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 217 records · Page 12

arcjetCV: A New Machine Learning Application for Extracting Time-Resolved Recession Measurements From Arc Jet Test Videos

Arc jet Computer Vision (ArcjetCV) is a software application built to automate analysis of arc jet ground test video footage. This includes tracking material recession and the shock-material standoff distance. This provides a new capability to resolve and validate new physics associated with non-linear processes. This is an essential step to reduce testing, modeling, and validation uncertainties for heatshield material performance. ArcjetCV uses several types of machine learning (convolutional neural net: CNN, decision tree: DT, k-means unsupervised clustering: KM) to automate the video processing pipeline. These include inferring the start/stop of time segments of interest (1D CNN), measuring the time-dependent 2D recession of the material samples (2D CNN, DT), measuring the time-dependent shock standoff distance (2D CNN, DT), and post-processing cleaning of the recession data (KM). The software also provides a graphical user interface for ease of use. The results of using this tool on arc jet videos show non-linear time-dependent effects can be important for certain materials and characterizing certain failure modes.

machine learning↗

Solving and Learning Soft Temporal Constraints: Experimental Scenario and Examples

Soft temporal constraint problems allow to describe in a natural way scenarios where events happen over time and preferences are associated to event distances and durations. However, sometimes such local preferences are difficult to set, and it may be easier instead to associate preferences to some complete solutions of the problem. To model everything in a uniform way via local preferences only, and also to take advantage of the existing constraint solvers which exploit only local preference use machine learning techniques which learn the local preferences from the global ones. In this paper we describe the existing framework for both solving and learning preferences in temporal constraint problems, the implemented modules, the experimental scenario, and preliminary results on some examples.

Rossi, F.↗

Representations and strategies for transferable machine learning improve model performance in chemical discovery

Strategies for machine-learning (ML)-accelerated discovery that are general across material composition spaces are essential, but demonstrations of ML have been primarily limited to narrow composition variations. By addressing the scarcity of data in promising regions of chemical space for challenging targets such as open-shell transition-metal complexes, general representations and transferable ML models that leverage known relationships in existing data will accelerate discovery. Over a large set (~1000) of isovalent transition-metal complexes, we quantify evident relationships for different properties (i.e., spin-splitting and ligand dissociation) between rows of the Periodic Table (i.e., 3d/4d metals and 2p/3p ligands). We demonstrate an extension to the graph-based revised autocorrelation (RAC) representation (i.e., eRAC) that incorporates the group number alongside the nuclear charge heuristic that otherwise overestimates dissimilarity of isovalent complexes. To address the common challenge of discovery in a new space where data are limited, we introduce a transfer learning approach in which we seed models trained on a large amount of data from one row of the Periodic Table with a small number of data points from the additional row. We demonstrate the synergistic value of the eRACs alongside this transfer learning strategy to consistently improve model performance. Analysis of these models highlights how the approach succeeds by reordering the distances between complexes to be more consistent with the Periodic Table, a property we expect to be broadly useful for other material domains.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

MRI-alone radiation therapy planning for prostate cancer: Automatic fiducial marker detection

