Search NASA⌕ Search

SEARCH · Search NASA

Results for “embedding”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Replacing non-biomedical concepts improves embedding of biomedical concepts

Embeddings are semantically meaningful representations of words in a vector space, commonly used to enhance downstream machine learning applications. Traditional biomedical embedding techniques often replace all synonymous words representing biological or medical concepts with a unique token, ensuring consistent representation and improving embedding quality. However, the potential impact of replacing non-biomedical concept synonyms has received less attention. Embedding approaches often employ concept replacement to replace concepts that span multiple words, such as non-small-cell lung carcinoma, with a single concept identifier (e.g., D002289). Also, all synonyms of each concept are merged into the same identifier. Here, we additionally leveraged WordNet to identify and replace sets of non-biomedical synonyms with their most common representatives. This combined approach aimed to reduce embedding noise from non-biomedical terms while preserving the integrity of biomedical concept representations. We applied this method to 1,055 biomedical concept sets representing molecular signatures or medical categories and assessed the mean pairwise distance of embeddings with and without non-biomedical synonym replacement. A smaller mean pairwise distance was interpreted as greater intra-cluster coherence and higher embedding quality. Embeddings were generated using the Word2Vec algorithm applied to a corpus of 10 million PubMed abstracts. Our results demonstrate that the addition of non-biomedical synonym replacement reduced the mean intra-cluster distance by an average of 8%, suggesting that this complementary approach enhances embedding quality. Future work will assess its applicability to other embedding techniques and downstream tasks. Python code implementing this method is provided under an open-source license.

algorithms↗
DOE OSTI2024

Mixed Delay/Nondelay Embeddings Based Neuromorphic Computing with Patterned Nanomagnet Arrays

Patterned nanomagnet arrays (PNAs) have been shown to exhibit a strong geometrically frustrated dipole interaction. Some PNAs have also shown emergent domain wall dynamics. Previous works have demonstrated methods to physically probe these magnetization dynamics of PNAs to realize neuromorphic reservoir systems that exhibit chaotic dynamical behavior and high-dimensional nonlinearity. These PNA reservoir systems from prior works leverage echo state properties and linear/nonlinear short-term memory of component reservoir nodes to map and preserve the dynamical information of the input time-series data into nondelay spatial embeddings. Such mappings enable these PNA reservoir systems to imitate and predict/forecast the input time series data. However, these prior PNA reservoir systems are based solely on the nondelay spatial embeddings obtained at component reservoir nodes. As a result, they require a massive number of component reservoir nodes, or a very large spatial embedding (i.e., high-dimensional spatial embedding) per reservoir node, or both, to achieve acceptable imitation and prediction accuracy. These requirements reduce the practical feasibility of such PNA reservoir systems. To address this shortcoming, we present a mixed delay/nondelay embeddings-based PNA reservoir system. Our system uses a single PNA reservoir node with the ability to obtain a mixture of delay/nondelay embeddings of the dynamical information of the time-series data applied at the input of a single PNA reservoir node. Our analysis shows that when these mixed delay/nondelay embeddings are used to train a perceptron at the output layer, our reservoir system outperforms existing PNA-based reservoir systems for the imitation of NARMA 2, NARMA 5, NARMA 7, and NARMA 10 time series data, and for the short-term and long-term prediction of the Mackey Glass time series data.

Ti, Changpeng↗
DOE OSTI2025

Projector‐Based Quantum Embedding Study of Iron Complexes

Projection‐based embedding theory (PBET) is used to calculate and assess the challenging spin‐crossover energies for a selection of small Fe‐containing systems by embedding the metal center into the frozen potential of the ligands. MP2, CCSD, and CCSD(T) are embedded in potentials from the SCAN and r 2 SCAN functionals and compared with the canonical values for the constituent methods and previously reported reference values. Considering the PBET calculations as a correction for the underlying DFT, the embedding calculations are able to provided improvement for most cases. In some cases, the PBET methods are able to compensate for limitations in the wave function methods and produce results similar to more rigorous calculations from the literature. For the systems with spin‐crossover energies near zero, the current methodology fails to provide consistent improvement. In conclusion, the isolated recalculation of the electronic structure around the metal center when embedded into a DFT treatment of the ligand field shows promise as a pragmatic and lower cost treatment compared to the canonical treatment of the whole system of the difficult class of spin‐crossover complexes.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Self-Sensing Composites via an Embedded 3D-Printed PVDF-MoS 2 Nanosensor for Structural Health Monitoring

