Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “predictive mapping”

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 361 records · Page 20
All sourcesNASA NTRSDOE OSTI
NASA NTRS2017

NASA's Space Launch System: Deep-Space Opportunities for SmallSats

Designed for human exploration missions into deep space, NASA's Space Launch System (SLS) represents a new spaceflight infrastructure asset, enabling a wide variety of unique utilization opportunities. While primarily focused on launching the large systems needed for crewed spaceflight beyond Earth orbit, SLS also offers a game-changing capability for the deployment of small satellites to deep-space destinations, beginning with its first flight. Currently, SLS is making rapid progress toward readiness for its first launch in two years, using the initial configuration of the vehicle, which is capable of delivering 70 metric tons (t) to Low Earth Orbit (LEO). On its first flight test of the Orion spacecraft around the moon, accompanying Orion on SLS will be small-satellite secondary payloads, which will deploy in cislunar space. The deployment berths are sized for "6U" CubeSats, and on EM-1 the spacecraft will be deployed into cislunar space following Orion separate from the SLS Interim Cryogenic Propulsion Stage. Payloads in 6U class will be limited to 14 kg maximum mass. Secondary payloads on EM-1 will be launched in the Orion Stage Adapter (OSA). Payload dispensers will be mounted on specially designed brackets, each attached to the interior wall of the OSA. For the EM-1 mission, a total of fourteen brackets will be installed, allowing for thirteen payload locations. The final location will be used for mounting an avionics unit, which will include a battery and sequencer for executing the mission deployment sequence. Following the launch of EM-1, deployments of the secondary payloads will commence after sufficient separation of the Orion spacecraft to the upper stage vehicle to minimize any possible contact of the deployed cubesats to Orion. Currently this is estimated to require approximately 4 hours. The allowed deployment window for the cubesats will be from the time the upper stage disposal maneuvers are complete to up to 10 days after launch. The upper stage will fly past the moon at a perigee of approximately 100km, and this closest approach will occur about 5 days after launch. The limiting factor for the latest deployment time is the available power in the sequencer system. Several NASA Mission Directorates were involved in the development of programs for the competition, selection, and development of EM-1 payloads that support directorate priorities. CubeSat payloads on EM-1 will include both NASA research experiments and spacecraft developed by industry, international and potentially academia partners. The Human Exploration and Operations Mission Directorate (HEOMD) Advanced Exploration Systems (AES) Division was allocated five payload opportunities on the EM-1 mission. Near Earth Asteroid (NEA) Scout is designed to rendezvous with and characterize a candidate NEA. A solar sail, an innovation the spacecraft will demonstrated for the CubeSat class, will provide propulsion. Lunar Flashlight will use a green propellant system and will search for potential ice deposits in the moon's permanently shadowed craters. BioSentinel is a yeast radiation biosensor, planned to measure the effects of space radiation on deoxyribonucleic acid (DNA). Lunar Icecube, a collaboration with Morehead State University, will prospect for water in ice, liquid, and vapor forms as well as other lunar volatiles from a low-perigee, highly inclined lunar orbit using a compact Infrared spectrometer. Skyfire, a partnership with Lockheed Martin, is a technology demonstration mission that will perform a lunar flyby, collecting spectroscopy, and thermography data to address questions related to surface characterization, remote sensing, and site selection. NASA's Space Technology Mission Directorate (STMD) was allocated three payload opportunities on the EM-1 mission. These slots will be filled via the 2 Centennial Challenges Program, NASA's flagship program for technology prize competitions, which directly engages the public, academia, and industry in open prize competitions to stimulate innovation. The NASA Science Mission Directorate (SMD) was allocated two payload opportunities on the EM-1 mission. The CubeSat Mission to Study Solar Particles (CuSP) payload will study the sources and acceleration mechanisms of solar and interplanetary particles in near-Earth orbit, support space weather research by determining proton radiation levels during Solar Energetic Particle (SEP) events and identifying suprathermal properties that could help predict geomagnetic storms. The LunaH-Map payload will help scientists understand the quantity of H-bearing materials in lunar cold traps (~10 km), determine the concentration of H-bearing materials with 1m depth, and constrain the vertical distribution of H-bearing materials. The final three payload opportunities for the EM-1 mission were allocated for NASA's international space agency counterparts. The flight opportunities are intended to benefit the international space agency and NASA as well as further the collective space exploration goals. ArgoMoon is sponsored by ESA/ASI and will fly along with the ICPS on its disposal trajectory to perform proximity operations with the ICPS post-disposal, take external imagery of engineering and historical significance, and perform an optical communications demonstration. EQUULEUS, sponsored by JAXA, will fly to a libration orbit around the Earth-Moon L2 point and demonstrate trajectory control techniques within the Sun-Earth-Moon region for the first time by a nano spacecraft. The mission will also contribute to the future human exploration scenario by understanding the radiation environment in geospace and deep space, characterizing the flux of impacting meteors on the far side of the moon, and demonstrating the future deep space exploration scenario using the "deep space port" at Lagrange points. OMOTENASHI, also sponsored by JAXA, will land the smallest lunar lander to date on the lunar surface to demonstrate the feasibility of the hardware for distributed cooperative exploration system. Small landers will enable multi-point exploration, which is complimentary with large-scale human exploration. Once on the lunar surface, the OMOTENASHI spacecraft will observe the radiation and soil environments of the lunar surface by active radiation measurements and soil shear measurements. Following EM-1, Space Launch System will evolve to the more-powerful Block 1B configuration, which uses a new Exploration Upper Stage to increase the vehicle's LEO payload capability from 70 t to 105 t. With that transition, the Orion Stage Adapter, which will carry the secondary payloads on EM-1, will be phased out, and a new Universal Stage Adapter will be introduced, creating opportunities for flying larger secondary payloads. This paper will provide a brief status of SLS progress toward first launch; an overview of smallsat accommodations, integration, and operations on EM-1; information about the specific payloads flying on that launch; and a discussion of future accommodations and opportunities for secondary payloads on SLS for Exploration Mission-2 and beyond.

