Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Semantic models”

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
NASA NTRSDate not supplied

Exploring Semantic Search Capability of Graph Convolutions Over a Knowledge Graph Built Using Earth Science Corpora

Traditional knowledge graphs tend to be too generic, and often perform poorly on complex scientific queries. Often times, precedence is given to pop culture over scientific knowledge for queries. This is predominantly due to the use of internet sources for building the knowledge graph. With this work, we aim to explore the effectiveness of combining a knowledge graph generated from earth science corpora with a language model and graph convolutions for the purpose of surfacing latent and related sentences given a natural language query. In this model, sentences are conceptualized in the graph as nodes which are connected through entities—words and phrases of interest found in the text—extracted using Google Cloud’s entity extraction model. The language model we used for this is Bidirectional Encoder Representations from Transformers (BERT).The sentences are given a numeric representation by the BERT model. Graph convolutions are then applied to sentence embeddings in order to obtain a vector representation of the sentence as well as the surrounding graph structure, thereby leveraging the power of adjacency inherently encoded in graph structures. With this presentation, we demonstrate the ability of graph convolutions and their improved ability to surface relevant, latent information based on the subject of the input query.

Muthukumaran Ramasubramanian↗
DOE OSTI2025

Towards Automated Reasoning Chains for Verification of LLM-Generated Scientific Code

With the rise of Large Language Model (LLM) generated code, including in domains like scientific computing, ensuring not only syntactical, but also mathematical correctness, has become a critical task. Traditional formal methods approaches often struggle with the ambiguity of floating-point code, and full symbolic execution is extremely costly and limited. We propose a chain-of-reasoning approach that iteratively lifts basic semantics from code into the SPIRAL system and then establishes numerical equivalency to the desired mathematical operation. Here, we leverage the ample mathematical knowledge already formalized in SPIRAL to enable the system to recognize not just different implementations of the same algorithm but fully separate approaches to solving the given problem. The chain establishes tight error bounds on the output of given code with respect to the true continuous solution it approximates, quantifying all sources of error. We demonstrate this approach by establishing the correctness of a pseudospectral solver for a simple 1-dimensional Poisson problem.

Oschatz, Quentin [Carnegie Mellon University,Pitts↗
DOE OSTI2020

Toward Large-Scale Image Segmentation on Summit

Semantic segmentation of images is an important computer vision task that emerges in a variety of application domains such as medical imaging, robotic vision and autonomous vehicles to name a few. While these domain-specific image analysis tasks involve relatively small image sizes (~ 10 2 × 10 2 ), there are many applications that need to train machine learning models on image data with extents that are orders of magnitude larger (~10 4 × 10 4 ). Training deep neural network (DNN) models on large extent images is extremely memory-intensive and often exceeds the memory limitations of a single graphical processing unit, a hardware accelerator of choice for computer vision workloads. Here, an efficient, sample parallel approach to train U-Net models on large extent image data sets is presented. Its advantages and limitations are analyzed and near-linear strong-scaling speedup demonstrated on 256 nodes (1536 GPUs) of the Summit supercomputer. Using a single node of the Summit supercomputer, an early evaluation of a recently released model parallel framework called GPipe is demonstrated to deliver ~ 2X speedup in executing a U-Net model with an order of magnitude larger number of trainable parameters than reported before. Performance bottlenecks for pipelined training of U-Net models are identified and mitigation strategies to improve the speedups are discussed. Together, these results open up the possibility of combining both approaches into a unified scalable pipelined and data parallel algorithm to efficiently train U-Net models with very large receptive fields on data sets of ultra-large extent images.

Seal, Sudip↗
DOE OSTI2026

Oak Ridge National Laboratory Building Envelope Library (ORNOBEL)

The Oak Ridge National Laboratory Building Envelope Library (ORNOBEL) is a collection of dense exterior building-facade point clouds acquired using a survey-grade terrestrial laser scanner. Each file represents an individual facade from a building on the Oak Ridge National Laboratory (ORNL) campus or in Knoxville, Tennessee, with an average point-cloud resolution of approximately 3 mm. The points in each facade are semantically labeled into three classes: (1) window/door, representing openings in the building envelope; (2) wall, representing planar opaque envelope surfaces; and (3) other, representing the remaining facade-adjacent elements, architectural features, and protrusions. ORNOBEL supports the development, training, and evaluation of advanced deep-learning methods for automated building-envelope segmentation, geometric reconstruction, and building information modeling (BIM).

