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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 415 records · Page 23

All sources NASA NTRS DOE OSTI

NASA NTRS1994

Passive mapping and intermittent exploration for mobile robots

An adaptive state space architecture is combined with diktiometric representation to provide the framework for designing a robot mapping system with flexible navigation planning tasks. This involves indexing waypoints described as expectations, geometric indexing, and perceptual indexing. Matching and updating the robot's projected position and sensory inputs with indexing waypoints involves matchers, dynamic priorities, transients, and waypoint restructuring. The robot's map learning can be opganized around the principles of passive mapping.

Engleson, Sean P.↗

DOE OSTI2026

Domain Knowledge Guided Bayesian Optimization For Autonomous Alignment Of Complex Scientific Instruments

Bayesian Optimization (BO) is a powerful tool for optimizing complex non-linear systems. However, its performance degrades in high-dimensional problems with tightly coupled parameters and highly asymmetric objective landscapes, where rewards are sparse. In such needle-in-a-haystack scenarios, even advanced methods like trust-region BO (TurBO) often lead to unsatisfactory results. We propose a domain knowledge guided Bayesian Optimization approach, which leverages physical insight to fundamentally simplify the search problem by transforming coordinates to decouple input features and align the active subspaces with the primary search axes. We demonstrate this approach's efficacy on a challenging 12-dimensional, 6-crystal Split-and-Delay optical system, where conventional approaches, including standard BO, TuRBO and multi-objective BO, consistently led to unsatisfactory results. When combined with an reverse annealing exploration strategy, this approach reliably converges to the global optimum. The coordinate transformation itself is the key to this success, significantly accelerating the search by aligning input co-ordinate axes with the problem's active subspaces. As increasingly complex scientific instruments, from large telescopes to new spectrometers at X-ray Free Electron Lasers are deployed, the demand for robust high-dimensional optimization grows. Our results demonstrate a generalizable paradigm: leveraging physical insight to transform high-dimensional, coupled optimization problems into simpler representations can enable rapid and robust automated tuning for consistent high performance while still retaining current optimization algorithms.

FOS: Computer and information sciences↗

DOE OSTI2025

Application of Machine Learning and Data Augmentation Algorithms in the Discovery of Metal Hydrides for Hydrogen Storage

The development of efficient and sustainable hydrogen storage materials is a key challenge for realizing hydrogen as a clean and flexible energy carrier. Among various options, metal hydrides offer high volumetric storage density and operational safety, yet their application is limited by thermodynamic, kinetic, and compositional constraints. In this work, we investigate the potential of machine learning (ML) to predict key thermodynamic properties—equilibrium plateau pressure, enthalpy, and entropy of hydride formation—based solely on alloy composition using Magpie-generated descriptors. We significantly expand an existing experimental dataset from ~400 to 806 entries and assess the impact of dataset size and data augmentation, using the PADRE algorithm, on model performance. Models including Support Vector Machines and Gradient Boosted Random Forests were trained and optimized via grid search and cross-validation. Results show a marked improvement in predictive accuracy with increased dataset size, while data augmentation benefits are limited to smaller datasets and do not improve accuracy in underrepresented pressure regimes. Furthermore, clustering and cross-validation analyses highlight the limited generalizability of models across different material classes, though high accuracy is achieved when training and testing within a single hydride family (e.g., AB2). The study demonstrates the viability and limitations of ML for accelerating hydride discovery, emphasizing the importance of dataset diversity and representation for robust property prediction.