Carbon fiber (CF)-reinforced epoxy composites are widely used in vehicle applications, where early damage detection is crucial for reliability and safety. To address this need, we developed a self-sensing epoxy/CF composite by embedding a PVDF-MoS 2 nanosensor via an embedded 3D printing method. By harnessing the intrinsic curing kinetics of epoxy, we tailored its rheological properties to optimize the embedded printing process, enabling precise and reliable support for sensor filaments without compromising the composite’s structural and functional integrity. Through comprehensive rheological and kinetic analysis, we established a quantitative relationship among curing temperature, conversion rate, and resulting yield modulus─defining a narrow processing window essential for successful sensor integration. Specifically, we identified that an epoxy yield modulus range of 180–294 Pa and a conversion rate below 10% are critical to support the PVDF-MoS 2 filament architecture. Here, this embedded 3D printing method produces complex and multimaterial PVDF-MoS 2 sensors within an epoxy matrix with minimal deformation and reduced postprocessing, which is scalable and adaptable for industrial applications. Under cyclic loading, the embedded sensors exhibited stable signals under constant loads and increased voltage signals in response to crack formation (17–35% higher) and catastrophic failure (1 order of magnitude higher), effectively capturing structural changes in real time. This study demonstrates the potential of PVDF-MoS 2 nanocomposite sensor materials for real-time structural health monitoring in epoxy–CF composite systems, enabling early detection of defects and stress anomalies, significantly reducing the risk of unexpected failures, and enhancing structural reliability.

PVDF-MoS2 sensor↗
DOE OSTI2025

Explaining word embeddings with perfect fidelity: a case study in predicting research impact

The best-performing approaches for scholarly document quality prediction are based on embedding models. In addition to their performance when used in classifiers, embedding models can also provide predictions even for words that were not contained in the labelled training data for the classification model, which is important in the context of the ever-evolving research terminology. Although model-agnostic explanation methods, such as Local interpretable model-agnostic explanations, can be applied to explain machine learning classifiers trained on embedding models, these produce results with questionable correspondence to the model. We introduce a new feature importance method, Self-Model Entities Rated (SMER), for logistic regression-based classification models trained on word embeddings. We show that SMER has theoretically perfect fidelity with the explained model, as the average of logits of SMER scores for individual words (SMER explanation) exactly corresponds to the logit of the prediction of the explained model. Quantitative and qualitative evaluation is performed through five diverse experiments conducted on 50,000 research articles (papers) from the CORD-19 corpus. In conclusion, through an AOPC curve analysis, we experimentally demonstrate that SMER produces better explanations than LIME, SHAP and global tree surrogates.

Coarse-grained models↗
DOE OSTI2025

DOME: Directional medical embedding vectors from Electronic Health Records

Motivation: The increasing availability of Electronic Health Record (EHR) systems has created enormous potential for translational research. Recent developments in representation learning techniques have led to effective large-scale representations of EHR concepts along with knowledge graphs that empower downstream EHR studies. However, most existing methods require training with patient-level data, limiting their abilities to expand the training with multi-institutional EHR data. On the other hand, scalable approaches that only require summary-level data do not incorporate temporal dependencies between concepts. Methods: We introduce a DirectiOnal Medical Embedding (DOME) algorithm to encode temporally directional relationships between medical concepts, using summary-level EHR data. Specifically, DOME first aggregates patient-level EHR data into an asymmetric co-occurrence matrix. Then it computes two Positive Pointwise Mutual Information (PPMI) matrices to correspondingly encode the pairwise prior and posterior dependencies between medical concepts. Following that, a joint matrix factorization is performed on the two PPMI matrices, which results in three vectors for each concept: a semantic embedding and two directional context embeddings. They collectively provide a comprehensive depiction of the temporal relationship between EHR concepts. Results: We highlight the advantages and translational potential of DOME through three sets of validation studies. First, DOME consistently improves existing direction-agnostic embedding vectors for disease risk prediction in several diseases, for example achieving a relative gain of 5.5% in the area under the receiver operating characteristic (AUROC) for lung cancer. Second, DOME excels in directional drug-disease relationship inference by successfully differentiating between drug side effects and indications, correspondingly achieving relative AUROC gain over the state-of-the-art methods by 10.8% and 6.6%. Finally, DOME effectively constructs directional knowledge graphs, which distinguish disease risk factors from comorbidities, thereby revealing disease progression trajectories. The source codes are provided at https://github.com/celehs/Directional-EHRembedding.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

