Enabling real-time multi-messenger astrophysics discoveries with deep learning

doi:10.1038/s42254-019-0097-4

This content will become publicly available on October 3, 2020

Title: Enabling real-time multi-messenger astrophysics discoveries with deep learning

Full Record
Other Related Research

Abstract

Multi-messenger astrophysics is a fast-growing, interdisciplinary field that combines data, which vary in volume and speed of data processing, from many different instruments that probe the Universe using different cosmic messengers: electromagnetic waves, cosmic rays, gravitational waves and neutrinos. In this Expert Recommendation, we review the key challenges of real-time observations of gravitational wave sources and their electromagnetic and astroparticle counterparts, and make a number of recommendations to maximize their potential for scientific discovery. These recommendations refer to the design of scalable and computationally efficient machine learning algorithms; the cyber-infrastructure to numerically simulate astrophysical sources, and to process and interpret multi-messenger astrophysics data; the management of gravitational wave detections to trigger real-time alerts for electromagnetic and astroparticle follow-ups; a vision to harness future developments of machine learning and cyber-infrastructure resources to cope with the big-data requirements; and finally, the need to build a community of experts to realize the goals of multi-messenger astrophysics.

Authors:

^[1];

^[1]; Andreoni, Igor ^[2];

^[3]; Bachelet, Etienne ^[4];

^[2]; Bianco, Federica B. ^[5];

^[6]; Carrasco Kind, Matias ^[1]; Chard, Kyle ^[7]; Cho, Minsik ^[8]; Cowperthwaite, Philip S. ^[9]; Etienne, Zachariah B. ^[10]; Fishbach, Maya ^[7]; Forster, Francisco ^[11]; George, Daniel ^[12]; Gibbs, Tom ^[13]; Graham, Matthew ^[2];

^[1]; Gruendl, Robert ^[1] more »

Univ. of Illinois at Urbana-Champaign, Urbana, IL (United States)
California Inst. of Technology, Pasadena, CA (United States)
Tecnologico de Monterrey, Zapopan (Mexico). School of Engineering and Sciences,
Las Cumbres Observatory, Goleta, CA (United States)
Univ. of Deleware, Newark, DE (United States)
Stockholm Univ., AlbaNova, Stockholm (Sweden). The Oskar Klein Centre for Cosmoparticle Physics
Univ. of Chicago, Chicago, IL (United States)
IBM T.J. Watson Research Center, New York, NY (United States)
Observatories of the Carnegie Inst. for Science, Pasadena, CA (United States)
West Virginia Univ., Morgantown, WV (United States)
Center for Mathematical Modelling, Santiago (Chile)
Google X, Mountain View, CA (United States)
NVIDIA, Santa Clara, CA (United States)
Argonne National Lab. (ANL), Argonne, IL (United States). Leadership Computing Facility
Massachusetts Inst. of Technology, Cambridge, MA (United States)
Columbia Univ. in the City of New York, New York, NY (United States)
Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Univ. de Guadalajara, Guadalajara (Mexico). Centro Univers. de Ciencias Exactas e Ingenieria
Univ. of Maryland, College Park, MD (United States)
Cardiff Univ., Cardiff (United Kingdom)
NASA Goddard Space Flight Center, Greenbelt, MD (United States)
Univ. of Washington, Seattle, WA (United States)
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)

Publication Date:: 2019-10-03

Research Org.:: Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)

Sponsoring Org.:: USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR) (SC-21)

OSTI Identifier:: 1569373

Grant/Contract Number:: AC05-00OR22725

Resource Type:: Accepted Manuscript

Journal Name:: Nature Reviews Physics

Additional Journal Information:: Journal Volume: 1; Journal Issue: 10; Journal ID: ISSN 2522-5820

