Search NASA⌕ Search

SEARCH · Search NASA

Results for “spatial representation 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.

83 records · Page 5
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

F-Hash: Feature-Based Hash Design for Time-Varying Volume Visualization via Multi-Resolution Tesseract Encoding

Interactive time-varying volume visualization is challenging due to its complex spatiotemporal features and sheer size of the dataset. Recent works transform the original discrete time-varying volumetric data into continuous Implicit Neural Representations (INR) to address the issues of compression, rendering, and super-resolution in both spatial and temporal domains. However, training the INR takes a long time to converge, especially when handling large-scale time-varying volumetric datasets. In this work, we proposed F-Hash, a novel feature-based multi-resolution Tesseract encoding architecture to greatly enhance the convergence speed compared with existing input encoding methods for modeling time-varying volumetric data. The proposed design incorporates multi-level collision-free hash functions that map dynamic 4D multi-resolution embedding grids without bucket waste, achieving high encoding capacity with compact encoding parameters. Our encoding method is agnostic to time-varying feature detection methods, making it a unified encoding solution for feature tracking and evolution visualization. Experiments show the F-Hash achieves state-of-the-art convergence speed in training various time-varying volumetric datasets for diverse features. We also proposed an adaptive ray marching algorithm to optimize the sample streaming for faster rendering of the time-varying neural representation.

deep learning↗
DOE OSTI2026

Multidimensional Distributional Neural Network Output Demonstrated in Super‐Resolution of Surface Wind Speed

Accurate quantification of uncertainty in neural network predictions remains a central challenge for scientific applications involving high-dimensional, correlated data. While existing methods capture either aleatoric or epistemic uncertainty, few offer closed-form, multidimensional distributions that preserve spatial correlation while remaining computationally tractable. In this work, we present a framework for training neural networks with a multidimensional Gaussian loss, generating a closed-form predictive distribution over outputs informed by non-identically distributed training data. Our approach captures aleatoric uncertainty by iteratively estimating the means and covariance matrices, and is demonstrated on a super-resolution example out-of-training-sample. We leverage a Fourier representation of the covariance matrix to stabilize network training and preserve spatial correlation. We introduce a novel regularization strategy—referred to as information sharing—that interpolates between image-specific and global covariance estimates, enabling convergence of the super-resolution downscaling network trained on image-specific distributional loss functions. This framework allows for efficient sampling, explicit correlation modeling, and extensions to more complex distribution families all without disrupting prediction performance. We demonstrate the method on a surface wind speed downscaling task and discuss its broader applicability to uncertainty-aware prediction in scientific models.

17 WIND ENERGY↗
DOE OSTI2025

FM4NPP: A Scaling Foundation Model for Nuclear and Particle Physics

Large language models have revolutionized artificial intelligence by enabling large, generalizable models trained through self-supervision. This paradigm has inspired the development of scientific foundation models (FMs). However, applying this capability to experimental particle physics is challenging due to the sparse, spatially distributed nature of detector data, which differs dramatically from natural language. This work addresses if an FM for particle physics can scale and generalize across diverse tasks. We introduce a new dataset with more than 11 million particle collision events and a suite of downstream tasks and labeled data for evaluation. We propose a novel self-supervised training method for detector data and demonstrate its neural scalability with models that feature up to 188 million parameters. With frozen weights and task-specific adapters, this FM consistently outperforms baseline models across all downstream tasks. The performance also exhibits robust data-efficient adaptation. Further analysis reveals that the representations extracted by the FM are task-agnostic but can be specialized via a single linear mapping for different downstream tasks.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

Reinforcement learning based hybrid bond-order coarse-grained interatomic potentials for exploring mesoscale aggregation in liquid–liquid mixtures

