Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Selective classification”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 451 records · Page 25

Impact of including second and later cancers in cause-specific survival estimates using population-based registry data

Background. Second or later primary cancers account for approximately 20% of incident cases in the United States. Currently, cause-specific survival (CSS) analyses exclude these cancers because the cause of death (COD) classification algorithm was available only for first cancers. The authors added rules for later cancers to the Surveillance, Epidemiology, and End Results cause-specific death classification algorithm and evaluated CSS to include individuals with prior tumors. Methods. The authors constructed 2 cohorts: 1) the first ever primary cohort, including patients whose first cancer was diagnosed during 2000 through 2016) and 2) the earliest matching primary cohort, including patients with any cancer who matched the selection criteria irrespective of whether it was the first or a later cancer diagnosed during 2000 through 2016. The cohorts' CSS estimates were compared using follow-up through December 31, 2017. The new rules were used in the second cohort for patients whose first cancers during 2000 through 2016 were their second or later cancers. Results. Overall, there were no statistically significant differences in CSS estimates between the 2 cohorts. Estimates were similar by age, stage, race, and time since diagnosis, except for patients with leukemia and those aged 65 to 74 years (3.4 percentage point absolute difference). Conclusions. The absolute difference in CSS estimates for the first cancer ever cohort versus earliest of any cancers cohort in the study period was small for most cancer types. As the number of newly diagnosed patients with prior cancers increases, the algorithm will make CSS more inclusive and enable estimating survival for a group of patients with cancer for whom life tables are not available or life tables are available but do not capture other-cause mortality appropriately.

Survival Analysis↗

DETECTING VARIABILITY IN MASSIVE ASTRONOMICAL TIME-SERIES DATA. II. VARIABLE CANDIDATES IN THE NORTHERN SKY VARIABILITY SURVEY

We present variability analysis of data from the Northern Sky Variability Survey (NSVS). Using the clustering method, which defines variable candidates as outliers from large clusters, we cluster 16,189,040 light curves having data points at more than 15 epochs as variable and non-variable candidates in 638 NSVS fields. Variable candidates are selected depending on how strongly they are separated from the largest cluster and how rarely they are grouped together in eight-dimensional space spanned by variability indices. All NSVS light curves are also cross-correlated with IRAS, AKARI, Two Micron All Sky Survey, Sloan Digital Sky Survey (SDSS), and GALEX objects, as well as known objects in the SIMBAD database. The variability analysis and cross-correlation results are provided in a public online database, which can be used to select interesting objects for further investigation. Adopting conservative selection criteria for variable candidates, we find about 1.8 million light curves as possible variable candidates in the NSVS data, corresponding to about 10% of our entire NSVS sample. Multi-wavelength colors help us find specific types of variability among the variable candidates. Moreover, we also use morphological classification from other surveys such as SDSS to suppress spurious cases caused by blending objects or extended sources due to the low angular resolution of the NSVS.

79 ASTRONOMY AND ASTROPHYSICS↗

One-shot gas detection with transformer paired neural networks in Mako collected longwave infrared hyperspectral imagery

To date, careful data treatment workflows and statistical detectors are used to perform hyperspectral image (HSI) detection of any gas contained in a spectral library, which is often expanded with physics models to incorporate different spectral characteristics. In general, surrounding evidence or known gas-release parameters are used to provide confidence in or confirm detection capability, respectively. This makes quantifying detection performance difficult as it is nearly impossible to develop an absolute ground truth for gas target pixel presence in collected HSI. Consequently, developing and comparing new detection methods, especially machine learning (ML)-based methods, is susceptible to subjectivity in derived detection map quality. Here, in this work, we demonstrate the first use of transformer-based paired neural networks (PNNs) for one-shot gas target detection for multiple gases while providing quantitative classification and detection metrics for their use on labeled data. Terabytes of training data are generated from a database of long-wave infrared HSI obtained from historical Mako sensor campaigns over Los Angeles. By incorporating labels, singular signature representations, and a model development pipeline, we can tune and select PNNs to detect multiple gas targets that are not seen in training on a quantitative basis. We additionally assess our test set detections using interpretability techniques widely employed with ML-based predictors, but less common with detection methods relying on learned latent spaces.

