Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Distance Learning”

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 469 records · Page 26

A Probabilistic Autoencoder for Type Ia Supernova Spectral Time Series

We construct a physically parameterized probabilistic autoencoder (PAE) to learn the intrinsic diversity of Type Ia supernovae (SNe Ia) from a sparse set of spectral time series. The PAE is a two-stage generative model, composed of an autoencoder that is interpreted probabilistically after training using a normalizing flow. We demonstrate that the PAE learns a low-dimensional latent space that captures the nonlinear range of features that exists within the population and can accurately model the spectral evolution of SNe Ia across the full range of wavelength and observation times directly from the data. By introducing a correlation penalty term and multistage training setup alongside our physically parameterized network, we show that intrinsic and extrinsic modes of variability can be separated during training, removing the need for the additional models to perform magnitude standardization. We then use our PAE in a number of downstream tasks on SNe Ia for increasingly precise cosmological analyses, including the automatic detection of SN outliers, the generation of samples consistent with the data distribution, and solving the inverse problem in the presence of noisy and incomplete data to constrain cosmological distance measurements. We find that the optimal number of intrinsic model parameters appears to be three, in line with previous studies, and show that we can standardize our test sample of SNe Ia with an rms of 0.091 ± 0.010 mag, which corresponds to 0.074 ± 0.010 mag if peculiar velocity contributions are removed.

79 ASTRONOMY AND ASTROPHYSICS↗

Contextually aware roadside radiation measurement testbed

Here we demonstrate a contextually aware multimodal roadside radiation measurement detection testbed for traffic monitoring applications in nuclear nonproliferation. Many variables in traffic such as vehicle or cargo size, mass, speed, shape, and distance of closest approach can have significant impacts on the radiation measured from a vehicle-transported radiation source. These factors can lead to uncertainties in the analysis of the radiation source, especially for lower-strength radiation sources of interest. Our testbed, known as the Multimodal Measurement System (MMS) uses non-radiation sensors including magnetometers, geophones, radiofrequency receivers, cameras, and LiDAR to extract contextual information about vehicles passing by the system. These contextual data can then be fused with data from radiation measurements to increase the system’s sensitivity and accuracy in nuclear threat detection applications. This work describes the instrumentation of the MMS and its data acquisition pipeline. Furthermore, we describe the pre-analysis performed on the raw multimodal data streams for data fusion, and the high-level machine learning analyses for detection and characterization. The variety of sensors within the MMS provides a valuable testbed that can be used to identify the combinations of contextual sensors that provide the greatest improvements to radiation source detection and characterization within the restrictions for various proliferation detection applications. The MMS is also modular so that additional combinations of sensors can be explored in the future.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Spray Foam Exterior Insulation with Stand-Off Furring - New York

IBACOS and Green Homes America 1 (GHA) collaborated with the New York State Energy Research and Development Authority (NYSERDA) Advanced Buildings Program to research a variation of a commercial curtain wall assembly for residential construction as part of a comprehensive whole-house deep energy retrofit (DER) package. The advantages of this strategy include minimizing the physical connections to each individual existing wall stud, using closedcell spray foam to encapsulate existing siding materials including lead paint, and creating a vented rain screen assembly to promote drying. As Moore (2011) states, "Closed-cell foam acts as air-sealing, insulation, and secondary drainage plane..." Field installations on a limited number of houses indicate that the incremental cost when installed as part of a typical siding and window replacement job adds approximately $10/ft2 of wall area. 2 x 4 framing members were attached to the wall at band joists and top plates using "L" clips, and spray foam was used to insulate the wall after the framing was installed. Windows were installed as the framing was put up, including extension jambs. Key lessons learned include the following: (1) The installed cost of the spray foam system was comparable to the installed cost of the rigid foam and furring strips. (2) Spray foam should be applied in such a way that it locks the framing members in place before the remaining foam is installed in the field of the wall. The spray foam has a tendency to move the new wall framing as it expands. Best practice is to "picture frame" the wall framing with spray foam and then apply the spray foam in the field of each bay. (3) Variations in the existing siding conditions must be accounted for when attaching the ledger boards and wall framing. A best practice is to uniformly shim the ledger boards off the walls so the new framing is a uniform distance from the ledger boards and the inside surface of the interior framing. This is important primarily for window and door installation and the associated extension jambs and trim. (4) From a sequencing perspective, it is advantageous to replace the windows at the same time as the exterior walls are being built. This requires a crew that can perform a number of different tasks (e.g., framing, flashing, window install, trim carpentry) and does not lend itself to subcontracting this approach piecemeal (e.g., framing subcontractor, window installer, drainage plane installer, trim carpenter). (5) Application of the brackets and associated fastener screws was more time consuming than anticipated. (6) It is important for the spray foam contractor to perform all preparatory work, which in this case included placing plastic over the windows and exposed foundation to minimize or eliminate the possibility of damage due to overspray.

