Search NASA⌕ Search

SEARCH · Search NASA

Results for “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.

At least 379 records · Page 21
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

U-Surf: a global 1 km spatially continuous urban surface property dataset for kilometer-scale urban-resolving Earth system modeling

High-resolution urban climate modeling has faced substantial challenges due to the absence of a globally consistent, spatially continuous, and accurate dataset to represent the spatial heterogeneity of urban surfaces and their biophysical properties. This deficiency has long obstructed the development of urban-resolving Earth system models (ESMs) and ultra-high-resolution urban climate modeling, over large domains. Here, we present U-Surf, a first-of-its-kind 1 km resolution present-day (circa 2020) global continuous urban surface parameter dataset. Using the urban canopy model (UCM) in the Community Earth System Model as a base model for satisfying dataset requirements, U-Surf leverages the latest advances in remote sensing, machine learning, and cloud computing to provide the most relevant urban surface biophysical parameters, including radiative, morphological, and thermal properties, for UCMs at the facet and canopy level. Generated using a systematically unified workflow, U-Surf ensures internal consistency among key parameters, making it the first globally coherent urban canopy surface dataset. U-Surf significantly improves the representation of the urban land heterogeneity both within and across cities globally; provides essential, high-fidelity surface biophysical constraints to urban-resolving ESMs; enables detailed city-to-city comparisons across the globe; and supports next-generation kilometer-resolution Earth system modeling across scales. U-Surf parameters can be easily converted or adapted to various types of UCMs, such as those embedded in weather and regional climate models, as well as air quality models. The fundamental urban surface constraints provided by U-Surf can also be used as features for machine learning models and can have other broad-scale applications for socioeconomic, public health, and urban planning contexts. We expect U-Surf to advance the research frontier of urban system science, climate-sensitive urban design, and coupled human–Earth systems in the future. The dataset is publicly available at https://doi.org/10.5281/zenodo.11247598 (Cheng et al., 2024).

Cheng, Yifan [Univ. of Illinois at Urbana-Champaig↗
NASA NTRS2007

Sensing Super-Position: Human Sensing Beyond the Visual Spectrum

The coming decade of fast, cheap and miniaturized electronics and sensory devices opens new pathways for the development of sophisticated equipment to overcome limitations of the human senses. This paper addresses the technical feasibility of augmenting human vision through Sensing Super-position by mixing natural Human sensing. The current implementation of the device translates visual and other passive or active sensory instruments into sounds, which become relevant when the visual resolution is insufficient for very difficult and particular sensing tasks. A successful Sensing Super-position meets many human and pilot vehicle system requirements. The system can be further developed into cheap, portable, and low power taking into account the limited capabilities of the human user as well as the typical characteristics of his dynamic environment. The system operates in real time, giving the desired information for the particular augmented sensing tasks. The Sensing Super-position device increases the image resolution perception and is obtained via an auditory representation as well as the visual representation. Auditory mapping is performed to distribute an image in time. The three-dimensional spatial brightness and multi-spectral maps of a sensed image are processed using real-time image processing techniques (e.g. histogram normalization) and transformed into a two-dimensional map of an audio signal as a function of frequency and time. This paper details the approach of developing Sensing Super-position systems as a way to augment the human vision system by exploiting the capabilities of Lie human hearing system as an additional neural input. The human hearing system is capable of learning to process and interpret extremely complicated and rapidly changing auditory patterns. The known capabilities of the human hearing system to learn and understand complicated auditory patterns provided the basic motivation for developing an image-to-sound mapping system. The human brain is superior to most existing computer systems in rapidly extracting relevant information from blurred, noisy, and redundant images. From a theoretical viewpoint, this means that the available bandwidth is not exploited in an optimal way. While image-processing techniques can manipulate, condense and focus the information (e.g., Fourier Transforms), keeping the mapping as direct and simple as possible might also reduce the risk of accidentally filtering out important clues. After all, especially a perfect non-redundant sound representation is prone to loss of relevant information in the non-perfect human hearing system. Also, a complicated non-redundant image-to-sound mapping may well be far more difficult to learn and comprehend than a straightforward mapping, while the mapping system would increase in complexity and cost. This work will demonstrate some basic information processing for optimal information capture for headmounted systems.