Exploring mesoscopic physical phenomena has always been a challenge for brute-force all-atom molecular dynamics simulations. Although recent advances in computing hardware have improved the accessible length scales, reaching mesoscopic timescales is still a significant bottleneck. Coarse-graining of all-atom models allows robust investigation of mesoscale physics with a reduced spatial and temporal resolution but preserves desired structural features of molecules, unlike continuum-based methods. Here, we present a hybrid bond-order coarse-grained forcefield (HyCG) for modeling mesoscale aggregation phenomena in liquid–liquid mixtures. The intuitive hybrid functional form of the potential offers interpretability to our model, unlike many machine learning based interatomic potentials. We parameterize the potential with the continuous action Monte Carlo Tree Search (cMCTS) algorithm, a reinforcement learning (RL) based global optimizing scheme, using training data from all-atom simulations. The resulting RL-HyCG correctly describes mesoscale critical fluctuations in binary liquid–liquid extraction systems. cMCTS, the RL algorithm, accurately captures the mean behavior of various geometrical properties of the molecule of interest, which were excluded from the training set. The developed potential model along with the RL-based training workflow could be applied to explore a variety of other mesoscale physical phenomena that are typically inaccessible to all-atom molecular dynamics simulations.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2026

Beyond interpolation: Physics-inspired gating transformers for extrapolating irradiation conditions to novel nuclear fuels

The qualification of advanced nuclear fuels relies on irradiation experiments in test reactors that emulate commercial conditions. Designing these tests requires accurate prediction of key irradiation quantities, particularly heat generation rate and burnup, yet obtaining them typically involves computationally expensive multi-step simulation workflows. We propose a physics-inspired gating transformer (PIGT) that integrates an inverse-square, distance-based attenuation into the encoder representation to bias attention toward physically relevant spatial relationships while retaining data-driven flexibility. Using MiniFuel irradiation data from the High Flux Isotope Reactor at Oak Ridge National Laboratory, we benchmark against ensemble methods, feedforward and recurrent networks, convolutional models, and standard transformers. While baseline models perform well under interpolation, they exhibit a pronounced generalization gap when evaluated on fuels not included in the training set. The proposed model consistently improves extrapolative accuracy and stability, yielding the strongest performance on unseen fuel configurations. These results indicate that a lightweight physics structure embedded within attention mechanisms can substantially improve robustness, enabling more reliable surrogate predictions to accelerate the design of nuclear fuel irradiation experiments.

Fuel qualification↗
DOE OSTI2022

Structure-Informed Graph Learning of Networked Dependencies for Online Prediction of Power System Transient Dynamics

Online transient analysis plays an increasingly important role in dynamic power grids as the renewable generation continues growing. Traditional numerical methods for transient analysis not only are computationally intensive but also require precise contingency information as input, and therefore, are not suitable for online applications. Existing online transient assessment studies focus on the determination of post-contingency system stability or stability margin. Here, this paper develops a novel graph-learning framework, Deep-learning Neural Representation or DNR, for online prediction, of the time-series trajectories of the system states using initial system responses that can be measured by phasor measurement units (PMUs). The proposed DNR framework consists of two sequential modules: a Network Constructor that captures network dependencies among generators, and a Dynamics Predictor that predicts the system trajectories. The key to improved prediction performance is the introduction of the spatio-temporal message-passing operations into graph neural networks with structural knowledge. Its effectiveness and scalability are validated through comparative studies, demonstrating the prediction performance under different contingency scenarios for systems of different sizes. This framework provides a solution to online predicting post-fault system dynamics based on real-time PMU measurements. Additionally, it can also be applied to facilitate the offline transient simulation without simulating the entire trajectories.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2022

Digital Twins for Materials

Digital twins are emerging as powerful tools for supporting innovation as well as optimizing the in-service performance of a broad range of complex physical machines, devices, and components. A digital twin is generally designed to provide accurate in-silico representation of the form (i.e., appearance) and the functional response of a specified (unique) physical twin. This paper offers a new perspective on how the emerging concept of digital twins could be applied to accelerate materials innovation efforts. Specifically, it is argued that the material itself can be considered as a highly complex multiscale physical system whose form (i.e., details of the material structure over a hierarchy of material length) and function (i.e., response to external stimuli typically characterized through suitably defined material properties) can be captured suitably in a digital twin. Accordingly, the digital twin can represent the evolution of structure, process, and performance of the material over time, with regard to both process history and in-service environment. This paper establishes the foundational concepts and frameworks needed to formulate and continuously update both the form and function of the digital twin of a selected material physical twin. The form of the proposed material digital twin can be captured effectively using the broadly applicable framework of n-point spatial correlations, while its function at the different length scales can be captured using homogenization and localization process-structure-property surrogate models calibrated to collections of available experimental and physics-based simulation data.

