Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Task Analysis”

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 1,135 records · Page 63
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Task 12 PV Sustainability - Life Cycle Assessment of Crystalline Silicon Photovoltaic Module Delamination with Hot Knife Technology

The objective of this study is to complete a life cycle assessment (LCA) of a novel technology that separates the crystalline silicon (c-Si) photovoltaic (PV) module front glass from the backsheet using hot knife technology. This is known to be the most challenging step in module recycling, where the choice of delamination approach can determine the process selection for the next steps of the recycling process, the economic value of the recovered materials, and environmental performance. The life cycle inventory (LCI) reported here is based on primary data from the technology manufacturer. Different LCIs are established following the cut-off approach and the end-of-life (EOL) approach. The environmental impacts of the hot knife delamination process are analysed based on six indicators, and the main contributors to delamination efforts are identified. For the EOL approach, the potential environmental benefits from the recovered materials are compared to the environmental impacts caused by the delamination process. The functional unit of this analysis is the delamination of 1 kg of used framed c-Si PV modules at the place of installation.

14 SOLAR ENERGY↗
DOE OSTI2020

Multi-Game Modeling for Counter-Smuggling

International trade provides an avenue for terrorists to smuggle illicit materials into a target country. Policymakers need models and decision support tools that are both reliable and germane to inform their responses to this. Game theoretic approaches have been used in the analysis of counterterrorism strategies, but the models involved have often been small and abstracted. To address this need, we have developed a multi-game model to account for both security-related and economic aspects of counter-smuggling interdiction efforts. Additionally, we use different games to represent different types of interactions, and these games are then coupled to each other to form an integrated model. In this paper, we demonstrate the model's capabilities on a representative system of ports (both foreign and domestic), trade routes, and commodities. We specifically investigate the impacts of changes in screening policies at domestic ports, detection device capabilities, shipping subsidies, and worldwide corruption levels. In these studies, we find that economic factors play a large role in the interdiction task and provide correspondingly important tools for deterrence.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗
DOE OSTI2026

Task Sharing of Proton Incorporation in Vertically Aligned Nanocomposite Triple Conductors: Growth, Structure, and Surface Exchange Kinetics

As protonic ceramic electrolysis cells emerge for efficient H 2 production, there is a need to develop air electrode materials enabling fast, durable steam splitting and proton incorporation. Single-phase triple conductors may fail to satisfy the myriad performance/stability requirements, and their critical charge-carriers (holes, oxygen vacancies, and protons) are in competition, limiting their concentrations. Instead, we propose task-sharing, vertically aligned nanocomposites (VANs), comprising a proton conductor (BaZr 0.9 Y 0.1 O 3-δ ) and a redox-active mixed ionic electronic conductor (Ce 0.9 Pr 0.1 O 2-δ ), that may enable rapid proton surface exchange at the solid–gas interface and transport along the solid–solid heterointerfaces. We grew VANs by pulsed laser deposition and investigated the interplay between their processing conditions, structure, and proton and oxygen surface exchange kinetics. We varied the substrate temperature, laser repetition rate, laser fluence, and processing oxygen pressure. The crystallinity and phases were characterized by grazing-incidence X-ray diffraction, and the strain and structural order as a function of depth were evaluated by angle-dependent synchrotron X-ray pair distribution function analysis. To evaluate the potential for interdiffusion, the formation energies of substitutional defects were simulated with density functional theory. Corresponding structural analysis and elemental mapping were performed by scanning/transmission electron microscopy, energy-dispersive X-ray spectroscopy, and electron energy-loss spectroscopy, indicating distinct nanoscale compositional regions with a hierarchical structure embedded in individual VANs columns and minimal interdiffusion across a bilayer film. Proton and oxygen surface exchange coefficients (k H , k O ) and polarization resistances were evaluated by electrical and optical relaxations and impedance spectroscopy of VAN-incorporated protonic ceramic electrochemical cells, respectively, at 400–500 °C, demonstrating values comparable to some of the best-known triple and mixed conductors.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Wavelet flow for extragalactic foreground simulations

