Learning-based physical models of room-temperature semiconductor detectors with reduced data

Abstract

Room-temperature semiconductor radiation detectors (RTSD) have broad applications in medical imaging, homeland security, astrophysics and others. RTSDs such as CdZnTe, CdTe are often pixelated, and characterization of these detectors at micron level can benefit 3-D event reconstruction at sub-pixel level. Material defects alongwith electron and hole charge transport properties need to be characterized which requires several experimental setups and is labor intensive. The current state-of-art approaches characterize each detector pixel, considering the detector in bulk. In this article, we propose a new microscopic learning-based physical models of RTSD based on limited data compared to what is dictated by the physical equations. Our learning models uses a physical charge transport considering trapping centers. Our models learn these material properties in an indirect manner from the measurable signals at the electrodes and/or free and/or trapped charges distributed in the RTSD for electron–hole charge pair injections in the material. Based on the amount of data used during training our physical model, our algorithm characterizes the detector for charge drifts, trapping, detrapping and recombination coefficients considering multiple trapping centers or as a single equivalent trapping center. The RTSD is segmented into voxels spatially, and in each voxel, the material properties are modeled as learnable parameters. Depending on the amount of data, our models can characterize the RTSD either completely or in an equivalent manner.

Identifying Defects without a priori Knowledge in a Room-Temperature Semiconductor Detector Using Physics Inspired Machine Learning Model

“…We demonstrate this approach for Physical Model-3, which is trained just on free electron and hole charges in the RTSD. However, this is also valid for other PI-ML models in [31] as well, which consist of all the trainable weights as dictated by the physical laws or a reduced set of trainable weights.…”

“…The signals are collected at the electrodes on either end of the RTSD. We consider a single cathode and nine grid anodes on either end of the RTSD as in [ 30 , 31 ].…”

“…Applying machine learning to the modeling of RTSDs has been done in the last few years. In our previous works [30][31][32][33][34] we developed a PI-ML model for characterizing the RTSD. In this model, the physics-based charge transport equations are combined with a machine learning model to identify the material properties of the RTSDs.…”

“…In each discretized volume (voxel), the different defects such as trapping, detrapping, recombination as well as electron and hole charge transport are formulated as unknown weights which are trained by the input electron–hole charge pair incident on the RTSD and the output signals and/or charges at the electrode on either ends of the RTSD. We developed the machine learning model considering the number of trainable weights as dictated by the physical laws [ 30 ], as well as a reduced set of trainable weights than what is dictated by the physical laws [ 31 ].…”

A physics based machine learning model to characterize room temperature semiconductor detectors in 3D

“… The mathematical operations in each voxel in this 3D PBML model is also described in simplified voxelized 1D models 47 , 48 . In our PBML model of charge transport the voxels are connected in a bidirectional manner in 3D to form a complicated PBML model.…”