Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Domain knowledge”

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 415 records · Page 23
All sourcesNASA NTRSDOE OSTI
NASA NTRS2004

Plan-graph Based Heuristics for Conformant Probabilistic Planning

In this paper, we introduce plan-graph based heuristics to solve a variation of the conformant probabilistic planning (CPP) problem. In many real-world problems, it is the case that the sensors are unreliable or take too many resources to provide knowledge about the environment. These domains are better modeled as conformant planning problems. POMDP based techniques are currently the most successful approach for solving CPP but have the limitation of state- space explosion. Recent advances in deterministic and conformant planning have shown that plan-graphs can be used to enhance the performance significantly. We show that this enhancement can also be translated to CPP. We describe our process for developing the plan-graph heuristics and estimating the probability of a partial plan. We compare the performance of our planner PVHPOP when used with different heuristics. We also perform a comparison with a POMDP solver to show over a order of magnitude improvement in performance.

Ramakrishnan, Salesh↗
NASA NTRSDate not supplied

Development of A Crew Health and Performance System Probabilistic Risk Assessment Tool: Proof-of-Concept Approach

The crew health and performance (CHP) system represents the span of technological interventions and tested processes and procedures that in combination address the human risk to space flight. The Human Research Program (HRP) mental model of the CHP system breaks the capabilities needed to meet NASA human flight systems standards into specific categories (i.e., countermeasures, behavioral health, medical intervention). These categories are further broken down into specific sub-groups generally associated with the human system risks that these capabilities seek to mitigate. Like the approach used to develop the Integrated Medical Model (IMM) and the Medical Extensible Dynamic Probabilistic Risk Analysis Tool (MEDPRAT), HRP tasked NASA GRC’s Cross-Cutting Computational Modeling Project with developing a CHP probabilistic risk assessment tool, the CHP-PRA. The CHP-PRA model seeks to quantify and relatively assess the human risk state within the crew health and performance domain, using a combination of knowledge about human system risks and technology and practices likely to be applied during space flight missions. This modeling system will incorporate customer and stakeholder feedback and be flexible enough to address multiple different questions about important low-level mission-specific parameters. This presentation will introduce the initial concept and development timeline for this tool and demonstrate proof-of-concept through an application addressing a specific human risk question posed within the Artemis program.

Risk analysis↗
NASA NTRS2024

Integrated (Physical and Digital) Collaborative Experimentation: Advancing Dialog and Leveraging by Aerospace Researchers and Developers

This paper 1) documents findings and observations from the American Institute of Aeronautics and Astronautics (AIAA) Ground Test Technical Committee (GTTC) Future of Ground Test Working Group and the Applied Aeronautics Technical Committee (APATC) Collaborative Experiments & Computation Discussion Group, and 2) develops a more focused approach for sharing and advancing integrated development and use of physical experimental and computational capabilities for aerospace research and development. The GTTC and APATC are engaging with the larger AIAA technical community by creating a Focus Group on this topical area that will support working together on common interests in the public domain. This paper summarizes the knowledge capture from the last ten+ years and proposes a structure and scope going forward for the new, combined Focus Group.