Extragalactic foregrounds in cosmic microwave background (CMB) observations are both a source of cosmological and astrophysical information and a nuisance to the CMB. Effective field-level modeling that captures their non-Gaussian statistical distributions is increasingly important for optimal information extraction, particularly given the low-noise observations from current and upcoming experiments. Here, we explore the use of Wavelet Flow (WF) models to tackle the novel task of modeling the field-level probability distributions of multi-component CMB secondaries and foregrounds. Specifically, we jointly train correlated CMB lensing convergence (κ) and cosmic infrared background (CIB) maps with a WF model and obtain a network that statistically recovers the input to high accuracy — the trained network generates samples of κ and CIB fields whose average power spectra are within a few percent of the inputs across all scales, and whose Minkowski functionals are similarly accurate compared to the inputs. Leveraging the multiscale architecture of these models, we fine-tune both the model parameters and the priors at each scale independently, optimizing performance across different resolutions. These results demonstrate that WF models can accurately simulate correlated components of CMB secondaries, supporting improved analysis of cosmological data. Our code and trained models can be found on this GitHub repo.

cosmological simulations↗
DOE OSTI2023

Cost of Fish Exclusion and Passage Technologies for Hydropower

Hydropower represents a reliable source of renewable energy and accounts for approximately 7% of the total electrical generation in the United States. Future expansion of hydropower is likely to be in the form of either smaller new stream development projects or powering existing non-powered dams. For these new projects to be successful, careful analysis of risks, costs, and uncertainty to offset reduced power production as well as ensuring the protection and safe passage of migratory fish to gain public support, will be required. Exclusion and passage are two common approaches to protect fish from entrainment and impingement at hydropower facilities. The thresholds for entrainment risk and requirements for exclusion and passage often differ depending on the species involved, the characteristics of the facility, and the goals of stakeholders. While the costs associated with environmental mitigations represent a large proportion of the total costs required for the licensing of hydropower facilities, little quantitative information is present within the literature regarding the specific costs of fish exclusion and passage. Working with FOA awardee Natel Energy, scientists at Oak Ridge National Laboratory were tasked with assessing the capital construction costs for downstream fish exclusion and passage infrastructure. This report used keyword searches of an existing environmental mitigation cost data set and manual extraction of additional cost data associated with protection, mitigation, and enhancement (PM&E) measures related to positive barrier screening and passage from regulatory licensing documents available in the Federal Energy Regulatory Commission (FERC) eLibrary. This approach yielded a total of 50 PM&E mitigation measures with estimated capital construction costs pertaining to positive barrier screens, 142 pertaining to passage studies, and 26 pertaining to passage-related studies. PM&E measures associated with positive barrier screens represented <10% of the 171 total FERC project dockets available in the data set. These data were highly skewed toward conventional relicensing projects, as <7% were associated with new stream development (NSD) projects. Results from these data indicate highly variable costs associated with fish screening, with flow-normalized costs one to two orders of magnitude higher for screening with the highest exclusion capability (≤0.09 in. spacing) compared with coarser screening (1 to 2 in.). Furthermore, estimated capital costs of passage infrastructure were positively related to the scale of the project based on installed capacity for some, but not all, types of passage. These data provide an initial baseline for estimating exclusion and passage costs for hydropower development and may help developers consider options for more fish-friendly generation technologies, though gaps remain relating to a lack of data, particularly for NSD projects. More data may still be available within the FERC eLibrary, but significant effort will be required to manually identify and extract the data for future analyses.

13 HYDRO ENERGY↗
DOE OSTI2022

Jobs, jobs, jobs: what’s an analyst to do?

