraints, either by studying the population of strong lenses or by measuring time delays in lensed quasars. Due to the rarity of galaxy-scale strongly lensed systems, fast and reliable automated lens finding methods will be essential in the era of large surveys such as LSST, Euclid, and WFIRST. To tackle this challenge, we introduce CMU DeepLens, a new fully automated galaxy-galaxy lens finding method based on Deep Learning. This supervised machine learning approach does not require any tuning after the training step which only requires realistic image simulations of strongly lensed systems. We train and validate our model on a set of 20,000 LSST-like mock observations including a range of lensed systems of various sizes and signal-to-noise ratios (S/N). We find on our simulated data set that for a rejection rate of non-lenses of 99%, a completeness of 90% can be achieved for lenses with Einstein radii larger than 1.4" and S/N larger than 20 on individual $g$-band LSST exposures. Finally, we emphasize the importance of realistically complex simulations for training such machine learning methods by demonstrating that the performance of models of significantly different complexities cannot be distinguished on simpler simulations. We make our code publicly available at https://github.com/McWilliamsCenter/CMUDeepLens .