Implementation of a machine learning technique for estimating gamma direction using a coaxial High Purity Germanium detector

We demonstrate the ability to obtain the direction of the gamma rays using a standard coaxial high purity germanium (HPGe) detector using the direction-sensitive information embedded in the shape of the pre-amplified HPGe signals. We deduced the complex relationship between the shape of the signal and the direction from which the gamma-ray enters the detector active volume using a two-step machine learning technique. In the first step, we collected pulses from the HPGe detector due to a ¹³³Ba radioactive source placed in four distinct positions around the detector while keeping the distance from the center of the detector crystal constant. A subset of the pulses collected with radioactive source kept at the four positions was used to train an artificial neural network (ANN) called a self-organizing map (SOM) to cluster the HPGe waveforms based on their shape. The trained SOM network was then utilized to produce direction-specific maps corresponding to pulses generated when the ¹³³Ba source is at a specific location with respect to the detector. In the second step, we used the SOM-generated direction-specific maps to train another network composed of a single feedforward layer for predicting the direction of the gamma ray from the pulses produced by the HPGe detector due to the gamma energy deposition. Our results show that even without employing complex methodologies, a standard coaxial HPGe detector can estimate the direction of incoming gamma rays and thus, provide initial guidance on the gamma-emitting radioactive source direction with reference to the detector.