ground testing↗
DOE OSTI2025

Knowledge Oriented Graph Unified Transformer (KOGUT) v0.1

KOGUT — Knowledge Oriented Graph Unified Transformer KOGUT implements the Relational Graph Transformer (RelGT) architecture for knowledge graph link prediction in biological domains, with a primary focus on microbial growth media prediction. While the original RelGT (arXiv:2505.10960) targets relational tables, time series, and multi-table databases, KOGUT adapts this architecture for heterogeneous biological knowledge graphs, providing first-in-class AI predictive models for microbial cultivation. Key Adaptations Beyond Original RelGT: - Knowledge Graph Focus: Applied to biological KGs with semantic node types (taxa, chemicals, media, phenotypes, environments) versus generic relational database tables, trained on the KG-Microbe knowledge graph (1.3M entities, 2.9M edges, 24 relation types). - Multimodal Node Encoding: Integrates node labels, categories, descriptions, and synonyms from KG metadata through learned embedding layers—adapting relational column features to graph node attributes with textual semantics. - Extended K-Hop Subgraph Strategy: Optimized neighborhood sampling (3-hop default, configurable up to 200 nodes) tuned for sparse biological networks, building on the original local-global attention framework with biological relation preservation. - Biolink Predicate Preservation: Type-specific transformations for 24 biological edge semantics (occurs_in, consumes, produces, has_phenotype, subclass_of) beyond standard relational foreign keys, enabling multi-relation link prediction. - Inductive Learning Support: Enables zero-shot predictions for novel taxa through feature-based embeddings (temperature, oxygen requirements, gram stain, cell shape), extending the original transductive relational benchmark scope to uncultured microorganisms. CheapSOTA Performance Optimizations (This Distribution): - VQ-EMA Centroid Attention: Vector quantization with exponential moving average for improved global context modeling (+5-10% MRR improvement). - HDF5 Precomputed Data Loading: One-time preprocessing of k-hop subgraphs to eliminate redundant graph traversals (2-5× training speedup). - Distributed Data Parallel Training: Multi-GPU support for scaling to larger knowledge graphs (tested on 4× NVIDIA A100 GPUs at NERSC Perlmutter). - Mixed Precision Training: Automatic mixed precision (AMP) for memory efficiency and faster training. Advantages Over Standard Knowledge Graph Embedding Models: Combines RelGT's proven multi-element tokenization (features, type, hop, structure) with graph-native biological representations, enabling interpretable link prediction across heterogeneous entities that standard embedding models (TransE, RotatE, ComplEx) and table-based transformers cannot directly model. Achieves near-perfect performance on microbial growth media prediction (MRR: 0.9966, Precision@1: 0.9932, Hit@10: 1.0000) while maintaining explainability through attention-based reasoning over biological pathways. Training Data: - KG-Microbe merged knowledge graph: 1,379,337 nodes, 2,960,472 edges - 24 biological relation types including taxonomic hierarchies, metabolic interactions, phenotype associations, and environmental relationships - Primary prediction task: Growth media suitability for microbial taxa (biolink:occurs_in, 50K edges) - Multi-relation capability: Predicts links for any of the 24 relation types, including chemical consumption/production, phenotype associations, and taxonomic classification Citation: Original RelGT Architecture: Dwivedi et al., "Relational Graph Transformer", arXiv:2505.10960, 2025 KOGUT Implementation: Knowledge Oriented Graph Unified Transformer for Microbial Growth Media Prediction Developed at Lawrence Berkeley National Laboratory (LBNL) Trained on NERSC Perlmutter supercomputer

Joachimiak, Marcin [Lawrence Berkeley National Lab↗
NASA NTRS2004

Implementation of a Message Passing Interface into a Cloud-Resolving Model for Massively Parallel Computing

The capability for massively parallel programming (MPP) using a message passing interface (MPI) has been implemented into a three-dimensional version of the Goddard Cumulus Ensemble (GCE) model. The design for the MPP with MPI uses the concept of maintaining similar code structure between the whole domain as well as the portions after decomposition. Hence the model follows the same integration for single and multiple tasks (CPUs). Also, it provides for minimal changes to the original code, so it is easily modified and/or managed by the model developers and users who have little knowledge of MPP. The entire model domain could be sliced into one- or two-dimensional decomposition with a halo regime, which is overlaid on partial domains. The halo regime requires that no data be fetched across tasks during the computational stage, but it must be updated before the next computational stage through data exchange via MPI. For reproducible purposes, transposing data among tasks is required for spectral transform (Fast Fourier Transform, FFT), which is used in the anelastic version of the model for solving the pressure equation. The performance of the MPI-implemented codes (i.e., the compressible and anelastic versions) was tested on three different computing platforms. The major results are: 1) both versions have speedups of about 99% up to 256 tasks but not for 512 tasks; 2) the anelastic version has better speedup and efficiency because it requires more computations than that of the compressible version; 3) equal or approximately-equal numbers of slices between the x- and y- directions provide the fastest integration due to fewer data exchanges; and 4) one-dimensional slices in the x-direction result in the slowest integration due to the need for more memory relocation for computation.