Robinson, Kimberly F.↗
NASA NTRS2019

The Semiannual and 4.4-Year Modulations of Extreme High Tides

In most places extreme high tides undergo a clear seasonal variation. It is well known that semidiurnal tides tend to peak during equinox seasons, and diurnals during solstice seasons. This is a consequence of the solar and lunar declinations, which when large maximize diurnal tides at the expense of semidiurnals. The semiannual range modulation of tidal extremes for a pure semidiurnal tide is determined mainly by the amplitude of the K2 constituent; a pure diurnal is determined mainly by P1. Mixed tidal regimes tend to experience maxima very roughly around the times of solstice, but not always, with the semiannual modulation generally a complicated function of constituent amplitudes and phases. These modulations are here mapped worldwide by analyzing tidal extremes predicted with a global tide model. The known 4.4-year modulation in extreme tides is a consequence of declinational and perigean effects coming in and out of phase. The phase of the 4.4-year modulation is controlled by the phase of the semiannual modulation, irrespective of whether the tide is diurnal, semidiurnal, or mixed.

Ray, R. D.↗
NASA NTRS1992

Interleaving Magellan altimetry data acquisition between mapping cycles 1 and 2

The Magellan spacecraft has been systematically mapping the surface of Venus since September 15, 1990, using side-looking synthetic aperture radar imaging and nadir-pointed altimetry. Venus rotates slowly under the nearly polar mapping orbit, completing a full revolution in 243 days, one 'mapping cycle'. The altimeter collects a 10 km swath of altitude measurements each orbit. The groundtrack advances 21 km each orbit due to the rotation of Venus, leaving an 11 km gap of unmeasured terrain. To obtain global surface coverage by the altimeter, these gaps are eliminated by interleaving the swaths collected during the second mapping cycle with those from the first mapping cycle. Interleaving was put into effect by a propulsive maneuver, executed at the end of the first mapping cycle, on May 17, 1991. The orbit node was changed by +0.106 degrees, so that the cycle 2 groundtracks would bisect adjacent cycle 1 groundtracks. This paper describes the maneuver design and execution results, including the problem and solution of the groundtrack prediction to the end of the first mapping cycle.

