I am working with Prof. Lyndsay Fletcher on the implementation of machine learning algorithms in solar observations. My main focus is on flare spectropolarimetry and how machine learning techniques can aid the data analysis process for carrying out chromospheric magnetic field diagnostics in a flaring atmosphere.
I have mainly applied supervised and unsupervised deep learning models to different solar aspects:
1. Deep convolutional neural network (CNN) for solar feature detection
2. Deep learning for correcting for atmospheric seeing in solar flare observations.
3. Invertible neural network (INN) for the inversion of solar flare line profiles.
A C.V. can be found here.
- “Fast Solar Image Classification Using Deep Learning and its Importance for Automation in Solar Physics”, J.A. Armstrong & L. Fletcher, Solar Physics, vol. 294:80, (2019). [doi] arXiv
- “RADYNVERSION: Learning to Invert a Solar Flare Atmosphere with Invertible Neural Networks”, C.M.J. Osborne, J.A. Armstrong & L. Fletcher, The Astrophysical Journal, vol. 873 (2), (2019). [doi] arXiv
- “Deep learning for the Sun”, J.A. Armstrong, C.M.J. Osborne & L. Fletcher, Astronomy & Geophysics, vol. 61, issue 3, June 2020, Pages 3.34–3.39 [doi]
School of Physics and Astronomy
University of Glasgow
Tel: +44 141 330 2960