No more glowing in the dark: how deep learning improves exposure date estimation in thermoluminescence dosimetry

Abstract

The time- or temperature-resolved detector signal from a thermoluminescence dosimeter can reveal additional information about circumstances of an exposure to ionising irradiation. We present studies using deep neural networks to estimate the date of a single irradiation with 12 mSv within a monitoring interval of 42 days from glow curves of novel TL-DOS personal dosimeters developed by the Materialprüfungsamt NRW in cooperation with TU Dortmund University. Using a deep convolutional network, the irradiation date can be predicted from raw time-resolved glow curve data with an uncertainty of roughly 1–2 days on a 68% confidence level without the need for a prior transformation into temperature space and a subsequent glow curve deconvolution (GCD). This corresponds to a significant improvement in prediction accuracy compared to a prior publication, which yielded a prediction uncertainty of 2–4 days using features obtained from a GCD as input to a neural network.

A machine learning approach for correcting glow curve anomalies in CaSO4:Dy-based TLD dosimeters used in personnel monitoring

“…Recently, researchers have explored the feasibility of using ML algorithms for identifying anomalous GCs, to study the characteristics of TL emission and for the estimation of elapsed time after exposure [3,[8][9][10][11][12][13][14][15]. As mentioned earlier, we demonstrated the effectiveness of ML algorithms in identifying abnormal GCs and classifying them based on the associated abnormalities [3].…”

Reflections on the future developments of research in retrospective physical dosimetry

“…Finally, a look at the future of research cannot ignore the role of the increasing opportunities offered by the field of Artificial Intelligence. For instance, deep learning and computer vision are increasingly being used in many sectors of dosimetry and radiation protection [143] and a few preliminary experiences in EPR and thermoluminescence dosimetry [144,145]. From these future scenarios, it is clear that computation will become more and more relevant to experimental dosimetry.…”

Artificial intelligence and radiation protection. A game changer or an update?

“…The official dose monitoring of workers is performed with passive dosimeters and active dosimeters are carried as a secondary device. Mentzel demonstrated that a NN trained on the glow curves of passive dosimeter can assess without the active dosimeter the date of a single high-dose irradiation; the method could be "extended to a wide range of additional insights into irradiation scenarios" (Mentzel, 2021).…”