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 253 records · Page 14
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Geospatial Data Platform for All

Spatiotemporal data has evolved in scale due to augmented use in cross-domain applications. Simultaneously, there is substantial growth in the availability of Geographic Information Systems (GIS) data provided by the United States Geological Survey (USGS) along with other federal, state, county, or local agencies through open-data portals and public access APIs. However, data availability does not equate with accessibility. Large-scale analyses and applications require robust, performant data management with co-location of data storage and computing. The insufficiency of data management infrastructure compels researchers to adopt ad hoc project- specific GIS data storage solutions (e.g., copying data to High-Performance computer file systems). As an ad hoc storage strategy does not scale, it hampers cross-domain analyses causing difficulty in data reuse and utilizing existing code bases. Furthermore, GIS data is complex and requires expertise to analyze and manipulate due to its intricate data structures and data-specific projection transformations. Despite the challenges, we recognize that derived GIS data products, e.g., satellite or LIDAR-based images, can be used in downstream applications such as AI by domain, but non-GIS experts. To address the data needs and overcome the challenges, we are working towards a GIS Data Platform focused on efficient data storage, data discovery and access, and an API to enable common workflows. We propose a knowledge-graph (KG) approach for data discovery, whereby datasets are semantically linked to higher- level constructs such as projects and research areas. The semantic data links enable researchers to explore datasets in a top-down approach by specifying relevant and meaningful terms (assists in finding hidden data). An advantage is that the nodes and edges in a knowledge graph create built-in semantic documentation. Deeper spatiotemporal connections between data sources can be encoded via Graph Neural Networks (GNN) (Zhang et al., 2021). The KG approach can be extended to integrate the data itself in a Virtual KG (VKG). Our work will derive inspiration from large-scale VKG efforts that have been undertaken or are currently underway as part of the OpenStreetMap project (Ding et al., 2021). For DOE Data Days, we share the proposed geospatial data platform hybrid (cloud/on-prem) architecture, our work-to-date on storing, retrieving, and transforming LiDAR and raster data relevant to two important NREL use-cases, including the Renewable Energy Potential (reV) Model, and present our proposal for a KG based data discovery engine.

data platform↗
DOE OSTI2021

Self-supervised Representation Learning for Astronomical Images

Sky surveys are the largest data generators in astronomy, making automated tools for extracting meaningful scientific information an absolute necessity. We show that, without the need for labels, self-supervised learning recovers representations of sky survey images that are semantically useful for a variety of scientific tasks. These representations can be directly used as features, or fine-tuned, to outperform supervised methods trained only on labeled data. We apply a contrastive learning framework on multiband galaxy photometry from the Sloan Digital Sky Survey (SDSS), to learn image representations. We then use them for galaxy morphology classification and fine-tune them for photometric redshift estimation, using labels from the Galaxy Zoo 2 data set and SDSS spectroscopy. In both downstream tasks, using the same learned representations, we outperform the supervised state-of-the-art results, and we show that our approach can achieve the accuracy of supervised models while using 2-4 times fewer labels for training. The codes, trained models, and data can be found at https://portal.nersc.gov/project/dasrepo/self-supervised-learning-sdss.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

An approach for collaborative development of a federated biomedical knowledge graph-based question-answering system: Question-of-the-Month challenges

Knowledge graphs have become a common approach for knowledge representation. Yet, the application of graph methodology is elusive due to the sheer number and complexity of knowledge sources. In addition, semantic incompatibilities hinder efforts to harmonize and integrate across these diverse sources. As part of The Biomedical Translator Consortium, we have developed a knowledge graph–based question-answering system designed to augment human reasoning and accelerate translational scientific discovery: the Translator system. We have applied the Translator system to answer biomedical questions in the context of a broad array of diseases and syndromes, including Fanconi anemia, primary ciliary dyskinesia, multiple sclerosis, and others. A variety of collaborative approaches have been used to research and develop the Translator system. One recent approach involved the establishment of a monthly “Question-of-the-Month (QotM) Challenge” series. Herein, we describe the structure of the QotM Challenge; the six challenges that have been conducted to date on drug-induced liver injury, cannabidiol toxicity, coronavirus infection, diabetes, psoriatic arthritis, and -related phenotypes; the scientific insights that have been gleaned during the challenges; and the technical issues that were identified over the course of the challenges and that can now be addressed to foster further development of the prototype Translator system. We close with a discussion on Large Language Models such as ChatGPT and highlight differences between those models and the Translator system.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

