Gamma-ray spectroscopy with deep learning

Signal processing and deep learning for gamma-ray spectrometry

Compensation of hardware limitations in gamma-ray spectrometry using modern signal processing and deep learning, in long-standing collaboration with Dr. Tom Trigano (SCE) and Prof. Yongxin Zhu’s group (Shanghai Advanced Research Institute, CAS).

Topics:

  • Activity estimation from short-duration recordings
  • Pile-up correction at high count rates
  • Energy spectrum estimation
  • Time-domain simulators for algorithm development
  • Self-supervised, semi-supervised, and contrastive learning for spectroscopic pulses
  • Open datasets for benchmarking

Representative publications:

  • T. Trigano and D. Bykhovsky, “Deep Learning Based Method for Activity Estimation from Short-Duration Gamma Spectroscopy Recordings,” IEEE Transactions on Instrumentation and Measurement, vol. 73, pp. 1–11, 2024. doi:10.1109/TIM.2024.3449943, accepted manuscript, details
  • Z. Chen, D. Bykhovsky, X. Zheng, T. Trigano, Y. Zhu, “GaSim: A Python Class to Generate Simulated Time Signals for Gamma Spectroscopy,” SoftwareX, vol. 29, p. 102037, Feb. 2025. doi:10.1016/j.softx.2025.102037
  • D. Bykhovsky, Z. Chen, Y. Huang, X. Zheng, T. Trigano, “Advanced Spectroscopy Time-Domain Signal Simulator for the Development of Machine and Deep Learning Algorithms,” IEEE Sensors Letters, vol. 9, no. 4, pp. 1–4, Apr. 2025. doi:10.1109/LSENS.2025.3544656, accepted manuscript, details
  • Y. Huang, X. Zheng, Y. Zhu, T. Trigano, D. Bykhovsky, Z. Chen, “Deep Learning Based Pile-Up Correction Algorithm for Spectrometric Data Under High-Count-Rate Measurements,” Sensors, vol. 25, no. 5, p. 1464, Feb. 2025. doi:10.3390/s25051464
  • Y. Huang, C. Lin, D. Bykhovsky, T. Trigano, Z. Chen, X. Zheng, Y. Zhu, “Deep Learning Based Energy Spectrum Estimation for High Counting Rate Nuclear Spectrometry,” IEEE Transactions on Instrumentation and Measurement, vol. 74, pp. 1–14, 2025. doi:10.1109/TIM.2025.3573370, accepted manuscript, details
  • C. Lin, X. Zheng, T. Trigano, D. Bykhovsky, Y. Zhu, L. Tian, “Spectroscopic Pulse Embeddings by Contrastive Learning from Unlabeled Data for Pile-Up Analysis,” Sensors, vol. 26, no. 7, p. 2138, Mar. 2026. doi:10.3390/s26072138
  • C. Lin, Z. Chen, C. Feng, S. Gu, X. Zheng, Y. Zhu, T. Trigano, D. Bykhovsky, “An open X-ray spectrometric dataset for deep learning-based pile-up correction,” WASA, Tokyo, Japan, Jun. 2025.
  • C. Lin, Y. Huang, Z. Chen, S. Gu, D. Bykhovsky, T. Trigano, X. Zheng, Y. Zhu, “Semi-Supervised Energy Spectrum Estimation in High Count-Rate Nuclear Spectrometry,” IEEE Transactions on Instrumentation and Measurement, vol. 75, art. no. 2512816, 2026. doi:10.1109/TIM.2026.3706156, accepted manuscript, details

Accepted manuscripts linked above are self-archived under the publishers’ green open-access policies. © IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.