Engelhardt, D. B.↗
NASA NTRS1995

Studies of Two-Phase Gas-Liquid Flow in Microgravity

Two-phase gas-liquid flows are expected to occur in many future space operations. Due to a lack of buoyancy in the microgravity environment, two-phase flows are known to behave differently than those in earth gravity. Despite these concerns, little research has been conducted on microgravity two-phase flow and the current understanding is poor. This dissertation describes an experimental and modeling study of the characteristics of two-phase flows in microgravity. An experiment was operated onboard NASA aircraft capable of producing short periods of microgravity. In addition to high speed photographs of the flows, electronic measurements of void fraction, liquid film thickness, bubble and wave velocity, pressure drop and wall shear stress were made for a wide range of liquid and gas flow rates. The effects of liquid viscosity, surface tension and tube diameter on the behavior of these flows were also assessed. From the data collected, maps showing the occurrence of various flow patterns as a function of gas and liquid flow rates were constructed. Earth gravity two-phase flow models were compared to the results of the microgravity experiments and in some cases modified. Models were developed to predict the transitions on the flow pattern maps. Three flow patterns, bubble, slug and annular flow, were observed in microgravity. These patterns were found to occur in distinct regions of the gas-liquid flow rate parameter space. The effect of liquid viscosity, surface tension and tube diameter on the location of the boundaries of these regions was small. Void fraction and Weber number transition criteria both produced reasonable transition models. Void fraction and bubble velocity for bubble and slug flows were found to be well described by the Drift-Flux model used to describe such flows in earth gravity. Pressure drop modeling by the homogeneous flow model was inconclusive for bubble and slug flows. Annular flows were found to be complex systems of ring-like waves and a substrate film. Pressure drop was best fitted with the Lockhart- Martinelli model. Force balances suggest that droplet entrainment may be a large component of the total pressure drop.

Bousman, William Scott↗
NASA NTRS1993

Neural network prediction of aluminum-lithium weld strengths from acoustic emission amplitude data

AE flaw growth activity was monitored in aluminum-lithium weld specimens from the onset of tensile loading to failure. Data on actual ultimate strengths together with AE data from the beginning of loading up to 25 percent of the expected ultimate strength were used to train a backpropagation neural network to predict ultimate strengths. Architecturally, the fully interconnected network consisted of an input layer for the AE amplitude data, a hidden layer to accommodate failure mechanism mapping, and an output layer for ultimate strength prediction. The trained network was then applied to the prediction of ultimate strengths in the remaining six specimens. The worst case prediction error was found to be +2.6 percent.

Hill, Eric V. K.↗
NASA NTRS1993

Neural Network Prediction of Aluminum-Lithium Weld Strengths from Acoustic Emission Amplitude Data

Acoustic Emission (AE) flaw growth activity was monitored in aluminum-lithium weld specimens from the onset tensile loading to failure. Data on actual ultimate strengths together with AE data from the beginning of loading up to 25 percent of the expected ultimate strength were used to train a backpropagation neural network to predict ultimate strengths. Architecturally, the fully interconnected network consisted of an input layer for the AE amplitude data, a hidden layer to accommodate failure mechanism mapping, and an output layer for ultimate strength prediction. The trained network was the applied to the prediction of ultimate strengths in the remaining six specimens. The worst case prediction error was found to be +2.6 percent.

