`

Timezone: »

 
DeepZipper: A Novel Deep Learning Architecture for Lensed Supernovae Identification
Robert Morgan · Brian Nord

The identification of gravitationally lensed supernovae in modern astronomical datasets is a needle-in-a-haystack problem with dramatic scientific implications: discovered systems can be used to directly measure and resolve the current tension on the value of the expansion rate of the Universe today. We hypothesize that the image-based features of the gravitational lensing and the temporal-based features of the time-varying brightness are equally important in classifications. We therefore develop a deep learning technique that utilizes long short-term memory cells for the time-varying brightness of astronomical systems and convolutional layers for the raw images of astronomical systems simultaneously, and then concatenates the feature maps with multiple fully connected layers. This novel approach achieves a receiver operating characteristic area under curve of 0.97 on simulated astronomical data and more importantly outperforms standalone versions of its recurrent and convolutional constituents. We find that combining recurrent and convolutional layers within one coherent network architecture allows the network to optimally weight and aggregate the temporal and image features to yield a promising tool for lensed supernovae identification.

Author Information

Robert Morgan (University of Wisconsin-Madison)

Rob is currently in the final year of his PhD at the University of Wisconsin-Madison with a focus on machine learning applications in large astronomical datasets. Over the past few years, Rob has led time-domain searches for the sources of both gravitational waves and high-energy neutrinos, and contributed to computer-vision-based searches for strong gravitational lensing systems. In both cases, he specializes in developing state-of-the-art detection methods for rare astronomical objects.

Brian Nord (Fermi National Accelerator Laboratory)

More from the Same Authors