Accelerating Embedding Potential Optimization by Reconstructing the Pseudo-Valence Electron Density

Density functional embedding theory (DFET) enables use of electronic structure methods with higher accuracy than density functional theory in a local region, with applications thus far ranging from (photo/electro)catalysis to reactions in solution. DFET partitions a large collection of atoms into smaller groups that interact via a shared embedding (interaction) potential V emb , determined via functional optimization. The optimized effective potential (OEP) process used to optimize V emb is time-consuming and becomes a computational bottleneck due to sharp, oscillating features of V emb near nuclei. Here, similar to pseudopotential theory, by reconstructing electron densities used in the OEP process from smoother pseudo-valence-only (PVO) electron densities as proxies for total densities of the full system and subsystems, we can retain accuracy in the embedded electronic structure calculations while potentially reducing the overhead of V emb construction, within the projector augmented-wave (PAW) formalism. We explore three different chemical reactions as exemplars to test PVO–DFET, namely, H 2 dissociative adsorption on a Cu(111) surface, H 2 O adsorption on a Pt(111) surface, and aqueous [Ca 2+ –SO 4 2– ] ion-pair formation. The PVO approximation works well for all three systems with minimal loss of accuracy (∼10–70 meV error relative to the original exact-derivative (ED) approach) while accelerating V emb generation for the Cu and Pt systems respectively by 20× and 5×. Given proper numerical convergence parameters, the spatial distributions of differences between PVO- and ED-based V emb outside the core regions are small, explaining the exceptional agreement between the two approaches. Finally, we anticipate that this more efficient PVO–DFET approximation will be useful whenever computation of V emb is much more expensive than subsequent embedded high-level electron correlation calculations.

approximation↗
DOE OSTI2026

Embedding Fiber Optic Sensors in Stainless Steel using Spark Plasma Sintering for Structural Health Monitoring in Harsh Environments

Embedded fiber optic sensors such as fiber Bragg gratings (FBGs) offer a unique route for distributed real-time in-situ imaging of various engineering parameters for numerous purposes. This study advanced the current sensor embedding approaches by exploring a spark plasma sintering (SPS)-assisted technology to embed FBGs in high-temperature structural materials and demonstrated the capability of temperature measurement. In this approach, single-mode FBGs were integrated into stainless steel (SS) 316L components using SPS, followed by the evaluation of the bonding quality between the FBGs and matrix, the optical attenuation of the fibers induced by embedding, and the sensing characters of the FBGs under temperature stimuli. The results demonstrated that superior bonding was achieved between the FBGs and highly-densified SS316L. Examination of the behavior of Bragg gratings validated signal fidelity after embedding. Real-time thermal imaging under temperature cycling using the FBGs demonstrated the effectiveness of the technique for smart materials manufacturing.