GraphAide: Advanced Graph-Assisted Query and Reasoning System

Curating knowledge from multiple siloed sources that contain both structured and unstructured data is a major challenge in many real-world applications. Pattern matching and querying represent fundamental tasks in modern data analytics that leverage this curated knowledge. The development of such applications necessitates overcoming several research challenges, including data extraction, named entity recognition, data modeling, and designing query interfaces. Moreover, the explainability of these functionalities is critical for their broader adoption. The emergence of Large Language Models (LLMs) has accelerated the development lifecycle of new capabilities. Nonetheless, there is an ongoing need for domain-specific tools tailored to user activities. The creation of digital assistants has gained considerable traction in recent years, with LLMs offering a promising avenue to develop such assistants utilizing domain-specific knowledge and assumptions. In this context, we introduce an advanced query and reasoning system, GraphAide, which constructs a knowledge graph (KG) from diverse sources and allows to query and reason over the resulting KG. GraphAide harnesses both the KG and LLMs to rapidly develop domain-specific digital assistants. It integrates design patterns from retrieval augmented generation (RAG) and the semantic web to create an agentic LLM application. GraphAide underscores the potential for streamlined and efficient development of specialized digital assistants, thereby enhancing their applicability across various domains.

Purohit, Sumit [BATTELLE (PACIFIC NW LAB)] (ORCID:↗
DOE OSTI2025

Poster Abstract: Leveraging Large Language Models to Reveal Interpretable Cooling Behaviors from Smart Thermostat Data

Frequent heatwaves and hot summers increasingly challenge occupant comfort, health, and energy grid stability. Addressing these challenges requires a detailed understanding of household cooling behaviors, such as thermostat adjustments and adaptive responses to extreme conditions. Traditional analyses often rely on aggregated numerical metrics that overlook subtle but important household-specific variations. In this study, we introduce a generalizable methodology that integrates large language models (LLMs) with vision capabilities to enable scalable and detailed analysis of residential thermostat data. Using Ecobee's Donate Your Data (DYD) dataset—which provides five-minute records of indoor temperatures, thermostat setpoints, and HVAC runtimes—we focus on two U.S. cities with contrasting summer climates : Austin (TX) and Phoenix (AZ). Because raw time-series data are not well suited for direct LLM analysis, we transform them into visual representations, such as daily indoor temperature trajectories and weekly runtime histograms, to better capture behavioral variations. Leveraging LLMs' visual interpretation, we extract descriptive behavioral features, including temperature preferences, time-of-day cooling orientation, anticipatory versus reactive heatwave responses, and behavioral consistency. These semantic features support unsupervised clustering to identify distinct occupant archetypes at scale, revealing differences—such as morning-centric anticipatory coolers versus households that shift toward warmer setpoints during heatwaves—that can inform demand response, resilience planning, and health-aware interventions. By converting raw numerical data into interpretable behavioral patterns, this methodology enables scalable and practical analysis of occupant behavior, supporting actionable insights for comfort, resilience, and energy management.