Hyperspectral imaging↗

Deep Learning for Automated Identification of Eels in Sonar Data

Freshwater eels, such as the American eel (Anguilla rostrata) present numerous challenges related to safe downstream fish passage at hydroelectric facilities. One of those challenges is effective monitoring of their abundance, movements, and behavior to facilitate design and operation of eel protection and passage facilities. A previous EPRI study documented the ability of human analysts to reliably identify American eels in data obtained with a 1100/1800 kHz, multibeam sonar. This report describes a project to develop deep learning (a subset of artificial intelligence) tools to automate the time-consuming, subjective process of eel identification in multibeam sonar data. The project exploited new data collected in the laboratory and the existing data from the prior EPRI field study to develop and test deep learning and other data analytic tools, including wavelet filtering, differencing for static object removal, and convolutional neural network analysis. The analysis of the laboratory data demonstrated feasibility of the approach, revealed object characteristics observed with the sonar that distinguish eels from similarly sized and shaped acoustic targets, and provided additional data for algorithm selection and training. Deep learning algorithms trained and tested on the laboratory data alone achieved accuracy rates of greater than 98% when classifying acoustic images of eels and similar-sized neutrally buoyant sticks. The algorithm trained and tested on the pre-existing field data alone, and yielded classification accuracy of 9.3% false positives and 13.3% false negatives when distinguishing between eels and sticks/PVC pipes based on video clips (i.e., multiple, consecutive images). This performance is comparable to the classification accuracy achieved by human analysts in the prior study. The deep learning algorithm trained on a combination of video clips obtained in the laboratory and the field and tested on video clips from the field, was able to distinguish eels from sticks and PVC pipes (a river debris analog) of similar size with 100% accuracy. Outreach to the hardware, software, and end-user communities early in the project helped to identify needs and specify the application space. Outreach to those communities at the end of the project communicated project results and opportunities for further development. The project achieved proof of concept for automated identification of eel in multibeam sonar data. Future work should focus on acquisition of additional data for more robust algorithm training and testing; modification of the software tools to accommodate multiple acoustic targets in the acoustic field at a given time; identification of additional object classes; incorporation of motion in the object identification and classification algorithms; operationalizing the software tools, including integration with other existing sonar data analysis tools; and partnering with hardware and software providers for distribution of the software tools with their commercial products.

13 HYDRO ENERGY↗

THE SPECTRAL ENERGY DISTRIBUTION OF FERMI BRIGHT BLAZARS

We have conducted a detailed investigation of the broadband spectral properties of the {gamma}-ray selected blazars of the Fermi LAT Bright AGN Sample (LBAS). By combining our accurately estimated Fermi {gamma}-ray spectra with Swift, radio, infra-red, optical, and other hard X-ray/{gamma}-ray data, collected within 3 months of the LBAS data taking period, we were able to assemble high-quality and quasi-simultaneous spectral energy distributions (SED) for 48 LBAS blazars. The SED of these {gamma}-ray sources is similar to that of blazars discovered at other wavelengths, clearly showing, in the usual log {nu}-log {nu} F {sub {nu}} representation, the typical broadband spectral signatures normally attributed to a combination of low-energy synchrotron radiation followed by inverse Compton emission of one or more components. We have used these SED to characterize the peak intensity of both the low- and the high-energy components. The results have been used to derive empirical relationships that estimate the position of the two peaks from the broadband colors (i.e., the radio to optical, {alpha}{sub ro}, and optical to X-ray, {alpha}{sub ox}, spectral slopes) and from the {gamma}-ray spectral index. Our data show that the synchrotron peak frequency ({nu} {sup S} {sub peak}) is positioned between 10{sup 12.5} and 10{sup 14.5} Hz in broad-lined flat spectrum radio quasars (FSRQs) and between 10{sup 13} and 10{sup 17} Hz in featureless BL Lacertae objects. We find that the {gamma}-ray spectral slope is strongly correlated with the synchrotron peak energy and with the X-ray spectral index, as expected at first order in synchrotron-inverse Compton scenarios. However, simple homogeneous, one-zone, synchrotron self-Compton (SSC) models cannot explain most of our SED, especially in the case of FSRQs and low energy peaked (LBL) BL Lacs. More complex models involving external Compton radiation or multiple SSC components are required to reproduce the overall SED and the observed spectral variability. While more than 50% of known radio bright high energy peaked (HBL) BL Lacs are detected in the LBAS sample, only less than 13% of known bright FSRQs and LBL BL Lacs are included. This suggests that the latter sources, as a class, may be much fainter {gamma}-ray emitters than LBAS blazars, and could in fact radiate close to the expectations of simple SSC models. We categorized all our sources according to a new physical classification scheme based on the generally accepted paradigm for Active Galactic Nuclei and on the results of this SED study. Since the LAT detector is more sensitive to flat spectrum {gamma}-ray sources, the correlation between {nu} {sup S} {sub peak} and {gamma}-ray spectral index strongly favors the detection of high energy peaked blazars, thus explaining the Fermi overabundance of this type of sources compared to radio and EGRET samples. This selection effect is similar to that experienced in the soft X-ray band where HBL BL Lacs are the dominant type of blazars.

