# Sim-to-real supervised domain adaptation for radioisotope identification

arXiv: https://arxiv.org/abs/2412.07069 · HTML: https://mlsanity.com/paper/2412.07069/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 58 references that are in the map.
- First posted on arXiv 10 Dec 2024.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [The frontier of simulation-based inference](https://mlsanity.com/paper/1911.01429/) (2019)
- [First U-Net Layers Contain More Domain Specific Information Than The Last Ones](https://mlsanity.com/paper/2008.07357/) (2020)
- [Machine Learning technique for isotopic determination of radioisotopes using HPGe γ-ray spectra](https://mlsanity.com/paper/2301.01415/) (2023)
- [An Application of CNNs to Time Sequenced One Dimensional Data in Radiation Detection](https://mlsanity.com/paper/1908.10887/) (2019)
- [Transfer Learning in Automated Gamma Spectral Identification](https://mlsanity.com/paper/2003.10524/) (2020)
- [Reduction of detection limit and quantification uncertainty due to interferent by neural classification with abstention](https://mlsanity.com/paper/2205.07609/) (2022)

## Built on by (most cited first, 3 of 3)

- [Unsupervised domain adaptation for radioisotope identification in gamma spectroscopy](https://mlsanity.com/paper/2603.05719/) (2026)
- [Peak-Based Nuclide Identification in HPGe γ-Spectrometry with Machine Learning and SHAP](https://mlsanity.com/paper/2606.14874/) (2026)
- [Computer vision-based neural networks for radioisotope identification in urban environments](https://mlsanity.com/paper/2607.00270/) (2026)

## Abstract (arXiv)

Machine learning has the potential to improve the speed and reliability of radioisotope identification using gamma spectroscopy. However, meticulously labeling an experimental dataset for training is often prohibitively expensive, while training models purely on synthetic data is risky due to the domain gap between simulated and experimental measurements. In this research, we demonstrate that supervised domain adaptation can substantially improve the performance of radioisotope identification models by transferring knowledge between synthetic and experimental data domains. We consider two domain adaptation scenarios: (1) a simulation-to-simulation adaptation, where we perform multi-label proportion estimation using simulated high-purity germanium detectors, and (2) a simulation-to-experimental adaptation, where we perform multi-class, single-label classification using measured spectra from handheld lanthanum bromide (LaBr) and sodium iodide (NaI) detectors. We begin by pretraining a spectral classifier on synthetic data using a custom transformer-based neural network. After subsequent fine-tuning on just 64 labeled experimental spectra, we achieve a test accuracy of 96% in the sim-to-real scenario with a LaBr detector, far surpassing a synthetic-only baseline model (75%) and a model trained from scratch (80%) on the same 64 spectra. Furthermore, we demonstrate that domain-adapted models learn more human-interpretable features than experiment-only baseline models. Overall, our results highlight the potential for supervised domain adaptation techniques to bridge the sim-to-real gap in radioisotope identification, enabling the development of accurate and explainable classifiers even in real-world scenarios where access to experimental data is limited.