Purpose: The feasibility of radiation therapy treatment planning using substitute computed tomography (sCT) generated from magnetic resonance images (MRIs) has been demonstrated by a number of research groups. One challenge with an MRI-alone workflow is the accurate identification of intraprostatic gold fiducial markers, which are frequently used for prostate localization prior to each dose delivery fraction. This paper investigates a template-matching approach for the detection of these seeds in MRI. Methods: Two different gradient echo T1 and T2* weighted MRI sequences were acquired from fifteen prostate cancer patients and evaluated for seed detection. For training, seed templates from manual contours were selected in a spectral clustering manifold learning framework. This aids in clustering “similar” gold fiducial markers together. The marker with the minimum distance to a cluster centroid was selected as the representative template of that cluster during training. During testing, Gaussian mixture modeling followed by a Markovian model was used in automatic detection of the probable candidates. The probable candidates were rigidly registered to the templates identified from spectral clustering, and a similarity metric is computed for ranking and detection. Results: A fiducial detection accuracy of 95% was obtained compared to manual observations. Expert radiation therapist observers were able to correctly identify all three implanted seeds on 11 of the 15 scans (the proposed method correctly identified all seeds on 10 of the 15). Conclusions: An novel automatic framework for gold fiducial marker detection in MRI is proposed and evaluated with detection accuracies comparable to manual detection. When radiation therapists are unable to determine the seed location in MRI, they refer back to the planning CT (only available in the existing clinical framework); similarly, an automatic quality control is built into the automatic software to ensure that all gold seeds are either correctly detected or a warning is raised for further manual intervention.

60 APPLIED LIFE SCIENCES↗

MO-DE-BRA-04: Hands-On Fluoroscopy Safety Training with Real-Time Patient and Staff Dosimetry

Purpose: Fluoroscopically guided interventions (FGI) are routinely performed across many different hospital departments. However, many involved staff members have minimal training regarding safe and optimal use of fluoroscopy systems. We developed and taught a hands-on fluoroscopy safety class incorporating real-time patient and staff dosimetry in order to promote safer and more optimal use of fluoroscopy during FGI. Methods: The hands-on fluoroscopy safety class is taught in an FGI suite, unique to each department. A patient equivalent phantom is set on the patient table with an ion chamber positioned at the x-ray beam entrance to the phantom. This provides a surrogate measure of patient entrance dose. Multiple solid state dosimeters (RaySafe i2 dosimetry systemTM) are deployed at different distances from the phantom (0.1, 1, 3 meters), which provide surrogate measures of staff dose. Instructors direct participating clinical staff to operate the fluoroscopy system as they view live fluoroscopic images, patient entrance dose, and staff doses in real-time. During class, instructors work with clinical staff to investigate how patient entrance dose, staff doses, and image quality are affected by different parameters, including pulse rate, magnification, collimation, beam angulation, imaging mode, system geometry, distance, and shielding. Results: Real-time dose visualization enables clinical staff to directly see and learn how to optimize their use of their own fluoroscopy system to minimize patient and staff dose, yet maintain sufficient image quality for FGI. As a direct result of the class, multiple hospital departments have implemented changes to their imaging protocols, including reduction of the default fluoroscopy pulse rate and increased use of collimation and lower dose fluoroscopy modes. Conclusion: Hands-on fluoroscopy safety training substantially benefits from real-time patient and staff dosimetry incorporated into the class. Real-time dose display helps clinical staff visualize, internalize, and ultimately utilize the safety techniques learned during the training. RaySafe/Unfors/Fluke lent us a portable version of their RaySafe i2 Dosimetry System for 6 months.

60 APPLIED LIFE SCIENCES↗

Milky Way Satellite Census. I. The Observational Selection Function for Milky Way Satellites in DES Y3 and Pan-STARRS DR1

We report the results of a systematic search for ultra-faint Milky Way satellite galaxies using data from the Dark Energy Survey (DES) and Pan-STARRS1 (PS1). Together, DES and PS1 provide multi-band photometry in optical/near-infrared wavelengths over ~80% of the sky. Our search for satellite galaxies targets ~25,000 deg$^2$ of the high-Galactic-latitude sky reaching a 10$\sigma$ point-source depth of $\gtrsim$ 22.5 mag in the $g$ and $r$ bands. While satellite galaxy searches have been performed independently on DES and PS1 before, this is the first time that a self-consistent search is performed across both data sets. We do not detect any new high-significance satellite galaxy candidates, while recovering the majority of satellites previously detected in surveys of comparable depth. We characterize the sensitivity of our search using a large set of simulated satellites injected into the survey data. We use these simulations to derive both analytic and machine-learning models that accurately predict the detectability of Milky Way satellites as a function of their distance, size, luminosity, and location on the sky. To demonstrate the utility of this observational selection function, we calculate the luminosity function of Milky Way satellite galaxies, assuming that the known population of satellite galaxies is representative of the underlying distribution. We provide access to our observational selection function to facilitate comparisons with cosmological models of galaxy formation and evolution.