36 MATERIALS SCIENCE↗
DOE OSTI2024

iButton snow-ground interface temperature measurements in Los Alamos, New Mexico from 2023-2024

Snow/ground interface temperature measurements were collected at two sites in Los Alamos, New Mexico. Data were collected from November 29, 2023 to April 8, 2024 using iButton Link DS1921G-F5# Thermochron miniature temperature sensors (https://www.ibuttonlink.com/products/ds1921g). These sensors are a cost-efficient way to collect snowpack temperatures at a higher spatial resolution than what is normally achieved. iButton data were collected every 3 hours from a total of 19 iButtons. iButtons were placed in pairs, with one iButton placed at the ground surface and another buried 1 - 5 cm below the ground surface. One buried iButton did not successfully collect data, and therefore was excluded from this dataset. Data were collected throughout the snow cover season so that snowpack characteristics could be derived using the temperature data. Specifically, this dataset was used as a validation source for a novel machine learning approach to estimating snow depth (see related publication). Sensors were placed in areas with bare ground or minimal grass coverage, located away from any large vegetation. At Site A (TA51), manual snow depths were collected as validation data. These measurements were taken next to iButtons periodically throughout the winter, and notes on other precipitation types were also recorded. At Site B (TA6 Meteorological Station), a nearby sensor collected snow depths throughout the winter. This dataset contains one *.csv file of snow/ground interface temperatures at two sites, one *.csv file of manually collected snow depths, and one *.kml file of sensor locations. The Next-Generation Ecosystem Experiments: Arctic (NGEE Arctic) was a 15-year research effort (2012-2027) to reduce uncertainty in Earth System Models by developing a predictive understanding of carbon-rich Arctic ecosystems and feedbacks to climate. NGEE Arctic was supported by the Department of Energy’s Office of Biological and Environmental Research.The NGEE Arctic project had two field research sites: 1) located within the Arctic polygonal tundra coastal region on the Barrow Environmental Observatory (BEO) and the North Slope near Utqiagvik (Barrow), Alaska and 2) multiple areas on the discontinuous permafrost region of the Seward Peninsula north of Nome, Alaska.Through observations, experiments, and synthesis with existing datasets, NGEE Arctic provided an enhanced knowledge base for multi-scale modeling and contributed to improved process representation at global pan-Arctic scales within the Department of Energy’s Earth system Model (the Energy Exascale Earth System Model, or E3SM), and specifically within the E3SM Land Model component (ELM).

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Vegetation classification map and covariates associated with NEON AOP survey, East River, CO 2018

This package includes geospatial data layers developed to investigate how environmental gradients—specifically topography and near-surface soil properties—drive the spatial arrangement of dominant plant communities in mountainous watersheds. The geospatial products, which support the analysis of these ecological relationships, are derived from airborne hyperspectral and LiDAR datasets acquired by the National Ecological Observatory Network (NEON) Airborne Observation Platform (AOP), in conjunction with an extensive ground field campaign conducted in summer 2018. This work is part of the DOE Watershed Function Science Focus Area (SFA) and features geospatial datasets developed based on observations and ground data collected at East River, Colorado, in collaboration with the National Ecological Observatory Network (NEON) Airborne Observation Platform (AOP) survey in June 2018. Classification Map: - Classification Map (PNG, GeoTIFF): Derived from hyperspectral and LiDAR airborne data using a machine learning approach. - Class Code Mapper (CSV): Associates pixel values with corresponding vegetation/non-vegetation classes. - Classification Reference Data (CSV): Reference data used in the machine learning procedure. LiDAR-Derived Products: - Topographical Metrics (GeoTIFFs): Elevation, slope, curvature, TWI, TPI, solar insolation, and canopy height model (CHM), smoothed with a 5x5 pixel window. Vegetation Indices: - GeoTIFFs of NDVI, NDNI, NDWI: Vegetation indices derived from hyperspectral data. Urban Masks: - Urban Mask (GeoTIFF): Applied to the mapping to convert bare soil classes to urban classes. Software Compatibility: GeoTIFFs: Can be visualized with GIS software or libraries that support GeoTIFF images. CSV Files: Can be opened with any software that handles comma-separated values. The FLMD file provides details and links to the source datasets used to derive the products. The manuscript (in the Method session) provides details on how each product was derived. This work was supported by the Watershed Function Science Focus Area at Lawrence Berkeley National Laboratory funded by the US Department of Energy, Office of Science, Biological and Environmental Research under Contract No. DE-AC02-05CH11231. Update on 2026-03-25: Since the original dataset publication date of 02/28/2020, this package has a new classification map derived by an improved methodology. This update also includes additional ground data that improved the representation of some of the communities. See the methods for further details on what has changed between versions.

