A new approach for quantifying morphological features of U3O8 for nuclear forensics using a deep learning model

Ly, Cuong; Olsen, Adam M.; Schwerdt, Ian J.; Porter, Reid B.; Sentz, Kari; McDonald, Luther W.; Taşdizen, Tolga

doi:10.1016/j.jnucmat.2019.01.042

Cited by 23 publications

(9 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Apart from traditional laboratory experiments and computational material simulation approaches, artificial Intelligence (AI) could be an alternative approach that is able to address the material design challenges mentioned above. For example, ML methods have already managed to (1) automate materials' characterization processes and effectively analyze the characterization dataset, [18][19][20][21] (2) quickly screen the vast material design space (e.g., reducing the prediction time of DFT from 10 3 s to 10 À2 s), [22][23][24][25] (3) realize property prediction in complex material systems with limited first-principles understanding, 26 (4) directly map high-dimensional synthesis recipes to materials with desired properties, 27,28 and (5) extract generalizable scientific principles from various material systems. 27,29,30 The reason why AI is particularly apt in material design is due to its inherently strong capabilities in handling huge amounts of data as well as high-dimensional analysis.…”

Section: Progress and Potentialmentioning

confidence: 99%

AI Applications through the Whole Life Cycle of Material Discovery

Lim

Yang

et al. 2020

Matter

101

View full text Add to dashboard Cite

We provide a review of machine learning (ML) tools for material discovery and sophisticated applications of different ML strategies. Although there have been a few published reviews on artificial intelligence (AI) for materials with an emphasis on a single material system or individual methods, this paper focuses on an applicationbased perspective in AI-enhanced material discovery. It shows how AI strategies are applied through material discovery stages (including characterization, property prediction, synthesis, and theory paradigm discovery). Also, by referring to the ML tutorial, readers can acquire a better understanding of the exact functions of ML methods in each application and how these methods work to realize the targets. We are aiming to enable a better integration of AI methods with the material discovery process. The keys to successful applications of AI in material discovery and challenges to be addressed are also highlighted.

show abstract

Section: Progress and Potentialmentioning

confidence: 99%

AI Applications through the Whole Life Cycle of Material Discovery

Lim

Yang

et al. 2020

Matter

101

View full text Add to dashboard Cite

show abstract

“…In particular, recent research has examined the morphology of various uranium oxides, with a focus on discerning process history or process conditions for a particular sample of material. [20][21][22][23][24][25][26][27][28][29][30][31][32]46 One outcome of these efforts was a lexicon to standardize descriptions of material images for nuclear forensics, indicating a likely increasing role for morphology within nuclear forensics. 33 Recent research has also investigated elemental and chemical impurities present in process samples of uranium compounds, also with a focus of discerning process history as well as the origin of the uranium.…”

Section: ■ Introductionmentioning

confidence: 99%

Progress in Uranium Chemistry: Driving Advances in Front-End Nuclear Fuel Cycle Forensics

et al. 2021

View full text Add to dashboard Cite

The front-end of the nuclear fuel cycle encompasses several chemical and physical processes used to acquire and prepare uranium for use in a nuclear reactor. These same processes can also be used for weapons or nefarious purposes, necessitating the need for technical means to help detect, investigate, and prevent the nefarious use of nuclear material and nuclear fuel cycle technology. Over the past decade, a significant research effort has investigated uranium compounds associated with the front-end of the nuclear fuel cycle, including uranium ore concentrates (UOCs), UF 4 , UF 6 , and UO 2 F 2 . These efforts have furthered uranium chemistry with an aim to expand and improve the field of nuclear forensics. Focus has been given to the morphology of various uranium compounds, trace elemental and chemical impurities in process samples of uranium compounds, the degradation of uranium compounds, particularly under environmental conditions, and the development of improved or new techniques for analysis of uranium compounds. Overall, this research effort has identified relevant chemical and physical characteristics of uranium compounds that can be used to help discern the origin, process history, and postproduction history for a sample of uranium material. This effort has also identified analytical techniques that could be brought to bear for nuclear forensics purposes. Continued research into these uranium compounds should yield additional relevant chemical and physical characteristics and analytical approaches to further advance front-end nuclear fuel cycle forensics capabilities.

show abstract

“…Figure 1 highlights some example SEM images acquired from nuclear materials. The left image is the raw unprocessed SEM image and the right image is the image following manual particle segmentation using the Morphological Analysis of Materials (MAMA) software [2,[8][9][10]. Morphological features are proving to be useful signatures to infer the chemical processing histories (which relate to forensics goals [1][2][3]) of uranium oxides.…”

Section: Introductionmentioning

confidence: 99%

“…Manual segmentation (locating, recognizing, and assigning boundaries to particles) requires significant time-consuming user inputs to only segment fully visible particles. An alternative automated segmentation method using a deep learning model (a U-net based on convolutional neural networks) was shown in [8] to effectively segment fully visible particles (see also Reference [11] for another segmentation option); however, this paper's focus is on inferring processing conditions using currently-available segmentation software, such as MAMA, that can also provide the 22 quantitative particle morphological metrics. This review paper illustrates statistical issues using 22 quantitative morphological metrics (Appendix A describes these 22 metrics) derived from the analysis of scanning electron microscopy images (SEM) of each segmented particle [2,4,5].…”

Section: Introductionmentioning

confidence: 99%

Overview of Algorithms for Using Particle Morphology in Pre-Detonation Nuclear Forensics

et al. 2021

Self Cite

View full text Add to dashboard Cite

A major goal in pre-detonation nuclear forensics is to infer the processing conditions and/or facility type that produced radiological material. This review paper focuses on analyses of particle size, shape, texture (“morphology”) signatures that could provide information on the provenance of interdicted materials. For example, uranium ore concentrates (UOC or yellowcake) include ammonium diuranate (ADU), ammonium uranyl carbonate (AUC), sodium diuranate (SDU), magnesium diuranate (MDU), and others, each prepared using different salts to precipitate U from solution. Once precipitated, UOCs are often dried and calcined to remove adsorbed water. The products can be allowed to react further, forming uranium oxides UO3, U3O8, or UO2 powders, whose surface morphology can be indicative of precipitation and/or calcination conditions used in their production. This review paper describes statistical issues and approaches in using quantitative analyses of measurements such as particle size and shape to infer production conditions. Statistical topics include multivariate t tests (Hotelling’s T2), design of experiments, and several machine learning (ML) options including decision trees, learning vector quantization neural networks, mixture discriminant analysis, and approximate Bayesian computation (ABC). ABC is emphasized as an attractive option to include the effects of model uncertainty in the selected and fitted forward model used for inferring processing conditions.

show abstract

A new approach for quantifying morphological features of U3O8 for nuclear forensics using a deep learning model

Cited by 23 publications

References 14 publications

AI Applications through the Whole Life Cycle of Material Discovery

AI Applications through the Whole Life Cycle of Material Discovery

Progress in Uranium Chemistry: Driving Advances in Front-End Nuclear Fuel Cycle Forensics

Overview of Algorithms for Using Particle Morphology in Pre-Detonation Nuclear Forensics

Contact Info

Product

Resources

About