Array↗

Fundamental Studies of Hydroporphyrin Architectures for Solar-Energy Applications

The long-term objective of the Bocian/Holten&Kirmaier/Lindsey research program is to design, synthesize, and characterize tetrapyrrole-based molecular architectures that absorb sunlight, funnel energy, and separate charge with high efficiency and in a manner compatible with current and future solar-energy conversion schemes. The synthetic tetrapyrroles include porphyrins and hydroporphyrins; the latter classes of molecules encompass analogues of the naturally occurring chlorophylls and bacteriochlorophylls (e.g., chlorins, bacteriochlorins, and their derivatives). The attainment of the goals of the research program requires the close interplay of molecular design and synthesis (Lindsey group), static and time-resolved optical spectroscopic measurements (Holten&Kirmaier group), and electrochemical, electron paramagnetic resonance, resonance Raman, and infrared studies, as well as density functional theory calculations (Bocian Group). The proposed research encompasses four interrelated themes: (i) Gain a deeper understanding of the spectral and electronic properties of bacteriochlorins, with a subsidiary aim of learning how to shift the long-wavelength absorption band deeper into the NIR region. Bacteriochlorins bearing diverse substituents, including annulated rings, will be prepared and examined. A set of bacteriochlorins with site-specific isotopic (13C, 2H) substitution patterns about the macrocycle perimeter will be prepared for studies of vibrational and electronic properties. (ii) Examine the underlying electronic origin of panchromatic absorption and excited-state behavior of strongly coupled rylene–tetrapyrrole arrays. The rylene constituents include a perylene-monoimide and a terrylene-monoimide. The tetrapyrroles include porphyrins (meso- or β-linked) and bacteriochlorins (β-linked). The objective is to achieve panchromatic absorption while preserving a viable, long-lived excited singlet state. (iii) Determine the rates of ground-state hole/electron transfer between (hydro)porphyrins as a function of array size, distance between components, linker type, site of linker connection, and frontier molecular orbital composition. (iv) Build upon the results of the aforementioned studies to design, synthesize, and characterize integrated architectures that incorporate a panchromatic absorber and other molecular components that that afford efficient hole/electron migration and long-lived charge separation. Such architectures will be examined on solid substrates to explore the viability of the component parts and processes under application-oriented conditions. Such architectures or successors may prove directly useful for solar-energy conversion systems. An equally important attribute is to serve as a test-bed for successful integration of the requisite properties and processes, some of which require rather weak coupling between constituents, some of which require very strong electronic interactions to elicit the desired behavior, and all of which should be tunable under molecular design control to the extent possible. Collectively, the proposed studies will provide fundamental insights into molecular properties, interactions, and processes relevant to the design of molecular architectures for solar-energy conversion. The accomplishment of these goals is only possible through a highly synergistic program that encompasses molecular design, synthesis, and in-depth characterization.

