Please use this identifier to cite or link to this item: http://hdl.handle.net/1893/22168
Appears in Collections:Biological and Environmental Sciences Journal Articles
Peer Review Status: Refereed
Title: Remediating radium contaminated legacy sites: Advances made through machine learning in routine monitoring of "hot" particles
Author(s): Varley, Adam
Tyler, Andrew
Smith, Leslie
Dale, Paul
Davies, Mike
Contact Email: a.l.varley@stir.ac.uk
Keywords: Radium remediation
Gamma spectroscopy
“Hot” particles
Machine learning
Monte Carlo
Sodium iodide
Lanthanum bromide
Issue Date: 15-Jul-2015
Date Deposited: 26-Aug-2015
Citation: Varley A, Tyler A, Smith L, Dale P & Davies M (2015) Remediating radium contaminated legacy sites: Advances made through machine learning in routine monitoring of "hot" particles. Science of the Total Environment, 521-522, pp. 270-279. https://doi.org/10.1016/j.scitotenv.2015.03.131
Abstract: The extensive use of radium during the 20th century for industrial, military and pharmaceutical purposes has led to a large number of contaminated legacy sites across Europe and North America. Sites that pose a high risk to the general public can present expensive and long-term remediation projects. Often the most pragmatic remediation approach is through routine monitoring operating gamma-ray detectors to identify, in real-time, the signal from the most hazardous heterogeneous contamination (hot particles); thus facilitating their removal and safe disposal. However, current detection systems do not fully utilise all spectral information resulting in low detection rates and ultimately an increased risk to the human health. The aim of this study was to establish an optimised detector-algorithm combination. To achieve this, field data was collected using two handheld detectors (sodium iodide and lanthanum bromide) and a number of Monte Carlo simulated hot particles were randomly injected into the field data. This allowed for the detection rate of conventional deterministic (gross counts) and machine learning (neural networks and support vector machines) algorithms to be assessed. The results demonstrated that a Neural Network operated on a sodium iodide detector provided the best detection capability. Compared to deterministic approaches, this optimised detection system could detect a hot particle on average 10cm deeper into the soil column or with half of the activity at the same depth. It was also found that noise presented by internal contamination restricted lanthanum bromide for this application.
DOI Link: 10.1016/j.scitotenv.2015.03.131
Rights: The publisher does not allow this work to be made publicly available in this Repository. Please use the Request a Copy feature at the foot of the Repository record to request a copy directly from the author. You can only request a copy if you wish to use this work for your own research or private study.
Licence URL(s): http://www.rioxx.net/licenses/under-embargo-all-rights-reserved

Files in This Item:
File Description SizeFormat 
Varley et al_Science of the Total Environment_2015.pdfFulltext - Published Version1.39 MBAdobe PDFUnder Embargo until 2999-12-04    Request a copy

Note: If any of the files in this item are currently embargoed, you can request a copy directly from the author by clicking the padlock icon above. However, this facility is dependent on the depositor still being contactable at their original email address.



This item is protected by original copyright



Items in the Repository are protected by copyright, with all rights reserved, unless otherwise indicated.

The metadata of the records in the Repository are available under the CC0 public domain dedication: No Rights Reserved https://creativecommons.org/publicdomain/zero/1.0/

If you believe that any material held in STORRE infringes copyright, please contact library@stir.ac.uk providing details and we will remove the Work from public display in STORRE and investigate your claim.