Scientists Pioneer Use of Deep Learning for Real-Time Gravitational Wave Discovery
The National Center for Supercomputing Applications, Wolfram Research and NVIDIA technologies make scientific discoveries possible
Jan 25, 2018, 01:00 ET
CHAMPAIGN, Ill., Jan. 25, 2018 /PRNewswire/ -- Scientists at the National Center for Supercomputing Applications (NCSA), located at the University of Illinois at Urbana-Champaign, have pioneered the use of deep learning for rapid detection and characterization of gravitational waves. This new approach will enable astronomers to study gravitational waves using minimal computational resources, reducing time to discovery and increasing the science reach of gravitational wave astrophysics. This innovative research was published in Physics Letters B.
Combining deep learning algorithms, numerical relativity simulations of black hole mergers––obtained with the Einstein Toolkit run on the Blue Waters supercomputer––and data from the LIGO Open Science Center, NCSA Gravity Group researchers Daniel George and Eliu Huerta produced Deep Filtering, an end-to-end time series signal processing method. Deep Filtering achieves similar sensitivities and lower errors compared to established gravitational wave detection algorithms, while being far more computationally efficient and resilient to noise anomalies. This method allows faster-than-real-time processing of gravitational waves in LIGO's raw data, and also enables new physics, since it can detect new classes of gravitational wave sources that may go unnoticed with existing detection algorithms. George and Huerta are extending this method to identify in real time electromagnetic counterparts to gravitational wave events in future LSST data.
NCSA's Gravity Group leveraged NCSA resources from its Innovative Systems Laboratory and NCSA's Blue Waters supercomputer, as well as collaborated with interdisciplinary staff at the University of Illinois. Wolfram Research played an important role, as the Wolfram Language was used in creating the deep learning framework. Also critical to this research were the GPUs (Tesla P100 and DGX-1) provided by NVIDIA, which enabled accelerated training of neural networks.
George and Huerta worked with NVIDIA and Wolfram researchers to create this demo to visualize the architecture of Deep Filtering, and to get insights into its neuronal activity during the detection and characterization of real gravitational wave events. This demo highlights the components of Deep Filtering, exhibiting detection sensitivity and computational performance.
More information can be found on the NCSA website.
ABOUT WOLFRAM RESEARCH
Wolfram has been defining the computational future for three decades. As the creator of Mathematica, Wolfram|Alpha and the Wolfram Language, Wolfram is the leader in developing technology and tools that inject sophisticated computation and knowledge into everything.
SOURCE Wolfram Research