36 - MATERIALS SCIENCE↗
DOE OSTI2025

Embedded random phase approximation for magnetic systems: H 2 dissociative adsorption on Fe(110)

The random phase approximation (RPA), a method for treating electron correlation, has been shown to be superior to standard density functional theory (DFT) approximations in numerous cases. However, the RPA’s computational cost is substantially higher than that of DFT, particularly restricting its application to extended surfaces. The recently introduced embedded RPA (emb-RPA) approach [Wei et al., J. Chem. Phys. 159(19), 194108 (2023)] reduces this computational cost by approximately two orders of magnitude. While previous applications of emb-RPA focused on non-spin-polarized systems, here we extend the approach to ferromagnetic ones. Unlike other embedded correlated wavefunction methods, such as embedded complete active space self-consistent field theory, emb-RPA is advantageous for spin-polarized systems because the RPA is compatible with unrestricted DFT solutions, which are eigenfunctions of the spin angular momentum operator S z but not the total spin-squared operator S 2 . By applying emb-RPA with specific magnetization constraints, we achieved a speedup of two to three orders of magnitude (one order when accounting for the one-time embedding potential optimization cost) with only small errors (∼50 meV) compared to full periodic RPA. Moreover, emb-RPA significantly reduces the over-binding errors of DFT approximations. In conclusion, we anticipate that the acceleration enabled by the spin-polarized emb-RPA approach will broaden the applicability of RPA to magnetic materials.

Density functional theory↗
DOE OSTI2026

Hierarchical-embedding autoencoder with a predictor as efficient architecture for learning time-evolution in multi-scale turbulent flows

We introduce a scale-aware, data-driven deep learning modeling framework for accurately predicting the time evolution of multi-scale turbulent plasma and liquid flows. The approach is motivated by the idea of scale separation. Structures of vastly different length scales emerge in these systems, and interactions between these structures occur only locally. To exploit this structure, the flow state is transformed by a hierarchical, fully convolutional autoencoder, not into a single embedding layer as in conventional convolutional surrogate models, but into a series of embedding layers. A stepwise training strategy ensures that fine-scale features are encoded on a high-resolution grid, while larger structures are represented on progressively coarser layers. The time evolution predictor advances all embedding layers in sync, capturing local interactions between features at the same scale as well as between all scales. This approach enables efficient modeling of multi-scale systems since negligible interactions between distant, small-scale structures do not need to be directly modeled. Our hierarchical-embedding autoencoder with a predictor framework is evaluated on canonical examples of multi-scale turbulence: two-dimensional Kolmogorov flow and Hasegawa–Wakatani plasma turbulence. In both cases, the proposed framework significantly improves predictive accuracy relative to conventional convolutional network architectures. A significant improvement in prediction accuracy was observed for crucial statistical characteristics of the Hasegawa–Wakatani plasma as well as for individual trajectories of the Kolmogorov flow turbulence. Importantly, the model's rollout for the Hasegawa–Wakatani problem demonstrates a four-order-of-magnitude speedup compared to traditional numerical solvers.

Khrabry, Alexander I. [Princeton Univ., NJ (United↗
DOE OSTI2025

DNABERT-S: pioneering species differentiation with species-aware DNA embeddings

SUMMARY: We introduce DNABERT-S, a tailored genome model that develops species-aware embeddings to naturally cluster and segregate DNA sequences of different species in the embedding space. Differentiating species from genomic sequences (i.e. DNA and RNA) is vital yet challenging, since many real-world species remain uncharacterized, lacking known genomes for reference. Embedding-based methods are therefore used to differentiate species in an unsupervised manner. DNABERT-S builds upon a pre-trained genome foundation model named DNABERT-2. To encourage effective embeddings to error-prone long-read DNA sequences, we introduce Manifold Instance Mixup (MI-Mix), a contrastive objective that mixes the hidden representations of DNA sequences at randomly selected layers and trains the model to recognize and differentiate these mixed proportions at the output layer. We further enhance it with the proposed Curriculum Contrastive Learning (C2LR) strategy. Empirical results on 28 diverse datasets show DNABERT-S's effectiveness, especially in realistic label-scarce scenarios. For example, it identifies twice more species from a mixture of unlabeled genomic sequences, doubles the Adjusted Rand Index (ARI) in species clustering, and outperforms the top baseline's performance in 10-shot species classification with just a 2-shot training. AVAILABILITY AND IMPLEMENTATION: Model, codes, and data are publically available at https://github.com/MAGICS-LAB/DNABERT_S.