Publisher:: Springer Nature

Country of Publication:: United States

Language:: English

Citation Formats


                    Huerta, E. A., Allen, Gabrielle, Andreoni, Igor, Antelis, Javier M., Bachelet, Etienne, Berriman, G. Bruce, Bianco, Federica B., Biswas, Rahul, Carrasco Kind, Matias, Chard, Kyle, Cho, Minsik, Cowperthwaite, Philip S., Etienne, Zachariah B., Fishbach, Maya, Forster, Francisco, George, Daniel, Gibbs, Tom, Graham, Matthew, Gropp, William, Gruendl, Robert, Gupta, Anushri, Haas, Roland, Habib, Sarah, Jennings, Elise, Johnson, Margaret W.  G., Katsavounidis, Erik, Katz, Daniel S., Khan, Asad, Kindratenko, Volodymyr, Kramer, William T.  C., Liu, Xin, Mahabal, Ashish, Marka, Zsuzsa, McHenry, Kenton, Miller, J. M., Moreno, Claudia, Neubauer, M. S., Oberlin, Steve, Olivas Jr., Alexander R., Petravick, Donald, Rebei, Adam, Rosofsky, Shawn, Ruiz, Milton, Saxton, Aaron, Schutz, Bernard F., Schwing, Alex, Seidel, Ed, Shapiro, Stuart L., Shen, Hongyu, Shen, Yue, Singer, Leo P., Sipocz, Brigitta M., Sun, Lunan, Towns, John, Tsokaros, Antonios, Wei, Wei, Wells, Jack, Williams, Timothy J., Xiong, Jinjun, and Zhao, Zhizhen. Enabling real-time multi-messenger astrophysics discoveries with deep learning.  United States: N. p., 2019. 
        Web.  doi:10.1038/s42254-019-0097-4.

Copy to clipboard


                    Huerta, E. A., Allen, Gabrielle, Andreoni, Igor, Antelis, Javier M., Bachelet, Etienne, Berriman, G. Bruce, Bianco, Federica B., Biswas, Rahul, Carrasco Kind, Matias, Chard, Kyle, Cho, Minsik, Cowperthwaite, Philip S., Etienne, Zachariah B., Fishbach, Maya, Forster, Francisco, George, Daniel, Gibbs, Tom, Graham, Matthew, Gropp, William, Gruendl, Robert, Gupta, Anushri, Haas, Roland, Habib, Sarah, Jennings, Elise, Johnson, Margaret W.  G., Katsavounidis, Erik, Katz, Daniel S., Khan, Asad, Kindratenko, Volodymyr, Kramer, William T.  C., Liu, Xin, Mahabal, Ashish, Marka, Zsuzsa, McHenry, Kenton, Miller, J. M., Moreno, Claudia, Neubauer, M. S., Oberlin, Steve, Olivas Jr., Alexander R., Petravick, Donald, Rebei, Adam, Rosofsky, Shawn, Ruiz, Milton, Saxton, Aaron, Schutz, Bernard F., Schwing, Alex, Seidel, Ed, Shapiro, Stuart L., Shen, Hongyu, Shen, Yue, Singer, Leo P., Sipocz, Brigitta M., Sun, Lunan, Towns, John, Tsokaros, Antonios, Wei, Wei, Wells, Jack, Williams, Timothy J., Xiong, Jinjun, & Zhao, Zhizhen. Enabling real-time multi-messenger astrophysics discoveries with deep learning.  United States.  doi:10.1038/s42254-019-0097-4.

Copy to clipboard


                    Huerta, E. A., Allen, Gabrielle, Andreoni, Igor, Antelis, Javier M., Bachelet, Etienne, Berriman, G. Bruce, Bianco, Federica B., Biswas, Rahul, Carrasco Kind, Matias, Chard, Kyle, Cho, Minsik, Cowperthwaite, Philip S., Etienne, Zachariah B., Fishbach, Maya, Forster, Francisco, George, Daniel, Gibbs, Tom, Graham, Matthew, Gropp, William, Gruendl, Robert, Gupta, Anushri, Haas, Roland, Habib, Sarah, Jennings, Elise, Johnson, Margaret W.  G., Katsavounidis, Erik, Katz, Daniel S., Khan, Asad, Kindratenko, Volodymyr, Kramer, William T.  C., Liu, Xin, Mahabal, Ashish, Marka, Zsuzsa, McHenry, Kenton, Miller, J. M., Moreno, Claudia, Neubauer, M. S., Oberlin, Steve, Olivas Jr., Alexander R., Petravick, Donald, Rebei, Adam, Rosofsky, Shawn, Ruiz, Milton, Saxton, Aaron, Schutz, Bernard F., Schwing, Alex, Seidel, Ed, Shapiro, Stuart L., Shen, Hongyu, Shen, Yue, Singer, Leo P., Sipocz, Brigitta M., Sun, Lunan, Towns, John, Tsokaros, Antonios, Wei, Wei, Wells, Jack, Williams, Timothy J., Xiong, Jinjun, and Zhao, Zhizhen. Thu .  
        "Enabling real-time multi-messenger astrophysics discoveries with deep learning".  United States.  doi:10.1038/s42254-019-0097-4.