Maldonado Puente, Bryan [ORNL] (ORCID:000000033880↗
DOE OSTI2020

Towards scalable dataframe systems

Dataframes are a popular abstraction to represent, prepare, and analyze data. Despite the remarkable success of dataframe libraries in R and Python, dataframes face performance issues even on moderately large datasets. Moreover, there is significant ambiguity regarding dataframe semantics. In this paper we lay out a vision and roadmap for scalable dataframe systems. To demonstrate the potential in this area, we report on our experience building Modin, a scaled-up implementation of the most widely-used and complex dataframe API today, Python's pandas. With pandas as a reference, we propose a simple data model and algebra for dataframes to ground discussion in the field. Given this foundation, we lay out an agenda of open research opportunities where the distinct features of dataframes will require extending the state of the art in many dimensions of data management. We discuss the implications of signature dataframe features including flexible schemas, ordering, row/column equivalence, and data/metadata fluidity, as well as the piecemeal, trial-and-error-based approach to interacting with dataframes.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2005

Software Certification for Temporal Properties With Affordable Tool Qualification

It has been recognized that a framework based on proof-carrying code (also called semantic-based software certification in its community) could be used as a candidate software certification process for the avionics industry. To meet this goal, tools in the "trust base" of a proof-carrying code system must be qualified by regulatory authorities. A family of semantic-based software certification approaches is described, each different in expressive power, level of automation and trust base. Of particular interest is the so-called abstraction-carrying code, which can certify temporal properties. When a pure abstraction-carrying code method is used in the context of industrial software certification, the fact that the trust base includes a model checker would incur a high qualification cost. This position paper proposes a hybrid of abstraction-based and proof-based certification methods so that the model checker used by a client can be significantly simplified, thereby leading to lower cost in tool qualification.

Xia, Songtao↗
DOE OSTI2026

Hierarchical Multi-agent Large Language Model Reasoning for Autonomous Heterogeneous Catalyst Discovery

Artificial intelligence is reshaping scientific exploration, but most methods automate procedural tasks without engaging in scientific reasoning, limiting autonomy in discovery. We demonstrate that hierarchical agentic large language model reasoning can efficiently drive simulation and scientific exploration. Across two chemical applications, CO adsorption on Cu surface transition metal adatoms and on M–N–C catalysts, reasoning-guided exploration reduces required atomistic simulations by up to 90% relative to heuristic or random selection. Comparisons across single-agent, multi-agent, and stochastic baselines show that hierarchical strategies yield more coherent and information-efficient search trajectories. Reasoning traces reveal chemically grounded decisions that cannot be explained by semantic bias or stochastic sampling. We realize these agentic reasoning strategies in Materials Agents for Simulation and Theory in Electronic-structure Reasoning (MASTER), a multimodal system that translates natural language into density functional theory workflows. Altogether, multi-agent collaboration accelerates heterogeneous catalyst discovery and marks a step toward more autonomous, reasoning-guided scientific exploration.

30 DIRECT ENERGY CONVERSION↗
NASA NTRS2018

Automated Semantic Segmentation for Volumetric Cardiovascular Feature Quantification and Pathology Assessment

We present a pipeline method that curtails the expense and observer bias of manual cardiac evaluation by combining semantic segmentation and disease classification as a fully automatic processing pipeline. The initial element consists of a 2D U-Net convolutional neural network architecture for voxel-wise segmentation of the myocardium and ventricular cavities. The results of the segmentation were used to compute a comprehensive volumetric feature matrix that captured diagnostic clinical procedure data and that was used to model a cardiac pathology classifier.Our approach evaluated anonymized parasternal MRI cardiac images from a database of 100 patients (4 pathology groups, 1 healthy group, 20 patients per group) examined at the University Hospital of Dijon. We achieved top average Dice index scores of 0.939, 0.849, 0.886 for structure segmentation of the left ventricle (LV), right ventricle (RV) and myocardium respectively. A 5-ary pathology classification accuracy of 90% was recorded on an independent test set using our trained model.

