Optimization of LASSO Reconstruction Scheme to Identify Radioactive Sources Based on Monitoring Air Dose Rates

Wei Shi; Masahiko Machida; Susumu Yamada; Koji Okamoto

doi:10.1007/978-981-95-3409-8_4

Optimization of LASSO Reconstruction Scheme to Identify Radioactive Sources Based on Monitoring Air Dose Rates

Wei Shi^*
, Masahiko Machida
, Susumu Yamada
, Koji Okamoto

^*Corresponding author for this work

Department of Mechanical Engineering

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

Abstract

Clarifying the distribution of radioactive sources within nuclear facilities is essential for ensuring worker safety during decommissioning and emergency responses. However, air dose rate measurements are often limited in complex and highly contaminated areas. To address this, we propose an optimized machine learning-based approach using the Least Absolute Shrinkage and Selection Operator (LASSO) for reconstructing radioactive source distributions. While LASSO performs well in simple room models, its accuracy diminishes in more complex environments due to obstacles and shielding effects. To overcome this, we developed an optimized LASSO scheme that normalizes radioactive contributions from sources, mitigating the impact of shielding. Numerical simulations demonstrate that the optimized approach significantly improves reconstruction accuracy compared to the non-optimized version. Experimental validation in a complex room further confirms the effectiveness of the method. This optimized LASSO scheme shows promise for future applications in monitoring and decommissioning nuclear facilities, providing high accuracy in both operational and damaged environments. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.

Original language	English
Title of host publication	Proceedings of the 32nd International Conference on Nuclear Engineering—Volume 13; ICONE 2025
Subtitle of host publication	Decontamination and Decommissioning, Radiation Protection, and Waste Management
Editors	Sichao Tan, Weiqiang Xu, Yanyan Zhu
Publisher	Springer Singapore
Chapter	4
Pages	39-50
Number of pages	12
ISBN (Electronic)	978-981-95-3409-8
ISBN (Print)	978-981-95-3411-1, 978-981-95-3408-1
DOIs	https://doi.org/10.1007/978-981-95-3409-8_4
Publication status	Published - 2026
Event	32nd International Conference on Nuclear Engineering (ICONE 2025) - Weihai, China Duration: 22 Jun 2025 → 26 Jun 2025 https://event.asme.org/ICONE http://icone32.ns.org.cn/index/www/index/ids/1?lang=en

Publication series

Name	Springer Proceedings in Physics
Volume	340
ISSN (Print)	0930-8989
ISSN (Electronic)	1867-4941

Conference

Conference	32nd International Conference on Nuclear Engineering (ICONE 2025)
Abbreviated title	ICONE 32
Place	China
City	Weihai
Period	22/06/25 → 26/06/25
Internet address	https://event.asme.org/ICONE http://icone32.ns.org.cn/index/www/index/ids/1?lang=en

Funding

This work is supported by “Joint research plan using machine learning technology for inverse estimation of radiation sources in nuclear power plant buildings” between Center for Computational Science and e-systems, Japan Atomic Energy Agency, and Dep. Nuclear Eng. and Man., Tokyo University. This work was also partially performed by the funds from the National Natural Science Foundation of China program “A framework for fusing risk identification with optimal defense in cyber risk assessment of cyber-physical system based on uncertainty analysis” (Grant No. 72101221).

Access Output

10.1007/978-981-95-3409-8_4

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Shi, W., Machida, M., Yamada, S., & Okamoto, K. (2026). Optimization of LASSO Reconstruction Scheme to Identify Radioactive Sources Based on Monitoring Air Dose Rates. In S. Tan, W. Xu, & Y. Zhu (Eds.), Proceedings of the 32nd International Conference on Nuclear Engineering—Volume 13; ICONE 2025: Decontamination and Decommissioning, Radiation Protection, and Waste Management (pp. 39-50). (Springer Proceedings in Physics; Vol. 340). Springer Singapore. https://doi.org/10.1007/978-981-95-3409-8_4

Shi, Wei ; Machida, Masahiko ; Yamada, Susumu et al. / Optimization of LASSO Reconstruction Scheme to Identify Radioactive Sources Based on Monitoring Air Dose Rates. Proceedings of the 32nd International Conference on Nuclear Engineering—Volume 13; ICONE 2025: Decontamination and Decommissioning, Radiation Protection, and Waste Management. editor / Sichao Tan ; Weiqiang Xu ; Yanyan Zhu. Springer Singapore, 2026. pp. 39-50 (Springer Proceedings in Physics).

@inproceedings{bcb4a70dcbfd4c988c4e6937cf36778e,

title = "Optimization of LASSO Reconstruction Scheme to Identify Radioactive Sources Based on Monitoring Air Dose Rates",

abstract = "Clarifying the distribution of radioactive sources within nuclear facilities is essential for ensuring worker safety during decommissioning and emergency responses. However, air dose rate measurements are often limited in complex and highly contaminated areas. To address this, we propose an optimized machine learning-based approach using the Least Absolute Shrinkage and Selection Operator (LASSO) for reconstructing radioactive source distributions. While LASSO performs well in simple room models, its accuracy diminishes in more complex environments due to obstacles and shielding effects. To overcome this, we developed an optimized LASSO scheme that normalizes radioactive contributions from sources, mitigating the impact of shielding. Numerical simulations demonstrate that the optimized approach significantly improves reconstruction accuracy compared to the non-optimized version. Experimental validation in a complex room further confirms the effectiveness of the method. This optimized LASSO scheme shows promise for future applications in monitoring and decommissioning nuclear facilities, providing high accuracy in both operational and damaged environments. {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.",

author = "Wei Shi and Masahiko Machida and Susumu Yamada and Koji Okamoto",

year = "2026",

doi = "10.1007/978-981-95-3409-8\_4",

language = "English",

isbn = "978-981-95-3411-1",

series = "Springer Proceedings in Physics",

publisher = "Springer Singapore",

pages = "39--50",

editor = "Sichao Tan and Weiqiang Xu and Yanyan Zhu",

booktitle = "Proceedings of the 32nd International Conference on Nuclear Engineering—Volume 13; ICONE 2025",

address = "Singapore",

note = "32nd International Conference on Nuclear Engineering (ICONE 2025), ICONE 32 ; Conference date: 22-06-2025 Through 26-06-2025",

url = "https://event.asme.org/ICONE, http://icone32.ns.org.cn/index/www/index/ids/1?lang=en",