Hill, Eric v. K.↗
DOE OSTI2026

The Role of Nuclear Data Sensitivities in Prompt α-Eigenvalue Predictions of Delayed Critical Benchmarks

Alpha (α) eigenvalues, which describe the logarithmic time derivative of the neutron population in a multiplying system, are integral to time-dependent behavior and diagnostic applications. However, uncertainties in the evaluated nuclear data can significantly impact the accuracy of transport simulations for such quantities. This work explores the use of machine learning models to predict two key outputs, α-eigenvalues and keff bias, using input features derived from α-eigenvalue sensitivities to nuclear data. The criticality safety benchmark models used in this study come from the International Handbook of Evaluated Criticality Safety Benchmark Experiments. Three models, random forest, XGBoost, and NGBoost, are trained on both energy-resolved and energy-summed α sensitivities. For the α-eigenvalue bias prediction, NGBoost achieved the highest R 2 (0.9476) using energy-resolved features, while XGBoost performed best using summed sensitivities. In contrast, when predicting the keff bias, all the models showed moderate predictive capability (best R 2 ≈ 0.72), as the mapping from the static α-sensitivities to the static keff bias was less direct. SHAP (SHapley Additive exPlanations) analysis was used to interpret the model predictions. Across both prediction tasks, the features associated with neutron capture [H-1 (n, γ)], uranium scattering reactions (such as 235 U elastic/inelastic), and actinide capture/fission reactions (such as 239 Pu and 234 U) were consistently identified as the most impactful. This highlights the key role of specific nuclear reactions and energy ranges in shaping both time-dependent and steady-state criticality behavior. These results demonstrated that α-sensitivities, despite being computed for time-dependent metrics, can provide valuable insights for predicting both α-eigenvalues and the keff bias. Moreover, machine learning models offer a promising pathway for uncovering important nuclear data dependencies and guiding future data evaluation efforts.

Nuclear data↗
DOE OSTI2022

Three‐Dimensional Permeability Inversion Using Convolutional Neural Networks and Positron Emission Tomography

Abstract Quantification of heterogeneous multiscale permeability in geologic porous media is key for understanding and predicting flow and transport processes in the subsurface. Recent utilization of in situ imaging, specifically positron emission tomography (PET), enables the measurement of three‐dimensional (3‐D) time‐lapse radiotracer solute transport in geologic media. However, accurate and computationally efficient characterization of the permeability distribution that controls the solute transport process remains challenging. Leveraging the relationship between local permeability variation and solute advection behavior, an encoder‐decoder based convolutional neural network (CNN) is implemented as a permeability inversion scheme using a single PET scan of a radiotracer pulse injection experiment as input. The CNN can accurately capture the 3‐D spatial correlation between the permeability and the radiotracer solute arrival time difference maps in geologic cores. We first test the inversion accuracy using synthetic test datasets and then test the accuracy on a suite of experimental PET imaging datasets acquired on four different geologic cores. The network‐predicted permeability maps from the geologic cores are used to parameterize forward numerical models that are directly compared with the experimental PET imaging data. The results indicate that a single trained network can generate robust 3‐D permeability inversion maps in seconds. Numerical models parameterized with these permeability maps closely capture the experimentally observed solute arrival time behavior. This work provides an unprecedented approach for efficiently characterizing multiscale permeability heterogeneity in complex geologic samples.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Data-Enabled Fusion Technology (Final Scientific/Technical Report)

