Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “tasks”

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 1,369 records · Page 76
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

PRMI: A Dataset of Minirhizotron Images for Diverse Plant Root Study

Understanding a plant's root system architecture (RSA) is crucial for a variety of plant science problem domains including sustainability and climate adaptation. Minirhizotron (MR) technology is a widely-used approach for phenotyping RSA non-destructively by capturing root imagery over time. Precisely segmenting roots from the soil in MR imagery is a critical step in studying RSA features. In this paper, we introduce a large-scale dataset of plant root images captured by MR technology. In total, there are over 72K RGB root images across six different species including cotton, papaya, peanut, sesame, sunflower, and switchgrass in the dataset. The images span a variety of conditions including varied root age, root structures, soil types, and depths under the soil surface. All of the images have been annotated with weak image-level labels indicating whether each image contains roots or not. The image-level labels can be used to support weakly supervised learning in plant root segmentation tasks. In addition, 63K images have been manually annotated to generate pixel-level binary masks indicating whether each pixel corresponds to root or not. These pixel-level binary masks can be used as ground truth for supervised learning in semantic segmentation tasks. By introducing this dataset, we aim to facilitate the automatic segmentation of roots and the research of RSA with deep learning and other image analysis algorithms.

Xu, Weihuang↗
DOE OSTI2024

Holographic pseudoentanglement and the complexity of the AdS/CFT dictionary

The `quantum gravity in the lab' paradigm suggests that quantum computers might shed light on quantum gravity by simulating the CFT side of the AdS/CFT correspondence and mapping the results to the AdS side. This relies on the assumption that the duality map (the `dictionary') is efficient to compute. In this work, we show that the complexity of the AdS/CFT dictionary is surprisingly subtle: there might be cases in which one can efficiently apply operators to the CFT state (a task we call 'operator reconstruction') without being able to extract basic properties of the dual bulk state such as its geometry (which we call 'geometry reconstruction'). Geometry reconstruction corresponds to the setting where we want to extract properties of a completely unknown bulk dual from a simulated CFT boundary state. We demonstrate that geometry reconstruction may be generically hard due to the connection between geometry and entanglement in holography. In particular we construct ensembles of states whose entanglement approximately obey the Ryu-Takayanagi formula for arbitrary geometries, but which are nevertheless computationally indistinguishable. This suggests that even for states with the special entanglement structure of holographic CFT states, geometry reconstruction might be hard. This result should be compared with existing evidence that operator reconstruction is generically easy in AdS/CFT. A useful analogy for the difference between these two tasks is quantum fully homomorphic encryption (FHE): this encrypts quantum states in such a way that no efficient adversary can learn properties of the state, but operators can be applied efficiently to the encrypted state. We show that quantum FHE can separate the complexity of geometry reconstruction vs operator reconstruction, which raises the question whether FHE could be a useful lens through which to view AdS/CFT.

FOS: Physical sciences↗
DOE OSTI2024

Uncertainty Propagation within Chained Models for Machine Learning Reconstruction of Neutrino-LAr Interactions

Sequential or chained models are increasingly prevalent in machine learning for scientific applications, due to their flexibility and ease of development. Chained models are particularly useful when a task is separable into distinct steps with a hierarchy of meaningful intermediate representations. In reliability-critical tasks, it is important to quantify the confidence of model inferences. However, chained models pose an additional challenge for uncertainty quantification, especially when input uncertainties need to be propagated. In such cases, a fully uncertainty-aware chain of models is required, where each step accepts a probability distribution over the input space, and produces a probability distribution over the output space. In this work, we present a case study for adapting a single model within an existing chain, designed for reconstruction within neutrino-Argon interactions, developed for neutrino oscillation experiments such as MicroBooNE, ICARUS, and the future DUNE experiment. We test the performance of an input uncertainty-enabled model against an uncertainty-blinded model using a method for generating synthetic noise. By comparing these two, we assess the increase in inference quality achieved by exposing models to upstream uncertainty estimates.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