Maluf, David A.↗
DOE OSTI2024

Chaotic neural dynamics facilitate probabilistic computations through sampling

Cortical neurons exhibit highly variable responses over trials and time. Theoretical works posit that this variability arises potentially from chaotic network dynamics of recurrently connected neurons. Here, we demonstrate that chaotic neural dynamics, formed through synaptic learning, allow networks to perform sensory cue integration in a sampling-based implementation. We show that the emergent chaotic dynamics provide neural substrates for generating samples not only of a static variable but also of a dynamical trajectory, where generic recurrent networks acquire these abilities with a biologically plausible learning rule through trial and error. Furthermore, the networks generalize their experience in the stimulus-evoked samples to the inference without partial or all sensory information, which suggests a computational role of spontaneous activity as a representation of the priors as well as a tractable biological computation for marginal distributions. These findings suggest that chaotic neural dynamics may serve for the brain function as a Bayesian generative model.

60 APPLIED LIFE SCIENCES↗
NASA NTRS2011

Feature Acquisition with Imbalanced Training Data

This work considers cost-sensitive feature acquisition that attempts to classify a candidate datapoint from incomplete information. In this task, an agent acquires features of the datapoint using one or more costly diagnostic tests, and eventually ascribes a classification label. A cost function describes both the penalties for feature acquisition, as well as misclassification errors. A common solution is a Cost Sensitive Decision Tree (CSDT), a branching sequence of tests with features acquired at interior decision points and class assignment at the leaves. CSDT's can incorporate a wide range of diagnostic tests and can reflect arbitrary cost structures. They are particularly useful for online applications due to their low computational overhead. In this innovation, CSDT's are applied to cost-sensitive feature acquisition where the goal is to recognize very rare or unique phenomena in real time. Example applications from this domain include four areas. In stream processing, one seeks unique events in a real time data stream that is too large to store. In fault protection, a system must adapt quickly to react to anticipated errors by triggering repair activities or follow- up diagnostics. With real-time sensor networks, one seeks to classify unique, new events as they occur. With observational sciences, a new generation of instrumentation seeks unique events through online analysis of large observational datasets. This work presents a solution based on transfer learning principles that permits principled CSDT learning while exploiting any prior knowledge of the designer to correct both between-class and withinclass imbalance. Training examples are adaptively reweighted based on a decomposition of the data attributes. The result is a new, nonparametric representation that matches the anticipated attribute distribution for the target events.

Thompson, David R.↗
NASA NTRSDate not supplied

Using Machine Learning to Classify Earth Science Articles

Developing a machine learning pipeline to automatic the classification of research article topics, where topics are geophysical descriptors. The resulting classified documents will be added to the Usage-Based Discovery graph database, along with corresponding NASA Earth Science datasets, with the intent of linking the NASA data product with uses of it that can be searched by topic. The project will aid in the following goals (1) creating a wider representation of how and how much NASA Earth Science data products are used, (2) identifying when NASA data products have been used even when they are not clearly cited, and (3) providing the UBD search tool end-user with set of recommended datasets based on a given topic query.

Machine Learning↗
NASA NTRSDate not supplied

Celestial Mapping System and Digital Lunar Library Initiative

We are preparing to create an interactive, global 3D lunar environment with integrated dataset and AI/ML tools to provide unique value to mission planners, scientists and the entire lunar community. This lunar environment will be based on NASA Ames Celestial Mapping System (CMS) [1] and Digital Lunar Library (DLL) Initiative. CMS provides a 3D virtual Lunar Globe with extensive user friendly tool sets, that include high resolution terrain visualization, elevation profiles, measurement kits, slope analysis, path optimization, line of sight analysis, equipment planning and placement tools and many other functionalities [1]. It has a thick client with less overhead to access hardware resources. This allows features such as terrain profiling and distance calculations to be performed on the client and on the fly. The application is developed to provide situational and domain awareness on the Lunar surface, planning capabilities for equipment placements and traverse path optimization. As data becomes available, CMS has the capabilities to integrate data sets that change dynamically in real-time, which will be useful for monitoring satellites and remotely-sensed data on the Lunar surface. CMS supports importing synthetic features in a variety of 3D, 2D, vector and raster formats. In the future, these capabilities will be enhanced by incorporating AI/ML tools and a plug-in architecture to enable customization by the user groups. With the help of DLL we will be able to : 1) Amplify the value of lunar information with AI-powered data enhancements 2) Acquire and integrate lunar data with AI-assisted georectification and homogenization 3) Analyze lunar data with advanced 3D visualization, intelligent search-by-example 4) Apply lunar data insights to specific use cases with an open plug-in architecture. The CMS-DLL initiative will have several potential use cases for NASA and the lunar community in general, including subsurface lava tube visualization and analysis, soil analysis, in-situ lunar resource visualization and representation on 3D globe, and data analytics for utilization. REFERENCES: [1] https://celestial.arc.nasa.gov/