Juang, Hann-Ming Henry↗
DOE OSTI2021

Reduced Complexity Model Intercomparison Project Phase 2: Synthesizing Earth System Knowledge for Probabilistic Climate Projections

Abstract Over the last decades, climate science has evolved rapidly across multiple expert domains. Our best tools to capture state‐of‐the‐art knowledge in an internally self‐consistent modeling framework are the increasingly complex fully coupled Earth System Models (ESMs). However, computational limitations and the structural rigidity of ESMs mean that the full range of uncertainties across multiple domains are difficult to capture with ESMs alone. The tools of choice are instead more computationally efficient reduced complexity models (RCMs), which are structurally flexible and can span the response dynamics across a range of domain‐specific models and ESM experiments. Here we present Phase 2 of the Reduced Complexity Model Intercomparison Project (RCMIP Phase 2), the first comprehensive intercomparison of RCMs that are probabilistically calibrated with key benchmark ranges from specialized research communities. Unsurprisingly, but crucially, we find that models which have been constrained to reflect the key benchmarks better reflect the key benchmarks. Under the low‐emissions SSP1‐1.9 scenario, across the RCMs, median peak warming projections range from 1.3 to 1.7°C (relative to 1850–1900, using an observationally based historical warming estimate of 0.8°C between 1850–1900 and 1995–2014). Further developing methodologies to constrain these projection uncertainties seems paramount given the international community's goal to contain warming to below 1.5°C above preindustrial in the long‐term. Our findings suggest that users of RCMs should carefully evaluate their RCM, specifically its skill against key benchmarks and consider the need to include projections benchmarks either from ESM results or other assessments to reduce divergence in future projections.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS2021

Reduced Complexity Model Intercomparison Project Phase 2: Synthesizing Earth System Knowledge for Probabilistic Climate Projections

Over the last decades, climate science has evolved rapidly across multiple expert domains. Our best tools to capture state-of-the-art knowledge in an internally self-consistent modelling framework are the increasingly complex fully coupled Earth System Models (ESMs). However, computational limitations and the structural rigidity of ESMs mean that the full range of uncertainties across multiple domains are difficult to capture with ESMs alone. The tools of choice are instead more computationally efficient reduced complexity models (RCMs), which are structurally flexible and can span the response dynamics across a range of domain-specific models and ESM experiments. Here we present Phase 2 of the Reduced Complexity Model Intercomparison Project (RCMIP Phase 2), the first comprehensive intercomparison of RCMs that are probabilistically calibrated with key benchmark ranges from specialized research communities. Unsurprisingly, but crucially, we find that models which have been constrained to reflect the key benchmarks better reflect the key benchmarks. Under the low-emissions SSP1-1.9 scenario, across the RCMs, median peak warming projections range from 1.3 to 1.7°C (relative to 1850-1900, using an observationally-based historical warming estimate of 0.8°C between 1850-1900 and 1995-2014). Further developing methodologies to constrain these projection uncertainties seems paramount given the international community's goal to contain warming to below 1.5°C above pre-industrial in the long-term. Our findings suggest that users of RCMs should carefully evaluate their RCM, specifically its skill against key benchmarks and consider the need to include projections benchmarks either from ESM results or other assessments to reduce divergence in future projections.