Lindsey, Tony↗
DOE OSTI2025

Bayesian SegNet for Semantic Segmentation with Improved Interpretation of Microstructural Evolution During Irradiation of Materials

Understanding the relationship between the evolution of microstructures of irradiated LiAlO2pellets and tritium diffusion, retention and release could improve predictions of tritium performance. Given expert-labeled segmented images of irradiated and unirradiated pellets, we trained Deep Convolutional Neural Networks to segment images into defect, grain, and boundary classes. Qualitative microstructural information was calculated from these segmented images to facilitate the comparison of unirradiated and irradiated pellets. We tested modifications to improve the sensitivity of the model, including incorporating meta-data into the model and utilizing uncertainty quantification. The predicted segmentation was similar to the expert-labeled segmentation for most methods of microstructural qualification, including pixel proportion, defect area, and defect density. Overall, the high performance metrics for the best models for both irradiated and unirradiated images shows that utilizing neural network models is a viable alternative to expert-labeled images.

Oostrom, Marjolein T.↗
NASA NTRS2022

Neurosymbolic Hybrid Approach to Driver Collision Warning

There are two main algorithmic approaches to autonomous driving systems: (1) An end-to-end system in which a single deep neural network learns to map sensory input directly into appropriate warning and driving responses. (2) A mediated hybrid recognition system in which a system is created by combining independent modules that detect each semantic feature. While some researchers believe that deep learning can solve any problem, others believe that a more engineered and symbolic approach is needed to cope with complex environments with less data. Deep learning alone has achieved state-of-the-art results in many areas, from complex gameplay to predicting protein structures. In particular, in image classification and recognition, deep learning models have achieved accuracies as high as humans. But sometimes it can be very difficult to debug if the deep learning model doesn't work. Deep learning models can be vulnerable and are very sensitive to changes in data distribution. Generalization can be problematic. It's usually hard to prove why it works or doesn't. Deep learning models can also be vulnerable to adversarial attacks. Here, we combine deep learning-based object recognition and tracking with an adaptive neurosymbolic network agent, called the Non-Axiomatic Reasoning System (NARS), that can adapt to its environment by building concepts based on perceptual sequences. We achieved an improved intersection-over-union (IOU) object recognition performance of 0.65 in the adaptive retraining model compared to IOU 0.31 in the COCO data pre-trained model. We improved the object detection limits using RADAR sensors in a simulated environment, and demonstrated the weaving car detection capability by combining deep learning-based object detection and tracking with a neurosymbolic model.

Wang, Pei↗
DOE OSTI2021

Demonstrating UPC++/Kokkos Interoperability in a Heat Conduction Simulation (Extended Abstract)

We describe the replacement of MPI with UPC++ in an existing Kokkos code that simulates heat conduction within a rectangular 3D object, as well as an analysis of the new code’s performance on CUDA accelerators. The key challenges were packing the halos in Kokkos data structures in a way that allowed for UPC++ remote memory access, and streamlining synchronization costs. Additional UPC++ abstractions used included global pointers, distributed objects, remote procedure calls, and futures. We also make use of the device allocator concept to facilitate data management in memory with unique properties, such as GPUs. Our results demonstrate that despite the algorithm’s good semantic match to message passing abstractions, straightforward modifications to use UPC++ communication deliver vastly improved performance and scalability in the common case. We find the one-sided UPC++ version written in a natural way exhibits good performance, whereas the message-passing version written in a straightforward way exhibits performance anomalies. We argue this represents a productivity benefit for one-sided communication models.

Waters, Daniel↗
DOE OSTI2025

Phenotypically anchored transcriptomics across diverse agrichemicals reveals conserved pathways and unique gene expression signatures in zebrafish