Copy to clipboard


                    
@article{osti_1569373,

  title        = {Enabling real-time multi-messenger astrophysics discoveries with deep learning},

  author       = {Huerta, E. A. and Allen, Gabrielle and Andreoni, Igor and Antelis, Javier M. and Bachelet, Etienne and Berriman, G. Bruce and Bianco, Federica B. and Biswas, Rahul and Carrasco Kind, Matias and Chard, Kyle and Cho, Minsik and Cowperthwaite, Philip S. and Etienne, Zachariah B. and Fishbach, Maya and Forster, Francisco and George, Daniel and Gibbs, Tom and Graham, Matthew and Gropp, William and Gruendl, Robert and Gupta, Anushri and Haas, Roland and Habib, Sarah and Jennings, Elise and Johnson, Margaret W.  G. and Katsavounidis, Erik and Katz, Daniel S. and Khan, Asad and Kindratenko, Volodymyr and Kramer, William T.  C. and Liu, Xin and Mahabal, Ashish and Marka, Zsuzsa and McHenry, Kenton and Miller, J. M. and Moreno, Claudia and Neubauer, M. S. and Oberlin, Steve and Olivas Jr., Alexander R. and Petravick, Donald and Rebei, Adam and Rosofsky, Shawn and Ruiz, Milton and Saxton, Aaron and Schutz, Bernard F. and Schwing, Alex and Seidel, Ed and Shapiro, Stuart L. and Shen, Hongyu and Shen, Yue and Singer, Leo P. and Sipocz, Brigitta M. and Sun, Lunan and Towns, John and Tsokaros, Antonios and Wei, Wei and Wells, Jack and Williams, Timothy J. and Xiong, Jinjun and Zhao, Zhizhen},

  abstractNote = {Multi-messenger astrophysics is a fast-growing, interdisciplinary field that combines data, which vary in volume and speed of data processing, from many different instruments that probe the Universe using different cosmic messengers: electromagnetic waves, cosmic rays, gravitational waves and neutrinos. In this Expert Recommendation, we review the key challenges of real-time observations of gravitational wave sources and their electromagnetic and astroparticle counterparts, and make a number of recommendations to maximize their potential for scientific discovery. These recommendations refer to the design of scalable and computationally efficient machine learning algorithms; the cyber-infrastructure to numerically simulate astrophysical sources, and to process and interpret multi-messenger astrophysics data; the management of gravitational wave detections to trigger real-time alerts for electromagnetic and astroparticle follow-ups; a vision to harness future developments of machine learning and cyber-infrastructure resources to cope with the big-data requirements; and finally, the need to build a community of experts to realize the goals of multi-messenger astrophysics.},

  doi          = {10.1038/s42254-019-0097-4},

  journal      = {Nature Reviews Physics},

  number       = 10,

  volume       = 1,

  place        = {United States},

  year         = {2019},

  month        = {10}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

This content will become publicly available on October 3, 2020

Publisher's Version of Record

DOI: 10.1038/s42254-019-0097-4

Other availability

Search WorldCat to find libraries that may hold this journal

Save / Share:

Export Metadata

Save to My Library

Similar Records in DOE PAGES and OSTI.GOV collections:

Enabling immersive engagement in energy system models with deep learning

Journal Article Bugbee, Bruce ; Bush, Brian W. ; Gruchalla, Kenny ; ... - Statistical Analysis and Data Mining