Nihar, Kopal↗
DOE OSTI2026

Agentic Diagrammatica: Towards Autonomous Symbolic Computation in High Energy Physics

We present Diagrammatica, a symbolic computation extension to the HEPTAPOD agentic framework, which enables LLM agents to plan and execute multi-step theoretical calculations. Symbolic computation poses a distinctive reliability challenge for LLM agents, as correctness is governed by implicit mathematical conventions that are not encoded in a form that can be easily checked in the computational backend. We identify two complementary remedies, tool-constrained computation and targeted knowledge grounding, and pursue the first as the primary architecture. Concretely, we concentrate the agent's action distribution onto tool calls with convention-fixing semantics, in which the agent specifies a compact, human-auditable diagram specification and a trusted backend performs the symbolic or numerical manipulations exactly. The toolkit provides two complementary calculation paths consuming a shared diagram specification: Naive Dimensional Analysis (NDA) for order-of-magnitude rate estimates and Exact Diagrammatic Analysis (EDA) for tree-level symbolic calculations via automatic FeynCalc code generation, both supplemented by automatic Feynman diagram enumeration and a navigable theory knowledge base. The architecture is validated on two benchmarks: (1) an exhaustive catalog of all tree-level, single-vertex $1\to 2$ partial decay widths across scalar, fermion, and vector parents, with complete massless and threshold limits and Standard Model validation; and (2) an NDA sensitivity study of the muon decay multiplicity $μ^+ \to ν_μ\barν_e + n(e^+e^-) + e^-$, determining the maximum observable $n$ at current and planned muon experiments.

Menzo, Tony [Alabama U.; Fermilab] (ORCID:00000002↗
DOE OSTI2023

The Human Phenotype Ontology in 2024: phenotypes around the world

The Human Phenotype Ontology (HPO) is a widely used resource that comprehensively organizes and defines the phenotypic features of human disease, enabling computational inference and supporting genomic and phenotypic analyses through semantic similarity and machine learning algorithms. The HPO has widespread applications in clinical diagnostics and translational research, including genomic diagnostics, gene-disease discovery, and cohort analytics. In recent years, groups around the world have developed translations of the HPO from English to other languages, and the HPO browser has been internationalized, allowing users to view HPO term labels and in many cases synonyms and definitions in ten languages in addition to English. Since our last report, a total of 2239 new HPO terms and 49235 new HPO annotations were developed, many in collaboration with external groups in the fields of psychiatry, arthrogryposis, immunology and cardiology. The Medical Action Ontology (MAxO) is a new effort to model treatments and other measures taken for clinical management. Finally, the HPO consortium is contributing to efforts to integrate the HPO and the GA4GH Phenopacket Schema into electronic health records (EHRs) with the goal of more standardized and computable integration of rare disease data in EHRs.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

MultiTaskDeltaNet: change detection-based image segmentation for operando ETEM with application to carbon gasification kinetics

Transforming in situ transmission electron microscopy (TEM) imaging into a tool for spatially-resolved operando characterization of solid-state reactions requires automated, high-precision semantic segmentation of dynamically evolving features. However, traditional deep learning methods for semantic segmentation often face limitations due to the scarcity of labeled data, visually ambiguous features of interest, and scenarios involving small objects. To tackle these challenges, we introduce MultiTaskDeltaNet (MTDN), a novel deep learning architecture that creatively reconceptualizes the segmentation task as a change detection problem. By implementing a unique Siamese network with a U-Net backbone and using paired images to capture feature changes, MTDN effectively leverages minimal data to produce high-quality segmentations. Furthermore, MTDN utilizes a multi-task learning strategy to exploit correlations between physical features of interest. In an evaluation using data from in situ environmental TEM (ETEM) videos of filamentous carbon gasification, MTDN demonstrated a significant advantage over conventional segmentation models, particularly in accurately delineating fine structural features. Notably, MTDN achieved a 10.22% performance improvement over conventional segmentation models in predicting small and visually ambiguous physical features. This work bridges key gaps between deep learning and practical TEM image analysis, advancing automated characterization of nanomaterials in complex experimental settings.

