Enhancing radioisotope identification in gamma spectra with transfer learning

Machine learning methods in gamma spectroscopy have the potential to provide accurate, real-time classification of unknown radioactive samples. However, obtaining sufficient experimental training data is often prohibitively expensive and time-consuming, and models trained solely on simulated data can struggle to generalize to the unpredictable range of real-world operating scenarios. In this work, we analyze the extent to which transfer learning can improve the performance of isotopic classification models. We begin by pretraining a model for radioisotope identification using synthetic data, and then fine-tune the model for a new target domain sharing the same label space. Results of this analysis indicate that fine-tuned models significantly outperform those trained exclusively on synthetic data or solely on target-domain data, particularly in the intermediate data regime ($\approx 10^2$ to $10^5$ target training samples). This conclusion is consistent across four different machine learning architectures (MLP, CNN, Transformer, and LSTM) considered in this study. This study serves as proof of concept for applying supervised domain adaptation techniques to scenarios in gamma spectroscopy where access to experimental data is limited.