Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “attention”

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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Attention-based functional-group coarse-graining: a deep learning framework for molecular prediction and design

Machine learning (ML) offers considerable promise for the design of new molecules and materials. In real-world applications, the design problem is often domain-specific, and suffers from insufficient data, particularly labeled data, for ML training. In this study, we report a data-efficient, deep-learning framework for molecular discovery that integrates a coarse-grained functional-group representation with a self-attention mechanism to capture intricate chemical interactions. Our approach exploits group-contribution concepts to create a graph-based intermediate representation of molecules, serving as a low-dimensional embedding that substantially reduces the data demands typically required for training. Using a self-attention mechanism to learn the subtle but highly relevant chemical context of functional groups, the method proposed here consistently outperforms existing approaches for predictions of multiple thermophysical properties. In a case study focused on adhesive polymer monomers, we train on a limited dataset comprising only 6,000 unlabeled and 600 labeled monomers. The resulting chemistry prediction model achieves over 92% accuracy in forecasting properties directly from SMILES strings, exceeding the performance of current state-of-the-art techniques. Furthermore, the latent molecular embedding is invertible, enabling the design pipeline to automatically generate new monomers from the learned chemical subspace. We illustrate this functionality by targeting several properties, including high and low glass transition temperatures (Tg), and demonstrate that our model can identify new candidates with values that surpass those in the training set. The ease with which the proposed framework navigates both chemical diversity and data scarcity offers a promising route to accelerate and broaden the search for functional materials.

Han, Ming [Univ. of Chicago, IL (United States)]↗
DOE OSTI2025

SA-GAT-SR: self-adaptable graph attention networks with symbolic regression for high-fidelity material property prediction

Recent advances in machine learning have demonstrated an enormous utility of deep learning approaches, particularly Graph Neural Networks (GNNs) for materials science. These methods have emerged as powerful tools for high-throughput prediction of material properties, offering a compelling enhancement and alternative to traditional first-principles calculations. While the community has predominantly focused on developing increasingly complex and universal models to enhance predictive accuracy, such approaches often lack physical interpretability and insights into materials behavior. Here, we introduce a novel computational paradigm—Self-Adaptable Graph Attention Networks integrated with Symbolic Regression (SA-GAT-SR)—that synergistically combines the predictive capability of GNNs with the interpretative power of symbolic regression. Our framework employs a self-adaptable encoding algorithm that automatically identifies and adjust attention weights so as to screen critical features from an expansive 180-dimensional feature space while maintaining O(n) computational scaling. The integrated SR module subsequently distills these features into compact analytical expressions that explicitly reveal quantum-mechanically meaningful relationships, achieving 23 × acceleration compared to conventional SR implementations that heavily rely on first-principle calculations-derived features as input. This work suggests a new framework in computational materials science, bridging the gap between predictive accuracy and physical interpretability, offering valuable physical insights into material behavior.

36 MATERIALS SCIENCE↗
DOE OSTI2026

PowerModelsGAT-AI: Physics-Informed Graph Attention for Multi-System Power Flow With Continual Learning

Solving the alternating current power flow equations in real time is essential for secure grid operation, yet classical Newton–Raphson solvers can be slow under stressed conditions. Existing graph neural networks for power flow are typically trained on a single system and often degrade on different systems. We present PowerModelsGAT-AI, a physics-informed graph attention network that predicts bus voltages and generator injections. The model uses bus-type-aware masking to handle different bus types and balances multiple loss terms, including a power-mismatch penalty, using learned weights. We evaluate the model on 14 benchmark systems (4 to 6,470 buses) and train a unified model on 13 of these under contingency conditions with up to two branch outages, achieving an average normalized mean absolute error of 0.89% for voltage magnitudes and R 2 >0.99 for voltage angles. We also show continual learning: when adapting a base model to a new 1,354-bus system, standard fine-tuning causes severe forgetting with error increases exceeding 1000% on base systems, while our experience replay and elastic weight consolidation strategy keeps error increases below 2% and in some cases improves base-system performance. Interpretability analysis shows that learned attention weights correlate with physical branch parameters (susceptance: r=0.38 ; thermal limits: r=0.22 ), and feature importance analysis supports that the model captures established power flow relationships.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

Leveraging BERT and Network-Based Attention Analysis for Identifying Treatment Milestones in EHRs

This study introduces a sophisticated data-driven framework for analyzing Electronic Health Records (EHRs) using transformer-based models to identify and disentangle overlapping treatment contexts. The framework leverages a preprocessing pipeline that transforms structured procedural codes into semantically enriched descriptive text, enabling the use of attention mechanisms to cluster medical events into treatment milestones—cohesive and distinct components of care processes. The methodology is rigorously validated using synthetic datasets derived from the MIMIC-III database, designed to simulate the heterogeneity and overlapping procedural contexts characteristic of real-world EHR scenarios. Quantitative evaluation highlights the framework’s robustness in disentangling concurrent care pathways, with attention metrics and unsupervised clustering approaches demonstrating the ability to preserve intra-context relationships while distinguishing inter-context dependencies. By addressing challenges inherent in data heterogeneity, this approach provides a foundation for uncovering complex treatment patterns, advancing clinical decision-making, and optimizing resource allocation in diverse healthcare environments.