Agrichemicals such as herbicides, fungicides, insecticides, and biocides are widely used in agriculture, yet some are associated with adverse effects in humans and the environment. While many of these chemicals have been extensively studied in vitro and are included in the EPA’s ToxCast program, comprehensive in vivo comparisons using RNA sequencing across structurally diverse agrichemicals, in a single screening platform, are lacking. In this study, we examined structurally diverse agrichemicals found in the U.S. Environmental Protection Agency’s (EPA) Toxcast Phase I and II library by statically exposing early life stage zebrafish at 6 h post fertilization (hpf) until 120 hpf at concentrations ranging from 0.25 to 100 µM. Morphological outcomes were assessed at 120 hpf across 10 endpoints, including yolk sac edema, craniofacial malformations, and axis abnormalities. Chemicals that produced robust concentration-response relationships were selected for transcriptomic profiling. For transcriptomic analysis, zebrafish were statically exposed to each chemical and sampled at 48 hpf, prior to the onset of morphological effects observed at 120 hpf. Differential expression analysis identified between 0 and 4,538 differentially expressed genes (DEGs) per chemical, with no clear correlation to morphological severity. Both DEG and co-expression network analyses revealed chemical-specific expression patterns that converged on shared biological pathways, including neurodevelopment and cytoskeletal organization. Key regulatory genes such as mylpfa and krt4 were identified within co-expression modules, suggesting their potential role in conserved toxicity mechanisms. Semantic similarity analysis of enriched gene ontology (GO) terms, when compared to existing datasets, highlighted gaps in the annotation of neurodevelopmental processes, indicating that some in vivo effects may not be fully captured by current curated resources. The results provide new insights into the modes of action of diverse agrichemicals and establish a framework for understanding how agrichemical structure relates to biological function in a vertebrate model.

agrichemical↗
NASA NTRS1993

Building a generalized distributed system model

The key elements in the 1992-93 period of the project are the following: (1) extensive use of the simulator to implement and test - concurrency control algorithms, interactive user interface, and replica control algorithms; and (2) investigations into the applicability of data and process replication in real-time systems. In the 1993-94 period of the project, we intend to accomplish the following: (1) concentrate on efforts to investigate the effects of data and process replication on hard and soft real-time systems - especially we will concentrate on the impact of semantic-based consistency control schemes on a distributed real-time system in terms of improved reliability, improved availability, better resource utilization, and reduced missed task deadlines; and (2) use the prototype to verify the theoretically predicted performance of locking protocols, etc.

Mukkamala, R.↗
DOE OSTI2024

RhizoNet segments plant roots to assess biomass and growth for enabling self-driving labs

Abstract Flatbed scanners are commonly used for root analysis, but typical manual segmentation methods are time-consuming and prone to errors, especially in large-scale, multi-plant studies. Furthermore, the complex nature of root structures combined with noisy backgrounds in images complicates automated analysis. Addressing these challenges, this article introduces RhizoNet, a deep learning-based workflow to semantically segment plant root scans. Utilizing a sophisticated Residual U-Net architecture, RhizoNet enhances prediction accuracy and employs a convex hull operation for delineation of the primary root component. Its main objective is to accurately segment root biomass and monitor its growth over time. RhizoNet processes color scans of plants grown in a hydroponic system known as EcoFAB, subjected to specific nutritional treatments. The root detection model using RhizoNet demonstrates strong generalization in the validation tests of all experiments despite variable treatments. The main contributions are the standardization of root segmentation and phenotyping, systematic and accelerated analysis of thousands of images, significantly aiding in the precise assessment of root growth dynamics under varying plant conditions, and offering a path toward self-driving labs.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Integrating multimodal data through interpretable heterogeneous ensembles

Motivation: Integrating multimodal data represents an effective approach to predicting biomedical characteristics, such as protein functions and disease outcomes. However, existing data integration approaches do not sufficiently address the heterogeneous semantics of multimodal data. In particular, early and intermediate approaches that rely on a uniform integrated representation reinforce the consensus among the modalities but may lose exclusive local information. The alternative late integration approach that can address this challenge has not been systematically studied for biomedical problems. Results: We propose Ensemble Integration (EI) as a novel systematic implementation of the late integration approach. EI infers local predictive models from the individual data modalities using appropriate algorithms and uses heterogeneous ensemble algorithms to integrate these local models into a global predictive model. We also propose a novel interpretation method for EI models. We tested EI on the problems of predicting protein function from multimodal STRING data and mortality due to coronavirus disease 2019 (COVID-19) from multimodal data in electronic health records. We found that EI accomplished its goal of producing significantly more accurate predictions than each individual modality. It also performed better than several established early integration methods for each of these problems. The interpretation of a representative EI model for COVID-19 mortality prediction identified several disease-relevant features, such as laboratory test (blood urea nitrogen and calcium) and vital sign measurements (minimum oxygen saturation) and demographics (age). These results demonstrated the effectiveness of the EI framework for biomedical data integration and predictive modeling.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2026

