Magnetic reconnection is a physical process occurring in highly conducting plasmas in which the magnetic topology is rearranged and magnetic energy is converted to kinetic energy, thermal energy, and particle acceleration. Identifying where reconnection is taking place usually has to be performed by human experts. In this project, we explore whether this identification can be automated. Our first results demonstrate that a machine learning algorithm can help to identify reconnection in 2D simulations of collisionless plasma turbulence.
The simulation dataset (UNIPI_TURB_2D, UNIPI_TURB_2D_2048) is available at Cineca on the AIDAdb. In order to access the meta-information and the link to the raw data, look at the tutorial at http://aida-space.eu/AIDAdb-iRODS.
"Identifying magnetic reconnection in 2D Hybrid Vlasov Maxwell simulations with Convolutional Neural Networks"
Accepted in the Astrophysical Journal (2020)
Authors: A. Hu, M. Sisti, F. Finelli, F. Califano, J. Dargent, M. Faganello, E. Camporeale, and J. Teunissen
The corresponding data can be found at: https://doi.org/10.5281/zenodo.3907309
The corresponding code can be found at: https://doi.org/10.5281/zenodo.3935887
later versions will be available via https://gitlab.com/aidaspace/aidapy)
Please contact us (firstname.lastname@example.org) if you need further information.
Hu, A., Teunissen, J., Sisti, M., Califano, F., Dargent, J., Pedrazzi, G., and Delli Ponti, F.: Using machine learning to identify magnetic reconnection in two-dimensional simulations , EGU General Assembly 2020, Online, 4–8 May 2020, EGU2020-12160,
https://doi.org/10.5194/egusphere-egu2020-12160, 2020 (oral presentation)