Kim, Minsu [ORNL] (ORCID:0000000224185535)↗
DOE OSTI2025

Rapid Event Detection via Synchro-Waveform Based Temporal Attention Network in Distributed Grid

Compared with the information collected from phasor measurement units, synchro-waveforms contain high-fidelity disturbances of the grid, which can be a granular and authentic representation of measurements in the modern power system. However, the dynamic changing morphology makes it challenging to effectively capture various disturbance information from the synchro-waveforms. To tackle this issue, this paper proposes a Synchro-waveform based Temporal Attention (STA) network to achieve rapid event detection. First, a multi-scenario distributed model with renewable integration is established to generate synchro-waveforms under various uncertainties. Then, three typical temporal features are extracted directly from the synchro-waveform measurements. Additionally, the lightweight STA network is deployed to identify the most common event types in renewable energy systems via the self-attention based vision transformer module. The results from simulated experiments demonstrate that the proposed approach can achieve rapid and real-time detection within 0.81 ms and over 96.27 % accuracy.

Dong, Yuqing [University of Tennessee (UT)]↗
DOE OSTI2025

Meta-Learning Enhanced Physics-Informed Graph Attention Convolutional Network for Distribution Power System State Estimation

Promptly perceiving distribution system states is challenged by frequent topology changes and uncertain power injections. To address these issues, a Meta-learning enhanced physics-informed graph attention convolutional network (Meta-PIGACN) model is proposed to handle topological variability in distribution system state estimation (DSSE). Specifically, physics information is integrated into the graph convolutional network, enabling a physics-informed edge-weighting process that incorporates physical information to control the aggregation of neighboring nodes. Besides, the graph attention mechanism automatically adjusts the importance of different neighboring nodes, allowing the capture and preservation of inherent system features across varying topologies, thereby improving state estimation accuracy. Furthermore, meta-learning is proposed to acquire empirical knowledge across multiple topologies so that the model can rapidly adapt to new configurations through iterative gradient descent updates even in large-scale systems. In conclusion, the simulation results based on the 33/118/1746-node distribution systems show the high accuracy and efficiency of the proposed model.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2026

4D Multimodal Co-attention Fusion Network with Latent Contrastive Alignment for Alzheimer’s Diagnosis

Multimodal neuroimaging provides complementary structural and functional insights into both human brain organization and disease-related dynamics. Recent studies demonstrate enhanced diagnostic sensitivity for Alzheimer’s disease (AD) through synergistic integration of neuroimaging data (e.g., sMRI, fMRI) with tabular data (e.g., behavioral and cognitive tests). However, the intrinsic heterogeneity across modalities (e.g., 4D spatiotemporal fMRI dynamics vs. 3D anatomical sMRI structure) presents critical challenges for discriminative feature fusion, often leading to information loss or biased fusion. To bridge this gap, we propose M2M-AlignNet: a multimodal co-attention network with latent alignment for early AD diagnosis using sMRI and fMRI. At the core of our approach is a multi-patch-to-multi-patch (M2M) contrastive loss function that quantifies and reduces representational discrepancies via weighted patch correspondence, explicitly aligning fMRI components across brain regions with their sMRI structural substrates without one-to-one constraints. Additionally, we propose a latent-as-query co-attention module to autonomously discover fusion patterns, circumventing modality prioritization biases while minimizing feature redundancy. We conduct extensive experiments to confirm the effectiveness of our method and highlight the correspondence between fMRI and sMRI as AD biomarkers.