Complex ensembles of energy simulation models have become crucial components of renewable energy research in recent years. Often the increasing computational cost, high-dimensional structure, and other complexities hinder researchers from fully utilizing these data sources for knowledge building. Researchers at National Renewable Energy Laboratory have determined an immersive visualization workflow to dramatically improve user engagement and analysis capability through a combination of low-dimensional structure analysis, deep learning, and custom visualization methods. We present case studies for two energy simulation platforms.
DOI: 10.1002/sam.11419

Full Text Available
DESAlert: Enabling Real-Time Transient Follow-Up with Dark Energy Survey Data

Journal Article Poci, A. ; Kuehn, K. ; Abbott, T. ; ... - Publications of the Astronomical Society of Australia

Here, the Dark Energy Survey is undertaking an observational programme imaging 1/4 of the southern hemisphere sky with unprecedented photometric accuracy. In the process of observing millions of faint stars and galaxies to constrain the parameters of the dark energy equation of state, the Dark Energy Survey will obtain pre-discovery images of the regions surrounding an estimated 100 gamma-ray bursts over 5 yr. Once gamma-ray bursts are detected by, e.g., the Swift satellite, the DES data will be extremely useful for follow-up observations by the transient astronomy community. We describe a recently-commissioned suite of software that listens continuously for automatedmore »« less
DOI: 10.1017/pasa.2016.42

Full Text Available
DeepWelding: a Deep Learning Enhanced Approach to GTAW Using Multi-source Sensing Images

Journal Article Feng, Yunhe ; Chen, Zongyao ; Wang, Dali ; ... - IEEE Transactions on Industrial Informatics

Deep learning has great potential to reshape manufacturing industries. In this paper, we present DeepWelding, a novel framework that applies deep learning techniques to improve gas tungsten arc welding (GTAW) process monitoring and penetration detection using multi-source sensing images. The framework is capable of analyzing multiple types of optical sensing images synchronously and consists of three deep learning enhanced consecutive phases: image preprocessing, image selection, and weld penetration classification. Specifically, we adopted generative adversarial networks (pix2pix) for image denoising and classic convolutional neural networks (AlexNet) for image selection. Both pix2pix and AlexNet delivered satisfactory performance. However, five individual neural networksmore »« less
DOI: 10.1109/TII.2019.2937563
Enabling fast, stable and accurate peridynamic computations using multi-time-step integration

Journal Article Lindsay, P. ; Parks, M. L. ; Prakash, A. - Computer Methods in Applied Mechanics and Engineering

Peridynamics is a nonlocal extension of classical continuum mechanics that is well-suited for solving problems with discontinuities such as cracks. This paper extends the peridynamic formulation to decompose a problem domain into a number of smaller overlapping subdomains and to enable the use of different time steps in different subdomains. This approach allows regions of interest to be isolated and solved at a small time step for increased accuracy while the rest of the problem domain can be solved at a larger time step for greater computational efficiency. Lastly, performance of the proposed method in terms of stability, accuracy, andmore »« less
Cited by 3
DOI: 10.1016/j.cma.2016.03.049

Full Text Available
Data-driven reinforcement learning–based real-time energy management system for plug-in hybrid electric vehicles

Journal Article Qi, Xuewei ; Wu, Guoyuan ; Boriboonsomsin, Kanok ; ... - Transportation Research Record

Plug-in hybrid electric vehicles (PHEVs) show great promise in reducing transportation-related fossil fuel consumption and greenhouse gas emissions. Designing an efficient energy management system (EMS) for PHEVs to achieve better fuel economy has been an active research topic for decades. Most of the advanced systems rely either on a priori knowledge of future driving conditions to achieve the optimal but not real-time solution (e.g., using a dynamic programming strategy) or on only current driving situations to achieve a real-time but nonoptimal solution (e.g., rule-based strategy). This paper proposes a reinforcement learning–based real-time EMS for PHEVs to address the trade-off betweenmore »« less
Cited by 4
DOI: 10.3141/2572-01

Full Text Available

Similar Records