Analysts and economists often face the task of using employment metrics to characterize industries of interest. Some key challenges can be understanding where to find employment metrics, the differences in various employment metrics, and when each metric should be used. This article analyzes a variety of publicly available employment data for the United States and compares these data. A detailed description of the intricacies of each data source is provided, which covers factors such as regionality, industry breakout, periodicity, and the types of jobs included. This article provides several case study examples, using the oil and gas extraction, coal mining, and chemical manufacturing sectors to portray challenges data users may face when developing employment estimates that suit their needs. Data users should be aware of a variety of data sources to understand alternative analysis options when data limitations are present and to determine which data source best meets their needs. Instances may occur in which information from one dataset may be used to help impute missing values.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2025

Recovery Simulator and Analysis Formulation: Mathematical Framework for Enhanced Resilience and Resource Allocation

This report introduces recovery simulator and analysis (RSA), a framework aimed at enhancing the resilience of electrical grids post-disruption. The RSA model leverages an optimization problem formulation that focuses on maximizing the load served (or optionally customers served) through a coordinated and cooptimized recovery of non-black start generation, transmission lines, feeders and substations subject to labor budget constraints. By integrating advanced linear programming techniques, the simulator selects efficient reocovery pathways, optimizing both short-term and long-term grid recovery strategies. The mathematical framework guides decision-making through a comprehensive evaluation of potential recovery actions, factoring in the trade-offs between labor constraints and load (or optionally customer) restoration efficacy. This enables grid operators to simulate diverse outage scenarios and delineate optimal recovery pathways, thereby prioritizing critical repair tasks and ensuring resource allocation is both economical and effective. The intended use case of RSA is to allow planners to explore many recovery scenarios quickly and determine assets most critical across a wide range of scenarios, and therefore strong candidates for hardening or additional investment. RSA might also be used in an operational setting, following a single event, for exploring efficient recovery pathways.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

A unified and constructive framework for the universality of neural networks

Abstract One of the reasons why many neural networks are capable of replicating complicated tasks or functions is their universal approximation property. Though the past few decades have seen tremendous advances in theories of neural networks, a single constructive and elementary framework for neural network universality remains unavailable. This paper is an effort to provide a unified and constructive framework for the universality of a large class of activation functions including most of the existing ones. At the heart of the framework is the concept of neural network approximate identity (nAI). The main result is as follows: any nAI activation function is universal in the space of continuous functions on compacta. It turns out that most of the existing activation functions are nAI, and thus universal. The framework induces several advantages over the contemporary counterparts. First, it is constructive with elementary means from functional analysis, probability theory, and numerical analysis. Second, it is one of the first unified and constructive attempts that is valid for most of the existing activation functions. Third, it provides new proofs for most activation functions. Fourth, for a given activation and error tolerance, the framework provides precisely the architecture of the corresponding one-hidden neural network with a predetermined number of neurons and the values of weights/biases. Fifth, the framework allows us to abstractly present the first universal approximation with a favorable non-asymptotic rate. Sixth, our framework also provides insights into the developments, and hence providing constructive derivations, of some of the existing approaches.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

NANO.PTML model for read-across prediction of nanosystems in neurosciences. computational model and experimental case of study

Abstract Neurodegenerative diseases involve progressive neuronal death. Traditional treatments often struggle due to solubility, bioavailability, and crossing the Blood-Brain Barrier (BBB). Nanoparticles (NPs) in biomedical field are garnering growing attention as neurodegenerative disease drugs (NDDs) carrier to the central nervous system. Here, we introduced computational and experimental analysis. In the computational study, a specific IFPTML technique was used, which combined Information Fusion (IF) + Perturbation Theory (PT) + Machine Learning (ML) to select the most promising Nanoparticle Neuronal Disease Drug Delivery (N2D3) systems. For the application of IFPTML model in the nanoscience, NANO.PTML is used. IF-process was carried out between 4403 NDDs assays and 260 cytotoxicity NP assays conducting a dataset of 500,000 cases. The optimal IFPTML was the Decision Tree (DT) algorithm which shown satisfactory performance with specificity values of 96.4% and 96.2%, and sensitivity values of 79.3% and 75.7% in the training (375k/75%) and validation (125k/25%) set. Moreover, the DT model obtained Area Under Receiver Operating Characteristic (AUROC) scores of 0.97 and 0.96 in the training and validation series, highlighting its effectiveness in classification tasks. In the experimental part, two samples of NPs (Fe 3 O 4 _A and Fe 3 O 4 _B) were synthesized by thermal decomposition of an iron(III) oleate (FeOl) precursor and structurally characterized by different methods. Additionally, in order to make the as-synthesized hydrophobic NPs (Fe 3 O 4 _A and Fe 3 O 4 _B) soluble in water the amphiphilic CTAB (Cetyl Trimethyl Ammonium Bromide) molecule was employed. Therefore, to conduct a study with a wider range of NP system variants, an experimental illustrative simulation experiment was performed using the IFPTML-DT model. For this, a set of 500,000 prediction dataset was created. The outcome of this experiment highlighted certain NANO.PTML systems as promising candidates for further investigation. The NANO.PTML approach holds potential to accelerate experimental investigations and offer initial insights into various NP and NDDs compounds, serving as an efficient alternative to time-consuming trial-and-error procedures.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2022