augmentation↗

NASA NTRS1997

Improving Search Properties in Genetic Programming

With the advancing computer processing capabilities, practical computer applications are mostly limited by the amount of human programming required to accomplish a specific task. This necessary human participation creates many problems, such as dramatically increased cost. To alleviate the problem, computers must become more autonomous. In other words, computers must be capable to program/reprogram themselves to adapt to changing environments/tasks/demands/domains. Evolutionary computation offers potential means, but it must be advanced beyond its current practical limitations. Evolutionary algorithms model nature. They maintain a population of structures representing potential solutions to the problem at hand. These structures undergo a simulated evolution by means of mutation, crossover, and a Darwinian selective pressure. Genetic programming (GP) is the most promising example of an evolutionary algorithm. In GP, the structures that evolve are trees, which is a dramatic departure from previously used representations such as strings in genetic algorithms. The space of potential trees is defined by means of their elements: functions, which label internal nodes, and terminals, which label leaves. By attaching semantic interpretation to those elements, trees can be interpreted as computer programs (given an interpreter), evolved architectures, etc. JSC has begun exploring GP as a potential tool for its long-term project on evolving dextrous robotic capabilities. Last year we identified representation redundancies as the primary source of inefficiency in GP. Subsequently, we proposed a method to use problem constraints to reduce those redundancies, effectively reducing GP complexity. This method was implemented afterwards at the University of Missouri. This summer, we have evaluated the payoff from using problem constraints to reduce search complexity on two classes of problems: learning boolean functions and solving the forward kinematics problem. We have also developed and implemented methods to use additional problem heuristics to fine-tune the searchable space, and to use typing information to further reduce the search space. Additional improvements have been proposed, but they are yet to be explored and implemented.

Janikow, Cezary Z.↗

NASA NTRS1990

System identification in the repetition domain

Procedures for system identification using realization theory in conjunction with learning control ideas are developed. The Markov parameters of the system are identified by combining data from repeated experiments. Three approaches are discussed for identification of as many Markov parameters as sample points in the experiment. Making use of all the parameters, realization theory is then employed to determine the system order and to obtain a minimal order representation. The first two approaches are non-recursive, which in the case of noise-free data yields a one step solution. The third approach uses a recursive formulation rendered from adaptive control but modified for successive experiments. A simple example shows the numerical convergence of the identified parameters as a function of the number of experiments. The procedure presented herein is an extension of the existing Eigensystem Realization Algorithm (ERA), which has been successfully applied for system identification of large structures.

Juang, Jer-Nan↗

NASA NTRS1999

A View from Space: Evolution of the 1997-98 El Nino and La Nina

After the last extreme El Nino in 1982-1983, an extensive in situ observing system was deployed in the tropical Pacific Ocean in support of monitoring and predicting El Nino. Within the past ten years a series of ocean and atmosphere remote sensing satellites have been launched that serve to supplement and enhance the observations being taken at the surface, and at depth, in the equatorial Pacific Ocean. The 1997-1998 "El Nino Event of the Century" has been the best monitored El Nino on record. The 1997-1998 El Nino will be the first time a major El Nino event and subsequent La Nina will have been observed from start to finish from a combination of remotely-sensed measurements of sea surface temperature, sea surface topography, sea surface winds, ocean color, and precipitation. Among some of the lessons learned to date from the 1997-1998 event have been the need for global observations in addition to just those in the equatorial Pacific Ocean. In this presentation the evolution of the 1997-1998 El Nino will be depicted from the unique vantage point provided by these space-based observations as analyzed separately, and together as a representation of the coupled system. Comparisons and contrasts with the evolution 1982-1983 El Nino and how the in situ and space-based observations complement each other will be discussed.