2018 NEON and 2025 CHESS Campaigns↗
DOE OSTI2022

Spatial patterns of snow distribution in the sub-Arctic

Abstract. The spatial distribution of snow plays a vital role in sub-Arctic and Arctic climate, hydrology, and ecology due to its fundamental influence on the water balance, thermal regimes, vegetation, and carbon flux. However, the spatial distribution of snow is not well understood, and therefore, it is not well modeled, which can lead to substantial uncertainties in snow cover representations. To capture key hydro-ecological controls on snow spatial distribution, we carried out intensive field studies over multiple years for two small (2017–2019; ∼ 2.5 km2) sub-Arctic study sites located on the Seward Peninsula of Alaska. Using an intensive suite of field observations (> 22 000 data points), we developed simple models of the spatial distribution of snow water equivalent (SWE) using factors such as topographic characteristics, vegetation characteristics based on greenness (normalized different vegetation index, NDVI), and a simple metric for approximating winds. The most successful model was random forest, using both study sites and all years, which was able to accurately capture the complexity and variability of snow characteristics across the sites. Approximately 86 % of the SWE distribution could be accounted for, on average, by the random forest model at the study sites. Factors that impacted year-to-year snow distribution included NDVI, elevation, and a metric to represent coarse microtopography (topographic position index, TPI), while slope, wind, and fine microtopography factors were less important. The characterization of the SWE spatial distribution patterns will be used to validate and improve snow distribution modeling in the Department of Energy's Earth system model and for improved understanding of hydrology, topography, and vegetation dynamics in the sub-Arctic and Arctic regions of the globe.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

3D Deep Learning Joint Inversion of Active Seismic Full Waveform and Passive Seismic Traveltime Data for Reservoir Imaging and Uncertainty Quantification

Here, we present deep learning (DL) networks for three-dimensional (3D) joint inversion of active seismic full waveform and passive seismic traveltime data to image reservoirs and their properties and quantify imaging uncertainties. Active seismic full-waveform data can provide high-resolution monitoring images but are collected only intermittently because of their high acquisition cost. In contrast, passive seismic data can be gathered at relatively low cost between regular active surveys, although their imaging quality can be compromised by factors such as low signal-to-noise ratios and limited ray coverage of the target. Although these datasets are routinely acquired together at CO 2 storage sites, their combined inversion within a 3D DL framework has not been previously demonstrated. To our knowledge, this is the first study to address this gap, combining the strength of both data types. For efficient data storage and DL training with large 3D seismic datasets, we use a 3D data matrix in which a random number of passive seismic traveltime data are stored as parabolic envelopes using one-hot encoding and a 3D full-waveform data matrix in which multiple shot gathers are summed. Two network architectures are evaluated: a single-encoder U-Net for single-data type inversion and a dual-encoder U-Net for joint inversion of active and passive seismic data. We also evaluate the single-encoder U-Net for joint inversion by concatenating full-waveform data and traveltime data. We propose a systematic approach for selecting an optimal dropout rate that balances regularization during training and Monte Carlo dropout-based uncertainty quantification during prediction by examining the correlation coefficient between standard deviation and prediction error, along with the training misfit, across a range of dropout rates. 3D DL inversion experiments include five different network configurations, with evaluations under ideal, noisy and dropout-enabled conditions. Both model and data uncertainties are assessed, as well as their combined effects. Across all conditions, the networks consistently predict accurate CO 2 saturation models with low prediction errors, such as a structural similarity index of 0.993 and CO 2 difference of 1.1%. Uncertainty estimates show strong spatial correlation with prediction errors, confirming the effectiveness of the proposed dropout selection approach. The results demonstrate that our DL approach, utilizing compact data representations and appropriate uncertainty quantification, yields accurate subsurface images under various inversion conditions and provides valuable insights into the reliability of predictions.

Um, Evan Schankee [Lawrence Berkeley National Labo↗