Wei, Yuxiang [Georgia Institute of Technology]↗
DOE OSTI2025

ATTNChecker: Highly-Optimized Fault Tolerant Attention for Large Language Model Training

Large Language Models (LLMs) have demonstrated remarkable performance in various natural language processing tasks. However, the training of these models is computationally intensive and susceptible to faults, particularly in the attention mechanism, which is a critical component of transformer-based LLMs. In this paper, we investigate the impact of faults on LLM training, focusing on INF, NaN, and near-INF values in the computation results with systematic fault injection experiments. We observe the propagation patterns of these errors, which can trigger non-trainable states in the model and disrupt training, forcing the procedure to load from checkpoints. To mitigate the impact of these faults, we propose ATTNChecker, the first Algorithm-Based Fault Tolerance (ABFT) technique tailored for the attention mechanism in LLMs. ATTNChecker is designed based on fault propagation patterns of LLM and incorporates performance optimization to adapt to both system reliability and model vulnerability while providing lightweight protection for fast LLM training. Evaluations on four LLMs show that ATTNChecker on average incurs on average 7% overhead on training while detecting and correcting all extreme errors. Compared with the state-of-the-art checkpoint/restore approach, ATTNChecker reduces recovery overhead by up to 49×.

Liang, Yuhang [University of Alabama - Birmingham]↗
DOE OSTI2026

Code for the manuscript "Lagrangian Attention Tensor Networks for Velocity Gradient Statistical Mode

We disclose a python/pytorch implementation of the physics-informed machine learning algorithm described in "Lagrangian Attention Tensor Networks for Velocity Gradient Statistical Modeling", LA-UR-24-30678. Direct numerical simulation (DNS) of ubiquitous turbulence phenomena is computationally infeasible for realistic flows. As a result, reduced modeling for turbulent flows aim to reduce the number of resolved scales while retaining accurate representations of the small-scale physics. The dynamics of the velocity gradient tensor (VGT) is a key ingredient in reduced or subgrid turbulence models. The evolution equation for the VGT involves nonlocal terms, requiring closure modeling. This implementation of the novel methodology of Lagrangian Attention Tensor Networks (LATN), utilizes a structured representation of the history of the VGT to inform a physics-informed machine learning algorithm. This addition of structured memory terms is shown to outperform previous models when trained and evaluated on DNS data.

Livescu, Daniel [LANL]↗
DOE OSTI2024

Transformer Neural Networks with Spatiotemporal Attention for Predictive Control and Optimization of Industrial Processes

In the context of real-time optimization and model predictive control of industrial systems, machine learning, and neural networks represent cutting-edge tools that hold promise for enhancing dynamic modeling. This work presents a novel transformer neural network architecture for real-time optimization and model predictive control. This network design includes a modified attention mechanism inspired by positional embedding attention from vision transformers and task-specific modifications to the input-output structure of the transformer’s decoder stack. Experiments were conducted using data from a 450 MW coal-fired power plant to evaluate this approach's effectiveness. The transformer neural network was compared with conventional recurrent models, including GRU and LSTM. The transformer exhibited a 6% increase in the R-squared (R2) value of predictions and an 83% reduction in mean squared error (MSE). Computation time was also reduced by 84% compared to conventional recurrent models.

Gallup, Ethan R.↗
DOE OSTI2025

A Dynamic Hierarchical Attention Framework for Multimodal Malware Detection

The increasing use of Android in the worldwide mobile ecosystem has come along with a significant increase in advanced malware, highlighting the critical necessity for efficient, scalable, and adaptable detection systems. Despite recent advancements in machine learning improving malware detection, the majority of current solutions are limited to one, two, or three data modalities, hence neglecting the comprehensive behavioral spectrum of contemporary multi-vector threats. This thesis presents the first comprehensive multimodal framework for Android malware detection, which combines textual, time-series (temporal), graph-based (structural), and visual information using an innovative hierarchical attention mechanism and Dynamic Fusion Controller (DFC). Our methodology consistently classifies and processes modalities as either sequential or structural, facilitating content-adaptive weighting and resilient cross-modal representation learning. We advance the implementation of cutting-edge time series techniques, such as MiniRocket, for malware detection, hence creating new opportunities for temporal analysis in cybersecurity. Comprehensive experimental assessment shows that our framework performs exceptionally well, with 99.46% classification accuracy and 97.15% detection accuracy, significantly outperforming existing approaches through effective multimodal integration and hierarchical attention mechanisms.