08 HYDROGEN↗
DOE OSTI2025

Consistent performance of large language models in rare disease diagnosis across ten languages and 4917 cases

Background Large language models (LLMs) are increasingly used medicine for diverse applications including differential diagnostic support. The training data used to create LLMs such as the Generative Pretrained Transformer (GPT) predominantly consist of English-language texts, but LLMs could be used across the globe to support diagnostics if language barriers could be overcome. Initial pilot studies on the utility of LLMs for differential diagnosis in languages other than English have shown promise, but a large-scale assessment on the relative performance of these models in a variety of European and non-European languages on a comprehensive corpus of challenging rare-disease cases is lacking. Methods We created 4917 clinical vignettes using structured data captured with Human Phenotype Ontology (HPO) terms with the Global Alliance for Genomics and Health (GA4GH) Phenopacket Schema. These clinical vignettes span a total of 360 distinct genetic diseases with 2525 associated phenotypic features. We used translations of the Human Phenotype Ontology together with language-specific templates to generate prompts in English, Chinese, Czech, Dutch, French, German, Italian, Japanese, Spanish, and Turkish. We applied GPT-4o, version gpt-4o-2024-08-06, and the medically fine-tuned Meditron3-70B to the task of delivering a ranked differential diagnosis using a zero-shot prompt. An ontology-based approach with the Mondo disease ontology was used to map synonyms and to map disease subtypes to clinical diagnoses in order to automate evaluation of LLM responses. Findings For English, GPT-4o placed the correct diagnosis at the first rank 19.9% and within the top-3 ranks 27.0% of the time. In comparison, for the nine non-English languages tested here the correct diagnosis was placed at rank 1 between 16.9% and 20.6%, within top-3 between 25.4% and 28.6% of cases. The Meditron3 model placed the correct diagnosis within the first 3 ranks for 20.9% of cases in English and between 19.9% and 24.0% for the other nine languages. Interpretation The differential diagnostic performance of LLMs across a comprehensive corpus of rare-disease cases was largely consistent across the ten languages tested. This suggests that the utility of LLMs in clinical settings may extend to non-English clinical settings.

Artificial intelligence↗
DOE OSTI2023

Skewering the silos: using Brick to enable portable analytics, modeling and controls in buildings

Nearly all large commercial buildings have heating, ventilation and air conditioning (HVAC) systems, lighting systems, safety and other systems controlled by a computer—a dedicated server with a building energy management system (BMS). However, these BMSs are proprietary with each building’s assets (that is, fans, valves, pumps, and their setpoints) named and coded uniquely by the BMS vendor or engineer; building analytics and control algorithms are written specific to the assets and the building. Thus, any control updates or analytics to improve building performance—especially critical to reduce greenhouse emissions or improve load flexibility—are labor intensive and costly. The Brick schema was developed so the same analysis or control algorithms can work on a variety of buildings if each is digitally represented in a Brick data model. The goal of this project was to further the development of Brick to extend it beyond an academic project with demonstrated success in a small field study, to a practical choice for industrial and commercial stakeholders seeking to realize value from building data. To do this, we executed four objectives: (1) expand the Brick schema including its modeling capabilities and vocabulary, (2) develop tools for integrating Brick with existing digital technologies and representations in buildings, (3) develop an open-source analytics platform to facilitate use of Brick in delivering data value, and (4) demonstrate Brick-driven analytics and controls in real settings.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2023

SeeQ: A Programming Model for Portable Data-Driven Building Applications

This paper introduces SeeQ, a programming model and an abstraction framework that facilitates the development of portable data- driven building applications. Data-driven approaches can provide insights into building operations and guide decision-making to achieve operational objectives. Yet the configuration of such applications per building requires extensive effort and tacit knowledge. In SeeQ, we propose a portable programming model and build a software system that enables self-configuration and execution across diverse buildings. The configuration of each building is captured in a unified data model - in this paper, we work with the Brick ontology without loss of generality. SeeQ focuses on the distinction between the application logic and the configuration of an application against building-specific data inputs and systems. We test the proposed approach by configuring and deploying a diverse range of applications across five heterogeneous real-world buildings. The analysis shows the potential of SeeQ to significantly reduce the efforts associated with the delivery of building analytics.