Busalacchi, Antonio J.↗

NASA NTRS1997

A View from Space: Evolution of the 1997-1998 El Nino and La Nina

Busalacchi, Antonio J.↗

NASA NTRS1999

A View From Space: Evolution of the 1997-1998 El Nino and La Nina

After the last extreme El Nino in 1982-1983, an extensive in situ observing system was deployed in the tropical Pacific Ocean in support of monitoring and predicting El Nino. Within the past ten years a series of ocean and atmosphere remote sensing satellites have been launched that serve to supplement and enhance the observations being taken at the surface, and at depth, in the equatorial Pacific Ocean. The 1997-1998 "El Nino Event of the Century" has been the best monitored El Nino on record. The 1997-1998 El Nino will be the first time a major El Nino event and subsequent La Nina will have been observed from start to finish from a combination of remotely-sensed measurements of sea surface temperature, sea surface topography, sea surface wind, ocean color, and precipitation, Among some of the lessons learned to date from the 1997-1998 event have been the need for global observation in addition to just those in the equatorial Pacific Ocean. In this presentation the evolution of the 1997-1998 El Nino will be depicted from the unique vantage point provided by these space-based observations as analyzed separately, and together as a representation of the coupled system. Comparisons and contrasts with the evolution 1982-1983 El Nino and how the in situ and space-based observations complement each other will be discussed.

Busalacchi, Antonio↗

DOE OSTI2025

Inference of response functions with the help of machine-learning algorithms

Response functions are a key quantity to describe the near-equilibrium dynamics of strongly interacting many-body systems. Recent techniques that attempt to overcome the challenges of calculating these ab initio have employed expansions in terms of orthogonal polynomials. We employ a neural network prediction algorithm to reconstruct a response function 𝑆⁡(𝜔) defined over a range in frequencies 𝜔. Here, we represent the calculated response function as a truncated Chebyshev series whose coefficients can be optimized to reduce the representation error. We compare the quality of response functions obtained using coefficients calculated using a neural network (NN) algorithm with those computed using the Gaussian integral transform (GIT) method. In the regime where only a small number of terms in the Chebyshev series are retained, we find that the NN scheme outperforms the GIT method.

Kurkcuoglu, Doga Murat [Fermi National Accelerator↗

DOE OSTI2026

Graph theory inspired anomaly detection at the LHC

Designing model-independent anomaly detection algorithms for analyzing LHC data remains a central challenge in the search for new physics, due to the high dimensionality of collider events. In this work, we develop a graph autoencoder as an unsupervised, model-agnostic tool for anomaly detection, using the LHC Olympics dataset as a benchmark. By representing jet constituents as a graph, we introduce a method to systematically control the information available to the model through sparse graph constructions that serve as physically motivated inductive biases. Specifically, (1) we construct graph autoencoders based on locally rigid Laman graphs and globally rigid unique graphs, and (2) we explore the clustering of jet constituents into subjets to interpolate between high- and low-level input representations. We obtain the best performance, measured in terms of the Significance Improvement Characteristic curve for an intermediate level of subjet clustering and certain sparse unique graph constructions. We further investigate the role of graph connectivity in jet classification tasks. Our results demonstrate the potential of leveraging graph-theoretic insights to refine and increase the interpretability of machine learning tools for collider experiments.

Automation↗

DOE OSTI2025

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

This study presents a prototype methodology for evaluating the reuse potential of Class II CO₂-enhanced oil recovery (CO₂-EOR) wells as Class VI wells for geologic carbon sequestration. The approach focuses on assessing wellbore construction materials—casing, cement, tubing, and packers—based on U.S. Environmental Protection Agency (EPA) Class VI well conversion guidelines. Utilizing Python scripts and JSON representations, the methodology automates checks on digitized Texas Railroad Commission (TRRC) data to rank wells based on regulatory and integrity criteria. Key factors include casing integrity, cementing techniques, tubing compatibility, and packer selection. Due to limitations in digitized data, manual verification is required for certain sections. Future enhancements include incorporating non-digitized data via web scraping and machine learning. This research provides a practical framework for well owners and regulators, supporting informed decision-making for sustainable CO₂ storage.

carbon sequestration↗

NASA NTRS2015

Enhancements of Bayesian Blocks; Application to Large Light Curve Databases

Bayesian Blocks are optimal piecewise linear representations (step function fits) of light-curves. The simple algorithm implementing this idea, using dynamic programming, has been extended to include more data modes and fitness metrics, multivariate analysis, and data on the circle (Studies in Astronomical Time Series Analysis. VI. Bayesian Block Representations, Scargle, Norris, Jackson and Chiang 2013, ApJ, 764, 167), as well as new results on background subtraction and refinement of the procedure for precise timing of transient events in sparse data. Example demonstrations will include exploratory analysis of the Kepler light curve archive in a search for "star-tickling" signals from extraterrestrial civilizations. (The Cepheid Galactic Internet, Learned, Kudritzki, Pakvasa1, and Zee, 2008, arXiv: 0809.0339; Walkowicz et al., in progress).