Advancing Scientific Understanding in Fusion Energy and Machine Learning This research represented a significant step forward in machine learning (ML) applications for fusion energy experiments. The project integrated advanced data-driven modeling, optimization techniques, and artificial intelligence to enhance the predictive capabilities and operational efficiency of plasma-based fusion systems. Specifically, tasks focused on ML-enhanced diagnostics, operator guidance tools, and predictive modeling helped improve the ability to interpret complex fusion experiments. Key areas of advancement included: 1) data-driven plasma control, i.e., using ML algorithms to optimize experimental conditions and classify plasma behaviors based on historical data; 2) spectroscopy and diagnostics, i.e., applying AI models to extract previously inaccessible insights from experimental spectroscopy data; and 3) configuration mapping and operator guidance, i.e., developing a predictive framework to assist scientists in identifying the most effective experimental parameters, reducing reliance on manual adjustments. By refining these ML-driven techniques, the project contributed to the broader scientific community’s understanding of plasma dynamics and fusion energy viability. Technical Effectiveness and Economic Feasibility The methods investigated demonstrated high technical effectiveness, as reflected in milestones assessing the predictive accuracy, performance, and optimization of fusion configurations. The development of an Operator Guidance Tool (OGT), for example, led to more precise control of plasma conditions by learning from experimental data and offering real-time adjustments. From an economic standpoint, DeFT provided: 1) the ability to reduce trial-and-error experimentation, which lowered operational costs; 2) improved data interpretation methods, which enabled more efficient resource allocation in large-scale fusion research projects; and 3) the automation of key diagnostic tasks, which reduced manual labor and human error, increasing overall efficiency. 13 The final assessments of predictive models and optimization strategies demonstrated that these approaches were scalable and could be implemented across multiple fusion energy research programs. Public Benefit and Societal Impact This project contributed directly to the broader goal of achieving sustainable and commercially viable fusion energy, which had profound implications for clean energy production and climate change mitigation. The integration of AI-driven solutions into fusion research: 1) sped up scientific discovery, accelerating progress towards achieving energy breakthroughs; 2) reduced the cost of experimentation, making fusion research more accessible; and 3) provided a framework for future AI applications in high-energy physics, benefiting adjacent fields like space exploration, material science, and renewable energy. Additionally, by fostering collaborations between AI researchers and plasma physicists, this project promoted interdisciplinary innovation that could lead to broader applications beyond fusion research.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2021

Improvement of the NOvA Near Detector Event Reconstruction and Primary Vertexing through the Application of Machine Learning Methods

The purpose of this work is to examine the application of a deep learning model in event reconstruction of neutrino interactions. The challenges faced in event reconstruction include the placement of an accurate primary neutrino interaction vertex which is used to support the particle track and prong algorithms. The result of accurate primary vertex ensures all particles involved in a neutrino interaction are included. We propose a regression-based Convolutional Neural Network (CNN) method to predict the primary vertex of a particle interaction. We show that with raw two-dimensional pixel map views as input, the regression-based CNN can predict the primary vertex in all three coordinates. This work is applied as part of the NOvA (NuMI Off-axis $\nu_e$ Appearance) near detector reconstruction efforts. The primary vertex predicted by the regression-based CNN model shows promising results for future applications. This deep learning method can be extended to secondary vertexing through a Kernel Density Estimate algorithm discussed in this work.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2022

A Simple Standard for Sharing Ontological Mappings (SSSOM)

Abstract Despite progress in the development of standards for describing and exchanging scientific information, the lack of easy-to-use standards for mapping between different representations of the same or similar objects in different databases poses a major impediment to data integration and interoperability. Mappings often lack the metadata needed to be correctly interpreted and applied. For example, are two terms equivalent or merely related? Are they narrow or broad matches? Or are they associated in some other way? Such relationships between the mapped terms are often not documented, which leads to incorrect assumptions and makes them hard to use in scenarios that require a high degree of precision (such as diagnostics or risk prediction). Furthermore, the lack of descriptions of how mappings were done makes it hard to combine and reconcile mappings, particularly curated and automated ones. We have developed the Simple Standard for Sharing Ontological Mappings (SSSOM) which addresses these problems by: (i) Introducing a machine-readable and extensible vocabulary to describe metadata that makes imprecision, inaccuracy and incompleteness in mappings explicit. (ii) Defining an easy-to-use simple table-based format that can be integrated into existing data science pipelines without the need to parse or query ontologies, and that integrates seamlessly with Linked Data principles. (iii) Implementing open and community-driven collaborative workflows that are designed to evolve the standard continuously to address changing requirements and mapping practices. (iv) Providing reference tools and software libraries for working with the standard. In this paper, we present the SSSOM standard, describe several use cases in detail and survey some of the existing work on standardizing the exchange of mappings, with the goal of making mappings Findable, Accessible, Interoperable and Reusable (FAIR). The SSSOM specification can be found at http://w3id.org/sssom/spec. Database URL: http://w3id.org/sssom/spec

