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 145 records · Page 8
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Morphology-Based Building Use-Type Modeling: Learnability-First Schema Discovery

This technical memorandum documents an update to the building use-type classification workflow, used in LandScan Mosaic, that replaces a fixed, semantically defined class schema with a learnability-first schema discovery procedure. Historically, the target label schema was specified a priori (e.g., predicting a chosen set of use-type codes), and model training and evaluation were performed within that fixed label space. In the updated workflow, the pipeline first evaluates which non-residential distinctions are learnable under spatial generalization and then collapses ambiguous classes into data-driven groupings before finalizing the schema used for production training.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

What Are Ontologies and When Should They Be Used?

Data without description is at best unusable, and at worst, misused. If we do not understand the assumptions and meaning of our data, we are unable to confidently use it. Data today is largely described within a database’s schema, detailing structure and primitive datatypes as part of a relational model, but if we require assurance some data value can be correctly evaluated alongside others beyond the immediate systems in which they are defined, a more portable, richer semantics is needed. Ontologies define knowledge unambiguously across systems and establish the means to reason upon said knowledge using logical inference. They model neutral domains of information rather than data definitions from software or databases that would only serve to enrich a single system’s idiosyncrasies. In this paper, we take a casual stance to explore what ontologies are, how they are built, why they are useful, and when they should be used.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

DeepAndes: A Self-Supervised Vision Foundation Model for Multispectral Remote Sensing Imagery of the Andes

By mapping sites at large scales usingremotely sensed data, archaeologists can generate unique insights into long-term demographic trends, interregional social networks, and human adaptations in the past. Remote sensing surveys complement field-based approaches, and their reach can be especially great when combined with deep learning and computer vision techniques. However, conventional supervised deep learning methods face challenges in annotating fine-grained archaeological features at scale. In addition, while recent vision foundation models have shown remarkable success in learning large-scale remote sensing data with minimal annotations, most off-the-shelf solutions are designed for RGB images rather than multispectral satellite imagery, such as the eight-band data used in our study. In this article, we introduce DeepAndes, a transformer-based vision foundation model trained on three million multispectral satellite images, specifically tailored for Andean archaeology. DeepAndes incorporates a customized DINOv2 self-supervised learning algorithm optimized for eight-band multispectral imagery, marking the first foundation model designed explicitly for the Andes region. We evaluate its image understanding performance through imbalanced image classification, image instance retrieval, and pixel-level semantic segmentation tasks. Our experiments show that DeepAndes achieves superior F1 scores, mean average precision, and Dice scores in few-shot learning scenarios, significantly outperforming models trained from scratch or pretrained on smaller datasets. This underscores the effectiveness of large-scale self-supervised pretraining in archaeological remote sensing.

Guo, Junlin [Vanderbilt Univ., Nashville, TN (Unit↗
DOE OSTI2024

OReole-FM: successes and challenges toward billion-parameter foundation models for high-resolution satellite imagery

While the pretraining of Foundation Models (FMs) for remote sensing (RS) imagery is on the rise, models remain restricted to a few hundred million parameters. Scaling models to billions of parameters has been shown to yield unprecedented benefits including emergent abilities, but requires data scaling and computing resources typically not available outside industry R&D labs. In this work, we pair high-performance computing resources including Frontier supercomputer, America's first exascale system, and high-resolution optical RS data to pretrain billion-scale FMs. Our study assesses performance of different pretrained variants of vision Transformers across image classification, semantic segmentation and object detection benchmarks, which highlight the importance of data scaling for effective model scaling. Moreover, we discuss construction of a novel TIU pretraining dataset, model initialization, with data and pretrained models intended for public release. By discussing technical challenges and details often lacking in the related literature, this work is intended to offer best practices to the geospatial community toward efficient training and benchmarking of larger FMs.