Kepler light curve archive↗

NASA NTRSDate not supplied

Machine Learning Emulators and Empirical Models Combining Climate and Global Crop Models for Seasonal Agricultural Production

We present results from several connected efforts to apply machine learning methods to estimates of seasonal agricultural production anomalies around the world. First, we apply the XGBoost Random Forest method to fit emulators that mimic global crop models participating in the Agricultural Model Intercomparison and Improvement Project (AgMIP) Global Gridded Crop Model Intercomparison (GGCMI). These are the same models used in the agricultural sector simulations of the Inter-Sectoral Impacts Model Intercomparison Project (ISIMIP). These emulators use 8 climate variables split across 5 sub-seasonal representations of the growing season for each ½ degree grid cell around the world for maize, wheat, rice and soybeans. Emulators are useful for estimating conditions that have not already been simulated by GGCMI (e.g., in a seasonal prediction model) and also to diagnose model differences and capabilities. For example, emulators of the pDSSAT maize model tend to be more reliant on mean temperatures than the LPJmL model, and few models have strong responses to cold extremes. Second, we use a similar XGBoost approach to fit empirical models for national production data for the top 20 producing countries according to the United Nations Food and Agricultural Organization (FAO). Models utilize both climate observations and the GGCM models as predictors, resulting in skillful models for many (but not all) top producing-countries. The patterns of climate and crop model features selected indicate regions and systems that are better or worse simulated by the GGCMs. For example, information in cold extreme predictors is often combined with GGCM output predictors to provide sensitivity that models may underrepresent.

machine learning↗

DOE OSTI2025

Direct NeTS sampling of nuclear graphite $S(α, β, T)$ in Serpent

For advanced reactor applications, Neural Thermal Scattering (NeTS) modules were developed to predict the thermal scattering law (TSL or $S(α, β, T)$) of a nuclear graphite neutron moderator. NeTS are multi-layer, feedforward artificial neural networks, which act as universal function approximators designed for TSL datasets. In this case, a 4-layer neural network with 164 neurons per layer is trained using FLASSH evaluated data in PyTorch and serialized as a torchscript dictionary to predict $S(α, β, T)$ on-the-fly. Relative, absolute and maximum percent deviations of NeTS from File 7 data generated using the FLASSH code are on the order of 0.01%, 0.1% and 1%, respectively, with low inference latencies of 0.000172 s per $S(α, β, T)$ at a given temperature. Capturing the full dimensionality of possible inelastic neutron-lattice interactions, NeTS functionality is embedded in the Serpent Monte Carlo code, where $S(α, β, T)_{NeTS}$ sampling is conducted on-the-fly and compared to ACE look-up-tables for predicting TREAT criticality. k-eff differences between sampling algorithms of 6 pcm are observed and are within the order of Monte Carlo uncertainty. Compared to discrete and continuous-energy ACE files (30 MB and 131 MB per temperature), the NeTS format is on the order of 200–300 kB for a continuous-temperature, interpolation-free representation of $S(α, β, T)$ and cross sections. NeTS-in-Serpent runtimes comparable with ACE look-up tables are achieved by scaling NeTS for high performance computing architectures with hybrid OpenMP + MPI parallelization. This work validates a novel, self-contained reactor physics framework for predictive cross sections, and demonstrates a general methodology for embedding modern machine learning libraries within existing neutronic analysis frameworks.

