No abstract

In Fall 2008 NASA selected a large international consortium to produce a comprehensive automated feature-recognition system for the Solar Dynamics Observatory (SDO). The SDO data that we consider are all of the Atmospheric Imaging Assembly (AIA) images plus surface magnetic-field images from the Helioseismic and Magnetic Imager (HMI). We produce robust, very efficient, professionally coded software modules that can keep up with the SDO data stream and detect, trace, and analyze numerous phenomena, inThe Solar Dynamics Observatory P.C.H. Martens et al.cluding flares, sigmoids, filaments, coronal dimmings, polarity inversion lines, sunspots, Xray bright points, active regions, coronal holes, EIT waves, coronal mass ejections (CMEs), coronal oscillations, and jets. We also track the emergence and evolution of magnetic elements down to the smallest detectable features and will provide at least four full-disk, nonlinear, force-free magnetic field extrapolations per day. The detection of CMEs and filaments is accomplished with Solar and Heliospheric Observatory (SOHO)/Large Angle and Spectrometric Coronagraph (LASCO) and ground-based Hα data, respectively. A completely new software element is a trainable feature-detection module based on a generalized imageclassification algorithm. Such a trainable module can be used to find features that have not yet been discovered (as, for example, sigmoids were in the pre-Yohkoh era). Our codes will produce entries in the Heliophysics Events Knowledgebase (HEK) as well as produce complete catalogs for results that are too numerous for inclusion in the HEK, such as the X-ray bright-point metadata. This will permit users to locate data on individual events as well as carry out statistical studies on large numbers of events, using the interface provided by the Virtual Solar Observatory. The operations concept for our computer vision system is that the data will be analyzed in near real time as soon as they arrive at the SDO Joint Science Operations Center and have undergone basic processing. This will allow the system to produce timely space-weather alerts and to guide the selection and production of quicklook images and movies, in addition to its prime mission of enabling solar science. We briefly describe the complex and unique data-processing pipeline, consisting of the hardware and control software required to handle the SDO data stream and accommodate the computer-vision modules, which has been set up at the Lockheed-Martin Space Astrophysics Laboratory (LMSAL), with an identical copy at the Smithsonian Astrophysical Observatory (SAO).

In Fall 2008 NASA selected a large international consortium to produce a comprehensive automated feature-recognition system for the Solar Dynamics Observatory (SDO). The SDO data that we consider are all of the Atmospheric Imaging Assembly (AIA) images plus surface magnetic-field images from the Helioseismic and Magnetic Imager (HMI). We produce robust, very efficient, professionally coded software modules that can keep up with the SDO data stream and detect, trace, and analyze numerous phenomena, inThe Solar Dynamics Observatory Guest Editors: W. Dean Pesnell, Phillip C. Chamberlin, and Barbara J. Thompson. cluding flares, sigmoids, filaments, coronal dimmings, polarity inversion lines, sunspots, Xray bright points, active regions, coronal holes, EIT waves, coronal mass ejections (CMEs), coronal oscillations, and jets. We also track the emergence and evolution of magnetic elements down to the smallest detectable features and will provide at least four full-disk, nonlinear, force-free magnetic field extrapolations per day. The detection of CMEs and filaments is accomplished with Solar and Heliospheric Observatory (SOHO)/Large Angle and Spectrometric Coronagraph (LASCO) and ground-based Hα data, respectively. A completely new software element is a trainable feature-detection module based on a generalized imageclassification algorithm. Such a trainable module can be used to find features that have not yet been discovered (as, for example, sigmoids were in the pre-Yohkoh era). Our codes will produce entries in the Heliophysics Events Knowledgebase (HEK) as well as produce complete catalogs for results that are too numerous for inclusion in the HEK, such as the X-ray bright-point metadata. This will permit users to locate data on individual events as well as carry out statistical studies on large numbers of events, using the interface provided by the Virtual Solar Observatory. The operations concept for our computer vision system is that the data will be analyzed in near real time as soon as they arrive at the SDO Joint Science Operations Center and have undergone basic processing. This will allow the system to produce timely space-weather alerts and to guide the selection and production of quicklook images and movies, in addition to its prime mission of enabling solar science. We briefly describe the complex and unique data-processing pipeline, consisting of the hardware and control software required to handle the SDO data stream and accommodate the computer-vision modules, which has been set up at the Lockheed-Martin Space Astrophysics Laboratory (LMSAL), with an identical copy at the Smithsonian Astrophysical Observatory (SAO).

Capabilities to predict onset and time profiles of solar‐driven events, including solar X‐ray flares; solar energetic particles (SEP); coronal mass ejections; and high‐speed streams, are critical in mitigating their potential impacts. We introduce the Space Radiation Intelligence System (SPRINTS). This NASA‐invested technology integrates preeruptive metadata and forecasts from the MAG4 system with posteruptive metadata in order to produce high fidelity and preeruptive to posteruptive transitional forecasts for solar‐driven events. To catalog start and end times of the four solar‐driven events, SPRINTS is capable of generating posteruptive forecasts based on automatic detections employed on 30+ years of GOES X‐ray and particle data as well as 20+ years of ACE and DSCOVR solar wind data. The prediction results for 1986–2016 presented here are from the SPRINTS posteruptive capability for forecasting SEPs leveraging GOES X‐ray metadata. We present onset, peak flux, and time profile SEP forecast metrics and results based on expert‐guided, statistical, and machine‐learned decision tree models. Operating on data from a 20 year period, a machine‐learned decision tree model provided the best results for predicting an S1 event (on the NOAA Space Weather Prediction Center Solar Radiation Scale): 86% probability of detection and 37% false alarm rate. Five flare‐related metadata sets were leveraged in the decision tree modeling. Consistently, flare‐integrated flux, flare heliolongitude, and flare decay‐phase duration were found to be the top three forecasting parameters, while flare magnitude and flare latitude had little to no impact on the SEP forecast model. For the solar‐driven events of March 2012, we demonstrate SPRINTS abilities to forecast solar flares, SEP onset, and SEP evolution.

No abstract