Compositional Reasoning for Hierarchical State Machines

Harel statecharts and its derivatives are popular graphical languages for specifying discrete control systems via hierarchical state machines. Separately, there has been a long line of work on specifying concurrent systems with process calculi which come equipped with an algebraic theory, the ability reason compositionally about various temporal properties, and strong type systems. While these two approaches to modeling systems are tantalizingly similar, the integrated reasoning principles that exist for process calculi have not been demonstrated in hierarchical state machines. A key issue is that operational theories for process calculi do not behave like control systems, and thus, there is virtually no tool support for modeling control systems with such languages. For a control system designer, bringing the integrated, more scalable reasoning from the process calculi to state-machine languages would enable the specification of more complex systems and a more modular systems development process. Our insight is that we can recover many important results from the process calculi in hierarchical state machines with local scope. We employ a structural operational semantics, which is ubiquitous in process and 𝜆-calculi but uncommon in hierarchical statemachine formalizations, to enable inductive reasoning about behavior. Taking inspiration from the structure of process calculi metatheories, we define a calculus of refinement and equivalence that we prove sound with respect to local notion of (bi)simulation. Furthermore, we prove that the calculus preserves the behavioral properties of reactivity, observational determinism, traces, and linear temporal properties. Our results are mechanized in the Rocq proof assistant.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Describing Point Defect Topology in 2D Energy Materials Through Computer Vision

Point defects such as vacancies and impurity atoms strongly impact the performance of 2D materials. Traditional efforts often rely on manual detection, a process that is time-intensive, prone to human error, and challenging to scale. Here we leverage machine learning (ML) methods to identify and quantify vacancies within 2D transition metal carbides (Ti3C2, MXenes), aiming to expedite detection while improving accuracy. MXenes exhibit valuable defect-defined electrochemical properties, but we currently lack statistical understanding of defect topology needed to fully harness these materials. Here we employ a convolutional neural network for semantic segmentation of experimental MXene images, opening an opportunity to conduct a rigorous statistical study on defect hierarchy while investigating local relaxation in the lattice. We show how the integration of ML can yield fundamental insight into point defects, providing a powerful tool that will play an increasingly crucial role in the future of materials science. ML is often not just a matter of straightforward application, and pretrained models proved ineffective in this case. Instead, we trained our own neural network (NN) and applied data augmentation techniques and fine-tuning to the training dataset. Since labeled microscopy data is often scarce, we developed training data from a previously published wide-frame MXene image, using customized Gaussian fitting to locate atomic positions. Our trained model was then applied to a large dataset of experimental images, enabling a statistical study of defect configurations across three samples prepared with different HF etchant concentrations (5%, 9.1%, and 12.5%), as shown in Fig. 1. This also allowed us to investigate local strain around vacancies, though we find that we are limited by the precision of measurements using high-angle annular dark field (HAADF) images, as shown in Fig. 2. This study demonstrates how ML enables large-scale, quantitative analysis of atomic defects - an otherwise infeasible task with traditional methods. While our NN was specialized for Ti3C2 MXenes, the pipeline we developed provides a foundation for future ML models tailored to other materials. Ultimately, we envision embedding the NN onto the microscope to give real-time feedback to the user. To make this a reality, continued work is necessary to fully understand the NN's capabilities and limitations. This study gets one step closer to our goals of automated experimentation moving away from traditional methods of manual labeling. As ML capabilities advance, we hope to continue adapting and applying these techniques in microscopy.

2D materials↗
NASA NTRS1990

Designing a training tool for imaging mental models

The training process can be conceptualized as the student acquiring an evolutionary sequence of classification-problem solving mental models. For example a physician learns (1) classification systems for patient symptoms, diagnostic procedures, diseases, and therapeutic interventions and (2) interrelationships among these classifications (e.g., how to use diagnostic procedures to collect data about a patient's symptoms in order to identify the disease so that therapeutic measures can be taken. This project developed functional specifications for a computer-based tool, Mental Link, that allows the evaluative imaging of such mental models. The fundamental design approach underlying this representational medium is traversal of virtual cognition space. Typically intangible cognitive entities and links among them are visible as a three-dimensional web that represents a knowledge structure. The tool has a high degree of flexibility and customizability to allow extension to other types of uses, such a front-end to an intelligent tutoring system, knowledge base, hypermedia system, or semantic network.

Dede, Christopher J.↗