Nuclear Criticality Safety Program (NCSP)↗

NASA NTRS1992

Sensor fusion IV: Control paradigms and data structures; Proceedings of the Meeting, Boston, MA, Nov. 12-15, 1991

Various papers on control paradigms and data structures in sensor fusion are presented. The general topics addressed include: decision models and computational methods, sensor modeling and data representation, active sensing strategies, geometric planning and visualization, task-driven sensing, motion analysis, models motivated biology and psychology, decentralized detection and distributed decision, data fusion architectures, robust estimation of shapes and features, application and implementation. Some of the individual subjects considered are: the Firefly experiment on neural networks for distributed sensor data fusion, manifold traversing as a model for learning control of autonomous robots, choice of coordinate systems for multiple sensor fusion, continuous motion using task-directed stereo vision, interactive and cooperative sensing and control for advanced teleoperation, knowledge-based imaging for terrain analysis, physical and digital simulations for IVA robotics.

Schenker, Paul S.↗

DOE OSTI2026

QCalEval: Benchmarking Vision-Language Models for Quantum Calibration Plot Understanding

Quantum computing calibration depends on interpreting experimental data, and calibration plots provide the most universal human-readable representation for this task, yet no systematic evaluation exists of how well vision-language models (VLMs) interpret them. We introduce QCalEval, the first VLM benchmark for quantum calibration plots: 243 samples across 87 scenario types from 22 experiment families, spanning superconducting qubits and neutral atoms, evaluated on six question types in both zero-shot and in-context learning settings. The best general-purpose zero-shot model reaches a mean score of 72.3, and many open-weight models degrade under multi-image in-context learning, whereas frontier closed models improve substantially. A supervised fine-tuning ablation at the 9-billion-parameter scale shows that SFT improves zero-shot performance but cannot close the multimodal in-context learning gap. As a reference case study, we release NVIDIA Ising Calibration 1, an open-weight model based on Qwen3.5-35B-A3B that reaches 74.7 zero-shot average score.

Cao, Shuxiang↗

NASA NTRS2023

Toward Physics-informed Neural Networks for 3D Multi-layer Cloud Mask Reconstruction

Three-dimensional (3D) cloud retrievals are critical for understanding their impact on climate and other applications such as aviation safety, weather prediction, and remote sensing. However, obtaining high-resolution and accurate vertical representation of clouds remains unsolved due to the limitations imposed by satellite instrumentation, viewing conditions, and the complexity of cloud dynamics. Cloud masks are essential for comprehending various cloud vertical properties, but deriving accurate 3D cloud masks from 2D satellite imagery data is a challenging task. To tackle these challenges, we introduce a physics-informed loss function for training deep learning models that can extend 2D cloud images into 3D cloud masks. The proposed loss, called CloudMask Loss, is composed of two domain knowledge-informed loss terms: one for evaluating cloud position and thickness, and the other for measuring the number of layers. By combining these loss terms, we improve the trainability of the deep learning models for more accurate and meaningful results. We apply the proposed loss function to different neural networks and demonstrate significant improvements in multi-layer cloud mask reconstruction. Utilizing the same neural network architecture, our proposed loss outperforms standard binary crossentropy loss in terms of multi-layer cloud classification accuracy, number of layers accuracy, and thickness mean absolute error (MAE). The proposed loss function can be readily integrated into various neural network architectures, resulting in substantial performance gains in 3D cloud mask generation.

multi-layer clouds↗

DOE OSTI2024

A prospective on machine learning challenges, progress, and potential in polymer science

Abstract Artificial intelligence and machine learning (ML) continue to see increasing interest in science and engineering every year. Polymer science is no different, though implementation of data-driven algorithms in this subfield has unique challenges barring widespread application of these techniques to the study of polymer systems. In this Prospective, we discuss several critical challenges to implementation of ML in polymer science, including polymer structure and representation, high-throughput techniques and limitations, and limited data availability. Promising studies targeting resolution of these issues are explored, and contemporary research demonstrating the potential of ML in polymer science despite existing obstacles are discussed. Finally, we present an outlook for ML in polymer science moving forward. Graphical Abstract

Struble, Daniel C. (ORCID:0009000093410612)↗