79 ASTRONOMY AND ASTROPHYSICS↗

Switchgrass (Panicum virgatum L.) Intraspecific Variation and Thermotolerance Classification Using in Vitro Seed Germination Assay

Cardinal temperatures for plant processes have been used for thermotolerance screening of genotypes, geoclimatic adaptability determination and phenological prediction. Current simulation models for switchgrass (Panicum virgatum L.) utilize single cardinal temperatures across genotypes for both vegetative and reproductive processes although in-tra-specific variation exists among genotypes. An experiment was conducted to estimate the cardinal temperatures for seed germination of 14 diverse switchgrass genotypes and to classify genotypes for temperature tolerance. Stratified seeds of each genotype were germinated at eight constant temperatures from 10 °C to 45 °C under a constant light intensity of 35 μmol m -2 s -1 for 12 hd -1 . Germination was recorded at 6-h intervals in all treatments. Maximum seed germination (MSG) and germination rate (GR), estimated by fitting Sigmoidal function to germination-time series data, varied among genotypes. Quadratic and bilinear models best described the MSG and GR responses to temperature, respectively. The mean cardinal temperatures, T min , T opt , and T max , were 8.1, 26.6, and 45.1 °C for MSG and 11.1, 33.1, and 46.0 °C for GR, respectively. Cardinal temperatures for MSG and GR; however, varied significantly among genotypes. Genotypes were classified as sensitive (Cave-in-Rock, Dacotah, Expresso, Forestburg, Kanlow, Sunburst, Trailblazer, and Tusca), intermediate (Alamo, Blackwell, Carthage, Shawnee, and Shelter) and tolerant (Summer) to high temperature based on cumulative temperature response index (CTRI) estimated by summing individual response indices estimated from the MSG and GR cardinal temperatures. Similarly, genotypes were also classified as sensitive (Alamo, Blackwell, Carthage, Dacotah, Shawnee, Shelter and Summer), moderately sensitive (Cave-in-rock, Forestburg, Kanlow, Sunburst, and Tusca), moderately tolerant (Trailblazer), and tolerant (Expresso) to low temperatures. The cardinal temperature estimates would be useful to improve switchgrass models for field applications. Additionally, the identified cold- and heat-tolerant genotypes can be selected for niche environments and in switchgrass breeding programs to develop new genotypes for low and high temperature environments.

09 BIOMASS FUELS↗

Ionic Liquid Engineering in Perovskite Photovoltaics

Over the past decade, perovskite photovoltaics have approached other currently available technologies and proven to be the most prospective type of solar cells. Although the many-sided research in this very active field has generated consistent results with regard to their undisputed consistently increasing power conversion efficiency, it also produced several rather contradictory opinions. Among other important details, debate surrounding their proneness to surface degradation and poor mechanical robustness, as well as the environmental footprint of this materials class, remains a moot point. The application of ionic liquids appears as one of the potential remedies to some of these challenges due to their high conductivity, the opportunities for chemical “tuning” of the structure, and relatively lower environmental footprint. This article provides an overview, classification, and applications of ionic liquids in perovskite solar cells. Here, we summarize the use and role of ionic liquids as versatile additives, solvents, and modifiers in perovskite precursor solution, in charge transport layer, and in interfacial and stability engineering. Finally, challenges and the future prospects for the design and/or selection of ionic liquids with a specific profile that meets the requirements for next-generation highly efficient and stable perovskite solar cells are proposed.