14 SOLAR ENERGY↗

Computational optimal transport for molecular spectra: The fully continuous case

Computational optimal transport is used to analyze the difference between pairs of continuous molecular spectra. It is demonstrated that transport distances which are derived from this approach may be a more appropriate measure of the difference between two continuous spectra than more familiar measures of distance under many common circumstances. Associated with the transport distances is the transport map which provides a detailed analysis of the difference between two molecular spectra and is a key component of our study of quantitative differences between two continuous spectra. The use of optimal transport for comparing molecular spectra is developed in detail here with a set of model spectra, so that the discussion is self-contained. The difference between the transport distance and more common definitions of distance is elucidated for some well-chosen examples and it is shown where transport distances may be very useful alternatives to standard definitions of distance. The transport distance between a theoretical and experimental electronic absorption spectrum for SO 2 is studied and it is shown how the theoretical spectrum can be modified to fit the experimental spectrum better adjusting the theoretical band origin and the resolution of the theoretical spectrum. In conclusion, this analysis includes the calculation of transport maps between the theoretical and experimental spectra suggesting future applications of the methodology.

74 ATOMIC AND MOLECULAR PHYSICS↗

Sci—Fri PM: Topics — 08: The Role and Benefits of Electromagnetic Needle-Tracking Technologies in Brachytherapy

In modern brachytherapy, application of large doses of ionizing radiation in a limited number of fractions is frequent. Furthermore, as with any surgical procedures, brachytherapy is subject to learning curve effects. In this context, there could be advantages of integrating real-time tracking of needles/catheters to existing protocols given the recent prominent advances in tracking technologies. In this work, we review the use of an electromagnetic tracking system (EMTS) based on the second generation Aurora® Planar Field Generator (Northern Digital Inc) and custom design needles (Philips Healthcare) for brachytherapy applications. The position and orientation information is obtained from 5 degrees of freedom sensors. Basic system performance characterization is performed in well-controlled conditions to establish accuracy and reproducibility as well as potential interference from standard brachytherapy equipment. The results show that sensor locations can be tracked to within 0.04mm (la) when located within 26cm of the generator. Orientation accuracy of the needle remained within ±1° in the same region, but rose quickly at larger distances. The errors on position and orientation strongly dependent the sensor position in the characterization volume (500×500×500mm{sup 3}). The presence of an ultrasound probe was shown to have negligible effects on tracking accuracy. The use of EMTS for automatic catheter/applicator reconstruction was also explored. Reconstruction time was less than 10 sec/channel and tips identification was within 0.69±0.29mm of the reference values. Finally, we demonstrate that hollow needle designs with special EM adaptation also allow for real-time seed drop position estimation. In phantom experiments showed that drop positions were on average within 1.6±0.9mm of the reference position measured from μCT. Altogether, EMTS offer promising benefits in a wide range of brachytherapy applications.

60 APPLIED LIFE SCIENCES↗

SU-F-T-450: The Investigation of Radiotherapy Quality Assurance and Automatic Treatment Planning Based On the Kernel Density Estimation Method

Purpose: To develop a fast automatic algorithm based on the two dimensional kernel density estimation (2D KDE) to predict the dose-volume histogram (DVH) which can be employed for the investigation of radiotherapy quality assurance and automatic treatment planning. Methods: We propose a machine learning method that uses previous treatment plans to predict the DVH. The key to the approach is the framing of DVH in a probabilistic setting. The training consists of estimating, from the patients in the training set, the joint probability distribution of the dose and the predictive features. The joint distribution provides an estimation of the conditional probability of the dose given the values of the predictive features. For the new patient, the prediction consists of estimating the distribution of the predictive features and marginalizing the conditional probability from the training over this. Integrating the resulting probability distribution for the dose yields an estimation of the DVH. The 2D KDE is implemented to predict the joint probability distribution of the training set and the distribution of the predictive features for the new patient. Two variables, including the signed minimal distance from each OAR (organs at risk) voxel to the target boundary and its opening angle with respect to the origin of voxel coordinate, are considered as the predictive features to represent the OAR-target spatial relationship. The feasibility of our method has been demonstrated with the rectum, breast and head-and-neck cancer cases by comparing the predicted DVHs with the planned ones. Results: The consistent result has been found between these two DVHs for each cancer and the average of relative point-wise differences is about 5% within the clinical acceptable extent. Conclusion: According to the result of this study, our method can be used to predict the clinical acceptable DVH and has ability to evaluate the quality and consistency of the treatment planning.