Travel Patterns and Characteristics of Elderly Population in New York State: 2017 Update

According to US Census Bureau, the elderly population (individuals 65 years and older) has grown by over a third during the past decade (2010 to 2019), and by 3.2% from 2018 to 2019. It is essential for policymakers and planners to understand transportation issues associated with the elderly to meet their increasing travel demands. These issues include transportation and mobility of the elderly population, factors impacting their travel behavior, and transportation safety. In this study, Oak Ridge National Laboratory was tasked by the New York State Department of Transportation (NYSDOT) to conduct a detailed examination of travel behaviors and identify patterns and trends of its elderly residents. The National Household Travel Survey (NHTS) was used as the primary data source to analyze subjects and address questions such as: Are there differences in traveler demographics between the elderly population and those of younger age groups who live in various New York State (NYS) regions, e.g., New York City (NYC), other urban areas of NYS, or other parts of the country? How do they compare with the population at large? Are there any regional differences (e.g., urban versus rural)? Do any unique travel characteristics or patterns exist within the elderly group? How did these patterns change over time? In addition to the analysis of NHTS data, roadway travel safety concerns associated with elderly travelers were also investigated. Specifically, data on crashes involving the elderly (including drivers, passengers, and pedestrians) as captured in the Fatal Analysis Reporting System database was analyzed to examine elderly drivers and elderly pedestrian travel safety issues in NYS. This study report provides a summary of travel behavior and social-demographic characteristics of NYS elderly residents. These statistics could be used to examine equity issue concerning elderly New Yorkers, as well as to evaluate how well their mobility needs are being met. With a deeper understanding of issues and needs that this special population group is facing, policymakers and transportation planners would be able to make informed decisions on transportation investments and design services that could better address them.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2024

On the Training and Generalization of Deep Operator Networks

Here, we present a novel training method for deep operator networks (DeepONets), one of the most popular neural network models for operators. DeepONets are constructed by two subnetworks, namely the branch and trunk networks. Typically, the two subnetworks are trained simultaneously, which amounts to solving a complex optimization problem in a high dimensional space. In addition, the nonconvex and nonlinear nature makes training very challenging. To tackle such a challenge, we propose a two-step training method that trains the trunk network first and then sequentially trains the branch network. The core mechanism is motivated by the divide-and-conquer paradigm and is the decomposition of the entire complex training task into two subtasks with reduced complexity. Therein the Gram–Schmidt orthonormalization process is introduced which significantly improves stability and generalization ability. On the theoretical side, we establish a generalization error estimate in terms of the number of training data, the width of DeepONets, and the number of input and output sensors. Numerical examples are presented to demonstrate the effectiveness of the two-step training method, including Darcy flow in heterogeneous porous media.

deep operator networks↗
DOE OSTI2020

Hawai‘i National Marine Renewable Energy Center (HINMREC)