14 SOLAR ENERGY↗

{sup 18}F-Fluorodeoxyglucose Positron Emission Tomography Can Quantify and Predict Esophageal Injury During Radiation Therapy

Purpose: We sought to investigate the ability of mid-treatment {sup 18}F-fluorodeoxyglucose positron emission tomography (PET) studies to objectively and spatially quantify esophageal injury in vivo from radiation therapy for non-small cell lung cancer. Methods and Materials: This retrospective study was approved by the local institutional review board, with written informed consent obtained before enrollment. We normalized {sup 18}F-fluorodeoxyglucose PET uptake to each patient's low-irradiated region (<5 Gy) of the esophagus, as a radiation response measure. Spatially localized metrics of normalized uptake (normalized standard uptake value [nSUV]) were derived for 79 patients undergoing concurrent chemoradiation therapy for non-small cell lung cancer. We used nSUV metrics to classify esophagitis grade at the time of the PET study, as well as maximum severity by treatment completion, according to National Cancer Institute Common Terminology Criteria for Adverse Events, using multivariate least absolute shrinkage and selection operator (LASSO) logistic regression and repeated 3-fold cross validation (training, validation, and test folds). This 3-fold cross-validation LASSO model procedure was used to predict toxicity progression from 43 asymptomatic patients during the PET study. Dose-volume metrics were also tested in both the multivariate classification and the symptom progression prediction analyses. Classification performance was quantified with the area under the curve (AUC) from receiver operating characteristic analysis on the test set from the 3-fold analyses. Results: Statistical analysis showed increasing nSUV is related to esophagitis severity. Axial-averaged maximum nSUV for 1 esophageal slice and esophageal length with at least 40% of axial-averaged nSUV both had AUCs of 0.85 for classifying grade 2 or higher esophagitis at the time of the PET study and AUCs of 0.91 and 0.92, respectively, for maximum grade 2 or higher by treatment completion. Symptom progression was predicted with an AUC of 0.75. Dose metrics performed poorly at classifying esophagitis (AUC of 0.52, grade 2 or higher mid treatment) or predicting symptom progression (AUC of 0.67). Conclusions: Normalized uptake can objectively, locally, and noninvasively quantify esophagitis during radiation therapy and predict eventual symptoms from asymptomatic patients. Normalized uptake may provide patient-specific dose-response information not discernible from dose.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

LUMINOUS AND VARIABLE STARS IN M31 AND M33. III. THE YELLOW AND RED SUPERGIANTS AND POST-RED SUPERGIANT EVOLUTION

Recent supernova (SN) and transient surveys have revealed an increasing number of non-terminal stellar eruptions. Though the progenitor class of these eruptions includes the most luminous stars, little is known of the pre-SN mechanics of massive stars in their most evolved state, thus motivating a census of possible progenitors. From surveys of evolved and unstable luminous star populations in nearby galaxies, we select a sample of yellow and red supergiant (RSG) candidates in M31 and M33 for review of their spectral characteristics and spectral energy distributions (SEDs). Since the position of intermediate- and late-type supergiants on the color–magnitude diagram can be heavily contaminated by foreground dwarfs, we employ spectral classification and multi-band photometry from optical and near-infrared surveys to confirm membership. Based on spectroscopic evidence for mass loss and the presence of circumstellar (CS) dust in their SEDs, we find that 30%–40% of the yellow supergiants are likely in a post-RSG state. Comparison with evolutionary tracks shows that these mass-losing, post-RSGs have initial masses between 20 and 40 M {sub ⊙}. More than half of the observed RSGs in M31 and M33 are producing dusty CS ejecta. We also identify two new warm hypergiants in M31, J004621.05+421308.06 and J004051.59+403303.00, both of which are likely in a post-RSG state.

79 ASTRONOMY AND ASTROPHYSICS↗

Dark Energy Survey Year 6 Results: Photometric Dataset for Cosmology

We describe the photometric dataset assembled from the full 6 yr of observations by the Dark Energy Survey (DES) in support of static-sky cosmology analyses. DES Y6 Gold is a curated dataset derived from DES Data Release 2 (DR2) that incorporates improved measurement, photometric calibration, object classification and value-added information. Y6 Gold comprises nearly 5000 deg$^{2}$ of grizY imaging in the south Galactic cap and includes 669 million objects with a depth of i$_{AB}$ ∼ 23.4 mag at a signal-to-noise ratio ∼ 10 for extended objects and a top-of-the-atmosphere photometric uniformity <2 mmag. Y6 Gold augments DES DR2 with simultaneous fits to multiepoch photometry for more robust galaxy shapes, colors, and photometric redshift estimates. Y6 Gold features improved morphological star–galaxy classification with an efficiency of 98.6% and a contamination of 0.8% for galaxies with 17.5 < i$_{AB}$ < 22.5. Additionally, it includes per-object quality information, and accompanying maps of the footprint coverage, masked regions, imaging depth, survey conditions, and astrophysical foregrounds that are used for cosmology analyses. After quality selections, benchmark samples contain 448 million galaxies and 120 million stars. This publication is complemented by data access and documentation.