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2022

Differentiable Predictions for Large Scale Structure with SHAMNet

In simulation-based models of the galaxy-halo connection, theoretical predictions for galaxy clustering and lensing are typically made based on Monte Carlo realizations of a mock universe. In this paper, we use Subhalo Abundance Matching (SHAM) as a toy model to introduce an alternative to stochastic predictions based on mock population, demonstrating how to make simulation-based predictions for clustering and lensing that are both exact and differentiable with respect to the parameters of the model. Conventional implementations of SHAM are based on iterative algorithms such as Richardson-Lucy deconvolution; here we use the JAX library for automatic differentiation to train SHAMNet, a neural network that accurately approximates the stellar-to-halo mass relation (SMHM) defined by abundance matching. In our approach to making differentiable predictions of large-scale structure, we map parameterized PDFs onto each simulated halo, and calculate gradients of summary statistics of the galaxy distribution by using autodiff to propagate the gradients of the SMHM through the statistical estimators used to measure one- and two-point functions. Our techniques are quite general, and we conclude with an overview of how they can be applied in tandem with more complex, higher-dimensional models, creating the capability to make differentiable predictions for the multi-wavelength universe of galaxies.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS1998

Lunar Prospector Orbit Determination Results

The orbit support for Lunar Prospector (LP) consists of three main areas: (1) cislunar orbit determination, (2) rapid maneuver assessment using Doppler residuals, and (3) routine mapping orbit determination. The cislunar phase consisted of two trajectory correction maneuvers during the translunar cruise followed by three lunar orbit insertion burns. This paper will detail the cislunar orbit determination accuracy and the real-time assessment of the cislunar trajectory correction and lunar orbit insertion maneuvers. The non-spherical gravity model of the Moon is the primary influence on the mapping orbit determination accuracy. During the first two months of the mission, the GLGM-2 lunar potential model was used. After one month in the mapping orbit, a new potential model was developed that incorporated LP Doppler data. This paper will compare and contrast the mapping orbit determination accuracy using these two models. LP orbit support also includes a new enhancement - a web page to disseminate all definitive and predictive trajectory and mission planning information. The web site provides definitive mapping orbit ephemerides including moon latitude and longitude, and four week predictive products including: ephemeris, moon latitude/longitude, earth shadow, moon shadow, and ground station view periods. This paper will discuss the specifics of this web site.

Beckman, Mark↗
NASA NTRS1974

Mapping snow extent in the Salt-Verde Watershed and the southern Sierra Nevada using ERTS imagery

In much of the western United States a large part of the utilized water comes from accumulated mountain snowpacks; thus, accurate measurements of snow distributions are required for input to streamflow prediction models. The application of ERTS imagery for mapping snow has been evaluated for two geographic areas, the Salt-Verde Watershed in central Arizona and the southern Sierra Nevada in California. Techniques have been developed to identify snow and to differentiate between snow and cloud. The snow extent for these two drainage areas has been mapped from the MSS-5 (0.6-0.7 micron) imagery and compared with aerial survey snow charts, aircraft photography, and ground-based snow measurements.

Barnes, J. C.↗
DOE OSTI2023

Evaluating E. coli genome‐scale metabolic model accuracy with high‐throughput mutant fitness data

Abstract The Escherichia coli genome‐scale metabolic model (GEM) is an exemplar systems biology model for the simulation of cellular metabolism. Experimental validation of model predictions is essential to pinpoint uncertainty and ensure continued development of accurate models. Here, we quantified the accuracy of four subsequent E. coli GEMs using published mutant fitness data across thousands of genes and 25 different carbon sources. This evaluation demonstrated the utility of the area under a precision–recall curve relative to alternative accuracy metrics. An analysis of errors in the latest (iML1515) model identified several vitamins/cofactors that are likely available to mutants despite being absent from the experimental growth medium and highlighted isoenzyme gene‐protein‐reaction mapping as a key source of inaccurate predictions. A machine learning approach further identified metabolic fluxes through hydrogen ion exchange and specific central metabolism branch points as important determinants of model accuracy. This work outlines improved practices for the assessment of GEM accuracy with high‐throughput mutant fitness data and highlights promising areas for future model refinement in E. coli and beyond.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Regional-scale soil carbon predictions can be enhanced by transferring global-scale soil–environment relationships