analytics↗
DOE OSTI2024

MFANS 2024 - Formally Proving Characteristics of Cyber-Physical Systems

Cyber-physical systems (CPS) are engineered systems that rely on the smooth integration of computational algorithms and physical elements. This integration presents new challenges for verifying that systems will behave as expected. The goal of this presentation is to present current challenges and potential solutions for the formal verification of cyber-physical systems. For cyber systems, formal methods refer to systematically rigorous mathematical techniques employed in the specification, development, analysis, and verification of both software and hardware systems. Recent advancements in computer science have yielded sophisticated tools specifically designed to address challenges associated with formal methods in complex systems. These tools leverage various foundational concepts such as logic, formal languages, program semantics, type systems, type theory, and automata theory. A notable achievement in the application of formal methods is the seL4 microkernel, claimed to be the first general-purpose operating-system kernel to be verified. Its proof implies the absence of bugs and guarantees that the kernel meets specifications. For physical systems, dynamic and control theory has a history of using rigorous analytic techniques to prove functional correctness. Lyapunov, optimal, classical, modern, and robust control theories all provide rigorous mathematical methods both to analyze system performance and to design controller that can be guaranteed to meet certain objectives. Recent computational techniques like level set theory and reachability analysis provide assertions that a system's state will avoid unsafe regions. Even though success has been independently achieved for cyber systems and physical systems, the integration of such systems creates new challenges. In particular, there is an obvious discrepancy between finite-state machines and infinite-state systems, resulting in different approaches for modeling and analyzing these system. While it is possible to simulate hybrid systems, this provides only a demonstration of a performance and not proof. For hybrid systems, current formal methods and system analysis approaches typically require a workarounds to work on hybrid systems like CPS. This paper will outline the state of the art and limits of current practice for formally verifying CPS and will identify possible research directions that require attention.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Distributed Intrusion Detection System using Semantic-based Rules for SCADA in Smart Grid

Cyber-physical system (CPS) security for the smart grid enables secure communication for the SCADA and wide-area measurement system data. Power utilities world-wide use various SCADA protocols, namely DNP3, Modbus, and IEC 61850, for the data exchanges across substation field devices, remote terminal units (RTUs), and control center applications. Adversaries may exploit compromised SCADA protocols for the reconnaissance, data exfiltration, vulnerability assessment, and injection of stealthy cyberattacks to affect power system operation. In this paper, we propose an efficient algorithm to generate robust rule sets. We integrate the rule sets into an intrusion detection system (IDS), which continuously monitors the DNP3 data traffic at a substation network and detects intrusions and anomalies in real-time. To enable CPS-aware wide-area situational awareness, we integrated the methodology into an open-source distributed-IDS (D-IDS) framework. The D-IDS facilitates central monitoring of the detected anomalies from the geographically distributed substations and to the control center. The proposed algorithm provides an optimal solution to detect network intrusions and abnormal behavior. Different types of IDS rules based on packet payload, packet flow, and time threshold are generated. Further, IDS testing and evaluation is performed with a set of rules in different sequences. The detection time is measured for different IDS rules, and the results are plotted. All the experiments are conducted at Power Cyber Lab, Iowa State University, for multiple power grid models. After successful testing and evaluation, knowledge and implementation are transferred to field deployment.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