}

Shi, W, Machida, M, Yamada, S & Okamoto, K 2026, Optimization of LASSO Reconstruction Scheme to Identify Radioactive Sources Based on Monitoring Air Dose Rates. in S Tan, W Xu & Y Zhu (eds), Proceedings of the 32nd International Conference on Nuclear Engineering—Volume 13; ICONE 2025: Decontamination and Decommissioning, Radiation Protection, and Waste Management. Springer Proceedings in Physics, vol. 340, Springer Singapore, pp. 39-50, 32nd International Conference on Nuclear Engineering (ICONE 2025), Weihai, China, 22/06/25. https://doi.org/10.1007/978-981-95-3409-8_4

Optimization of LASSO Reconstruction Scheme to Identify Radioactive Sources Based on Monitoring Air Dose Rates. / Shi, Wei; Machida, Masahiko; Yamada, Susumu et al.
Proceedings of the 32nd International Conference on Nuclear Engineering—Volume 13; ICONE 2025: Decontamination and Decommissioning, Radiation Protection, and Waste Management. ed. / Sichao Tan; Weiqiang Xu; Yanyan Zhu. Springer Singapore, 2026. p. 39-50 (Springer Proceedings in Physics; Vol. 340).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Optimization of LASSO Reconstruction Scheme to Identify Radioactive Sources Based on Monitoring Air Dose Rates

AU - Shi, Wei

AU - Machida, Masahiko

AU - Yamada, Susumu

AU - Okamoto, Koji

PY - 2026

Y1 - 2026

N2 - Clarifying the distribution of radioactive sources within nuclear facilities is essential for ensuring worker safety during decommissioning and emergency responses. However, air dose rate measurements are often limited in complex and highly contaminated areas. To address this, we propose an optimized machine learning-based approach using the Least Absolute Shrinkage and Selection Operator (LASSO) for reconstructing radioactive source distributions. While LASSO performs well in simple room models, its accuracy diminishes in more complex environments due to obstacles and shielding effects. To overcome this, we developed an optimized LASSO scheme that normalizes radioactive contributions from sources, mitigating the impact of shielding. Numerical simulations demonstrate that the optimized approach significantly improves reconstruction accuracy compared to the non-optimized version. Experimental validation in a complex room further confirms the effectiveness of the method. This optimized LASSO scheme shows promise for future applications in monitoring and decommissioning nuclear facilities, providing high accuracy in both operational and damaged environments. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.

AB - Clarifying the distribution of radioactive sources within nuclear facilities is essential for ensuring worker safety during decommissioning and emergency responses. However, air dose rate measurements are often limited in complex and highly contaminated areas. To address this, we propose an optimized machine learning-based approach using the Least Absolute Shrinkage and Selection Operator (LASSO) for reconstructing radioactive source distributions. While LASSO performs well in simple room models, its accuracy diminishes in more complex environments due to obstacles and shielding effects. To overcome this, we developed an optimized LASSO scheme that normalizes radioactive contributions from sources, mitigating the impact of shielding. Numerical simulations demonstrate that the optimized approach significantly improves reconstruction accuracy compared to the non-optimized version. Experimental validation in a complex room further confirms the effectiveness of the method. This optimized LASSO scheme shows promise for future applications in monitoring and decommissioning nuclear facilities, providing high accuracy in both operational and damaged environments. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.

UR - https://www.webofscience.com/wos/woscc/full-record/WOS:001723809400004

U2 - 10.1007/978-981-95-3409-8_4

DO - 10.1007/978-981-95-3409-8_4

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 978-981-95-3411-1

SN - 978-981-95-3408-1

T3 - Springer Proceedings in Physics

SP - 39

EP - 50

BT - Proceedings of the 32nd International Conference on Nuclear Engineering—Volume 13; ICONE 2025

A2 - Tan, Sichao

A2 - Xu, Weiqiang

A2 - Zhu, Yanyan

PB - Springer Singapore

T2 - 32nd International Conference on Nuclear Engineering (ICONE 2025)

Y2 - 22 June 2025 through 26 June 2025

ER -

Shi W, Machida M, Yamada S, Okamoto K. Optimization of LASSO Reconstruction Scheme to Identify Radioactive Sources Based on Monitoring Air Dose Rates. In Tan S, Xu W, Zhu Y, editors, Proceedings of the 32nd International Conference on Nuclear Engineering—Volume 13; ICONE 2025: Decontamination and Decommissioning, Radiation Protection, and Waste Management. Springer Singapore. 2026. p. 39-50. (Springer Proceedings in Physics). Epub 2026 Jan 2. doi: 10.1007/978-981-95-3409-8_4

Optimization of LASSO Reconstruction Scheme to Identify Radioactive Sources Based on Monitoring Air Dose Rates

Abstract

Publication series

Conference

Funding

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this