Zhou, Zhihan↗
DOE OSTI2025

Thermal Modeling and Limitations for Power Electronics Embedded in Medium-Voltage Cables

As next-generation energy technologies gain traction and power demand increases, the existing electrical infrastructure faces significant stress, prompting innovative solutions to enhance the grid's capacity and lifespan. This work explores the possibility of embedding medium-voltage (MV) power electronics directly inline with the cable, and the resulting thermal challenges. Since the majority of power distribution cables installed in the U.S. are passively cooled, the work focuses primarily on passive cooling, with an emphasis on the limitations of axial heat spreading within the cable. To date, literature on axial spreading of high incident heat loads on cables and cable environments is limited, typically reporting cases with <10 W of incident heat load. This work will explore the considerations, limits, and tradeoffs of cable-embedded heat loads significantly larger than the cable losses. Both external and internal effects are modeled analytically in nondimensional terms via a Biot number analysis, allowing fundamental limits and tradeoffs to be derived. The work culminates in the design and experimental validation of a cable-embedded thermal system capable of passively dissipating 300 W of heat from a coaxial SiC mosfet switch module over a length of 20 cm, thus validating the possibility of MV cable-embedded power electronics from a thermal standpoint.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Visualizing Temporal Topic Embeddings with a Compass

—Dynamic topic modeling is useful at discovering the development and change in latent topics over time. However, present methodology relies on algorithms that separate document and word representations. This prevents the creation of a meaningful embedding space where changes in word usage and documents can be directly analyzed in a temporal context. This paper proposes an expansion of the compass-aligned temporal Word2Vec methodology into dynamic topic modeling. Such a method allows for the direct comparison of word and document embeddings across time in dynamic topics. This enables the creation of visualizations that incorporate temporal word embeddings within the context of documents into topic visualizations. In experiments against the current state-of-the-art, our proposed method demonstrates overall competitive performance in topic relevancy and diversity across temporal datasets of varying size. Simultaneously, it provides insightful visualizations focused on temporal word embeddings while maintaining the insights provided by global topic evolution, advancing our understanding of how topics evolve over time.

Cluster analysis↗
DOE OSTI2026

Dispersion Loss Counteracts Embedding Condensation and Improves Generalization in Small Language Models

Large language models (LLMs) achieve remarkable performance through ever-increasing parameter counts, but scaling incurs steep computational costs. To better understand LLM scaling, we study representational differences between LLMs and their smaller counterparts, with the goal of replicating the representational qualities of larger models in smaller models. We observe a geometric phenomenon which we term embedding condensation, where token embeddings collapse into a narrow cone-like subspace in some language models. Through systematic analyses across multiple Transformer families, we show that small models such as GPT2 and Qwen3-0.6B exhibit severe condensation, whereas larger models such as GPT2-x1 and Qwen3-32B are more resistant to this phenomenon. Additional observations show that embedding condensation is not reliably mitigated by knowledge distillation from larger models. To fight against it, we formulate a dispersion loss that explicitly encourages embedding dispersion during training. Experiments demonstrate that it mitigates condensation, recovers dispersion patterns seen in larger models, and yields performance gains across 10 benchmarks. We believe this work offers a principled path toward improving smaller Transformers without additional parameters.

Xiao, Xi [ORNL] (ORCID:0009000009316982)↗
DOE OSTI2026

Commuting embeddings for parallel strategies in non-local games

Non-local games provide a versatile framework for probing quantum correlations and for benchmarking the power of entanglement. In finite dimensions, the standard method for playing several games in parallel requires a tensor product of the local Hilbert spaces, which scales additively in the number of qubits. In this work, we show that this additive cost can be reduced by exploiting algebraic embeddings. We introduce two forms of compressions. First, when a referee selects one game from a finite collection of games at random, the game quantum strategy can be implemented using a maximally entangled state of dimension equal to the largest individual game, thereby eliminating the need for repeated state preparations. Second, we establish conditions under which several games can be played simultaneously in parallel on fewer qubits than the tensor product baseline. These conditions are expressed in terms of commuting embeddings of the game algebras. Moreover, we provide a constructive framework for building such embeddings. Using tools from Lie theory, we show that aligning the various game algebras into a common Cartan decomposition enables such a qubit reduction. Beyond the theoretical contribution, our framework casts NLGs as algebraic primitives for distributed and resource-constrained quantum computations and suggested NLGs as a comparable device-independent dimension witness.

