Artificial intelligence methods applied for quantitative analysis of natural radioactive sources

X-ray dose profiles using artificial neural networks

This paper introduces a novel computational method to simulate and predict radiation dose profiles in a water phantom irradiated by X-rays of 6 and 15 MV at different depths and field sizes using Artificial Neural Networks within the error margin required by the code of practice 398 of the International Atomic Energy Agency (IAEA). Our method uses deep-learning Artificial Neural Networks as an alternative to the Monte Carlo methods usually used nowadays. It reproduces the radiation dose profiles for X-rays of 6 and 15 MV data reported in the British Journal of Radiology (Aird, 1996). Even more, our method reproduces data from other sources with acceptable errors. These simulations pave the way to enhance radiotherapy techniques in planning patient doses and calibrating ionizing radiation measurement instruments used in the fight against cancer.

Artificial neural network modeling in environmental radioactivity studies - A review

The development of nuclear technologies has directed environmental radioactivity research toward continuously improving existing and developing new models for different interpolation, optimization, and classification tasks. Due to their adaptability to new data without knowing the actual modeling function, artificial neural networks (ANNs) are extensively used to resolve the tasks for which the application of traditional statistical methods has not provided an adequate response. This study presents an overview of ANN-based modeling in environmental radioactivity studies, including identifying and quantifying radionuclides, predicting their migration in the environment, mapping their distribution, optimizing measurement methodologies, monitoring processes in nuclear plants, and real-time data analysis. Special attention is paid to highlighting the scope of the different case studies and discussing the techniques used in model development over time. The performances of ANNs are evaluated from the perspective of prediction accuracy, emphasizing the advantages and limitations encountered in their use. The most critical elements in model optimization were identified as network structure, selection of input parameters, the properties of input data set, and applied learning algorithm. The analysis of strategies and methods for improving the performance of ANNs has shown that developing integrated and hybrid artificial intelligent tools could provide a new path in environmental radioactivity modeling toward more reliable outcomes and higher accuracy predictions. The review highlights the potential of neural networks and challenges in their application in environmental radioactivity studies and proposes directions for future research.

State-of-the-Art Mobile Radiation Detection Systems for Different Scenarios

In the last decade, the development of more compact and lightweight radiation detection systems led to their application in handheld and small unmanned systems, particularly air-based platforms. Examples of improvements are: the use of silicon photomultiplier-based scintillators, new scintillating crystals, compact dual-mode detectors (gamma/neutron), data fusion, mobile sensor networks, cooperative detection and search. Gamma cameras and dual-particle cameras are increasingly being used for source location. This study reviews and discusses the research advancements in the field of gamma-ray and neutron measurements using mobile radiation detection systems since the Fukushima nuclear accident. Four scenarios are considered: radiological and nuclear accidents and emergencies; illicit traffic of special nuclear materials and radioactive materials; nuclear, accelerator, targets, and irradiation facilities; and naturally occurring radioactive materials monitoring-related activities. The work presented in this paper aims to: compile and review information on the radiation detection systems, contextual sensors and platforms used for each scenario; assess their advantages and limitations, looking prospectively to new research and challenges in the field; and support the decision making of national radioprotection agencies and response teams in respect to adequate detection system for each scenario. For that, an extensive literature review was conducted.

Simultaneous quantitative analysis of 3H and 14C radionuclides in aqueous samples via artificial neural network with a liquid scintillation counter

Liquid scintillation counters are common instruments used in the measurement of pure beta-emitting radionuclides, and while they represent a conventional radiometric technique, they are still competitive for their potential to measure multiple radionuclides simultaneously. In this work, we propose an algorithm based on an artificial neural network (ANN) for the simultaneous analysis of the beta-ray spectra of ³H and ¹⁴C in dual beta-labeled samples using a liquid scintillation counter. We achieved percentage deviations below 5.0% using the proposed algorithm in 16 out of 18 cases, with RMSDs below 1.5% in 17 out of 18 cases. The trained ANN also produced activity ratios with high accuracy even while having to deal with highly fluctuating spectra. Results demonstrate that the rapid predictions with a short measurement time from our proposed ANN method are compatible with the calculated ones from previous studies that were obtained with long measurement times.