60 APPLIED LIFE SCIENCES↗

Evaluating the Interplay between Trajectory Segmentation and Mode Inference Error

Travel behavior changes are essential to transportation decarbonization. Travel diaries, consisting of sequences of trips between places, are typically used to instrument human travel behavior. However, these diaries are only as accurate as the underlying methods used to construct them. Travel diary algorithms have been a popular research topic since the advent of Global Positioning System tracking surveys. These algorithms have typically been validated using prompted recall of presegmented trips, thus disregarding the continuity of mode inference. Phone operating systems have adopted battery-conserving techniques, but the resulting data collection errors have not been studied extensively. We introduce a framework to evaluate the accuracy of trip length computations and mode inference by analyzing continuous mode-segmented trajectories for groups of trips. We then use the framework to identify the input data quality and the impact of postprocessing. Our primary inputs to this evaluation are MobilityNet, a public dataset containing information from three artificial timelines covering 15 different travel modes, and sample open-source travel diary creation algorithms from the OpenPATH project. Our framework concretely shows that the variance of the distance error drops from (0.217, 0.0848) to (o.011, 0.0407) (Android, iOS) after postprocessing. Similarly, the weighted F-scores for mode inference increase from (0.25, 0.29) to (0.60, 0.74) (iOS, Android) between random forest and geographic information system-based models. We hope that this standardized method will be adapted to evaluate other, potentially proprietary, travel diary algorithms. Finally, the results can be used to understand and improve the state of the art in the travel diary creation field.

33 ADVANCED PROPULSION SYSTEMS↗

Uncertainty Quantification via Stable Distribution Propagation

We propose a new approach for propagating stable probability distributions through neural networks. Our method is based on local linearization, which we show to be an optimal approximation in terms of total variation distance for the ReLU non-linearity. This allows propagating Gaussian and Cauchy input uncertainties through neural networks to quantify their output uncertainties. To demonstrate the utility of propagating distributions, we apply the proposed method to predicting calibrated confidence intervals and selective prediction on out-of-distribution data. The results demonstrate a broad applicability of propagating distributions and show the advantages of our method over other approaches such as moment matching.

Artificial Intelligence (cs.AI)↗

Report on the AAPM grand challenge on deep generative modeling for learning medical image statistics

Abstract Background The findings of the 2023 AAPM Grand Challenge on Deep Generative Modeling for Learning Medical Image Statistics are reported in this Special Report. Purpose The goal of this challenge was to promote the development of deep generative models for medical imaging and to emphasize the need for their domain‐relevant assessments via the analysis of relevant image statistics. Methods As part of this Grand Challenge, a common training dataset and an evaluation procedure was developed for benchmarking deep generative models for medical image synthesis. To create the training dataset, an established 3D virtual breast phantom was adapted. The resulting dataset comprised about 108 000 images of size 512 512. For the evaluation of submissions to the Challenge, an ensemble of 10 000 DGM‐generated images from each submission was employed. The evaluation procedure consisted of two stages. In the first stage, a preliminary check for memorization and image quality (via the Fréchet Inception Distance [FID]) was performed. Submissions that passed the first stage were then evaluated for the reproducibility of image statistics corresponding to several feature families including texture, morphology, image moments, fractal statistics, and skeleton statistics. A summary measure in this feature space was employed to rank the submissions. Additional analyses of submissions was performed to assess DGM performance specific to individual feature families, the four classes in the training data, and also to identify various artifacts. Results Fifty‐eight submissions from 12 unique users were received for this Challenge. Out of these 12 submissions, 9 submissions passed the first stage of evaluation and were eligible for ranking. The top‐ranked submission employed a conditional latent diffusion model, whereas the joint runners‐up employed a generative adversarial network, followed by another network for image superresolution. In general, we observed that the overall ranking of the top 9 submissions according to our evaluation method (i) did not match the FID‐based ranking, and (ii) differed with respect to individual feature families. Another important finding from our additional analyses was that different DGMs demonstrated similar kinds of artifacts. Conclusions This Grand Challenge highlighted the need for domain‐specific evaluation to further DGM design as well as deployment. It also demonstrated that the specification of a DGM may differ depending on its intended use.

