Abstract
The National Aeronautics Space Agency (NASA) Solar Dynamics Observatory (SDO) mission has given us unprecedented insight into the Sun’s activity. By capturing approximately 70,000 images a day, this mission has created one of the richest and biggest repositories of solar image data available to mankind. With such massive amounts of information, researchers have been able to produce great advances in detecting solar events. In this resource, we compile SDO solar data into a single repository in order to provide the computer vision community with a standardized and curated large-scale dataset of several hundred thousand solar events found on high resolution solar images. This publicly available resource, along with the generation source code, will accelerate computer vision research on NASA’s solar image data by reducing the amount of time spent performing data acquisition and curation from the multiple sources we have compiled. By improving the quality of the data with thorough curation, we anticipate a wider adoption and interest from the computer vision to the solar physics community.
Highlights
Background & SummaryNational Aeronautics Space Agency (NASA)’s Living With a Star (LWS) program initiated the Solar Dynamic Observatory (SDO) mission on February 11, 2010
There are two other modules, namely the Extreme Ultraviolet Variability Experiment (EVE) and Helioseismic and Magnetic Imager (HMI), which generate a different type of imaging beyond the scope of this dataset
We investigated the most suitable wavelength for each event type according to the SDO Feature Finding Team (FFT) modules[2]
Summary
NASA’s Living With a Star (LWS) program initiated the Solar Dynamic Observatory (SDO) mission on February 11, 2010. The SDO FFT modules report detected events to the Heliophysics Event Knowledge Base (HEK) system which provides access to the data through a public Application Programming Interface (API)[4]. Since the data collection requires a significant amount of time and attention to detail, researchers need to cautiously collect and prepare appropriate data from these sources to avoid form errors during the preparation process To overcome these issues, we are presenting a ready-to-use dataset for event retrieval applications. The majority of our dataset is prepared for the research area of Content-Based Image Retrieval (CBIR) For this purpose, we include the full-disk image of the Sun with temporal and spatial features of the event records in the dataset. As a result of several tests to validate and clean the dataset, we make available approximately 260,000 images taken by the AIA module with image parameters and 270,000 event records in a well-prepared format for future research
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have