79 ASTRONOMY AND ASTROPHYSICS↗

Adaptive planning for applications with dynamic objectives

We devise a qualitative control layer to be integrated into a real-time multi-agent reactive planner. The reactive planning system consists of distributed planning agents attending to various perspectives of the task environment. Each perspective corresponds to an objective. The set of objectives considered are sometimes in conflict with each other. Each agent receives information about events as they occur, and a set of actions based on heuristics can be taken by the agents. Within the qualitative control scheme, we use a set of qualitative feature vectors to describe the effects of applying actions. A qualitative transition vector is used to denote the qualitative distance between the current state and the target state. We will then apply on-line learning at the qualitative control level to achieve adaptive planning. Our goal is to design a mechanism to refine the heuristics used by the reactive planner every time an action is taken toward achieving the objectives, using feedback from the results of the actions. When the outcome is compared with expectations, our prior objectives may be modified and a new set of objectives (or a new assessment of the relative importance of the different objectives) can be introduced. Because we are able to obtain better estimates of the time-varying objectives, the reactive strategies can be improved and better prediction can be achieved.

Hadavi, Khosrow↗

The Heliopause Electrostatic Rapid Transit System (HERTS) Design, Trades, and Analyses Performed in the First Year of a Two Year Investigation

The Heliopause Electrostatic Rapid Transit System (HERTS)1 was one of the seven total Phase II NASA Innovative Advanced Concepts (NIAC) that was down-selected in 2015 for continued funding and research. In Phase I we learned that a spacecraft propelled by an Electric Sail (E-Sail) can travel great astronomical distances, such as to the Heliopause region of the solar system (approx.100 to 120 AU) in approximately one quarter of the time (10 years) versus the time it took the Voyager spacecraft launched in 1977 (36 years). The current work within the Phase II NIAC effort builds upon the work that was done in the Phase I NIAC and is focused on: 1) Testing of plasma interaction with a charged wire in a unique MSFC test chamber, 2) Development of a Particle-in-Cell (PIC) models that are validated in the plasma testing and used to extrapolate to the E-Sail propulsion system design. 3) Further down select of a wire deployment and control approach from those narrowed down in the Phase I effort. This paper will document the findings to date (June, 2016) of the above focused areas.

Wiegmann, Bruce M.↗

The Heliopause Electrostatic Rapid Transit System (HERTS) Design, Trades, and Analyses Performed in a Two Year NASA Investigation of Electric Sail Propulsion Systems

The Heliopause Electrostatic Rapid Transit System (HERTS) was one of the seven total Phase II NASA Innovative Advanced Concepts (NIAC) that was down-selected in 2015 for continued funding and research. In Phase I our team learned that a spacecraft propelled by an Electric Sail (E-Sail) can travel great astronomical distances, such as to the Heliopause region of the solar system (approx. 100 to 120 AU) in approximately one quarter of the time (10 years) versus the time it took the Voyager spacecraft launched in 1977 (36 years). The completed work within the Phase II NIAC funded effort builds upon the work that was done in the Phase I NIAC and is focused on: 1) Testing of plasma interaction with a charged wire in a MSFC simulated solar environment vacuum test chamber. 2) Development of a Particle-in-Cell (PIC) models that are validated in the plasma testing and used to extrapolate to the E-Sail propulsion system design. 3) Conceptual design of a Technology Demonstration Mission (TDM) spacecraft developed to showcase E-Sail propulsion systems. 4) Down selection of both: a) Materials for a multi km length conductor and, b) Best configuration of the proposed conductor deployment subsystem. This paper will document the findings to date (June, 2017) of the above focused areas.