KGML-ag: a modeling framework of knowledge-guided machine learning to simulate agroecosystems: a case study of estimating N<sub>2</sub>O emission using data from mesocosm experiments

Abstract. Agricultural nitrous oxide (N2O) emission accounts for a non-trivial fraction of global greenhouse gas (GHG) budget. To date, estimating N2O fluxes from cropland remains a challenging task because the related microbial processes (e.g., nitrification and denitrification) are controlled by complex interactions among climate, soil, plant and human activities. Existing approaches such as process-based (PB) models have well-known limitations due to insufficient representations of the processes or uncertainties of model parameters, and due to leverage recent advances in machine learning (ML) a new method is needed to unlock the “black box” to overcome its limitations such as low interpretability, out-of-sample failure and massive data demand. In this study, we developed a first-of-its-kind knowledge-guided machine learning model for agroecosystems (KGML-ag) by incorporating biogeophysical and chemical domain knowledge from an advanced PB model, ecosys, and tested it by comparing simulating daily N2O fluxes with real observed data from mesocosm experiments. The gated recurrent unit (GRU) was used as the basis to build the model structure. To optimize the model performance, we have investigated a range of ideas, including (1) using initial values of intermediate variables (IMVs) instead of time series as model input to reduce data demand; (2) building hierarchical structures to explicitly estimate IMVs for further N2O prediction; (3) using multi-task learning to balance the simultaneous training on multiple variables; and (4) pre-training with millions of synthetic data generated from ecosys and fine-tuning with mesocosm observations. Six other pure ML models were developed using the same mesocosm data to serve as the benchmark for the KGML-ag model. Results show that KGML-ag did an excellent job in reproducing the mesocosm N2O fluxes (overall r2=0.81, and RMSE=3.6 mgNm-2d-1 from cross validation). Importantly, KGML-ag always outperforms the PB model and ML models in predicting N2O fluxes, especially for complex temporal dynamics and emission peaks. Besides, KGML-ag goes beyond the pure ML models by providing more interpretable predictions as well as pinpointing desired new knowledge and data to further empower the current KGML-ag. We believe the KGML-ag development in this study will stimulate a new body of research on interpretable ML for biogeochemistry and other related geoscience processes.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

International collaboration in disposal research: comparative modeling of coupled processes in the DECOVALEX project

Abstract. This presentation gives an overview of an international research collaboration for advancing the understanding and modeling of coupled thermo-hydro-mechanical-chemical (THMC) processes in geological systems. The creation of the international DECOVALEX project, now running for more than 25 years, was motivated by the recognition that prediction of these coupled effects is an essential part of the performance and safety assessment of geologic disposal systems for radioactive waste and spent nuclear fuel. DECOVALEX emphasizes joint analysis and comparative modeling of state-of-the-art field and laboratory experiments, across a range of host rock options and repository designs. Participating research teams are from radioactive waste management organizations, national research institutes, regulatory agencies, universities, and consulting groups, providing a wide range of perspectives and solutions to these complex problems. The presentation provides examples of the research contributions made collectively in past DECOVALEX tasks and also touches on the unique modeling challenges tackled in the ongoing project phase, referred to as DECOVALEX-2023. The current phase comprises 17 partner organizations, about 50 modeling teams, and 7 modeling tasks, which cover a broad portfolio from fundamental studies on gas migration to full-scale in situ heater experiments in different host rocks to performance assessment studies. Together, these examples illustrate that the insight and scientific knowledge gained within the DECOVALEX project would not have been possible if one group had studied these complex THMC modeling challenges alone rather than within a truly collaborative setting.

