Abstract Details
Name: Dattaraj Dhuri Affiliation: Tata Institute of Fundamental Research Conference ID: ASI2018_1633 Title : Prediction of solar flares from photospheric magnetic field using machine learning Authors and Co-Authors : Shravan Hanasoge, Tata Institute of Fundamental Research, Mumbai, India Abstract Type : Contributed Talk Abstract Category : Sun and the Solar System Abstract : Solar flares are eruptions on the surface of Sun caused by the rapid restructuring of magnetic field lines in active regions. The radiation and charged particles released in the process pose a threat to space and ground based communication instruments. Understanding mechanism leading to solar flares and their prediction is an outstanding problem in the field. Helioseismic and Magnetic Imager (onboard NASA’s Solar Dynamic Observatory) makes available high resolution solar vector-magnetic-field data with 12 minutes cadence. We use this data to train machine learning algorithms for prediction of solar flares with accuracy greater than 85%. We analyse performance of trained machine learning algorithms to shed light on underlying physics responsible for triggering solar flares. |