Nazmin, Tamanna↗
DOE OSTI2025

An attention-based neural ordinary differential equation framework for modeling inelastic processes

To preserve strictly conservative behavior as well as model the variety of dissipative behavior displayed by solid materials, we propose a significant enhancement to the internal state variable-neural ordinary differential equation (ISV-NODE) framework. In this data-driven, physics-constrained modeling framework internal states are inferred rather than prescribed. The ISV-NODE consists of: (a) a stress model dependent on observable deformation and inferred internal state, and (b) a model of the evolution of the internal states. The enhancements to ISV-NODE proposed in this work are multifold: (a) a partially input convex neural network stress potential provides polyconvexity in terms of observed strain while leaving the inferred state unconstrained, and (b) an internal state flow model uses common latent features to inform novel attention-based gating and drives the flow of internal state only in dissipative regimes. We demonstrated that this architecture can accurately model dissipative and conservative behavior across an isotropic, isothermal elastic-viscoelastic-elastoplastic spectrum with three exemplars, while maintaining fundamental principles by design.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Reconstruction of boosted and resolved multi-Higgs-boson events with symmetry-preserving attention networks

The production of multiple Higgs bosons at the CERN LHC provides a direct way to measure the trilinear and quartic Higgs self-interaction strengths as well as potential access to beyond the standard model effects that can enhance production at large transverse momentum p T . The largest event fraction arises from the fully hadronic final state in which every Higgs boson decays to a bottom quark-antiquark pair ($b\bar{b}$). This introduces a combinatorial challenge known as the jet assignment problem: assigning jets to sets representing Higgs boson candidates. Symmetry-preserving attention networks (SPA-Nets) have been developed to address this challenge. However, the complexity of jet assignment increases when simultaneously considering both H → $b\bar{b}$ reconstruction possibilities, i.e., two “resolved” small-radius jets each containing a shower initiated by a b quark or one “boosted” large-radius jet containing a merged shower initiated by a $b\bar{b}$ pair. The latter improves the reconstruction efficiency at high p T . In this work, we introduce a generalization to the SPA-Net approach to simultaneously consider both boosted and resolved reconstruction possibilities and unambiguously interpret an event as “fully resolved”, “fully boosted”, or in between. We report the performance of baseline methods, the original SPA-Net approach, and our generalized version on nonresonant HH and HHH production at the LHC. Considering both boosted and resolved topologies, our SPA-Net approach increases the Higgs boson reconstruction purity by 56–80% and the efficiency by 37–38% compared to the baseline method depending on the final state.

Higgs Production↗
DOE OSTI2026

Imputation of urban environmental sensor data using gated attention bidirectional long short-term memory (GA-BiLSTM): methods, performance, and implications

Urban environmental monitoring networks frequently encounter significant data gaps due to sensor malfunctions, environmental disturbances, and communication failures. Reliable approaches to address these gaps are essential for ensuring the continuity and quality of environmental data streams. In this study, we developed a gated attention bidirectional long short-term memory (GA-BiLSTM) model to impute missing data in a dense urban monitoring network. Using observations from the CROCUS network in Chicago, we evaluated GA-BiLSTM against widely used approaches (XGBoost and K-nearest neighbors) under scenarios of both short-term intermittent gaps and prolonged outages. GA-BiLSTM consistently outperformed comparative methods, particularly during extended outages of up to ten days, demonstrating its ability to capture spatiotemporal dependencies across sensor nodes. Beyond performance metrics, feature importance and spatial network analyses highlighted the unexpected but critical predictive role of peripheral rural nodes, underlining their strategic value for maintaining robust urban monitoring systems. These results emphasize that advanced imputation methods can substantially improve the reliability of environmental monitoring networks and support more resilient data infrastructures for urban sustainability.

Data imputation↗
DOE OSTI2024

CoarsenConf: Equivariant Coarsening with Aggregated Attention for Molecular Conformer Generation

Molecular conformer generation (MCG) is an important task in cheminformatics and drug discovery. The ability to efficiently generate low-energy 3D structures can avoid expensive quantum mechanical simulations, leading to accelerated virtual screenings and enhanced structural exploration. Several generative models have been developed for MCG, but many struggle to consistently produce high-quality conformers for meaningful downstream applications. To address these issues, we introduce CoarsenConf, which coarse-grains molecular graphs based on torsional angles and integrates them into an SE(3)-equivariant hierarchical variational autoencoder. Through equivariant coarse-graining, we aggregate the fine-grained atomic coordinates of subgraphs connected via rotatable bonds, creating a variable-length coarse-grained latent representation. Our model uses a novel aggregated attention mechanism to restore fine-grained coordinates from the coarse-grained latent representation, enabling efficient generation of accurate conformers. Furthermore, we evaluate the chemical and biochemical quality of our generated conformers on multiple downstream applications, including property prediction and large-scale oracle-based protein docking. Overall, CoarsenConf generates more accurate conformer ensembles compared to prior generative models.