Birkholzer, Jens T.↗
DOE OSTI2023

Progress in the validation of rotor aerodynamic codes using field data

Within the framework of the fourth phase of the International Energy Agency (IEA) Wind Task 29, a large comparison exercise between measurements and aeroelastic simulations has been carried out featuring three simulation cases in axial, sheared and yawed inflow conditions. Results were obtained from more than 19 simulation tools originating from 12 institutes, ranging in fidelity from blade element momentum (BEM) to computational fluid dynamics (CFDs) and compared to state-of-the-art field measurements from the 2 MW DanAero turbine. More than 15 different variable types ranging from lifting-line variables to blade surface pressures, loads and velocities have been compared for the different conditions, resulting in over 250 comparison plots. The result is a unique insight into the current status and accuracy of rotor aerodynamic modeling. For axial flow conditions, a good agreement was found between the various code types, where a dedicated grid sensitivity study was necessary for the CFD simulations. However, compared to wind tunnel experiments on rotors featuring controlled conditions, it remains a challenge to achieve good agreement of absolute levels between simulations and measurements in the field. For sheared inflow conditions, uncertainties due to rotational and unsteady effects on airfoil data result in the CFD predictions standing out above the codes that need input of sectional airfoil data. However, it was demonstrated that using CFD-synthesized airfoil data is an effective means to bypass this shortcoming. For yawed flow conditions, it was observed that modeling of the skewed wake effect is still problematic for BEM codes where CFD and free vortex wake codes inherently model the underlying physics correctly. The next step is a comparison in turbulent inflow conditions, which is featured in IEA Wind Task 47. Doing this analysis in cooperation under the auspices of the IEA Wind Technology Collaboration Program (TCP) has led to many mutual benefits for the participants. The large size of the consortium brought ample manpower for the analysis where the learning process by combining several complementary experiences and modeling techniques gave valuable insights that could not be found when the analysis is carried out individually.

17 WIND ENERGY↗
DOE OSTI2025

Producing High-fidelity Synthetic Population Ensembles at Scale

Used within social simulations, synthetic population ensembles enable uncertainty quantification (UQ) methods for obtaining more robust model inference and prediction. A synthetic population ensemble is a series of plausible virtual reconstructions of an area’s population at the granularity of people and residences, generated stochastically to preserve privacy of the source population survey’s respondents. In this paper, we demonstrate the production of large synthetic population ensembles for the US via Oak Ridge National Laboratory’s UrbanPop framework to support modeling of high spatial resolution energy affordability metrics from nationwide social surveys in collaboration with the fusionACS project. Our initial task involves creating ensembles for 17 US metropolitan areas, each consisting of 41 population instances (a base realization and 40 replicates). To accomplish this task at scale, we configured an integrated system comprised of a research cloud, virtual containerization, GPU-enhanced functionality, and a dual API/CLI to interact with UrbanPop’s maturing Likeness Python ecosystem. We observe a reduction in theoretical execution time while maintaining high-fidelity approximations of residential totals by metropolitan area and the demographic characteristics of neighborhoods. We discuss expansion of our approach to produce synthetic population ensembles for the entire US, particularly plans to establish automated workflows for job orchestration to increase computational efficiency, as well as provide outlook for broadening applications of the ensembles.

Gaboardi, James [ORNL] (ORCID:0000000247766826)↗
DOE OSTI2023

Screening and Brief Interventions for Alcohol Use During Pregnancy: Practices Among US Primary Care Clinicians, DocStyles 2019

Alcohol use during pregnancy can cause birth defects and developmental disabilities. From 2018 through 2020, 13.5% of pregnant women reported current drinking. The US Preventive Services Task Force recommends evidence-based tools (eg, AUDIT-C and SASQ) for implementing screening and brief interventions to reduce excessive alcohol use among adults, including pregnant people, for whom any alcohol use is considered excessive. We used DocStyles 2019 data to conduct a cross-sectional analysis to examine current screening and brief intervention practices that primary care clinicians conduct among pregnant patients; clinicians’ confidence levels in conducting screening, brief interventions, and referral to treatment; and the documentation of brief interventions in the medical record. A total of 1,500 US adult medicine clinicians completed the entire survey. Among the respondents who conduct screening (N = 1,373) and brief interventions (N = 1,357) in their practice, nearly all reported implementing screening (94.6%) and brief interventions (94.9%) with their pregnant patients for alcohol use, but fewer than half felt confident about conducting their screening practices (46.5%). Two-thirds (64%) reported using a tool that met the criteria recommended by the US Preventive Services Task Force (USPSTF). Over half documented brief interventions in electronic health record notes (51.7%) or designated space (50.7%). Pregnancy presents a unique opportunity for clinicians to incorporate screening into routine obstetric care and encourage behavior change among patients. Most providers reported always screening their pregnant patients for alcohol use, but fewer used evidence-based USPSTF-recommended screening tools. Increased clinician confidence in screening and brief intervention, the use of standardized screening tools tailored to pregnant people, and maximal use of electronic health record technology may enhance the benefits of their application to alcohol use, which ultimately can reduce adverse outcomes associated with alcohol use during pregnancy.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2023