AEPF: Attention-Enabled Point Fusion for 3D Object Detection

Current state-of-the-art (SOTA) LiDAR-only detectors perform well for 3D object detection tasks, but point cloud data are typically sparse and lacks semantic information. Detailed semantic information obtained from camera images can be added with existing LiDAR-based detectors to create a robust 3D detection pipeline. With two different data types, a major challenge in developing multi-modal sensor fusion networks is to achieve effective data fusion while managing computational resources. With separate 2D and 3D feature extraction backbones, feature fusion can become more challenging as these modes generate different gradients, leading to gradient conflicts and suboptimal convergence during network optimization. To this end, we propose a 3D object detection method, Attention-Enabled Point Fusion (AEPF). AEPF uses images and voxelized point cloud data as inputs and estimates the 3D bounding boxes of object locations as outputs. An attention mechanism is introduced to an existing feature fusion strategy to improve 3D detection accuracy and two variants are proposed. These two variants, AEPF-Small and AEPF-Large, address different needs. AEPF-Small, with a lightweight attention module and fewer parameters, offers fast inference. AEPF-Large, with a more complex attention module and increased parameters, provides higher accuracy than baseline models. Experimental results on the KITTI validation set show that AEPF-Small maintains SOTA 3D detection accuracy while inferencing at higher speeds. AEPF-Large achieves mean average precision scores of 91.13, 79.06, and 76.15 for the car class’s easy, medium, and hard targets, respectively, in the KITTI validation set. Results from ablation experiments are also presented to support the choice of model architecture.

Chemistry↗
DOE OSTI2021

Development of a Unified Taxonomy for HVAC System Faults

Detecting and diagnosing HVAC faults is critical for maintaining building operation performance, reducing energy waste, and ensuring indoor comfort. An increasing deployment of commercial fault detection and diagnostics (FDD) software tools in commercial buildings in the past decade has significantly increased buildings’ operational reliability and reduced energy consumption. A massive amount of data has been generated by the FDD software tools. However, efficiently utilizing FDD data for ‘big data’ analytics, algorithm improvement, and other data-driven applications is challenging because the format and naming conventions of those data are very customized, unstructured, and hard to interpret. This paper presents the development of a unified taxonomy for HVAC faults. A taxonomy is an orderly classification of HVAC faults according to their characteristics and causal relations. The taxonomy includes fault categorization, physical hierarchy, fault library, relation model, and naming/tagging scheme. The taxonomy employs both a physical hierarchy of HVAC equipment and a cause-effect relationship model to reveal the root causes of faults in HVAC systems. A structured and standardized vocabulary library is developed to increase data representability and interpretability. The developed fault taxonomy can be used for HVAC system ‘big data’ analytics such as HVAC system fault prevalence analysis or the development of an HVAC FDD software standard. A common type of HVAC equipment-packaged rooftop unit (RTU) is used as an example to demonstrate the application of the developed fault taxonomy. Two RTU FDD software tools are used to show that after mapping FDD data according to the taxonomy, the meta-analysis of the multiple FDD reports is possible and efficient.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2025

Parallel sorting algorithm classification: is manual instrumentation necessary?

Understanding parallel algorithms is crucial for accelerating scientific simulations on complex, distributed memory, high-performance computers. Modern algorithm classification approaches learn semantics directly from source code to differentiate between algorithms, however, accessing source code is not always possible. We can learn about parallel algorithms from observing their performance, as programs running the same algorithms and using the same hardware should exhibit similar performance characteristics. We present an approach to learn algorithm classes from parallel performance data directly in order to classify algorithms without access to the source code. We extend previous work to enable classifying parallel sorting algorithms using automatic instrumentation instead of requiring manual region annotations in the source code. In this work, we design and demonstrate a study for classification of parallel sorting algorithms using parallel performance data collected from automatic instrumentation, and evaluate the performance of our new methodology on classification. We leverage Caliper to collect the performance data, Thicket for our exploratory data analysis (EDA), and PyTorch and Scikit-learn to evaluate the effectiveness of random forests, support vector machines (SVMs), decision trees, neural networks, and logistic regressions on parallel performance data. Additionally, we study noise in parallel performance data, whether the removal of noise and pre-processing of the data is necessary to accurately classify parallel sorting algorithms, and determine the effectiveness of features created from performance data. In conclusion, we demonstrate classification accuracy for these five different models of up to 97.7% across four different parallel algorithm classes.