Climate↗
NASA NTRS2005

Knowledge Representation Standards and Interchange Formats for Causal Graphs

In many domains, automated reasoning tools must represent graphs of causally linked events. These include fault-tree analysis, probabilistic risk assessment (PRA), planning, procedures, medical reasoning about disease progression, and functional architectures. Each of these fields has its own requirements for the representation of causation, events, actors and conditions. The representations include ontologies of function and cause, data dictionaries for causal dependency, failure and hazard, and interchange formats between some existing tools. In none of the domains has a generally accepted interchange format emerged. The paper makes progress towards interoperability across the wide range of causal analysis methodologies. We survey existing practice and emerging interchange formats in each of these fields. Setting forth a set of terms and concepts that are broadly shared across the domains, we examine the several ways in which current practice represents them. Some phenomena are difficult to represent or to analyze in several domains. These include mode transitions, reachability analysis, positive and negative feedback loops, conditions correlated but not causally linked and bimodal probability distributions. We work through examples and contrast the differing methods for addressing them. We detail recent work in knowledge interchange formats for causal trees in aerospace analysis applications in early design, safety and reliability. Several examples are discussed, with a particular focus on reachability analysis and mode transitions. We generalize the aerospace analysis work across the several other domains. We also recommend features and capabilities for the next generation of causal knowledge representation standards.

Throop, David R.↗
NASA NTRS1988

Knowledge-based requirements analysis for automating software development

We present a new software development paradigm that automates the derivation of implementations from requirements. In this paradigm, informally-stated requirements are expressed in a domain-specific requirements specification language. This language is machine-understable and requirements expressed in it are captured in a knowledge base. Once the requirements are captured, more detailed specifications and eventually implementations are derived by the system using transformational synthesis. A key characteristic of the process is that the required human intervention is in the form of providing problem- and domain-specific engineering knowledge, not in writing detailed implementations. We describe a prototype system that applies the paradigm in the realm of communication engineering: the prototype automatically generates implementations of buffers following analysis of the requirements on each buffer.

Markosian, Lawrence Z.↗
DOE OSTI2025

Rapid Adaptation of Chemical Named Entity Recognition Using Few-Shot Learning and LLM Distillation

Named entity recognition (NER) has been widely used in chemical text mining for the automatic identification and extraction of chemical entities. However, existing chemical NER systems primarily focus on scenarios with abundant training data, requiring significant human effort on annotations. This poses challenges for applications in the chemical field, such as catalysis, where many advancements have traditionally relied on trial-and-error investigations and incremental adjustment of variables. This hinders catalysis science and technology progress in addressing emerging energy and environmental crises. In this work, we propose a few-shot NER model that can quickly adapt to extract new types of chemical entities by using only a limited number of annotated examples. Our model employs a metric-learning approach to transfer entity similarity knowledge from high-resource chemical domains (with abundant annotations) to enable effective entity recognition in low-resource specialized domains (limited annotation). We validate the effectiveness of our model on a few-shot chemical NER benchmark built based on six existing chemical NER data sets. Experiments show that the proposed few-shot NER model can achieve reasonable performance with only 5 examples per entity type and shows consistent improvement as the number of examples increases. Furthermore, we demonstrate how the proposed model can be trained with large language model (LLM) annotated data, opening a new pathway for rapid adaptation of NER systems. Furthermore, our approach leverages the knowledge broadness of large language models for chemistry while distilling this knowledge into a lightweight model suitable for efficient and in-house use.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
NASA NTRS2018

Using a Knowledge Graph to Discover Earth Science Information

Knowledge graphs link key entities within a specific domain to other entities via relationships. Researchers are able to mine these relationships from numerous sources to infer new knowledge. Text extraction from peer-reviewed papers and scientific reports are untapped resources that can be leveraged by knowledge graphs to accelerate scientific discovery.