Ambrozio Dias, Philipe↗
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↗
DOE OSTI2024

Structured Prompt Interrogation and Recursive Extraction of Semantics (SPIRES): a method for populating knowledge bases using zero-shot learning

Abstract Motivation Creating knowledge bases and ontologies is a time consuming task that relies on manual curation. AI/NLP approaches can assist expert curators in populating these knowledge bases, but current approaches rely on extensive training data, and are not able to populate arbitrarily complex nested knowledge schemas. Results Here we present Structured Prompt Interrogation and Recursive Extraction of Semantics (SPIRES), a Knowledge Extraction approach that relies on the ability of Large Language Models (LLMs) to perform zero-shot learning and general-purpose query answering from flexible prompts and return information conforming to a specified schema. Given a detailed, user-defined knowledge schema and an input text, SPIRES recursively performs prompt interrogation against an LLM to obtain a set of responses matching the provided schema. SPIRES uses existing ontologies and vocabularies to provide identifiers for matched elements. We present examples of applying SPIRES in different domains, including extraction of food recipes, multi-species cellular signaling pathways, disease treatments, multi-step drug mechanisms, and chemical to disease relationships. Current SPIRES accuracy is comparable to the mid-range of existing Relation Extraction methods, but greatly surpasses an LLM’s native capability of grounding entities with unique identifiers. SPIRES has the advantage of easy customization, flexibility, and, crucially, the ability to perform new tasks in the absence of any new training data. This method supports a general strategy of leveraging the language interpreting capabilities of LLMs to assemble knowledge bases, assisting manual knowledge curation and acquisition while supporting validation with publicly-available databases and ontologies external to the LLM. Availability and implementation SPIRES is available as part of the open source OntoGPT package: https://github.com/monarch-initiative/ontogpt.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

MapSpace: POI-based Multi-Scale Global Land Use Modeling

Accurate and up-to-date land use maps are important to the study of human-environment interactions, urban morphology, environmental justice, etc. Traditional land use mapping approaches involve several surveys and expert knowledge of the region to be mapped. While traditional approaches generate accurate and authoritative maps, it is expensive and takes a long time to develop a new version of map. Besides, such maps have region-specific spatial embedding, making them difficult to benchmark and compare against other land use maps. This work introduces a scalable POI-based land use modeling approach to generate global land use maps at multiple spatial scales and different semantic granularities. In addition, our land use maps adhere to a unified land use categories and can be compared for accuracy and precision.

Thakur, Gautam Malviya↗
DOE OSTI2023

Ontologizing health systems data at scale: making translational discovery a reality

Common data models solve many challenges of standardizing electronic health record (EHR) data but are unable to semantically integrate all of the resources needed for deep phenotyping. Open Biological and Biomedical Ontology (OBO) Foundry ontologies provide computable representations of biological knowledge and enable the integration of heterogeneous data. However, mapping EHR data to OBO ontologies requires significant manual curation and domain expertise. We introduce OMOP2OBO, an algorithm for mapping Observational Medical Outcomes Partnership (OMOP) vocabularies to OBO ontologies. Using OMOP2OBO, we produced mappings for 92,367 conditions, 8611 drug ingredients, and 10,673 measurement results, which covered 68–99% of concepts used in clinical practice when examined across 24 hospitals. When used to phenotype rare disease patients, the mappings helped systematically identify undiagnosed patients who might benefit from genetic testing. By aligning OMOP vocabularies to OBO ontologies our algorithm presents new opportunities to advance EHR-based deep phenotyping.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2022

Out of Distribution Detection with Neural Network Anchoring

This is code to reproduce and build on OOD detection from the paper "Out of Distribution Detection with Neural Network Anchoring". Our goal here is to exploit heteroscedastic temperature scaling as a calibration strategy for out of distribution (OOD) detection. Heteroscedasticity here refers to the fact that the optimal temperature parameter for each sample can be different, as opposed to conventional approaches that use the same value for the entire distribution. To enable this, we propose a new training strategy called anchoring that can estimate appropriate temperature values for each sample, leading to state-of-the-art OOD detection performance across several benchmarks. Using NTK theory, we show that this temperature function estimate is closely linked to the epistemic uncertainty of the classifier, which explains its behavior. In contrast to some of the best-performing OOD detection approaches, our method does not require exposure to additional outlier datasets, custom calibration objectives, or model ensembling. Through empirical studies with different OOD detection settings - far OOD, near OOD, and semantically coherent OOD - we establish a highly effective OOD detection approach.