79 ASTRONOMY AND ASTROPHYSICS↗

CA 19-9 Level as Indicator of Early Distant Metastasis and Therapeutic Selection in Resected Pancreatic Cancer

Purpose: In patients with pancreatic cancer treated with curative resection, we evaluated the effect of clinicopathologic parameters on early distant metastasis within 6 months (DM{sup 6m}) to identify patients who might benefit from surgery. Methods and Materials: The study involved 84 patients with pancreatic cancer who had undergone curative resection between August 2001 and April 2009. The parameters of gender, age, tumor size, histologic differentiation, T classification, N classification, pre- and postoperative carbohydrate antigen (CA) 19-9 level, resection margin, and adjuvant chemoradiotherapy were analyzed to identify the risk factors associated with DM{sup 6m}. Results: Of the 84 patients, locoregional recurrence developed in 35 (41.7%) and distant metastasis in 58 (69%). Of the 58 patients with distant metastasis, DM{sup 6m} had developed in 27 (46.6%). Multivariate analysis showed that preoperative CA 19-9 level was significantly associated with DM{sup 6m} (p < .05). Of all 84 patients, DM{sup 6m} was observed in 9.1%, 50%, and 80% of those with a preoperative CA 19-9 level of {<=}100 U/mL, 101-400 U/mL, and >400 U/mL, respectively (p < .001). Conclusions: The preoperative CA 19-9 level might be a useful predictor of DM{sup 6m} and to identify those who would benefit from surgical resection.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Error modeling for surrogates of dynamical systems using machine learning: Machine-learning-based error model for surrogates of dynamical systems

A machine learning–based framework for modeling the error introduced by surrogate models of parameterized dynamical systems is proposed. The framework entails the use of high-dimensional regression techniques (eg, random forests, and LASSO) to map a large set of inexpensively computed “error indicators” (ie, features) produced by the surrogate model at a given time instance to a prediction of the surrogate-model error in a quantity of interest (QoI). This eliminates the need for the user to hand-select a small number of informative features. The methodology requires a training set of parameter instances at which the time-dependent surrogate-model error is computed by simulating both the high-fidelity and surrogate models. Using these training data, the method first determines regression-model locality (via classification or clustering) and subsequently constructs a “local” regression model to predict the time-instantaneous error within each identified region of feature space. We consider 2 uses for the resulting error model: (1) as a correction to the surrogate-model QoI prediction at each time instance and (2) as a way to statistically model arbitrary functions of the time-dependent surrogate-model error (eg, time-integrated errors). We then apply the proposed framework to model errors in reduced-order models of nonlinear oil-water subsurface flow simulations, with time-varying well-control (bottom-hole pressure) parameters. The reduced-order models used in this work entail application of trajectory piecewise linearization in conjunction with proper orthogonal decomposition. Moreover, when the first use of the method is considered, numerical experiments demonstrate consistent improvement in accuracy in the time-instantaneous QoI prediction relative to the original surrogate model, across a large number of test cases. When the second use is considered, results show that the proposed method provides accurate statistical predictions of the time- and well-averaged errors.

97 MATHEMATICS AND COMPUTING↗

LANL Regular Employee Population and Demographics, FY15-21

This document summarizes an effort to compile and analyze the LANL regular employee population’s demographic attributes and trends between FY15-FY21 using MicroStrategy, a web-based data analytics and visualization tool. LANL’s HR Division collected and prepared data for the Weapons Program’s annual reporting activities for the 2017 through 2023 NNSA Stockpile Stewardship and Management Plan (SSMP). Los Alamos workforce data represent the fiscal year-end snapshot of the permanent employee population who are categorized by the Common Occupational Classification System (COCS). This work enables further analyses, including trends for all workforce attributes presented in the SSMPs as well as a definition of a crosswalk between COCS categorization and the internal laboratory job classification hierarchy. Data for other sites and the federal workforce, as shown in the SSMPs, are included and corresponding figures can be visualized within the MicroStrategy tool. A portable, Excel-based version of the tool was developed and shared with the multi-site workforce working group. This summary highlights selected aspects of the LANL regular workforce. The data analyses and visualizations communicate insights within three major themes regarding permanent LANL employees: 1) demographic transformation, 2) attrition, and 3) skills. Regarding demographic transformation, and consistent with the general trend across the enterprise, early career regular employees are the fastest growing group, with growth ranging between 12-34% year-to-year over the seven-year period analyzed. The data also reflect effects of internal and external factors on attrition; the large spike in separations in FY18 aligns with the contract transition from LANS to Triad and the dip in attrition between FY20-FY21 is likely a result of the global pandemic. The population of regular employees in general management, engineer, and operator COCS categories have the fastest growth rates amongst all the occupational categories. The MicroStrategy and Excel tools provide additional details and trends.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Nutritional status and random blood glucose, cholesterol and triglyceride test among Malaysian Army (MA) personnel in Kuala Lumpur