The Hawaii National Marine Renewable Energy Center (HINMREC) was established to facilitate the commercialization of wave energy converter (WEC) devices, and to accelerate development and testing of Ocean Thermal Energy Conversion (OTEC) technologies. Housed at the Hawaii Natural Energy Institute (HNEI) of the University of Hawaii (UH), this program started with execution of the contract between the US Department of Energy (DOE) and UH in March 2009, and activities ran through the end of the project in September 2019. The DOE tasked HINMREC with facilitating and accelerating the build-out of the Navy’s Wave Energy Test Site (WETS), the nation’s first grid-connected open water wave energy conversion test facility, located off Marine Corps Base Hawaii (MCBH) in Kaneohe, on the island of Oahu. WETS was expanded from an existing test berth at 30m water depth to include test berths at 60m and 80m water depths. In recognition of the high costs associated with at-sea testing and evaluation of WEC devices, it was deemed imperative that HINMREC seek ways to reduce costs to developers by providing key research support to these early-stage technologies. WETS and HINMREC’s support allowed development of wave energy technology by providing a testing infrastructure that allows technology developers to test, demonstrate and evaluate their WEC devices, and generate data in order to advance WEC designs toward commercial readiness. HINMREC’s roles have included support in the establishment of the full site, including of wave resource characterization and site survey, followed by the essential roles of independent WEC device power performance assessment and environmental monitoring in support of deployed pre-commercial WECs. This DOE-funded work transitioned effectively to continue Navy-funded tasks for OTEC development, and activities at WETS, now under Naval Facilities Engineering Command (NAVFAC) funding. A secondary objective in the establishment of HINMREC was to assist the private sector in moving OTEC systems beyond proof-of-concept to pre-commercialization, primarily focused on system and component engineering, and local and global investigations into the potential environmental impacts of OTEC systems. HINMREC was tasked with maintaining high-resolution models of ocean thermal resources and the potential sustainable power output of OTEC systems. Ongoing tests begun previously under Navy funding at the OTEC Heat Exchangers (HXs) Test Facility at the Natural Energy Laboratory of Hawaii Authority (NELHA), in Kona on Hawaii Island, have been continued to identify cost-effective aluminum alloys for use in OTEC systems operating in the corrosive marine environment.

16 TIDAL AND WAVE POWER↗
DOE OSTI2022

Development of Surface Sampling Techniques for the Canister Deposition Field Demonstration (FY22 Update)

This report describes the proposed surface sampling techniques and plan for the multi-year Canister Deposition Field Demonstration (CDFD). The CDFD is primarily a dust deposition test that will use three commercial 32PTH2 NUHOMS welded stainless steel storage canisters in Advanced Horizontal Storage Modules, with planned exposure testing for up to 10 years at an operating ISFSI site. One canister will be left at ambient condition, unheated; the other two will have heaters to achieve canister surface temperatures that match, to the degree possible, spent nuclear fuel (SNF) loaded canisters with heat loads of 10 kW and 40 kW. Surface sampling campaigns for dust analysis will take place on a yearly or bi-yearly basis. The goal of the planned dust sampling and analysis is to determine important environmental parameters that impact the potential occurrence of stress corrosion cracking on SNF dry storage canisters. Specifically, measured dust deposition rates and deposited particle sizes will improve parameterization of dust deposition models employed to predict the potential occurrence and timing of stress corrosion cracks on the stainless steel SNF canisters. The size, morphology, and composition of the deposited dust and salt particles will be quantified, as well as the soluble salt load per unit area and the rate of deposition, as a function of canister surface temperature, location, time, and orientation. Previously, a preliminary sampling plan was developed, identifying possible sampling locations on the canister surfaces and sampling intervals; possible sampling methods were also described. Further development of the sampling plan has commenced through three different tasks. First, canister surface roughness, a potentially important parameter for air flow and dust deposition, was characterized at several locations on one of the test canisters. Second, corrosion testing to evaluate the potential lifetime and aging of thermocouple wires, spot welds, and attachments was initiated. Third, hand sampling protocols were developed, and initial testing was carried out. The results of those efforts are presented in this report. The information obtained from the CDFD will be critical for ongoing efforts to develop a detailed understanding of the potential for stress corrosion cracking of SNF dry storage canisters.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2023