Test and Evaluation of Systems with Embedded Machine Learning Components

As Machine Learning (ML) continues to advance, it is being integrated into more systems. Often, the ML component represents a significant portion of the system that reduces the burden on the end user or significantly improves task performance. However, the ML component represents an unknown complex phenomenon that is learned from collected data without the need to be explicitly programmed. Despite the improvement in task performance, the models are often black boxes. Evaluating the credibility and the vulnerabilities of ML models poses a gap in current test and evaluation practice. For high consequence applications, the lack of testing and evaluation procedures represents a significant source of uncertainty and risk. To help reduce that risk, here we present considerations to evaluate systems embedded with an ML component within a red-teaming inspired methodology. We focus on (1) cyber vulnerabilities to an ML model, (2) evaluating performance gaps, and (3) adversarial ML vulnerabilities.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

Hierarchical power distribution in large scale computing systems

Techniques for managing power distribution amongst processors in a massively parallel computer architecture are disclosed. The techniques utilize a hierarchy that organizes the various processors of the massively parallel computer architecture. The hierarchy groups numbers of the processors at the lowest level. When processors complete tasks, the power assigned to those processors is distributed to other processors in the same group so that the performance of those processors can be increased. Hierarchical organization simplifies the calculations required for determining how and when to distribute power, because when tasks are complete and power is available for distribution, a relatively small number of processors are available for consideration to receive that power. The number of processors that are grouped together can be adjusted in real time based on performance factors to improve the trade-off between calculation speed and power distribution efficacy.

42 ENGINEERING↗
DOE OSTI2020

Enabling Highly Efficient Capsule Networks Processing Through A PIM-Based Architecture Design

In recent years, the CNNs have achieved great successes in the image processing tasks, e.g., image recognition and object detection. Unfortunately, traditional CNN's classication is found to be easily misled by increasingly complex image features due to the usage of pooling operations, hence unable to preserve accurate position and pose information of the objects. To address this challenge, a novel neural network structure called Capsule Network has been proposed, which introduces equivariance through capsules to signicantly enhance the learning ability for image segmentation and object detection. Due to its requirement of performing a high volume of matrix operations, CapsNets have been generally accelerated on modern GPU platforms that provide highly optimized software library for common deep learning tasks. However, based on our performance characterization on modern GPUs, CapsNets exhibit low effciency due to the special program and execution features of their routing procedure, including massive unshareable intermediate variables and intensive syn- chronizations, which are very dicult to optimize at software level. To address these challenges, we propose a hybrid computing architecture design named PIM-CapsNet. It preserves GPU's on-chip computing capability for accelerating CNN types of layers in CapsNet, while pipelining with an off-chip in-memory acceleration solution that effectively tackles routing procedure's ineffciency by leveraging the processing-in-memory capability of today's 3D stacked memory. Using routing procedure's inherent parallellization feature, our design enables hierarchical improvements on CapsNet inference effciency through minimizing data movement and maximizing parallel processing in memory. Evaluation results demonstrate that our proposed design can achieve substantial improvement on both performance and energy savings for CapsNet inference, with almost zero accuracy loss. The results also suggest good performance scalability in optimizing the routing procedure with increasing network size.