Wiegmann, Bruce M.↗

ArcjetCV: A New Machine Learning Application for Extracting Time-Resolved Recession Measurements From Arc Jet Test Videos

Arc jet Computer Vision (ArcjetCV) is a software application built to automate analysis of arc jet ground test video footage. This includes tracking material recession, sting arm motion, and the shock-material standoff distance. This provides a new capability to resolve and validate new physics associated with non-linear processes. This is an essential step to reduce testing, modeling, and validation uncertainties for heatshield material performance. ArcjetCV uses several types of machine learning (convolutional neural net: CNN, decision tree: DT, k-means unsupervised clustering: KM) to automate the video processing pipeline. These include inferring the start/stop of time segments of interest (1D CNN), measuring the time-dependent 2D recession of the material samples (2D CNN, DT), measuring the time-dependent shock standoff distance (2D CNN, DT), and post-processing cleaning of the recession data (KM). The software also provides a graphical user interface for ease of use. The results of using this tool on arc jet videos show non-linear time-dependent effects can be important for certain materials.

machine learning↗

ArcjetCV: a new machine learning application for extracting time-resolved recession measurements from arc jet test videos

Arc jet Computer Vision (ArcjetCV) is a software application built to automate analysis of arc jet ground test video footage. This includes tracking material recession, sting arm motion, and the shock-material standoff distance. This provides a new capability to resolve and validate new physics associated with non-linear processes. This is an essential step to reduce testing, modeling, and validation uncertainties for heatshield material performance. ArcjetCV uses several types of machine learning (convolutional neural net: CNN, decision tree: DT, k-means unsupervised clustering: KM) to automate the video processing pipeline. These include inferring the start/stop of time segments of interest (1D CNN), measuring the time-dependent 2D recession of the material samples (2D CNN, DT), measuring the time-dependent shock standoff distance (2D CNN, DT), and post-processing cleaning of the recession data (KM). The software also provides a graphical user interface for ease of use. The results of using this tool on arc jet videos show non-linear time-dependent effects can be important for certain materials.

machine learning↗

Towards Autonomous Lunar Resource Excavation via Reinforcement Learning

To continue on a sustainable and flexible path, NASA needs to address the challenge of collecting and moving large amounts of regolith at the destination. NASA’s Regolith Advanced Surface Systems Operations Robot (RASSOR) is principally designed to mine and deliver regolith for In-Situ Resource Utilization (ISRU) processing. RASSOR’s design enables it to efficiently collect and deposit regolith, return collected material for processing, and myriad related ISRU activities. To reliably perform these operations on the lunar surface, RASSOR software and sensory systems need to be robust and maximize the information extracted from a reduced sensor payload. Herein, we present preliminary findings from the Intelligent Capabilities Enhanced RASSOR project. We created reduced-order simulation environments to develop autonomous trenching controllers via reinforcement learning and prototype state estimation architectures. The goal of reinforcement learning is for an agent to learn a policy (task strategy) through interactions with an environment. When the agent performs an action, a change occurs in environment state and a numerical reward is received which informs the agent whether the action performed was good or not. Since reinforcement learning algorithms learn through trial-and-error, a simulation is a desirable first environment for development and learning. We developed two simulations, the first is a 2D excavation simulation developed to facilitate parameter selection, and a 3D simulation developed using a game physics engine, to simulate simplified soil interactions and increase the fidelity of the dynamic models of the robotic agents. The development of this 3D simulation has enabled the training of additional sensing capabilities and research both at the granular mechanics and operations levels. We experimented with various virtual sensor payloads to identify a combination that enabled efficient excavation operation and learning. Our reward function is based on how much material is excavated per step. A penalty is also received for leaving the dig site and to smooth the acceleration of the drum arms. We implemented pseudo time-of-flight sensors to report distance from each drum to ground and the height above ground which was found to be more efficient than existing solutions. Our findings suggest that reinforcement learning for autonomous operations has learned viable trenching strategies within 3000 training episodes in our simplified 2D environment and helped identify desirable sensing capabilities, arrangements, and considerations such as the positioning of time-of-flight sensors. Future work includes expanding our simulation to more complex environments and scenarios, and transfer learning from simulation to RASSOR 2.0 hardware for deployment in the Regolith Test Bin at NASA's Kennedy Space Center.