ZeoNet: 3D convolutional neural networks for predicting adsorption in nanoporous zeolites

Zeolites are one of the most widely used materials in the chemical industry due to their nanometer-sized pores that can adsorb and react upon molecules selectively. With hundreds of known framework topologies and hundreds of thousands of computationally predicted structures, the ability to rapidly predict zeolite performance allows researchers to prioritize their efforts on the most promising structures for a given application. Although the accuracy of forcefield-based atomistic simulations has advanced significantly in the past two decades, these simulations can be computationally expensive, especially for long-chain, complex molecules. Here, we present ZeoNet, a representation learning framework using convolutional neural networks (ConvNets) and 3D volumetric representations for predicting adsorption in zeolites. ZeoNet was trained on the task of predicting Henry's constants for adsorption, k H , of n-octadecane in more than 330 000 known and predicted zeolite materials. Employing a 3D grid based on the distances to solvent-accessible surfaces, a volumetric representation that can be generated efficiently, the best-performing ZeoNet achieved a correlation coefficient r 2 = 0.977 and a mean-squared error MSE = 3.8 in ln k H , which corresponds to an error of 9.3 kJ mol -1 in adsorption free energy. In comparison, a model based on hand-designed geometric features has values of r 2 = 0.783 and MSE = 35.7. ZeoNet is also relatively efficient and can process ≈8 structures per second on an Nvidia RTX 2080TI GPU, orders of magnitude faster than forcefield-based simulations. A systematic analysis was conducted to investigate how the choice of ConvNet architectures, the linear dimension (L) and spatial resolution (Δd) of the distance grids, batch size, optimizer, and learning rate impact the model performance. We found that ConvNets based on the ResNet architecture offer the best tradeoff between expressiveness and efficiency. The performance for all models reaches a plateau at L = 30–45 Å and depends less sensitively on grid resolution, with a small benefit around Δd = 0.30–0.45 Å. Finally, saliency maps were visualized to identify which regions of the materials contributed the most to model predictions. It was found, interestingly, that the predictions are driven primarily by the accessible pore volume rather than the region occupied by the framework atoms.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Interpreting and Stabilizing Machine-Learning Parametrizations of Convection

Neural networks are a promising technique for parameterizing subgrid-scale physics (e.g., moist atmospheric convection) in coarse-resolution climate models, but their lack of interpretability and reliability prevents widespread adoption. For instance, it is not fully understood why neural network parameterizations often cause dramatic instability when coupled to atmospheric fluid dynamics. This paper introduces tools for interpreting their behavior that are customized to the parameterization task. First, we assess the nonlinear sensitivity of a neural network to lower-tropospheric stability and the midtropospheric moisture, two widely studied controls of moist convection. Second, we couple the linearized response functions of these neural networks to simplified gravity wave dynamics, and analytically diagnose the corresponding phase speeds, growth rates, wavelengths, and spatial structures. To demonstrate their versatility, these techniques are tested on two sets of neural networks, one trained with a super-parameterized version of the Community Atmosphere Model (SPCAM) and the second with a near-global cloud-resolving model (GCRM). Additionally, even though the SPCAM simulation has a warmer climate than the cloud-resolving model, both neural networks predict stronger heating/drying in moist and unstable environments, which is consistent with observations. Moreover, the spectral analysis can predict that instability occurs when GCMs are coupled to networks that support gravity waves that are unstable and have phase speeds larger than 5 m s -1 . In contrast, standing unstable modes do not cause catastrophic instability. Using these tools, differences between the SPCAM-trained versus GCRM-trained neural networks are analyzed, and strategies to incrementally improve both of their coupled online performance unveiled.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Unified Medical Language System resources improve sieve-based generation and Bidirectional Encoder Representations from Transformers (BERT)–based ranking for concept normalization