Zhang, Xingyao↗
DOE OSTI2020

Achieving balanced execution through runtime detection of performance variation

Systems, apparatuses, and methods for achieving balanced execution in a multi-node cluster through runtime detection of performance variation are described. During a training phase, performance counters and an amount of time spent waiting for synchronization is monitored for a plurality of tasks for each node of the multi-node cluster. These values are utilized to generate a model which correlates the values of the performance counters to the amount of time spent waiting for synchronization. Once the model is built, the values of the performance counters are monitored for a period of time at the start of each task, and these values are input into the model. The model generates a prediction of whether a given node is on the critical path. If the given node is predicted to be on the critical path, the power allocation of the given node is increased.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Modeling and Simulation of Automated Mobility Districts

Increasing interest and investment in connected, automated, and electric vehicles (CAEVs), and mobility-as-a-service (MaaS) concepts are paving the way for the next major shift in transportation through automated and shared mobility. The initial excitement towards rapid deployment and adoption of automated vehicles has subsided, and low-speed automated shuttles are emerging as a more pragmatic pathway for introducing automated mobility in geo-fenced districts. Such shuttles hold the promise to provide a viable alternative for serving short trips in urban districts with high travel densities. As interest in low-speed automated shuttle systems (to improve urban mobility) increases, the need for tools that can inform communities regarding benefits or dis-benefits of automated shuttle deployments is imminent. However, most of the existing transportation planning and simulation tools are not capable of handling emerging shared automated mobility options. This presentation provide the details of a microscopic simulation toolkit that can be used by cities and communities to plan for the deployment of low-speed automated shuttles systems, as well as other shared mobility options. Labeled as Automated Mobility District (AMD) modeling and simulation toolkit, the proposed decision support tool intends to help cities evaluate the mobility and sustainability impacts of deploying shared automated vehicles in geofenced regions.The AMD modeling and simulation task is funded through DOE's SMART Mobility Consortium. This presentation outlines the progress of the AMD modeling and simulation task in FY19, including case studies conducted in Greenville, SC, and Austin, TX.

47 OTHER INSTRUMENTATION↗
DOE OSTI2020

Milestone 2.7: Evaluation of Techniques for the Measurement of Molecular Hydrogen Gas in Helium Matrices

Published data by Task 2 (Oxyhydroxide Layer Radiolytic Gas Generation Resolution) for Technical Considerations and Challenges for Extended (>50 yrs) Dry Storage of Aluminum Cladded Spent Nuclear Fuel (ASNF), demonstrated that radiolytic molecular hydrogen (H2) production from gamma irradiated aluminum alloy 1100 (Al-1100) coupons exhibited significant dependence on backfill gaseous environment conditions: air, due to the presence of oxygen, completely inhibited H2 production; nitrogen promoted H2 production; and argon yielded more H2 than nitrogen environments. The concern here is that helium has been proposed as the backfill gas for extended storage and is more inert than argon, which may translate into significantly more H2 production than current Task 3 argon-based models predict. However, the measurement of H2 in helium media was not possible using the previously establish gas chromatography (GC) flame ionization detector, due to similarities in thermal conductivity. This milestone was initiated to evaluate an alternative GC approach that employed a mercuric oxide (HgO) reduction gas detector (RGD). Using the HgO RGD setup, H2 was successfully calibrated in the presence of a helium carrier gas, and then subsequently measured in control and irradiated crush-tube sample vials, consistent with previous sample measurements. Overall, the HgO RGD approach was found to be sufficient for future helium environment irradiations.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗
DOE OSTI2020

Reinforcement-based Program Induction in a Neural Virtual Machine

We present a neural virtual machine that can be trained to perform algorithmic tasks. Rather than combining a neural controller with non-neural memory storage as has been done in the past, this architecture is purely neural and emulates tape-based memory via fast associative weights (onestep learning). Here we formally define the architecture, and then extend the system to learn programs using recurrent policy gradient reinforcement learning based on examples of program inputs labeled with corresponding output targets, which are compared against actual output to generate a sparse reward signal. We describe the policy gradient training procedure used, and report its empirical performance on a number of smallscale list processing tasks, such as finding the maximum list element, filtering out certain elements, and reversing the order of the elements. These results show that program induction via reinforcement learning is possible using sparse rewards and solely neural computations.