3D Globe↗
DOE OSTI2024

End-to-end codesign of Hessian-aware quantized neural networks for FPGAs

Here, we develop an end-to-end workflow for the training and implementation of co-designed neural networks (NNs) for efficient field-programmable gate array (FPGA) hardware. Our approach leverages Hessian-aware quantization of NNs, the Quantized Open Neural Network Exchange intermediate representation, and the hls4ml tool flow for transpiling NNs into FPGA firmware. This makes efficient NN implementations in hardware accessible to nonexperts in a single open sourced workflow that can be deployed for real-time machine-learning applications in a wide range of scientific and industrial settings. We demonstrate the workflow in a particle physics application involving trigger decisions that must operate at the 40-MHz collision rate of the CERN Large Hadron Collider (LHC). Given the high collision rate, all data processing must be implemented on FPGA hardware within the strict area and latency requirements. Based on these constraints, we implement an optimized mixed-precision NN classifier for high-momentum particle jets in simulated LHC proton-proton collisions.

47 OTHER INSTRUMENTATION↗
NASA NTRS2010

Lessons Learned in Launching Ares I-X

The Ares I-X flight test, scheduled for 2009, is the first opportunity for the Constellation Program and Ares Projects to obtain important data on the in-flight loads, first stage recovery, and ground-handling characteristics of the Ares I crew launch vehicle. The flight test vehicle will incorporate a mix of flight and mockup hardware, reflecting an acceptable representation of the mass and outer mold line characteristics of the operational Ares I vehicle. It will be powered by a four-segment solid rocket motor from the Space Shuttle inventory and will include a fifth, inert spacer segment and new forward structures to make it the same shape as the Ares I first stage. The vehicle also includes mass simulators for the upper stage, Orion crew module, and launch abort system to match the outer mold line of Ares I; an active roll control system; and avionics derived from Shuttle and Atlas hardware. This suborbital mission will take the flight test vehicle from stacking in the Vehicle Assembly Building (VAB) at Kennedy Space Center (KSC) through liftoff, maximum dynamic pressure, first stage separation, and recovery. Ares I-X presented NASA with unique project management challenges. This presentation will address those unique challenges, including managing a virtual nationwide team under a constrained timeline; designing and building the launch vehicle and ground systems; working concurrently with Space Shuttle activities; and integrating technical and management functions. It also will identify key data collected and lessons learned from the flight that will be applied to future exploration missions.

Davis, Stephan R.↗
DOE OSTI2026

Active learning of a crystal plasticity flow rule from discrete dislocation dynamics simulations

Continuum-scale material deformation models, such as crystal plasticity (CP), can significantly enhance their predictive accuracy by incorporating input from lower-scale (i.e. mesoscale) models. The procedure to generate and extract the relevant information is however typically complex and ad hoc, involving decision and intervention by domain experts, leading to long development times. In this study, we develop a principled approach for calibration of continuum-scale models using lower scale information by representing a CP flow rule as a Gaussian process model. This representation allows for efficient parameter space exploration, guided by the uncertainty embedded in the model through a process known as Bayesian optimization (BO). We demonstrate a semi-autonomous BO loop which instantiates discrete dislocation dynamics simulations whose initial conditions are automatically chosen to optimize the uncertainty of a model CP flow rule. Our self-guided computational pipeline efficiently generated a dataset and corresponding model whose error, uncertainty, and physical feature sensitivities were validated with comparison to an independent dataset four times larger, demonstrating a valuable and efficient active learning implementation readily transferable to similar material systems.

36 MATERIALS SCIENCE↗
NASA NTRS2000

Neural activation during response competition

The flanker task, introduced by Eriksen and Eriksen [Eriksen, B. A., & Eriksen, C. W. (1974). Effects of noise letters upon the identification of a target letter in a nonsearch task. Perception & Psychophysics, 16, 143--149], provides a means to selectively manipulate the presence or absence of response competition while keeping other task demands constant. We measured brain activity using functional magnetic resonance imaging (fMRI) during performance of the flanker task. In accordance with previous behavioral studies, trials in which the flanking stimuli indicated a different response than the central stimulus were performed significantly more slowly than trials in which all the stimuli indicated the same response. This reaction time effect was accompanied by increases in activity in four regions: the right ventrolateral prefrontal cortex, the supplementary motor area, the left superior parietal lobe, and the left anterior parietal cortex. The increases were not due to changes in stimulus complexity or the need to overcome previously learned associations between stimuli and responses. Correspondences between this study and other experiments manipulating response interference suggest that the frontal foci may be related to response inhibition processes whereas the posterior foci may be related to the activation of representations of the inappropriate responses.

