Neutron Dosimetry and Neutron Spectrum Unfolding Using Neural Networks

An artificial neural network has been designed to obtain the neutron spectra from the Bonner spheres spectrometer's count rates. The neural network was trained using 101 neutron spectra taken from IAEA's compilations. These include calibration, reference and operational neutron spectra whose energy distribution is different from UTA4 response matrix, therefore the spectra were converted from lethargy to energy spectra. Energy spectra were used as source term in MCNP 4C code to change them to the UTA4 matrix energy distribution. Rebinned spectra and UTA4 matrix were used to calculate the expected count rates in Bonner spheres spectrometer. These count rates were used as input and correspondent spectrum was used as output during neural network training. The network has 7 inputs, 56-neurons hidden layer and 31-neuron output layer. After training the network was tested with the Bonner spheres count rates produced by twelve neutron spectra. The network allows unfolding the neutron spectrum from count rates measured with Bonner spheres. Good results are obtained when testing count rates belong to neutron spectra used during training, acceptable results are obtained for count rates obtained from actual neutron fields; however the network fails when count rates belong to monoenergetic neutron sources.