Unmanned Aerial System Integrated Sensor for Remote Gamma and Neutron Monitoring

Tools for remote radiation sensing are essential for environmental safety and nuclear power applications. The use of unmanned aerial systems (UASs) equipped with sensors allows for substantially reducing the radiation exposure of personnel. An ambient temperature Cs₂LiYCl₆:Ce³⁺ (CLYC) elpasolite scintillation sensor for simultaneous gamma and neutron measurements was designed as a user-friendly "plug and fly" module integrated into an octocopter robotic platform. Robot Operating System (ROS) was used to analyze the sensor's data. The measured CLYC's energy resolution was <5% at 662 keV gamma rays; neutron flux was measured using ⁶Li(n,α)t reaction. Time and GPS data were combined with radiation data in the ROS, supporting real time monitoring and assessment tasks, as well as radiation source search missions. Because UASs can be irradiated, radiation damage of the sensor and robot's electronics was estimated using FLUKA code.

Application of neural network method to detect type of uranium contamination by estimation of activity ratio in environmental alpha spectra

The discrimination of the composition of environmental and non-environmental materials by the estimation of the (234)U/(238)U activity ratio in alpha-particle spectrometry is important in many applications. If the interfering elements are not completely separated from the uranium, they can interfere with the determination of (234)U. Thickness as a result of the existence of iron in the source preparation phase and their alpha lines can broaden the alpha line of (234)U in alpha spectra. Therefore, the asymmetric broadening of the alpha line of (234)U and overlapping of peaks make the analysis of the alpha particle spectra and the interpretation of the results difficult. Applying Artificial Neural Network (ANN) to a spectrometry system is a good idea because it eliminates limitations of classical approaches by extracting the desired information from the input data. In this work, the average of a partial uranium raw spectrum, were considered. Each point that its slope was of the order of 0-1% per 10 channels, was used as input to the multi-layer feed forward error-back propagation network. The network was trained by an alpha spectrum library which has been developed in the present work. The training data in this study was actual spectral data with any reasonable thickness and interfering elements. According to the results, the method applied to estimate the activity ratio in this work, can examine the alpha spectrum for peaks which would not be expected for a source of given element and provide the clues about composition of uranium contamination in the environmental samples in a fast screening and classifying procedures.

Evaluation of the suitability of neural network method for prediction of uranium activity ratio in environmental alpha spectra

Applying Artificial Neural Network to an alpha spectrometry system is a good idea to discriminate the composition of environmental and non-environmental materials by the estimation of the (234)U/(238)U activity ratio. Because it eliminates limitations of classical approaches by the extraction the desired information from the average of a partial uranium raw spectrum. The network was trained by an alpha spectrum library which was developed in this work. The results indicated that there was a small difference between the target values and the predictions. These results were acceptable, because the thickness of samples and the inferring elements were different in the real library.

Remediating radium contaminated legacy sites: Advances made through machine learning in routine monitoring of "hot" particles

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.

Development of a neural network approach to characterise (226)Ra contamination at legacy sites using gamma-ray spectra taken from boreholes

There are a large number of sites across the UK and the rest of the world that are known to be contaminated with (226)Ra owing to historical industrial and military activities. At some sites, where there is a realistic risk of contact with the general public there is a demand for proficient risk assessments to be undertaken. One of the governing factors that influence such assessments is the geometric nature of contamination particularly if hazardous high activity point sources are present. Often this type of radioactive particle is encountered at depths beyond the capabilities of surface gamma-ray techniques and so intrusive borehole methods provide a more suitable approach. However, reliable spectral processing methods to investigate the properties of the waste for this type of measurement have yet to be developed since a number of issues must first be confronted including: representative calibration spectra, variations in background activity and counting uncertainty. Here a novel method is proposed to tackle this issue based upon the interrogation of characteristic Monte Carlo calibration spectra using a combination of Principal Component Analysis and Artificial Neural Networks. The technique demonstrated that it could reliably distinguish spectra that contained contributions from point sources from those of background or dissociated contamination (homogenously distributed). The potential of the method was demonstrated by interpretation of borehole spectra collected at the Dalgety Bay headland, Fife, Scotland. Predictions concurred with intrusive surveys despite the realisation of relatively large uncertainties on activity and depth estimates. To reduce this uncertainty, a larger background sample and better spatial coverage of cores were required, alongside a higher volume better resolution detector.

Analysis of (7)Be behaviour in the air by using a multilayer perceptron neural network

A multilayer perceptron artificial neural network (ANN) model for the prediction of the (7)Be behaviour in the air as the function of meteorological parameters was developed. The model was optimized and tested using (7)Be activity concentrations obtained by standard gamma-ray spectrometric analysis of air samples collected in Belgrade (Serbia) during 2009-2011 and meteorological data for the same period. Good correlation (r = 0.91) between experimental values of (7)Be activity concentrations and those predicted by ANN was obtained. The good performance of the model in prediction of (7)Be activity concentrations could provide basis for construction of models which would forecast behaviour of other airborne radionuclides.