Results for “model queries” — Page 4

DOE OSTI2025

Extraction and Analysis of Time Series Data from Building Automation Systems Using Large Language Models

Semantic schemas like Haystack 4, Brick and ASHRAE standard 223 enable the structured, standardized, and machine-readable representation of building data, facilitating interoperability, data integration, and advanced analytics. However, extracting information from these models requires specialized expertise in SPARQL and other programming languages, skills that are not commonly found among building professionals. Recent advancements in Large Language Models (LLMs), such as ChatGPT, enable the construction of queries using natural language, making it easier for individuals to interact with these systems in a manner that resembles everyday speech. However, these methods have not yet been tested on building semantic ontologies. This paper introduces a novel workflow and tool for enabling users to ask questions about a specific building's data, using natural language and receive answers automatically generated by GPT-4o. Our approach integrates semantic ontologies with advanced LLM capabilities to automate three critical steps: (1) generating SPARQL queries to retrieve time series references from ontological models, (2) extracting the corresponding time series data from the Building Automation System, and (3) performing computations and visualizations tailored to the user's query. The proposed method simplifies access to BAS data, allowing both domain experts and non-specialists to conduct sophisticated analyses without needing extensive technical knowledge of semantic web technologies. By demonstrating this pipeline, we facilitate more accessible and scalable data-driven decision-making in building operations and management.

Mulayim, Ozan Baris↗

DOE OSTI2025

Extraction and Analysis of Time Series Data from Building Automation Systems Using Large Language Models

Semantic schemas like Haystack 4, Brick and ASHRAE standard 223 enable the structured, standardized, and machine-readable representation of building data, facilitating interoperability, data integration, and advanced analytics. However, extracting information from these models requires specialized expertise in SPARQL and other programming languages, skills that are not commonly found among building professionals. Recent advancements in Large Language Models (LLMs), such as ChatGPT, enable the construction of queries using natural language, making it easier for individuals to interact with these systems in a manner that resembles everyday speech. However, these methods have not yet been tested on building semantic ontologies. This paper introduces a novel workflow and tool for enabling users to ask questions about a specific building's data, using natural language and receive answers automatically generated by GPT-4o. Our approach integrates semantic ontologies with advanced LLM capabilities to automate three critical steps: (1) generating SPARQL queries to retrieve time series references from ontological models, (2) extracting the corresponding time series data from the Building Automation System, and (3) performing computations and visualizations tailored to the user's query. The proposed method simplifies access to BAS data, allowing both domain experts and non-specialists to conduct sophisticated analyses without needing extensive technical knowledge of semantic web technologies. By demonstrating this pipeline, we facilitate more accessible and scalable data-driven decision-making in building operations and management.

Mulayim, Ozan Baris↗

DOE OSTI2021

QLiG: Query Like a Graph For Subgraph Matching

A graph is a natural and flexible modeling approach to represent entities and relationships between them in real-world. A Knowledge Graphs (KG) is a specialized graph with formal and structured representation of facts, relationships, annotated with semantic descriptions. Subgraph matching is one of the fundamental graph problems to identify relationships, interactions and activities of interest within a large graph. A query specification is a collection of abstract components, operations, and constraints to express a pattern. The specification can be implemented in different ways based on underlying data model. Various graph query specifications have been developed over the years and have led to the development of different open-sourced and vendor-specific query languages. Such specification are modeled as an extension of relational algebra used to develop relational query languages such as SQL. Such relational concepts do not inherently support graph queries. There is a need to represent graph queries in terms on graph-based components to expedite query construction by non-database experts. We present a graph-based query approach QLiG (pronounced cleeg), to perform subgraph matching in Labeled Property Graph. We present the query specifications, salient features, and a use case to show functional examples.

Purohit, Sumit↗

NASA NTRS1990

The application of connectionism to query planning/scheduling in intelligent user interfaces

In the mid nineties, the Earth Observing System (EOS) will generate an estimated 10 terabytes of data per day. This enormous amount of data will require the use of sophisticated technologies from real time distributed Artificial Intelligence (AI) and data management. Without regard to the overall problems in distributed AI, efficient models were developed for doing query planning and/or scheduling in intelligent user interfaces that reside in a network environment. Before intelligent query/planning can be done, a model for real time AI planning and/or scheduling must be developed. As Connectionist Models (CM) have shown promise in increasing run times, a connectionist approach to AI planning and/or scheduling is proposed. The solution involves merging a CM rule based system to a general spreading activation model for the generation and selection of plans. The system was implemented in the Rochester Connectionist Simulator and runs on a Sun 3/260.