Radiology, Nuclear Medicine & Medical Imaging↗

Single photon emitters in van der Waals solids for quantum photonics: materials, theory and molecular-scale characterization probes

Strong light–matter interactions in two-dimensional layered materials (2D materials) have attracted the interest of researchers from interdisciplinary fields for more than a decade now. A unique phenomenon in some 2D materials is their large exciton binding energies (BEs), increasing the likelihood of exciton survival at room temperature. It is this large BE that mediates the intense light–matter interactions of many of the 2D materials, particularly in their monolayer limit, where the interplay of excitonic phenomena poses a wealth of opportunities for high-performance optoelectronics and quantum photonics. Within quantum photonics, quantum information science (QIS) is growing rapidly, where photons are a promising platform for information processing due to their low-noise properties, excellent modal control, and long-distance propagation. A central element for QIS applications is a single photon emitter (SPE) source, where an ideal on-demand SPE emits exactly one photon at a time into a given spatiotemporal mode. Recently, 2D materials have shown practical appeal for QIS which is directly driven from their unique layered crystalline structure. This structural attribute of 2D materials facilitates their integration with optical elements more easily than the SPEs in conventional three-dimensional solid state materials, such as diamond and SiC. In this review article, we will discuss recent advances made with 2D materials towards their use as quantum emitters, where the SPE emission properties maybe modulated deterministically. Here, the use of unique scanning tunneling microscopy tools for the in-situ generation and characterization of defects is presented, along with theoretical first-principles frameworks and machine learning approaches to model the structure-property relationship of exciton–defect interactions within the lattice towards SPEs. Given the rapid progress made in this area, the SPEs in 2D materials are emerging as promising sources of nonclassical light emitters, well-poised to advance quantum photonics in the future.

2D layered materials↗

Understanding the Drivers of Mobility during the COVID-19 Pandemic in Florida, USA Using a Machine Learning Approach

As of March 2021, the State of Florida, U.S.A. had accounted for approximately 6.67% of total COVID-19 (SARS-CoV-2 coronavirus disease) cases in the U.S. The main objective of this research is to analyze mobility patterns during a three month period in summer 2020, when COVID-19 case numbers were very high for three Florida counties, Miami-Dade, Broward, and Palm Beach counties. To investigate patterns, as well as drivers, related to changes in mobility across the tri-county region, a random forest regression model was built using sociodemographic, travel, and built environment factors, as well as COVID-19 positive case data. Mobility patterns declined in each county when new COVID-19 infections began to rise, beginning in mid-June 2020. While the mean number of bar and restaurant visits was lower overall due to closures, analysis showed that these visits remained a top factor that impacted mobility for all three counties, even with a rise in cases. Our modeling results suggest that there were mobility pattern differences between counties with respect to factors relating, for example, to race and ethnicity (different population groups factored differently in each county), as well as social distancing or travel-related factors (e.g., staying at home behaviors) over the two time periods prior to and after the spike of COVID-19 cases.

60 APPLIED LIFE SCIENCES↗

Effects of pre- and postnatal exposure to the UV-filter Octyl Methoxycinnamate (OMC) on the reproductive, auditory and neurological development of rat offspring

