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

Integrating artificial intelligence, machine learning, and deep learning approaches into remediation of contaminated sites: A review

The growing number of contaminated sites across the world pose a considerable threat to the environment and human health. Remediating such sites is a cumbersome process with the complexity originating from the need for extensive sampling and testing during site characterization. Selection and design of remediation technology is further complicated by the uncertainties surrounding contaminant attributes, concentration, as well as soil and groundwater properties, which influence the remediation efficiency. Additionally, challenges emerge in identifying contamination sources and monitoring the affected area. Often, these problems are overly simplified, and the data gathered is underutilized rendering the remediation process inefficient. The potential of artificial intelligence (AI), machine-learning (ML), and deep-learning (DL) to address these issues is noteworthy, as their emergence revolutionized the process of data management/analysis. Researchers across the world are increasingly leveraging AI/ML/DL to address remediation challenges. Current study aims to perform a comprehensive literature review on the integration of AI/ML/DL tools into contaminated site remediation. A brief introduction to various emerging and existing AI/ML/DL technologies is presented, followed by a comprehensive literature review. In essence, ML/DL based predictive models can facilitate a thorough understanding of contamination patterns, reducing the need for extensive soil and groundwater sampling. Additionally, AI/ML/DL algorithms can play a pivotal role in identifying optimal remediation strategies by analyzing historical data, simulating scenarios through surrogate models, parameter-optimization using nature inspired algorithms, and enhancing decision-making with AI-based tools. Overall, with supportive measures like open-data policies and data integration, AI/ML/DL possess the potential to revolutionize the practice of contaminated site remediation.

Preliminary risk assessment of regional industrial enterprise sites based on big data

An accurate and inexpensive preliminary risk assessment of industrial enterprise sites at a regional scale is critical for environmental management. In this study, we propose a novel framework for the preliminary risk assessment of industrial enterprise sites in the Yangtze River Delta, which is one of the fastest economic development and most prominent contaminated regions in China. Based on source-pathway-receptors, this framework integrated text and spatial analyses and machine learning, and its feasibility was validated with 8848 positive and negative samples with a calibration and validation set ratio of 8:2. The results indicated that the random forest performed well for risk assessment; and its accuracy, precision, recall, and F1 scores in the calibration set were all 1.0, and the four indicators for the validation set ranged from 0.97 to 0.98, which was better than that for the other models (e.g., logistic regression, support vector machine, and convolutional neural network). The preliminary risk ranking of industrial enterprise sites by the random forest showed that high risks (probabilities) were mainly distributed in Shanghai, southern Jiangsu, and northeastern Zhejiang from 2000 to 2015. The relative importance of the site industrial, production, and geographical features in the random forest was 69%, 22%, and 9%, respectively. Our study highlights that we could quickly and effectively establish a priority (or ranking) list of industrial enterprise sites that require further investigations, using the proposed framework, and identify potentially contaminated sites.

Optimization and validation of a LaBr3(Ce) detector model for use in Monte Carlo simulations

A reliable detector model is needed for Monte Carlo efficiency calibration. A LaBr₃(Ce) detector model was optimized and verified using different radioactive sources (²⁴¹Am,¹³³Ba,¹³⁷Cs,⁶⁰Co and¹⁵²Eu) and geometries (point, extended and surface). PENELOPE and MCNP were used for Monte Carlo simulations. A good agreement was observed between simulated and experimental full energy peak efficiencies (FEPE) as their mean relative difference was 2.84% ± 1.93% and 2.79% ± 1.99% for PENELOPE and MCNP simulation, respectively. The differences between simulated FEPEs of two Monte Carlo codes were negligible except for low energies (< 100 keV).

Radon Off-Gassing From Military Artifacts

Military historical artifacts found in museum displays and storage locations were analyzed for their Ra and Rn progeny activities to determine the fraction of Rn lost to the environment. Gamma-ray spectroscopy using high-purity germanium detectors was used to determine Ra activity and infer Rn activity based on Pb and Bi. Analyses were conducted without affecting the structural integrity of the artifacts. Ra was measured directly after correction for solid angle and finite sample-detector distance. Although Rn can be similarly analyzed, the collection in charcoal of Rn off-gassed from the artifact after the establishment of secular equilibrium was preferable. Rn off-gassing rates vary greatly between the six devices studied, with a maximum off-gassing rate of 1,850 ± 50 Bq h. Large variations in off-gassing rate were also observed between an additional 30 nominally identical dials, with a mean and standard deviation of 7.7 ± 7.1 Bq h. The work is not predictive of airborne Rn activity within museums, where building size and ventilation are significant and unique to each location. However, the significant off-gassing rates and their large variation suggest that Rn activities may be elevated in enclosed locations, such as aircraft cockpits and storage facilities.

Integration of Ground- Penetrating Radar and Gamma-Ray Detectors for Nonintrusive Characterisation of Buried Radioactive Objects

The characterisation of buried radioactive wastes is challenging because they are not readily accessible. Therefore, this study reports on the development of a method for integrating ground-penetrating radar (GPR) and gamma-ray detector measurements for nonintrusive characterisation of buried radioactive objects. The method makes use of the density relationship between soil permittivity models and the flux measured by gamma ray detectors to estimate the soil density, depth and radius of a disk-shaped buried radioactive object simultaneously. The method was validated using numerical simulations with experimentally-validated gamma-ray detector and GPR antenna models. The results showed that the method can simultaneously retrieve the soil density, depth and radius of disk-shaped radioactive objects buried in soil of varying conditions with a relative error of less than 10%. This result will enable the development of an integrated GPR and gamma ray detector tool for rapid characterisation of buried radioactive objects encountered during monitoring and decontamination of nuclear sites and facilities.