With the rising trend of obesity among the general population, it is also important to assess the obesity and health status among military population. The aim of this study was to determine the prevalence of overweight and obesity among Malaysian Army (MA) personnel as well as the relationship between selected socio-demographics factors, antropometric profiles, body composition and random blood test value. A cross sectional study involving 378 male military personnel aged between 20 to 48 years old was conducted at two MA bases in Kuala Lumpur between November and December 2012. Antropometric measurements included height, weight and waist circumference (WC). Body fat percentage was measured using bioelectrical impedance analysis method (Tanita TBF-300A). Mean height, weight, BMI, WC, body fat percentage, age, monthly income and duration of service were 1.71 ± 0.6 m, 71.7 ± 12.2 kg, 24.6 ± 4.1 kg/m{sup 2}, 87.0 ± 10.0 cm, 23.4 ± 6.6%, 29.1 ± 5.5 years, RM 2115.12 ± 860.70 and 9.9 ± 5.6 years respectively. According to WHO (1998) classification of BMI, 3.2% of the subjects were underweight, 54.8% normal, 32.8% overweight and 9.3% obese. It was obeserved that 40.2% of the subjects had waist circumference value of 90 cm or more and were considered high risk for diebetes and cardiovascular diseases. This study found that BMI was highly correlated with weight (r=0.925, p<0.05), WC (r=0.852, p<0.05) and body fat percentage. Body fat percentage also show high correlation with weight (r=0.759, p<0.05) and WC (r=0.768, p<0.05. The result from 173 of 378 subjects that were selected for random blood test found that 4.6%, 3.5% and 26.0% had diabetes, high cholesterol and high triglyceride respectively. There was a weak correlation between random blood glucose level with weight (r=0.221, p<0.05), BMI (r=0.243, p<0.05), WC (r=0.298, p<0.05), body fat percentage (r=0.163, p<0.05) and age (r=0.223, p<0.05). Random blood cholesterol level had significant correlation with weight (r=0.284, p<0.05), BMI (r=0.260, p<0.05), WC (r=0.362, p<0.05) and body fat percentage (r=0.313, p<0.05). It was also noted that random blood triglyceride level was significantly correlated with weight (r=0.223, p<0.05), BMI (r=0.312, p<0.05), WC (r=0.288, p<0.05), body fat percentage (r=0.287, p<0.05) and age (r=0.268 p<0.05). These results call for attention to the existence of overweight and obesity as well as the risk of non-communicable diseases among military population. Therefore, future intervention from the aspect of nutritional education and health awareness can benefit thus optimizing the health status of MA military personnel.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Predictive analytics of selections of russet potatoes

We explore the application of machine learning algorithms specifically to enhance the selection process of Russet potato (Solanum tuberosum L.) clones in breeding trials by predicting their suitability for advancement. This study addresses the challenge of efficiently identifying high-yield, disease-resistant, and climate-resilient potato varieties that meet processing industry standards. Leveraging manually collected data from trials in the state of Oregon, we investigate the potential of a wide variety of state-of-the-art binary classification models. The dataset includes 1086 clones, with data on 38 attributes recorded for each clone, focusing on yield, size, appearance, and frying characteristics, with several control varieties planted consistently across four Oregon regions from 2013 to 2021. We conduct a comprehensive analysis of the dataset that includes preprocessing, feature engineering, and imputation to address missing values. We focus on several key metrics such as accuracy, F1-score, and Matthews correlation coefficient (MCC) for model evaluation. The top-performing models, namely a feedforward neural network classifier (Neural Net), a histogram-based gradient boosting classifier (HGBC), and a support vector machine classifier (SVM), demonstrate consistent and significant results. To further validate our findings, we conducted a simulation study using the aims, data-generating mechanisms, estimands, methods, and performance measures (ADEMP) framework, simulating different data-generating scenarios to assess model robustness and performance through true positive, true negative, false positive, and false negative distributions, area under the receiver operating characteristic curve (AUC-ROC) and MCC. The simulation results highlight that non-linear models like SVM and HGBC consistently show higher AUC-ROC and MCC than logistic regression, thus outperforming the traditional linear model across various distributions, and emphasizing the importance of model selection and tuning in agricultural trials. Variable selection further enhances model performance and identifies influential features in predicting trial outcomes. The findings emphasize the potential of machine learning in streamlining the selection process for potato varieties, offering benefits such as increased efficiency, substantial cost savings, and judicious resource utilization. Our study contributes insights into precision agriculture and showcases the relevance of advanced technologies for informed decision-making in breeding programs.