Octyl Methoxycinnamate (OMC) is a frequently used UV-filter in sunscreens and other cosmetics. The aim of the present study was to address the potential endocrine disrupting properties of OMC, and to investigate how OMC induced changes in thyroid hormone levels would be related to the neurological development of treated offspring. Groups of 14-18 pregnant Wistar rats were dosed with 0, 500, 750 or 1000 mg OMC/kg bw/day during gestation and lactation. Serum thyroxine (T{sub 4}), testosterone, estradiol and progesterone levels were measured in dams and offspring. Anogenital distance, nipple retention, postnatal growth and timing of sexual maturation were assessed. On postnatal day 16, gene expression in prostate and testes, and weight and histopathology of the thyroid gland, liver, adrenals, prostate, testes, epididymis and ovaries were measured. After weaning, offspring were evaluated in a battery of behavioral and neurophysiological tests, including tests of activity, startle response, cognitive and auditory function. In adult animals, reproductive organ weights and semen quality were investigated. Thyroxine (T{sub 4}) levels showed a very marked decrease during the dosing period in all dosed dams, but were less severely affected in the offspring. On postnatal day 16, high dose male offspring showed reduced relative prostate and testis weights, and a dose-dependent decrease in testosterone levels. In OMC exposed female offspring, motor activity levels were decreased, while low and high dose males showed improved spatial learning abilities. The observed behavioral changes were probably not mediated solely by early T{sub 4} deficiencies, as the observed effects differed from those seen in other studies of developmental hypothyroxinemia. At eight months of age, sperm counts were reduced in all three OMC-dosed groups, and prostate weights were reduced in the highest dose group. Taken together, these results indicate that perinatal OMC-exposure can affect both the reproductive and neurological development of rat offspring, which may be a cause of concern, as humans are systematically exposed to the compound through usage of sunscreens and other cosmetics.

60 APPLIED LIFE SCIENCES↗

HIPED: Machine learning framework for spherical tokamak pedestal prediction and optimization

We introduce a Machine Learning framework, HIPED (HeIght and width Predictor for Edge Dynamics), for predicting and optimizing pedestal and core performance in spherical tokamak plasmas. Trained on pedestal and core datasets from the third MAST-U campaign, HIPED provides accurate estimates of pedestal height and width. The results reveal notable differences compared with conventional aspect-ratio studies; for instance, a simple power-law relation between pedestal width and height has very low accuracy. Instead, additional parameters such as normalized plasma pressure, elongation, and Greenwald fraction significantly improve accuracy. HIPED can also be trained only on `control room parameters' to inform experimentalists of which controllable parameters to adjust for improving core-integrated performance. The framework further includes a multi-objective optimization scheme that helps guide experimental planning and optimization. We find Pareto-optimal discharges with respect to various features, including distance from edge-localized modes and normalized plasma pressure, track their parameter trajectories over time, and identify the control room parameters required for these Pareto-optimal discharges. This provides a framework for systematically optimizing core and edge performance according to different experimental priorities.

Parisi, Jason F. [Princeton Plasma Physics Laborat↗

The ecosystem approach in ecological impact assessment: Lessons learned from windfarm developments on peatlands in Scotland

Highlights: • Recent wind energy projects in Scotland mostly fail to consider ecosystem-level impacts on peatland. • Projects on peatland illustrate the usefulness of an ecosystem approach to Environmental Impact Assessment. • Defining more meaningful functional management units can improve Environmental Impact Assessment outcomes. • VAn ecosystem approach could also improve ecosystem services assessments. - Abstract: The Ecosystem Approach introduced in 1994 through the Convention on Biological Diversity, together with related Ecosystem-based Management and Landscape Approaches, are frequently called upon to improve ecological impact assessment. Current practice typically does not have such a systems focus and we explore the potential for explicitly adopting an Ecosystem Approach in the Environmental Impact Assessment process using wind energy development on peatland, in Scotland, as a case study. Based on a review of 21 windfarm projects (>50 MW) approved by the Scottish Government we provide an overview of current practice and identify and discuss how the 12 principles of the Ecosystem Approach can help identify options for more appropriate impact assessment. These include defining functional units of analysis that reflect the spatial and temporal linkages of peatland elements through hydrological connections, rather than a focus on individual vegetation types and simple distance buffers. Our conclusions are not limited to peatland and are relevant wherever meaningful functional management units can be defined, including in marine environments. Our results also show that environmental statements for wind energy development in Scotland largely ignore ecosystem services and the people that benefit from them. As for threatened species and other biodiversity features, an Ecosystem Approach is a prerequisite to the meaningful inclusion of ecosystem services in impact assessment.