rassor↗

SU-E-T-598: Parametric Equation for Quick and Reliable Estimate of Stray Neutron Doses in Proton Therapy and Application for Intracranial Tumor Treatments

Purpose: Development of a parametric equation suitable for a daily use in routine clinic to provide estimates of stray neutron doses in proton therapy. Methods: Monte Carlo (MC) calculations using the UF-NCI 1-year-old phantom were exercised to determine the variation of stray neutron doses as a function of irradiation parameters while performing intracranial treatments. This was done by individually changing the proton beam energy, modulation width, collimator aperture and thickness, compensator thickness and the air gap size while their impact on neutron doses were put into a single equation. The variation of neutron doses with distance from the target volume was also included in it. Then, a first step consisted in establishing the fitting coefficients by using 221 learning data which were neutron absorbed doses obtained with MC simulations while a second step consisted in validating the final equation. Results: The variation of stray neutron doses with irradiation parameters were fitted with linear, polynomial, etc. model while a power-law model was used to fit the variation of stray neutron doses with the distance from the target volume. The parametric equation fitted well MC simulations while establishing fitting coefficients as the discrepancies on the estimate of neutron absorbed doses were within 10%. The discrepancy can reach ∼25% for the bladder, the farthest organ from the target volume. Finally, the validation showed results in compliance with MC calculations since the discrepancies were also within 10% for head-and-neck and thoracic organs while they can reach ∼25%, again for pelvic organs. Conclusion: The parametric equation presents promising results and will be validated for other target sites as well as other facilities to go towards a universal method.

61 RADIATION PROTECTION AND DOSIMETRY↗

How the Galaxy–Halo Connection Depends on Large-scale Environment

We investigate the connection between galaxies, dark matter halos, and their large-scale environments at z = 0 with Illustris TNG300 hydrodynamic simulation data. We predict stellar masses from subhalo properties to test two types of machine learning (ML) models: explainable boosting machines (EBMs) with simple galaxy environment features and E(3)-invariant graph neural networks (GNNs). The best-performing EBM models leverage spherically averaged overdensity features on 3 Mpc scales. Interpretations via SHapley Additive exPlanations also suggest that in the context of the TNG300 galaxy–halo connection, simple spherical overdensity on ∼3 Mpc scales is more important than cosmic web distance features measured using the DisPerSE algorithm. Meanwhile, a GNN with connectivity defined by a fixed linking length, L, outperforms the EBM models by a significant margin. As we increase the linking length scale, GNNs learn important environmental contributions up to the largest scales we probe (L = 10 Mpc). We conclude that 3 Mpc distance scales are most critical for describing the TNG galaxy–halo connection using the spherical overdensity parameterization, but that information on larger scales, which is not captured by simple environmental parameters or cosmic web features, can further augment these models. Our study highlights the benefits of using interpretable ML algorithms to explain models of astrophysical phenomena, and the power of using GNNs to flexibly learn complex relationships directly from data while imposing constraints from physical symmetries.

