Automated Object Classification for Large Scale Future Surveys: A Strong Lensing Example with Machine Learning
Abstract: Gravitational lensing offers a direct probe of the underlying mass distribution of lensing systems, a window to the high redshift universe, and a geometric probe of cosmological models. The advent of large scale surveys such as the Large Synoptic Sky Telescope and Euclid has prompted a need for automatic and efficient identification of strong lensing systems. We present (1) (ALL) Automated Lensing Learner, a strong lensing identification pipeline that will be publicly released as open source software, and (2) a publicly available mock LSST dataset with strong galaxy-galaxy lenses. In this first application of the pipeline, we employ a fast feature extraction method, Histogram of Oriented Gradients (HOG), to capture edge patterns that are characteristic of strong gravitational arcs in galaxy-galaxy lensing. We use logistic regression to train a supervised classifier model on the HOG of HST- and LSST-like images. Our tests demonstrate an efficient and effective method for automatically identifying strong lenses that captures much of the complexity of the arc finding problem. The linear classifier both runs on a personal laptop and can easily scale to large data sets on a computing cluster, all while using existing open source tools.