54 ENVIRONMENTAL SCIENCES↗

Replacing non-biomedical concepts improves embedding of biomedical concepts

Embeddings are semantically meaningful representations of words in a vector space, commonly used to enhance downstream machine learning applications. Traditional biomedical embedding techniques often replace all synonymous words representing biological or medical concepts with a unique token, ensuring consistent representation and improving embedding quality. However, the potential impact of replacing non-biomedical concept synonyms has received less attention. Embedding approaches often employ concept replacement to replace concepts that span multiple words, such as non-small-cell lung carcinoma, with a single concept identifier (e.g., D002289). Also, all synonyms of each concept are merged into the same identifier. Here, we additionally leveraged WordNet to identify and replace sets of non-biomedical synonyms with their most common representatives. This combined approach aimed to reduce embedding noise from non-biomedical terms while preserving the integrity of biomedical concept representations. We applied this method to 1,055 biomedical concept sets representing molecular signatures or medical categories and assessed the mean pairwise distance of embeddings with and without non-biomedical synonym replacement. A smaller mean pairwise distance was interpreted as greater intra-cluster coherence and higher embedding quality. Embeddings were generated using the Word2Vec algorithm applied to a corpus of 10 million PubMed abstracts. Our results demonstrate that the addition of non-biomedical synonym replacement reduced the mean intra-cluster distance by an average of 8%, suggesting that this complementary approach enhances embedding quality. Future work will assess its applicability to other embedding techniques and downstream tasks. Python code implementing this method is provided under an open-source license.

algorithms↗

Modeling freight mode choice using machine learning classifiers: a comparative study using Commodity Flow Survey (CFS) data

This study explores the usefulness of machine learning classifiers for modeling freight mode choice. We investigate eight commonly used machine learning classifiers, namely Naïve Bayes, Support Vector Machine, Artificial Neural Network, K-Nearest Neighbors, Classification and Regression Tree, Random Forest, Boosting and Bagging, along with the classical Multinomial Logit model. US 2012 Commodity Flow Survey data are used as the primary data source; we augment it with spatial attributes from secondary data sources. The performance of the classifiers is compared based on prediction accuracy results. The current research also examines the role of sample size and training-testing data split ratios on the predictive ability of the various approaches. In addition, the importance of variables is estimated to determine how the variables influence freight mode choice. The results show that the tree-based ensemble classifiers perform the best. Specifically, Random Forest produces the most accurate predictions, closely followed by Boosting and Bagging. With regard to variable importance, shipment characteristics, such as shipment distance, industry classification of the shipper and shipment size, are the most significant factors for freight mode choice decisions.

42 ENGINEERING↗

Dark Energy Survey Year 3 results: galaxy sample for BAO measurement

Here, we present and validate the galaxy sample used for the analysis of the baryon acoustic oscillation (BAO) signal in the Dark Energy Survey (DES) Y3 data. The definition is based on a colour and redshift-dependent magnitude cut optimized to select galaxies at redshifts higher than 0.5, while ensuring a high-quality determination. The sample covers ~ 4100 square degrees to a depth of i = 22.3 (AB) at 10σ. It contains 7,031,993 galaxies in the redshift range from z = 0.6 to 1.1, with a mean effective redshift of 0.835. Redshifts are estimated with the machine learning algorithm DNF, and are validated using the VIPERS PDR2 sample. We find a mean redshift bias of z bias ~ 0.01 and a mean uncertainty, in units of 1 + z, of σ 68 ~ 0.03$. We evaluate the galaxy population of the sample, showing it is mostly built upon Elliptical to Sbc types. Furthermore, we find a low level of stellar contamination of ≲ 4 %. We present the method used to mitigate the effect of spurious clustering coming from observing conditions and other large-scale systematics. We apply it to the BAO sample and calculate weights that are used to get a robust estimate of the galaxy clustering signal. This paper is one of a series dedicated to the analysis of the BAO signal in DES Y3. In the companion papers, we present the galaxy mock catalogues used to calibrate the analysis and the angular diameter distance constraints obtained through the fitting to the BAO scale.

79 ASTRONOMY AND ASTROPHYSICS↗