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

Gut microbiome changes with micronutrient supplementation in children with attention–deficit/hyperactivity disorder: the MADDY study

Micronutrients have demonstrated promise in managing inattention and emotional dysregulation in children with attention-deficit/hyperactivity disorder (ADHD). The biological mechanism by which micronutrients improve these symptoms remains unclear. One plausible pathway is through the gut-brain axis, the bi-directional communication network that links the gastrointestinal tract with the brain. This study examines changes in gut microbiome composition and diversity after micronutrients supplementation in children with ADHD (N=44) and sheds light on potential mechanisms responsible for the response to micronutrients as measured by clinician-rated global impression. Participants from this investigation represent a sub-group of the Micronutrients for ADHD in Youth (MADDY) study, a double blind randomized controlled study in which participants received either micronutrients or a placebo for 8 weeks, followed by an 8-week open label extension with micronutrients for all participants. Stool samples collected at baseline, week 8, and week 16 were analyzed using 16S rRNA amplicon sequencing targeting the V4 hypervariable region. Pairwise compositional analyses served as the primary means for investigating changes in gut microbiome composition between micronutrients versus placebo groups and responders versus non-responders. A significant change in microbial evenness, as measured by alpha diversity, was observed following micronutrients, and the phylum Actinobacteriota decreased in the micronutrients group compared to placebo. Additionally, two bacterial families: Rikenellaceae and Oscillospiraceae, exhibited a significant increase in change of gut microbiome composition following micronutrients between responders and non-responders. These findings suggest that micronutrients modulated the composition of the gut microbiome and point towards specific bacterial changes associated with response to micronutrients.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2026

Predictive analytics to direct clinical attention to complex patients with elevated suicide risk: enhancement of the Veterans Health Administration REACH VET model

Suicide is a major public health concern, particularly among Veterans. The U.S. Department of Veterans Affairs Veterans Health Administration (VHA) employs the Recovery Engagement and Coordination for Health–Veterans Enhanced Treatment (REACH VET) model to prioritise high-risk patients for targeted clinical attention. REACH VET 1.0 (RV 1.0) was developed on 2008–2011 data. To reflect changes in clinical practice and populations, VHA updated it to REACH VET 2.0 (RV 2.0). This study describes its development and validation. RV 2.0 used longitudinal data from 7,248,170 VHA patients (4,967 suicide deaths) in 2018–2019, with 650 time-varying demographic, clinical and area-level predictors derived from a 2-year lookback (2016–2019). An ensemble of Elastic-Net logistic regression models was trained on 2018 data and evaluated monthly at the population level in 2019, focusing on the top 0.1% intervention risk tier. Analyses assessed model discrimination, suicide detection, risk concentration, subgroup consistency (sex, age and race/ethnicity) and performance relative to RV 1.0 using the same percentile-based risk strata. RV 2.0 outperformed RV 1.0 across all risk strata, with better discrimination (C-statistic 0.76 vs 0.69) and consistent performance across demographic subgroups. Within the top 0.1% of predicted risk, RV 2.0 identified more deaths, higher suicide rates and greater mortality risk concentration both when averaged across the 12 monthly 2019 test sets (5.6 vs 3.6; 83.6 vs 53.7 per 100,000 person-years; 21.0 vs 14.1) and when annualised for 2019 (67 vs 43; 2.7% vs 1.7%; 1,003 vs 644 per 100,000 person-years; 26.7 vs 17.1). RV 2.0 improves suicide risk stratification among Veterans, demonstrating better performance and consistent prediction across subgroups and highlighting the need for regular model updates and evaluation.

Peluso, Alina [Oak Ridge National Laboratory (ORNL↗
DOE OSTI2025

Equivariant Graph Attention Network - 3D Conformers & Feature Fusion

EGAN-3F (Equivariant Graph Attention Network - 3D Conformers & Feature Fusion) presents an innovative approach for predicting binding affinity between small molecules and protein targets, a fundamental task in drug discovery. Traditional structure-based methods often depend on protein-ligand complex structures obtained from crystallography or molecular docking. In contrast, ligand-only machine learning models using 1D or 2D representations such as SMILES have been developed to predict binding affinity without structural information about the target; however, their accuracy is often limited due to the lack of 3D ligand information. EGAN-3F addresses this limitation by integrating spatially aware graph learning with traditional descriptor-based features. We systematically investigate how combining 2D and 3D molecular representations enhances binding affinity prediction from SMILES strings. This approach underscores the importance of modeling conformational diversity and incorporating chemically meaningful descriptors to improve predictive accuracy. The key innovation of EGAN-3F lies in its ability to achieve robust ligand-based binding affinity predictions without requiring protein-ligand complex structures, effectively bridging the gap between purely structural and ligand-only modeling paradigms.

Shim, Heesung [Lawrence Livermore National Laborat↗