Commuting embeddings↗
DOE OSTI2026

Multireference Embedding and Fragmentation Methods for Classical and Quantum Computers: From Model Systems to Realistic Applications

One of the primary challenges in quantum chemistry is the accurate modeling of strong electron correlation. While multireference methods effectively capture such correlation, their steep scaling with system size prohibits their application to large molecules and extended materials. Quantum embedding offers a promising solution by partitioning complex systems into manageable subsystems. In this Review, we highlight recent advances in multireference density matrix embedding and localized active space self-consistent field approaches for complex molecules and extended materials. We discuss both classical implementations and the emerging potential of these methods on quantum computers. Here, by extending classical embedding concepts to the quantum landscape, these algorithms have the potential to expand the reach of multireference methods in quantum chemistry and materials.

Algorithms↗
DOE OSTI2025

Embedded Sensing in Additive Manufacturing Metal and Polymer Parts: A Comparative Study of Integration Techniques and Structural Health Monitoring Performance

This study presents a comparative evaluation of post-process sensor integration in additively manufactured (AM) metal and the in-situ process for polymer structures for structural health monitoring (SHM), with an emphasis on embedded sensors. Geometrically identical specimens were fabricated using copper via metal fused filament fabrication (FFF) and PLA via polymer FFF, with piezoelectric transducers (PZTs) inserted into internal cavities to assess the influence of material and placement on sensing fidelity. Mechanical testing under compressive and point loads generated signals that were transformed into time–frequency spectrograms using a Short-Time Fourier Transform (STFT) framework. An engineered RGB representation was developed, combining global amplitude scaling with an amplitude-envelope encoding to enhance contrast and highlight subtle wave features. These spectrograms served as inputs to convolutional neural networks (CNNs) for classification of load conditions and detection of damage-related features. Results showed reliable recognition in both copper and PLA specimens, with CNN classification accuracies exceeding 95%. Embedded PZTs were especially effective in PLA, where signal damping and environmental sensitivity often hinder surface-mounted sensors. This work demonstrates the advantages of embedded sensing in AM structures, particularly when paired with spectrogram-based feature engineering and CNN modeling, advancing real-time SHM for aerospace, energy, and defense applications.

additive manufacturing↗
DOE OSTI2026

Transfer Learning Meets Embedded Correlated Wavefunction Theory for Chemically Accurate Molecular Simulations: Application to Calcium Carbonate Ion Pairing

Achieving chemical accuracy for molecular simulations remains a central challenge in computational chemistry. Here, we present an embedded correlated wavefunction transfer learning (ECW-TL) framework for accurately simulating molecular dynamics in the condensed phase. ECW-TL incorporates high-level electron exchange and correlation effects in ECW theory while preserving the training and computational efficiency of machine-learned interatomic potentials. We demonstrate the framework on Ca 2+ –CO 3 2– ion pairing in aqueous solution, a key process underlying CO 2 mineralization in seawater. As proof of principle, we first show that fine-tuning a DFT-revPBE-D3(BJ) baseline model with embedded-DFT-SCAN data reproduces the DFT-SCAN free-energy surface within 1 kcal/mol across all solvation states. Extending the framework to embedded MP2 and localized natural-orbital CCSD(T) further refines the free-energy profile, revealing the crucial role of exact electron exchange and correlation in determining ion-pair stability and structure. The computed ion-pair association free energy is in quantitative agreement with experimental measurements, further validating the accuracy of the ECW-TL framework. ECW-TL thus provides a general, data-efficient route for transferring CW accuracy to efficient simulations of complex aqueous and interfacial chemical processes.

cluster chemistry↗