Brain Mapping/methods↗
DOE OSTI2026

Leveraging large language models to address data scarcity in machine learning for graphene synthesis

Machine learning in experimental materials science faces significant challenges due to the scarcity of data, which are costly and time-consuming to generate, particularly when relying on in-house experiments. Literature data mining offers a potential solution but introduces issues like mixed data quality, inconsistent formats, and non-uniform reporting of synthesis parameters, resulting in partially missing and heterogeneous features across the dataset. Here, we propose data imputation and feature engineering methods that employ pre-trained large language models (LLMs) to enhance machine learning performance on scarce, heterogeneous datasets, demonstrated on graphene CVD synthesis data and the ML-HydPARK hydrogen storage dataset. GPT models perform data imputation via tailored prompting and semantic normalization of inconsistently reported features through embeddings, for example, to harmonize the complex nomenclature of CVD substrates. Beyond yielding more diverse and richer feature representations than traditional methods such as K-nearest neighbors (KNN) and Multivariate Imputation by Chained Equations (MICE), LLM-based data imputation is evaluated against dataset characteristics and prompting strategies. We vary the level of autonomy granted to the LLM, from generic prompting that leverages pre-trained knowledge for autonomous data generation to data-informed prompting that constrains outputs using target-specific information, and demonstrate which level of autonomy yields superior imputation performance across datasets and feature types. The proposed data engineering methods markedly improve downstream performance; for example, in graphene layer number classification using a support vector machine (SVM), binary accuracy increases from 39% to 65% and ternary accuracy from 52% to 72%. Fine-tuning experiments on both datasets show that combining our proposed LLM-based data imputation and feature encoding methods with numerical machine learning predictors outperforms standalone fine-tuned LLM predictors in data-scarce settings. The proposed strategies emphasize data enhancement techniques rather than refining learning architectures or regularizing loss functions, offering a broadly applicable framework for improving machine learning performance on scarce, inhomogeneous datasets.

Chemical vapor deposition↗
NASA NTRS1990

Knowledge acquisition and representation for the Systems Test and Operations Language (STOL) Intelligent Tutoring System (ITS)

This presentation concentrates on knowledge acquisition and its application to the development of an expert module and a user interface for an Intelligent Tutoring System (ITS). The Systems Test and Operations Language (STOL) ITS is being developed to assist NASA control center personnel in learning a command and control language as it is used in mission operations rooms. The objective of the tutor is to impart knowledge and skills that will permit the trainee to solve command and control problems in the same way that the STOL expert solves those problems. The STOL ITS will achieve this object by representing the solution space in such a way that the trainee can visualize the intermediate steps, and by having the expert module production rules parallel the STOL expert's knowledge structures.

Seamster, Thomas L.↗
DOE OSTI2025

A kinetic-based regularization method for data science applications

We propose a physics-based regularization technique for function learning, inspired by statistical mechanics. By drawing an analogy between optimizing the parameters of an interpolator and minimizing the energy of a system, we introduce corrections that impose constraints on the lower-order moments of the data distribution. This minimizes the discrepancy between the discrete and continuum representations of the data, in turn allowing to access more favorable energy landscapes, thus improving the accuracy of the interpolator. Our approach improves performance in both interpolation and regression tasks, even in high-dimensional spaces. Unlike traditional methods, it does not require empirical parameter tuning, making it particularly effective for handling noisy data. We also show that thanks to its local nature, the method offers computational and memory efficiency advantages over Radial Basis Function interpolators, especially for large datasets.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Comparative study of machine learning techniques for post-combustion carbon capture systems

Computational analysis of countercurrent flows in packed absorption columns, often used in solvent-based post-combustion carbon capture systems (CCSs), is challenging. Typically, computational fluid dynamics (CFD) approaches are used to simulate the interactions between a solvent, gas, and column's packing geometry while accounting for the thermodynamics, kinetics, heat, and mass transfer effects of the absorption process. These simulations can then be used explain a column's hydrodynamic characteristics and evaluate its CO 2 -capture efficiency. However, these approaches are computationally expensive, making it difficult to evaluate numerous designs and operating conditions to improve efficiency at industrial scales. In this work, we comprehensively explore the application of statistical ML methods, convolutional neural networks (CNNs), and graph neural networks (GNNs) to aid and accelerate the scale-up and design optimization of solvent-based post-combustion CCSs. We apply these methods to CFD datasets of countercurrent flows in absorption columns with structured packings characterized by several geometric parameters. We train models to use these parameters, inlet velocity conditions, and other model-specific representations of the column to estimate key determinants of CO 2 -capture efficiency without having to simulate additional CFD datasets. We also evaluate the impact of different input types on the accuracy and generalizability of each model. We discuss the strengths and limitations of each approach to further elucidate the role of CNNs, GNNs, and other machine learning approaches for CO 2 -capture property prediction and design optimization.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Developing a Prototype Methodology to Rank CO2-EOR Wells and Assess Their Reuse Potential for Geologic Carbon Storage