Thiagarajan, Jayaraman↗
DOE OSTI2024

chatHPC: Empowering HPC users with large language models

The ever-growing number of pre-trained large language models (LLMs) across scientific domains presents a challenge for application developers. While these models offer vast potential, fine-tuning them with custom data, aligning them for specific tasks, and evaluating their performance remain crucial steps for effective utilization. However, applying these techniques to models with tens of billions of parameters can take days or even weeks on modern workstations, making the cumulative cost of model comparison and evaluation a significant barrier to LLM-based application development. To address this challenge, we introduce an end-to-end pipeline specifically designed for building conversational and programmable AI agents on high performance computing (HPC) platforms. Our comprehensive pipeline encompasses: model pre-training, fine-tuning, web and API service deployment, along with crucial evaluations for lexical coherence, semantic accuracy, hallucination detection, and privacy considerations. Here, we demonstrate our pipeline through the development of chatHPC, a chatbot for HPC question answering and script generation. Leveraging our scalable pipeline, we achieve end-to-end LLM alignment in under an hour on the Frontier supercomputer. We propose a novel self-improved, self-instruction method for instruction set generation, investigate scaling and fine-tuning strategies, and conduct a systematic evaluation of model performance. The established practices within chatHPC will serve as a valuable guidance for future LLM-based application development on HPC platforms.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Tackling the Challenges in Scene Graph Generation With Local-to-Global Interactions

In this work, we seek new insights into the underlying challenges of the scene graph generation (SGG) task. Quantitative and qualitative analysis of the visual genome (VG) dataset implies: 1) ambiguity: even if interobject relationship contains the same object (or predicate), they may not be visually or semantically similar; 2) asymmetry: despite the nature of the relationship that embodied the direction, it was not well addressed in previous studies; and 3) higher-order contexts: leveraging the identities of certain graph elements can help generate accurate scene graphs. Motivated by the analysis, we design a novel SGG framework, Local-to-global interaction networks (LOGINs). Locally, interactions extract the essence between three instances of subject, object, and background, while baking direction awareness into the network by explicitly constraining the input order of subject and object. Globally, interactions encode the contexts between every graph component (i.e., nodes and edges). Finally, Attract and Repel loss is utilized to fine-tune the distribution of predicate embeddings. By design, our framework enables predicting the scene graph in a bottom-up manner, leveraging the possible complementariness. To quantify how much LOGIN is aware of relational direction, a new diagnostic task called Bidirectional Relationship Classification (BRC) is also proposed. Overall, experimental results demonstrate that LOGIN can successfully distinguish relational direction than existing methods (in BRC task), while showing state-of-the-art results on the VG benchmark (in SGG task).

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Background-Aware 3-D Point Cloud Segmentation With Dynamic Point Feature Aggregation

With the proliferation of LiDAR sensors and 3-D vision cameras, 3-D point cloud analysis has attracted significant attention in recent years. In this article, we propose a novel 3-D point cloud learning network, referred to as dynamic point feature aggregation network (DPFA-Net), by selectively performing the neighborhood feature aggregation (FA) with dynamic pooling and an attention mechanism. DPFA-Net has two variants for semantic segmentation and classification of 3-D point clouds. As the core module of the DPFA-Net, we propose an FA layer, in which features of the dynamic neighborhood of each point are aggregated via a self-attention mechanism. In contrast to other segmentation models, which aggregate features from fixed neighborhoods, our approach can aggregate features from different neighbors in different layers providing a more selective and broader view to the query points and focusing more on the relevant features in a local neighborhood. In addition, to further improve the performance of semantic segmentation, we exploit the background–foreground (BF) information and present two novel approaches, namely, two-stage BF-Net and BF regularization. Experimental results show that the proposed DPFA-Net achieves the state-of-the-art overall accuracy score of 89.22% for semantic segmentation on the Stanford large-scale 3-D Indoor Spaces (S3DIS) dataset and provides consistently satisfactory performance across different tasks of semantic segmentation, part segmentation, and 3-D object classification. Furthermore, our model achieves 93.1% accuracy on the ModelNet40 dataset and provides a mean shape intersection-over-union (IoU) value of 85.5% for part segmentation on the ShapeNet-Part dataset. It is a also computationally more efficient compared to other methods.