Freitag, Brian↗
DOE OSTI2024

3D Multiresolution Velocity Model Fusion with Probability Graphical Models

ABSTRACT The variability in spatial resolution of seismic velocity models obtained via tomographic methodologies is attributed to many factors, including inversion strategies, ray-path coverage, and data integrity. Integration of such models, with distinct resolutions, is crucial during the refinement of community models, thereby enhancing the precision of ground-motion simulations. Toward this goal, we introduce the probability graphical model (PGM), combining velocity models with heterogeneous resolutions and nonuniform data point distributions. The PGM integrates data relations across varying resolution subdomains, enhancing detail within low-resolution (LR) domains by utilizing information and prior knowledge from high-resolution (HR) subdomains through a maximum posterior problem. Assessment of efficacy, utilizing both 2D and 3D velocity models—consisting of synthetic checkerboard models and a fault-zone model from Ridgecrest, California—demonstrates noteworthy improvements in accuracy, compared to state-of-the-art fusion techniques. Specifically, we find reductions of 30% and 44% in computed travel-time residuals for 2D and 3D models, respectively, as compared to conventional smoothing techniques. Unlike conventional methods, the PGM’s adaptive weight selection facilitates preserving and learning details from complex, nonuniform HR models and applies the enhancements to the LR background domain.

Geochemistry & Geophysics↗
NASA NTRS1994

Delivering spacecraft control centers with embedded knowledge-based systems: The methodology issue

Matra Marconi Space (MMS) occupies a leading place in Europe in the domain of satellite and space data processing systems. The maturity of the knowledge-based systems (KBS) technology, the theoretical and practical experience acquired in the development of prototype, pre-operational and operational applications, make it possible today to consider the wide operational deployment of KBS's in space applications. In this perspective, MMS has to prepare the introduction of the new methods and support tools that will form the basis of the development of such systems. This paper introduces elements of the MMS methodology initiatives in the domain and the main rationale that motivated the approach. These initiatives develop along two main axes: knowledge engineering methods and tools, and a hybrid method approach for coexisting knowledge-based and conventional developments.

Ayache, S.↗
NASA NTRS1990

Diagnosing multiple faults in SSM/PMAD

Multiple fault diagnosis for SSM/PMAD (space station module/power management and distribution) using the knowledge management design system as applied to the SSM/PMAD domain (KNOMAD-SSM/PMAD) is discussed. KNOMAD-SSM/PMAD provides a powerful facility for knowledge representation and reasoning which has been used to build the second generation of FRAMES (fault recovery and management expert system). FRAMES now handles the diagnosis of multiple faults and provides support for a more powerful interface for user interaction during autonomous operation. There are two types of multiple fault diagnosis handled in FRAMES. The first diagnoses hard faults, soft faults, and incipient faults simultaneously. The second diagnoses multiple hard faults which occur in close proximity in time to one another. Multiple fault diagnosis in FRAMES is performed using a rule-based approach. This rule-based approach, enabled by the KNOMAD-SSM/PMAD system, has proven to be powerful. Levels of autonomy are discussed, focusing on the approach taken in FRAMES for providing at least three levels of autonomy: complete autonomy, partial autonomy, and complete manual mode.

Riedesel, Joel↗
NASA NTRS1990

Supplemental knowledge acquisition through external product interface for CLIPS

Traditionally, the acquisition of knowledge for expert systems consisted of the interview process with the domain or subject matter expert (SME), observation of domain environment, and information gathering and research which constituted a direct form of knowledge acquisition (KA). The knowledge engineer would be responsible for accumulating pertinent information and/or knowledge from the SME(s) for input into the appropriate expert system development tool. The direct KA process may (or may not) have included forms of data or documentation to incorporate from the SME's surroundings. The differentiation between direct KA and supplemental KA (indirect) would be the difference in the use of data. In acquiring supplemental knowledge, the knowledge engineer would access other types of evidence (manuals, documents, data files, spreadsheets, etc.) that would support the reasoning or premises of the SME. When an expert makes a decision in a particular task, one tool that may have been used to justify a recommendation, would have been a spreadsheet total or column figure. Locating specific decision points from that data within the SME's framework would constitute supplemental KA. Data used for a specific purpose in one system or environment would be used as supplemental knowledge for another, specifically a CLIPS project.