79 ASTRONOMY AND ASTROPHYSICS↗

Enhancing Cluster Identification in Atom Probe Tomography Data Using Transfer Learning

Atom Probe Tomography (APT) is a powerful technique for visualizing the atomic-scale distribution of solutes in materials, but quantitative cluster analysis of APT datasets remains a challenge due to the need for subjective parameter selection in clustering algorithms. While distance-based and density-based methods such as HDBSCAN are widely used, their performance is highly sensitive to user-defined parameters, which undermines reproducibility and accuracy. This study proposes an image-based, deep learning-aided workflow for automating parameter selection and cluster detection in APT data analysis. By projecting 3D APT point clouds onto 2D planes, we leverage pretrained convolutional neural networks (ConvNeXt-Tiny and ResNet-50) through transfer learning to predict the number of clusters present in synthetic datasets. The output is used to guide K-means clustering and estimate HDBSCAN parameters, specifically minimum cluster size and minimum sample points. This approach reduces reliance on manual parameter tuning, improving consistency and scalability. The methodology demonstrates the feasibility of using image-based deep learning for interpreting complex spatial patterns in APT data, enabling faster and more objective analysis. The complete workflow and code are made publicly available to support reproducibility and future research.

Density-based clustering↗

Antarctic Exploration Parallels for Future Human Planetary Exploration: Science Operations Lessons Learned, Planning, and Equipment Capabilities for Long Range, Long Duration Traverses

The purpose for this workshop can be summed up by the question: Are there relevant analogs to planetary (meaning the Moon and Mars) to be found in polar exploration on Earth? The answer in my opinion is yes or else there would be no reason for this workshop. However, I think some background information would be useful to provide a context for my opinion on this matter. As all of you are probably aware, NASA has been set on a path that, in its current form, will eventually lead to putting human crews on the surface of the Moon and Mars for extended (months to years) in duration. For the past 50 V 60 years, starting not long after the end of World War II, exploration of the Antarctic has accumulated a significant body of experience that is highly analogous to our anticipated activities on the Moon and Mars. This relevant experience base includes: h Long duration (1 year and 2 year) continuous deployments by single crews, h Established a substantial outpost with a single deployment event to support these crews, h Carried out long distance (100 to 1000 kilometer) traverses, with and without intermediate support h Equipment and processes evolved based on lessons learned h International cooperative missions This is not a new or original thought; many people within NASA, including the most recent two NASA Administrators, have commented on the recognizable parallels between exploration in the Antarctic and on the Moon or Mars. But given that level of recognition, relatively little has been done, that I am aware of, to encourage these two exploration communities to collaborate in a significant way. [Slide 4] I will return to NASA s plans and the parallels with Antarctic traverses in a moment, but I want to spend a moment to explain the objective of this workshop and the anticipated products. We have two full days set aside for this workshop. This first day will be taken up with a series of presentations prepared by individuals with experience that extends back as far as the late 1940s and includes contemporary experience. The people presenting bring a variety of points of view, including not only U.S. but international, although most, if not all, have collaborated on international teams. The second day will consist of a series of small focused group interactions centered on those elements likely to be needed for traverse missions, such as mobility, habitation, and extravehicular activity (EVA, aka space suits). Our invited participants will be talking with people that specialize in these elements so that we can foster more direct interaction and exchange of experiences between these two exploration communities. After the workshop we will be preparing a report documenting these presentations and the essence of the focused interactions.

Hoffman, Stephen J.↗

Feature selection with distance correlation

Choosing which properties of the data to use as input to multivariate decision algorithms—also known as feature selection—is an important step in solving any problem with machine learning. While there is a clear trend towards training sophisticated deep networks on large numbers of relatively unprocessed inputs (so-called automated feature engineering), for many tasks in physics, sets of theoretically well-motivated and well-understood features already exist. Working with such features can bring many benefits, including greater interpretability, reduced training and run time, and enhanced stability and robustness. We develop a new feature selection method based on distance correlation, and demonstrate its effectiveness on the tasks of boosted top- and W -tagging. Using our method to select features from a set of over 7,000 energy flow polynomials, we show that we can match the performance of much deeper architectures, by using only ten features and two orders-of-magnitude fewer model parameters. Published by the American Physical Society 2024

Astronomy & Astrophysics↗