Katz, Garrett E.↗
DOE OSTI2020

Autonomous Monitoring of Nuclear Repositories: Current State of the Art and Future Directions

Geological repositories for nuclear waste, including spent nuclear fuel, present a significant challenge for traditional International Atomic Energy Agency (IAEA) safeguards tools due to their inaccessibility and demanding operational conditions. The IAEA has been working closely with Member State organizations currently involved in repository construction and planning, including Euratom, the Finnish and Swedish regulatory authorities, and relevant facility operators. However, the verification challenge remains unsolved, and there persists an out- standing need for tools and approaches that will help the IAEA verify that no nuclear material is diverted from a repository environment. The challenge is also not static. Activities must encompass verification of the design, prior to and during the construction/operation phase, and post backfill. Throughout these various phases, it is imperative that the IAEA maintains a continuity of knowledge (CoK) of all material including information on material inventory and flow. This paper highlights these challenges and outlines how they might be addressed by using remote or autonomous vehicles. Specifically, we discuss the current state of the art in robotic autonomy for known or partially known environment mapping and patrolling, as well as shared autonomy, where humans collaborate with closed-loop autonomation to complete tasks. We explore the feasibility of using rovers for these verification tasks, along with the challenges associated with system implementation. Hardware and software suggestions are provided based on the adoption of similar technologies in other comparable areas and ability to close technical gaps. Lastly, human-robotic interactions are considered based on the challenges of the environment of the repository and effective deployment and continued operation of the robot system.

geologic repository, safeguards, IAEA, Robotics↗
DOE OSTI2020

Video Summarization Using Deep Action Recognition Features and Robust Principal Components Analysis

In an instance where desired pre-defined actions, behaviors, or other categories are known a priori, various video classification and recognition models can be trained to discover those classifications and their location within the video. Absent that information, one might still be tasked with identifying interesting portions within a video, a process which—if done manually—is onerous and time-consuming as it requires manual inspection of the video itself. Recognizing high-level interesting segments within a whole video has been a general area of interest due to the ubiquity of video data. However the size of the data makes storage, retrieval, and inspection of large collections of videos cumbersome. This problem motivates the task of generating shortened clips highlighting the primary content of a video, relieving the burden of having to watch the entire video. This paper presents an unsupervised method of creating shortened clips of videos, enabling the rapid review of the most interesting content within a video. Our method uses features extracted from pre-trained action recognition models as input to online moving window robust principal component analysis to generate summaries. The procedure is tested on a publicly available video summarization dataset and demonstrates comparable performance to state-of-the-art in an un-augmented setting while requiring no training.

Claborne, Daniel M.↗
DOE OSTI2020

Multimodal Data Representation with Deep Learning for Extracting Cancer Characteristics from Clinical Text

This paper presents a multimodal data representation to improve the performance of deep learning models for extracting cancer key characteristics from unstructured text in pathology reports. Specifically, in addition to using the text as the input to deep learning models, we use concept unique identifiers (CUIs) as another source of information to the models. We analyze the performance of different text and CUI data representations, including word embeddings and bag of embeddings (BOE), with a convolutional neural network (CNN) and a fully connected multilayer perceptron neural network (MLP-NN). The high level document embeddings from text and CUI inputs are combined by concatenating them and then applying a classifier. The model is used for extracting cancer subsite and histology from pathology reports. These two classification tasks have a large number of labels, i.e. 317 for subsite and 556 for histology, with extreme class imbalance. We compare the performance of the developed DL models across the two tasks based on micro- and macro-F1 scores. The evaluation shows that a multi-channel DL model that utilizes text represented by word embeddings and CUIs represented by BOE outperforms other DL models. Also, this approach significantly improves the model performance on low prevalence classes.

Alawad, Mohammed↗