3-D↗
DOE OSTI2022

Machine Reading at Scale: A Search Engine for Scientific and Academic Research

The Internet, much like our universe, is ever-expanding. Information, in the most varied formats, is continuously added to the point of information overload. Consequently, the ability to navigate this ocean of data is crucial in our day-to-day lives, with familiar tools such as search engines carving a path through this unknown. In the research world, articles on a myriad of topics with distinct complexity levels are published daily, requiring specialized tools to facilitate the access and assessment of the information within. Recent endeavors in artificial intelligence, and in natural language processing in particular, can be seen as potential solutions for breaking information overload and provide enhanced search mechanisms by means of advanced algorithms. As the advent of transformer-based language models contributed to a more comprehensive analysis of both text-encoded intents and true document semantic meaning, there is simultaneously a need for additional computational resources. Information retrieval methods can act as low-complexity, yet reliable, filters to feed heavier algorithms, thus reducing computational requirements substantially. In this work, a new search engine is proposed, addressing machine reading at scale in the context of scientific and academic research. It combines state-of-the-art algorithms for information retrieval and reading comprehension tasks to extract meaningful answers from a corpus of scientific documents. The solution is then tested on two current and relevant topics, cybersecurity and energy, proving that the system is able to perform under distinct knowledge domains while achieving competent performance.

Sousa, Norberto (ORCID:0000000329194817)↗
DOE OSTI2022

Scaling Building Energy Audits through Machine Learning Methods on Novel Drone Image Data

Building energy audits are time-consuming and labor-intensive. This paper describes a new method using machine learning (ML) techniques on novel data sources (drone images) to improve the identification of building characteristics and retrofit opportunities, and thereby reduce the effort for audits. The new ML method includes: (1) Building footprint extraction using line extraction, polygonization, and polygon-merging, (2) Building envelope extraction using PIX4d modeling software to reconstruct a building 3D model, (3) Visualization tool for viewing images from the 3D model, (4) Window-to-wall ratio (WWR) using state-of-art deep neural network semantic segmentation, (5) Envelope thermal anomaly detection using an unsupervised machine learning clustering algorithm, and (6) Rooftop energy equipment detection based on an object detection algorithm. The testing of this method involved a comparison of additional ML-generated information overlaid on current ‘state-of-practice’ audit and remote assessment baselines using evaluation metrics: labor time and associated cost, marginal benefits of using ML-generated information in workflows for audits and remote assessments, integration potential with existing processes and tools, and replicability/scalability of the method. In two test buildings in California that had comprehensive drawings and meter data available, the ML method effectively generated a building footprint, envelope, rooftop equipment, WWR, and locations of envelope thermal anomalies. Projected target segments of the ML method are sites with minimal drawings and energy data, and underserved sectors such as multistoried housing, disadvantaged communities, and schools for which the ML method can enable identification of building asset characteristics and prioritization of envelope retrofits and decentralized energy equipment retrofits.

Singh, Reshma↗
DOE OSTI2020

Shepherding Metadata Through the Building Lifecycle

Many different digital representations of a building are produced over the course of its lifecycle. These representations contain the metadata required to support different stages of the building, from initial planning and design, to construction and commissioning, through operations, audits, retrofits and maintenance. However, because of differences in the semantics, structure and syntax of these representations, the metadata they contain is not interoperable. We present a novel method for leveraging these representations to create a unified, authoritative Brick metadata model for a building that can be continually maintained over the course of the building lifecycle. A simple synchronization protocol relays inferred Brick metadata from existing metadata sources such as gbXML, BuildingSync, Project Haystack and Modelica to a central integration server, which merges the metadata into a valid Brick model.