This paper presents a prototype methodology to assess the possible transition of Class II carbon dioxide-enhanced oil recovery (CO2-EOR) wells to Class VI wells. The focus is on wellbore construction materials—casing, cement, tubing, and the packer—and includes comprehensive workflows to evaluate these materials, with primary emphasis on compliance with Environmental Protection Agency (EPA) Class VI well construction and conversion guidelines. These workflows systematically assess material properties and performance criteria to ensure regulatory compliance and optimize long-term wellbore integrity and functionality. Utilizing Python scripts and JavaScript Object Notation (JSON) representations, the study automates checks on digitized Texas Railroad Commission (TRRC) data to rank wells based on workflow criteria. By emphasizing critical factors such as casing integrity, cementing techniques, tubing compatibility, and packer selection, the methodology helps well owners and operators prioritize wells for potential reuse as CO2 injection wells. Given limitations in digitized data, manual user verification is required in some sections. Future improvements include integrating non-digitized data through web scraping and machine learning techniques. This research serves as a practical guide for stakeholders, supporting environmental compliance and sustainable well operations.

geologic carbon sequestration↗
DOE OSTI2025

Enhancing Drinking Water Quality Modeling: Leveraging Physics Informed Neural Networks for Learning with Imperfect Reaction Models and Partial Data

Chemical kinetics models, typically formulated as systems of ordinary or partial differential equations, are valuable tools for simulating drinking water quality. However, these models often face inaccuracies due to discrepancies between the laboratory and the real-world conditions, as well as limitations in experimental analytical methods, hindering the accurate representation of the true underlying chemical mechanisms. In this study, we propose a Physics Informed Neural Network (PINN), using the eXtreme Theory of Functional Connections, to improve the prediction of chemical concentrations over time. The PINN method accounts for imperfect chemical models and incorporates partial data to improve predictions. Focusing on reactions describing water disinfection residual and disinfectant byproduct formation, which are crucial for public health and regulatory compliance, we demonstrate that the PINN model is able to accurately predict the concentrations of chemical species across various pH values. Notably, the model extends its accuracy to predict concentrations of chemical species not originally included in its training data. The developed method can be extended to a variety of chemical systems, offering a wide array of potential applications.

13 HYDRO ENERGY↗
DOE OSTI2026

Challenges and Vision for Standardization of Biopolymer Data Sets for Machine Learning

Machine learning (ML) is transforming materials research, yet potential for biopolymer discovery remains constrained by fragmented data and nonstandardized reporting. Biopolymers differ significantly from synthetic polymers, requiring specialized approaches to represent their biosynthetic origins, hierarchical structures, and application-specific metrics. In this Perspective, we identify three core challenges limiting biopolymer representation: information encoding, data quality, and data sharing. We describe the most pressing issues and propose commensurate approaches to address each key challenge. Recommendations include the design and adoption of biopolymer-specific fingerprinting and representation frameworks, development of hybrid human-large language model (LLM) data extraction strategies, and expanding Findable, Accessible, Interoperable, Reusable (FAIR)-compliant repositories. We propose a robust foundation to define interoperable, high-quality data sets that capture the full context of biopolymer materials. Standardized metadata, shared ontologies, and community-driven infrastructure would enable scalable, reproducible workflows and accelerate the ML-driven development of biopolymers.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Manifold Learning: What, How, and Why

Manifold learning (ML), also known as nonlinear dimension reduction, is a set of methods to find the low-dimensional structure of data. Dimension reduction for large, high-dimensional data is not merely a way to reduce the data; the new representations and descriptors obtained by ML reveal the geometric shape of high-dimensional point clouds and allow one to visualize, denoise, and interpret them. This review presents the underlying principles of ML, its representative methods, and their statistical foundations, all from a practicing statistician's perspective. It describes the trade-offs and what theory tells us about the parameter and algorithmic choices we make in order to obtain reliable conclusions.

Mathematics↗