Algorithm Classification↗
DOE OSTI2025

BuildingQA: A Benchmark for Natural Language Question Answering over Building Knowledge Graphs

Graph-based representations of building metadata using ontologies like Brick are vital for smart building applications, but querying them remains a challenge for practitioners. Knowledge Graph Question Answering (KGQA) systems, meant to retrieve answers from natural language questions, traditionally require large-scale training data, making them ill-suited for the specialized and data-scarce building domain. The advent of Large Language Models (LLMs) offers a paradigm shift, enabling zero-shot natural language querying without building/domain-specific training. Yet, there is no standardized benchmark for building-specific KGQA which can guide and validate research in this area. To address this gap, our work makes three primary contributions. First, we introduce the BuildingQA Benchmark Dataset, constructed through a multi-stage process of collecting practitioner data, augmenting it with LLMs for linguistic diversity, and curating a final set of 188 questions across 4 buildings. Second, we characterize the benchmark's complexity and ambiguity, introducing a novel method to quantify its "lexical gap" and providing a four-stage diagnostic framework for analyzing how systems fail. Third, we benchmark zero-shot LLM-powered KGQA systems to establish baseline performance and analyze their failure modes. Our evaluation reveals that top-performing systems achieve a maximum F1 score of only 0.38. This result does not indicate a failure of these powerful systems, but rather underscores the unique challenges posed by our benchmark. It demonstrates a critical performance gap, showing that current methods successful on general KGs struggle with the specific lexical and structural nuances of the building domain. BuildingQA1 thus provides the benchmark dataset and foundational analysis needed to drive the development of novel, domain-aware methods required to unlock the use of semantic data in buildings.

Mulayim, Ozan Baris↗
DOE OSTI2022

Multiview Incomplete Knowledge Graph Integration with application to cross-institutional EHR data harmonization

Objective: The growing availability of electronic health records (EHR) data opens opportunities for integrative analysis of multi-institutional EHR to produce generalizable knowledge. A key barrier to such integrative analyses is the lack of semantic interoperability across different institutions due to coding differences. We propose a Multiview Incomplete Knowledge Graph Integration (MIKGI) algorithm to integrate information from multiple sources with partially overlapping EHR concept codes to enable translations between healthcare systems. Methods: The MIKGI algorithm combines knowledge graph information from (i) embeddings trained from the co-occurrence patterns of medical codes within each EHR system and (ii) semantic embeddings of the textual strings of all medical codes obtained from the Self-Aligning Pretrained BERT (SAPBERT) algorithm. Due to the heterogeneity in the coding across healthcare systems, each EHR source provides partial coverage of the available codes. MIKGI synthesizes the incomplete knowledge graphs derived from these multi-source embeddings by minimizing a spherical loss function that combines the pairwise directional similarities of embeddings computed from all available sources. MIKGI outputs harmonized semantic embedding vectors for all EHR codes, which improves the quality of the embeddings and enables direct assessment of both similarity and relatedness between any pair of codes from multiple healthcare systems. Results: With EHR co-occurrence data from Veteran Affairs (VA) healthcare and Mass General Brigham (MGB), MIKGI algorithm produces high quality embeddings for a variety of downstream tasks including detecting known similar or related entity pairs and mapping VA local codes to the relevant EHR codes used at MGB. Based on the cosine similarity of the MIKGI trained embeddings, the AUC was 0.918 for detecting similar entity pairs and 0.809 for detecting related pairs. For cross-institutional medical code mapping, the top 1 and top 5 accuracy were 91.0% and 97.5% when mapping medication codes at VA to RxNorm medication codes at MGB; 59.1% and 75.8% when mapping VA local laboratory codes to LOINC hierarchy. When trained with 500 labels, the lab code mapping attained top 1 and 5 accuracy at 77.7% and 87.9%. MIKGI also attained best performance in selecting VA local lab codes for desired laboratory tests and COVID-19 related features for COVID EHR studies. Compared to existing methods, MIKGI attained the most robust performance with accuracy the highest or near the highest across all tasks. Conclusions: The proposed MIKGI algorithm can effectively integrate incomplete summary data from biomedical text and EHR data to generate harmonized embeddings for EHR codes for knowledge graph modeling and cross-institutional translation of EHR codes.

Zhou, Doudou↗