Title: Applications of neural networks for free unfolding of experimental data from fusion neutron spectrometers

Authors: Emanuele Ronchi, S. Conroy, E. Andersson Sunden, G. Ericsson, M. Gatu Johnson, C. Hellesen, H. Sjostrand, M. Weiszflog, JET-EFDA contributors

Addresses: Division of Applied Nuclear Physics, Department of Physics and Astronomy, Angstromlab, Uppsala University, Box 525 SE75120, Uppsala, Sweden; JET-EFDA, Culham Science Centre, OX14 3DB, Abingdon, UK. ' Division of Applied Nuclear Physics, Department of Physics and Astronomy, Angstromlab, Uppsala University, Box 525 SE75120, Uppsala, Sweden; JET-EFDA, Culham Science Centre, OX14 3DB, Abingdon, UK. ' Division of Applied Nuclear Physics, Department of Physics and Astronomy, Angstromlab, Uppsala University, Box 525 SE75120, Uppsala, Sweden; JET-EFDA, Culham Science Centre, OX14 3DB, Abingdon, UK. ' Division of Applied Nuclear Physics, Department of Physics and Astronomy, Angstromlab, Uppsala University, Box 525 SE75120, Uppsala, Sweden; JET-EFDA, Culham Science Centre, OX14 3DB, Abingdon, UK. ' Division of Applied Nuclear Physics, Department of Physics and Astronomy, Angstromlab, Uppsala University, Box 525 SE75120, Uppsala, Sweden; JET-EFDA, Culham Science Centre, OX14 3DB, Abingdon, UK. ' Division of Applied Nuclear Physics, Department of Physics and Astronomy, Angstromlab, Uppsala University, Box 525 SE75120, Uppsala, Sweden; JET-EFDA, Culham Science Centre, OX14 3DB, Abingdon, UK. ' Division of Applied Nuclear Physics, Department of Physics and Astronomy, Angstromlab, Uppsala University, Box 525 SE75120, Uppsala, Sweden; JET-EFDA, Culham Science Centre, OX14 3DB, Abingdon, UK. ' Division of Applied Nuclear Physics, Department of Physics and Astronomy, Angstromlab, Uppsala University, Box 525 SE75120, Uppsala, Sweden; JET-EFDA, Culham Science Centre, OX14 3DB, Abingdon, UK. ' JET-EFDA, Culham Science Centre, OX14 3DB, Abingdon, UK

Abstract: Free unfolding in neutron spectroscopy means reconstructing energy spectra from experimental data without a priori assumptions regarding their shape. Due to the ill-conditioned nature of the problem, this cannot be done analytically. Neural Networks (NNs) were applied to this task and synthetic data was used for training and testing. Results showed very consistent performance especially in the region of low and medium counts, where they fall near the Poisson statistical boundary. Comparison with other unfolding methods validated these results. Application time on the order of ms makes NNs suitable for real-time analysis. This approach can be applied to any instrument of which the response function is known.

Keywords: neural networks; free unfolding; unfolding; NE213; magnetic proton recoil upgrade; MPRu; fusion neutron spectrometers; deconvolution; real-time.

DOI: 10.1504/IJNKM.2010.031152

International Journal of Nuclear Knowledge Management, 2010 Vol.4 No.1, pp.25 - 31

Published online: 22 Jan 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article