Saito, Tim↗
DOE OSTI2023

Deep learning Hamiltonians from disordered image data in quantum materials

The capabilities of image probe experiments are rapidly expanding, providing new information about quantum materials on unprecedented length- and timescales. Many such materials feature inhomogeneous electronic properties with intricate pattern formation on the observable surface. This rich spatial structure contains information about interactions, dimensionality, and disorder—a spatial encoding of the Hamiltonian driving the pattern formation. Image recognition techniques from machine learning are an excellent tool for interpreting information encoded in the spatial relationships in such images. Here, we develop a deep learning framework for using the rich information available in these spatial correlations in order to discover the underlying Hamiltonian driving the patterns. We first vet the method on a known case, scanning near-field optical microscopy on a thin film of V⁢O 2 . We then apply our trained convolutional neural network architecture to new optical microscope images of a different V⁢O 2 film as it goes through the metal-insulator transition. We find that a two-dimensional Hamiltonian with both interactions and random field disorder is required to explain the intricate, fractal intertwining of metal and insulator domains during the transition. This detailed knowledge about the underlying Hamiltonian paves the way for using the model to control the pattern formation via, e.g., tailored hysteresis protocols. Finally, we also introduce a distribution-based confidence measure on the results of a multilabel classifier, which does not rely on adversarial training. In addition, we propose a machine-learning-based criterion for diagnosing a physical system's proximity to criticality.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2024

AutoCheck: Automatically Identifying Variables for Checkpointing by Data Dependency Analysis

Checkpoint/Restart (C/R) has been widely deployed in numerous HPC systems, Clouds, and industrial data centers, which are typically operated by system engineers. Nevertheless, there is no existing approach that helps system engineers without domain expertise and domain scientists without system fault tolerance knowledge identify those critical variables accounted for correct application execution restoration in a failure for C/R. To address this problem, we propose an analytical model and a tool (AutoCheck) that can automatically identify critical variables to checkpoint for C/R. AutoCheck relies on first, analytically tracking and optimizing data dependency between variables and other application execution state, and second, a set of heuristics that identify critical variables for checkpointing from the refined data dependency graph (DDG). AutoCheck allows programmers to pinpoint critical variables to checkpoint quickly within a few minutes. We evaluate AutoCheck on 13 representative HPC benchmarks, demonstrating that AutoCheck can efficiently identify correct critical variables to checkpoint.

HPC↗
DOE OSTI2024

Strain phase equilibria and phase‐field method of ferroelectric polydomain: A case study of monoclinic K x Na 1 − x NbO 3 thin films

Abstract Knowledge of the thermodynamic equilibria and domain structures of ferroelectrics is critical to establishing their structure–property relationships that underpin their applications from piezoelectric devices to nonlinear optics. Here, we establish the strain condition for strain phase separation and polydomain formation and analytically predict the corresponding domain volume fractions and wall orientations of, relatively low symmetry and theoretically more challenging, monoclinic ferroelectric thin films by integrating thermodynamics of ferroelectrics, strain phase equilibria theory, microelasticity, and phase‐field method. Using monoclinic K x Na 1 − x NbO 3 (0.5 < x < 1.0) thin films as a model system, we establish the polydomain strain–strain phase diagrams, from which we identify two types of monoclinic polydomain structures. The analytically predicted strain conditions of formation, domain volume fractions, and domain wall orientations for the two polydomain structures are consistent with phase‐field simulations and in good agreement with experimental results in the literature. The present study demonstrates a general, powerful analytical theoretical framework to predict the strain phase equilibria and domain wall orientations of polydomain structures applicable to both high‐ and low‐symmetry ferroelectrics and provide fundamental insights into the equilibrium domain structures of ferroelectric K x Na 1 − x NbO 3 thin films that are of technology relevance for lead‐free dielectric and piezoelectric applications.

36 MATERIALS SCIENCE↗