Concept normalization, the task of linking phrases in text to concepts in an ontology, is useful for many downstream tasks including relation extraction, information retrieval, etc. We present a generate-and-rank concept normalization system based on our participation in the 2019 National NLP Clinical Challenges Shared Task Track 3 Concept Normalization. The shared task provided 13 609 concept mentions drawn from 100 discharge summaries. We first design a sieve-based system that uses Lucene indices over the training data, Unified Medical Language System (UMLS) preferred terms, and UMLS synonyms to generate a list of possible concepts for each mention. We then design a listwise classifier based on the BERT (Bidirectional Encoder Representations from Transformers) neural network to rank the candidate concepts, integrating UMLS semantic types through a regularizer. Our generate-and-rank system was third of 33 in the competition, outperforming the candidate generator alone (81.66% vs 79.44%) and the previous state of the art (76.35%). During postevaluation, the model’s accuracy was increased to 83.56% via improvements to how training data are generated from UMLS and incorporation of our UMLS semantic type regularizer. Analysis of the model shows that prioritizing UMLS preferred terms yields better performance, that the UMLS semantic type regularizer results in qualitatively better concept predictions, and that the model performs well even on concepts not seen during training. Our generate-and-rank framework for UMLS concept normalization integrates key UMLS features like preferred terms and semantic types with a neural network–based ranking model to accurately link phrases in text to UMLS concepts.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2021

Parallel String Graph Construction and Transitive Reduction for De Novo Genome Assembly

One of the most computationally intensive tasks in computational biology is de novo genome assembly, the decoding of the sequence of an unknown genome from redundant and erroneous short sequences. A common assembly paradigm identifies overlapping sequences, simplifies their layout, and creates consensus. Despite many algorithms developed in the literature, the efficient assembly of large genomes is still an open problem. In this work, we introduce new distributed-memory parallel algorithms for overlap detection and layout simplification steps of de novo genome assembly, and implement them in the diBELLA 2D pipeline. Our distributed memory algorithms for both overlap detection and layout simplification are based on linear-algebra operations over semirings using 2D distributed sparse matrices. Our layout step consists of performing a transitive reduction from the overlap graph to a string graph. We provide a detailed communication analysis of the main stages of our new algorithms. diBELLA 2D achieves near linear scaling with over 80% parallel efficiency for the human genome, reducing the runtime for overlap detection by 1.2-1.3× for the human genome and 1.5-1.9× for C.elegans compared to the state-of-the-art. Our transitive reduction algorithm outperforms an existing distributed-memory implementation by 10.5-13.3× for the human genome and 18-29× for the C. elegans. Our work paves the way for efficient de novo assembly of large genomes using long reads in distributed memory.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Effect of image resolution on automated classification of chest X-rays

Deep learning (DL) models have received much attention lately for their ability to achieve expert-level performance on the accurate automated analysis of chest X-rays (CXRs). Recently available public CXR datasets include high resolution images, but state-of-the-art models are trained on reduced size images due to limitations on graphics processing unit memory and training time. As computing hardware continues to advance, it has become feasible to train deep convolutional neural networks on high-resolution images without sacrificing detail by downscaling. This study examines the effect of increased resolution on CXR classification performance. We used the publicly available MIMIC-CXR-JPG dataset, comprising 377,110 high resolution CXR images for this study. We applied image downscaling from native resolution to 2048 × 2048 pixels, 1024 × 1024 pixels, 512 × 512 pixels, and 256 × 256 pixels and then we used the DenseNet121 and EfficientNet-B4 DL models to evaluate clinical task performance using these four downscaled image resolutions. We find that while some clinical findings are more reliably labeled using high resolutions, many other findings are actually labeled better using downscaled inputs. We qualitatively verify that tasks requiring a large receptive field are better suited to downscaled low resolution input images, by inspecting effective receptive fields and class activation maps of trained models. Lastly, we show that stacking an ensemble across resolutions outperforms each individual learner at all input resolutions while providing interpretable scale weights, indicating that diverse information is extracted across resolutions.

47 OTHER INSTRUMENTATION↗