Fierro, Gabe↗
DOE OSTI2022

Interactively Assessing Disentanglement in GANs

Abstract Generative adversarial networks (GAN) have witnessed tremendous growth in recent years, demonstrating wide applicability in many domains. However, GANs remain notoriously difficult for people to interpret, particularly for modern GANs capable of generating photo‐realistic imagery. In this work we contribute a visual analytics approach for GAN interpretability, where we focus on the analysis and visualization of GAN disentanglement. Disentanglement is concerned with the ability to control content produced by a GAN along a small number of distinct, yet semantic, factors of variation. The goal of our approach is to shed insight on GAN disentanglement, above and beyond coarse summaries, instead permitting a deeper analysis of the data distribution modeled by a GAN. Our visualization allows one to assess a single factor of variation in terms of groupings and trends in the data distribution, where our analysis seeks to relate the learned representation space of GANs with attribute‐based semantic scoring of images produced by GANs. Through use‐cases, we show that our visualization is effective in assessing disentanglement, allowing one to quickly recognize a factor of variation and its overall quality. In addition, we show how our approach can highlight potential dataset biases learned by GANs.

Jeong, Sangwon↗
DOE OSTI2022

Towards a Stronger Foundation: Digitizing Commercial Buildings with Brick to Enable Portable Advanced Applications

Most large commercial buildings have digital controls for their heating, ventilation, and air-conditioning (HVAC) and lighting systems with the potential to implement advanced control strategies and data analytics. However, advanced control strategies and data analytics are rarely deployed at scale due to non-standard naming conventions and heterogenous building configurations. Semantic metadata standards, like Brick, show promise to proliferate these applications across many buildings, but they have not been widely adopted by industry due to barriers such as perceived risk and unfamiliarity with the technology. This paper describes the workflow we established and evaluated while using it to develop over ten Brick models of existing buildings. Through this process, we observed that digitizing existing commercial buildings is a cost and labor-intensive effort in which understanding the buildings’ data streams is the major bottleneck. Yet, we conclude this investment is worthwhile since various use case applications such as fault detection and diagnostics, thermal comfort analysis, and HVAC control optimization can utilize the same Brick model. The paper also explores the challenges and lessons learned we encountered while creating these data models, such as: 1) difficulties in finding metadata descriptions and relationships for existing buildings; 2) handling missing concepts in the schema needed to model a building; 3) lack of guidance on how to structure the data model or how much detail to include; 4) unfamiliarity with technologies, which makes the learning curve steep for applications developers. Finally, we also describe future directions for semantic metadata research and development to make such transformative technologies more accessible to practitioners.

Roa, Carlos Duarte↗
DOE OSTI2024

AstroCLIP: a cross-modal foundation model for galaxies

ABSTRACT We present AstroCLIP, a single, versatile model that can embed both galaxy images and spectra into a shared, physically meaningful latent space. These embeddings can then be used – without any model fine-tuning – for a variety of downstream tasks including (1) accurate in-modality and cross-modality semantic similarity search, (2) photometric redshift estimation, (3) galaxy property estimation from both images and spectra, and (4) morphology classification. Our approach to implementing AstroCLIP consists of two parts. First, we embed galaxy images and spectra separately by pre-training separate transformer-based image and spectrum encoders in self-supervised settings. We then align the encoders using a contrastive loss. We apply our method to spectra from the Dark Energy Spectroscopic Instrument and images from its corresponding Legacy Imaging Survey. Overall, we find remarkable performance on all downstream tasks, even relative to supervised baselines. For example, for a task like photometric redshift prediction, we find similar performance to a specifically trained ResNet18, and for additional tasks like physical property estimation (stellar mass, age, metallicity, and specific-star-formation rate), we beat this supervised baseline by 19 per cent in terms of R2. We also compare our results with a state-of-the-art self-supervised single-modal model for galaxy images, and find that our approach outperforms this benchmark by roughly a factor of two on photometric redshift estimation and physical property prediction in terms of R2, while remaining roughly in-line in terms of morphology classification. Ultimately, our approach represents the first cross-modal self-supervised model for galaxies, and the first self-supervised transformer-based architectures for galaxy images and spectra.

Parker, Liam (ORCID:0009000749521674)↗