Nonintrusive Depth Estimation of Buried Radioactive Wastes Using Ground Penetrating Radar and a Gamma Ray Detector

This study reports on the combination of data from a ground penetrating radar (GPR) and a gamma ray detector for nonintrusive depth estimation of buried radioactive sources. The use of the GPR was to enable the estimation of the material density required for the calculation of the depth of the source from the radiation data. Four different models for bulk density estimation were analysed using three materials, namely: sand, gravel and soil. The results showed that the GPR was able to estimate the bulk density of the three materials with an average error of 4.5%. The density estimates were then used together with gamma ray measurements to successfully estimate the depth of a 658 kBq ceasium-137 radioactive source buried in each of the three materials investigated. However, a linear correction factor needs to be applied to the depth estimates due to the deviation of the estimated depth from the measured depth as the depth increases. This new application of GPR will further extend the possible fields of application of this ubiquitous geophysical tool.

An in situ method for the high resolution mapping of 137Cs and estimation of vertical depth penetration in a highly contaminated environment

The Chernobyl nuclear power plant meltdown has to date been the single largest release of radioactivity into the environment. As a result, radioactive contamination that poses a significant threat to human health still persists across much of Europe with the highest concentrations associated with Belarus, Ukraine, and western Russia. Of the radionuclides still prevalent with these territories ¹³⁷Cs presents one of the most problematic remediation challenges. Principally, this is due to the localised spatial and vertical heterogeneity of contamination within the soil (~10's of meters), thus making it difficult to accurately characterise through conventional measurement techniques such as static in situ gamma-ray spectrometry or soil cores. Here, a practical solution has been explored, which utilises a large number of short-count time spectral measurements made using relatively inexpensive, lightweight, scintillators (sodium iodide and lanthanum bromide). This approach offers the added advantage of being able to estimate activity and burial depth of ¹³⁷Cs contamination in much higher spatial resolution compared to traditional approaches. During the course of this work, detectors were calibrated using the Monte Carlo Simulations and depth distribution was estimated using the peak-to-valley ratio. Activity and depth estimates were then compared to five reference sites characterised using soil cores. Estimates were in good agreement with the reference sites, differences of ~25% and ~50% in total inventory were found for the three higher and two lower activity sites, respectively. It was concluded that slightly longer count times would be required for the lower activity (<1MBqm^-2) sites. Modelling and reference site results suggest little advantage would be gained through the use of the substantially more expensive lanthanum bromide detector over the sodium iodide detector. Finally, the potential of the approach was demonstrated by mapping one of the sites and its surrounding area in high spatial resolution.

A Methodology to Evaluate Ecological Resources and Risk Using Two Case Studies at the Department of Energy's Hanford Site

An assessment of the potential risks to ecological resources from remediation activities or other perturbations should involve a quantitative evaluation of resources on the remediation site and in the surrounding environment. We developed a risk methodology to rapidly evaluate potential impact on ecological resources for the U.S. Department of Energy's Hanford Site in southcentral Washington State. We describe the application of the risk evaluation for two case studies to illustrate its applicability. The ecological assessment involves examining previous sources of information for the site, defining different resource levels from 0 to 5. We also developed a risk rating scale from non-discernable to very high. Field assessment is the critical step to determine resource levels or to determine if current conditions are the same as previously evaluated. We provide a rapid assessment method for current ecological conditions that can be compared to previous site-specific data, or that can be used to assess resource value on other sites where ecological information is not generally available. The method is applicable to other Department of Energy's sites, where its development may involve a range of state regulators, resource trustees, Tribes and other stakeholders. Achieving consistency across Department of Energy's sites for valuation of ecological resources on remediation sites will assure Congress and the public that funds and personnel are being deployed appropriately.

Mapping the spatial distribution and activity of (226)Ra at legacy sites through Machine Learning interpretation of gamma-ray spectrometry data

Radium ((226)Ra) contamination derived from military, industrial, and pharmaceutical products can be found at a number of historical sites across the world posing a risk to human health. The analysis of spectral data derived using gamma-ray spectrometry can offer a powerful tool to rapidly estimate and map the activity, depth, and lateral distribution of (226)Ra contamination covering an extensive area. Subsequently, reliable risk assessments can be developed for individual sites in a fraction of the timeframe compared to traditional labour-intensive sampling techniques: for example soil coring. However, local heterogeneity of the natural background, statistical counting uncertainty, and non-linear source response are confounding problems associated with gamma-ray spectral analysis. This is particularly challenging, when attempting to deal with enhanced concentrations of a naturally occurring radionuclide such as (226)Ra. As a result, conventional surveys tend to attribute the highest activities to the largest total signal received by a detector (Gross counts): an assumption that tends to neglect higher activities at depth. To overcome these limitations, a methodology was developed making use of Monte Carlo simulations, Principal Component Analysis and Machine Learning based algorithms to derive depth and activity estimates for (226)Ra contamination. The approach was applied on spectra taken using two gamma-ray detectors (Lanthanum Bromide and Sodium Iodide), with the aim of identifying an optimised combination of detector and spectral processing routine. It was confirmed that, through a combination of Neural Networks and Lanthanum Bromide, the most accurate depth and activity estimates could be found. The advantage of the method was demonstrated by mapping depth and activity estimates at a case study site in Scotland. There the method identified significantly higher activity (<3 Bq g(-1)) occurring at depth (>0.4m), that conventional gross counting algorithms failed to identify. It was concluded that the method could easily be employed to identify areas of high activity potentially occurring at depth, prior to intrusive investigation using conventional sampling techniques.