Accurate modelling and mapping soil organic carbon are crucial for supporting soil health restoration and climate change mitigation at both regional and global scales. However, regional soil predictions often suffer from data scarcity and high prediction uncertainty. Utilizing a pre-trained global-to-regional soil carbon predictive model can be a potential solution to address this challenge. Despite its promise, how to construct and apply the global-scale model to enhance regional-scale soil carbon mapping remains largely unexplored. Here, we propose the Global Soil Carbon Pre-trained Model (GSoilCPM), a deep-learning-based domain adaptative model, to enhance regional-scale soil carbon predictions. Based on large amount of environmental covariate data and 106,167 soil samples across the globe, we verify our hypothesis of the effectiveness of this 'global-to-regional' modelling strategy. The pre-trained model can be then transferred and fine-tuned to bridge the regional- and global-scale soil–environment relationships. We applied and validated this modelling strategy in four regional-scale study areas, three in the Northern Hemisphere and one in the Southern Hemisphere, each with distinct environmental background. Compared to traditional modelling approaches as a baseline, four case studies all demonstrated significant improvement in prediction accuracy across diverse environments and varying data availabilities. The average percentage improvement across all regions is 10.93% (absolute values decreased by 1.20 g kg−1 averagely) in MAE and 29.04% (absolute values increased by 0.10 averagely) in CCC. The applicability and future horizons of using GSoilCPM were further discussed. We further reveal that regions with fewer soil samples or lower baseline accuracy benefit more from the pre-trained global model. Our findings highlight the advantages of leveraging the generalized knowledge from global models to enhance specifically localized soil modelling, positioning a potential paradigm shift in digital soil mapping, and far-reaching implications for soil monitoring and land management.

Deep learning↗
NASA NTRS1987

Post-game analysis: An initial experiment for heuristic-based resource management in concurrent systems

In concurrent systems, a major responsibility of the resource management system is to decide how the application program is to be mapped onto the multi-processor. Instead of using abstract program and machine models, a generate-and-test framework known as 'post-game analysis' that is based on data gathered during program execution is proposed. Each iteration consists of (1) (a simulation of) an execution of the program; (2) analysis of the data gathered; and (3) the proposal of a new mapping that would have a smaller execution time. These heuristics are applied to predict execution time changes in response to small perturbations applied to the current mapping. An initial experiment was carried out using simple strategies on 'pipeline-like' applications. The results obtained from four simple strategies demonstrated that for this kind of application, even simple strategies can produce acceptable speed-up with a small number of iterations.

Yan, Jerry C.↗
DOE OSTI2023

Automated segmentation of porous thermal spray material CT scans with predictive uncertainty estimation

Abstract Thermal sprayed metal coatings are used in many industrial applications, and characterizing the structure and performance of these materials is vital to understanding their behavior in the field. X-ray computed tomography (CT) enables volumetric, nondestructive imaging of these materials, but precise segmentation of this grayscale image data into discrete material phases is necessary to calculate quantities of interest related to material structure. In this work, we present a methodology to automate the CT segmentation process as well as quantify uncertainty in segmentations via deep learning. Neural networks (NNs) have been shown to excel at segmentation tasks; however, memory constraints, class imbalance, and lack of sufficient training data often prohibit their deployment in high resolution volumetric domains. Our 3D convolutional NN implementation mitigates these challenges and accurately segments full resolution CT scans of thermal sprayed materials with maps of uncertainty that conservatively bound the predicted geometry. These bounds are propagated through calculations of material properties such as porosity that may provide an understanding of anticipated behavior in the field.

Martinez, Carianne↗