60 APPLIED LIFE SCIENCES↗

Characterization of Used Nuclear Fuel with Multivariate Analysis for Process Monitoring

The Multi-Isotope Process (MIP) Monitor combines gamma spectroscopy and multivariate analysis to detect anomalies in various process streams in a nuclear fuel reprocessing system. Measured spectra are compared to models of nominal behavior at each measurement location to detect unexpected changes in system behavior. In order to improve the accuracy and specificity of process monitoring, fuel characterization may be used to more accurately train subsequent models in a full analysis scheme. This paper presents initial development of a reactor-type classifier that is used to select a reactor-specific partial least squares model to predict fuel burnup. Nuclide activities for prototypic used fuel samples were generated in ORIGEN-ARP and used to investigate techniques to characterize used nuclear fuel in terms of reactor type (pressurized or boiling water reactor) and burnup. A variety of reactor type classification algorithms, including k-nearest neighbors, linear and quadratic discriminant analyses, and support vector machines, were evaluated to differentiate used fuel from pressurized and boiling water reactors. Then, reactor type-specific partial least squares models were developed to predict the burnup of the fuel. Using these reactor type-specific models instead of a model trained for all light water reactors improved the accuracy of burnup predictions. The developed classification and prediction models were combined and applied to a large dataset that included eight fuel assembly designs, two of which were not used in training the models, and spanned the range of the initial 235U enrichment, cooling time, and burnup values expected of future commercial used fuel for reprocessing. Error rates were consistent across the range of considered enrichment, cooling time, and burnup values. Average absolute relative errors in burnup predictions for validation data both within and outside the training space were 0.0574% and 0.0597%, respectively. The errors seen in this work are artificially low, because the models were trained, optimized, and tested on simulated, noise-free data. However, these results indicate that the developed models may generalize well to new data and that the proposed approach constitutes a viable first step in developing a fuel characterization algorithm based on gamma spectra.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Hazardous waste status of discarded electronic cigarettes

Highlights: • Electronic cigarettes were tested using TCLP and WET. • Several electronic cigarette products leached lead at hazardous waste levels. • Lead was the only element that exceeded hazardous waste concentration thresholds. • Nicotine solution may cause hazardous waste classification when discarded unused. - Abstract: The potential for disposable electronic cigarettes (e-cigarettes) to be classified as hazardous waste was investigated. The Toxicity Characteristic Leaching Procedure (TCLP) was performed on 23 disposable e-cigarettes in a preliminary survey of metal leaching. Based on these results, four e-cigarette products were selected for replicate analysis by TCLP and the California Waste Extraction Test (WET). Lead was measured in leachate as high as 50 mg/L by WET and 40 mg/L by TCLP. Regulatory thresholds were exceeded by two of 15 products tested in total. Therefore, some e-cigarettes would be toxicity characteristic (TC) hazardous waste but a majority would not. When disposed in the unused form, e-cigarettes containing nicotine juice would be commercial chemical products (CCP) and would, in the United States (US), be considered a listed hazardous waste (P075). While household waste is exempt from hazardous waste regulation, there are many instances in which such waste would be subject to regulation. Manufactures and retailers with unused or expired e-cigarettes or nicotine juice solution would be required to manage these as hazardous waste upon disposal. Current regulations and policies regarding the availability of nicotine-containing e-cigarettes worldwide were reviewed. Despite their small size, disposable e-cigarettes are consumed and discarded much more quickly than typical electronics, which may become a growing concern for waste managers.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