Short, Nicholas, Jr.↗

DOE OSTI2022

Training calibration-based counterfactual explainers for deep learning models in medical image analysis

The rapid adoption of artificial intelligence methods in healthcare is coupled with the critical need for techniques to rigorously introspect models and thereby ensure that they behave reliably. This has led to the design of explainable AI techniques that uncover the relationships between discernible data signatures and model predictions. In this context, counterfactual explanations that synthesize small, interpretable changes to a given query while producing desired changes in model predictions have become popular. This under-constrained, inverse problem is vulnerable to introducing irrelevant feature manipulations, particularly when the model’s predictions are not well-calibrated. Hence, in this paper, we propose the TraCE (training calibration-based explainers) technique, which utilizes a novel uncertainty-based interval calibration strategy for reliably synthesizing counterfactuals. Given the wide-spread adoption of machine-learned solutions in radiology, our study focuses on deep models used for identifying anomalies in chest X-ray images. Using rigorous empirical studies, we demonstrate the superiority of TraCE explanations over several state-of-the-art baseline approaches, in terms of several widely adopted evaluation metrics. Our findings show that TraCE can be used to obtain a holistic understanding of deep models by enabling progressive exploration of decision boundaries, to detect shortcuts, and to infer relationships between patient attributes and disease severity.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

DOE OSTI2022

Contextual Active Online Model Selection with Expert Advice

How can we collect the most useful labels to learn a model selection policy, when presented with arbitrary heterogeneous data streams? In this paper, we formulate this task as a contextual active model selection problem, where at each round the learner receives an unlabeled data point along with a context. The goal is to output the best model for any given context without obtaining an excessive amount of labels. In particular, we focus on the task of selecting pre-trained classifiers, and propose a contextual active model selection algorithm (CAMS), which relies on a novel uncertainty sampling query criterion defined on a given policy class for adaptive model selection. In comparison to prior art, our algorithm does not assume a globally optimal model. We provide rigorous theoretical analysis for the regret and query complexity under both adversarial and stochastic settings. Our experiments on several benchmark classification datasets demonstrate the algorithm’s effectiveness in terms of both regret and query complexity. Notably, to achieve the same accuracy, CAMS incurs less than 10% of the label cost when compared to the best online model selection baselines on CIFAR10.

Liu, Xuefeng↗

NASA NTRS2001

Efficient hemodynamic event detection utilizing relational databases and wavelet analysis

Development of a temporal query framework for time-oriented medical databases has hitherto been a challenging problem. We describe a novel method for the detection of hemodynamic events in multiparameter trends utilizing wavelet coefficients in a MySQL relational database. Storage of the wavelet coefficients allowed for a compact representation of the trends, and provided robust descriptors for the dynamics of the parameter time series. A data model was developed to allow for simplified queries along several dimensions and time scales. Of particular importance, the data model and wavelet framework allowed for queries to be processed with minimal table-join operations. A web-based search engine was developed to allow for user-defined queries. Typical queries required between 0.01 and 0.02 seconds, with at least two orders of magnitude improvement in speed over conventional queries. This powerful and innovative structure will facilitate research on large-scale time-oriented medical databases.

NASA Discipline Cardiopulmonary↗

DOE OSTI2022

Calibrating hypersonic turbulence flow models with the HIFiRE-1 experiment using data-driven machine-learned models.

In this paper we study the efficacy of combining machine-learning methods with projection-based model reduction techniques for creating data-driven surrogate models of computationally expensive, high-fidelity physics models. Such surrogate models are essential for many-query applications e.g., engineering design optimization and parameter estimation, where it is necessary to invoke the high-fidelity model sequentially, many times. Surrogate models are usually constructed for individual scalar quantities. However there are scenarios where a spatially varying field needs to be modeled as a function of the model’s input parameters. Here we develop a method to do so, using projections to represent spatial variability while a machine-learned model captures the dependence of the model’s response on the inputs. The method is demonstrated on modeling the heat flux and pressure on the surface of the HIFiRE-1 geometry in a Mach 7.16 turbulent flow. The surrogate model is then used to perform Bayesian estimation of freestream conditions and parameters of the SST (Shear Stress Transport) turbulence model embedded in the high-fidelity (Reynolds-Averaged Navier–Stokes) flow simulator, using shock-tunnel data. The paper provides the first-ever Bayesian calibration of a turbulence model for complex hypersonic turbulent flows. We find that the primary issues in estimating the SST model parameters are the limited information content of the heat flux and pressure measurements and the large model-form error encountered in a certain part of the flow.

42 ENGINEERING↗

NASA NTRS1990

AiGERM: A logic programming front end for GERM

AiGerm (Artificially Intelligent Graphical Entity Relation Modeler) is a relational data base query and programming language front end for MCC (Mission Control Center)/STP's (Space Test Program) Germ (Graphical Entity Relational Modeling) system. It is intended as an add-on component of the Germ system to be used for navigating very large networks of information. It can also function as an expert system shell for prototyping knowledge-based systems. AiGerm provides an interface between the programming language and Germ.

Hashim, Safaa H.↗

DOE OSTI2024

a priori uncertainty quantification of reacting turbulence closure models using Bayesian neural networks

While many physics-based closure model forms have been posited for the sub-filter scale (SFS) in large eddy simulation (LES), vast amounts of data available from direct numerical simulations (DNS) create opportunities to leverage data-driven modeling techniques. Albeit flexible, data-driven models still depend on the dataset and the functional form of the model chosen. Increased adoption of such models requires reliable uncertainty estimates both in the data-informed and out-of-distribution regimes. Here, in this work, we employ Bayesian neural networks (BNNs) to capture both epistemic and aleatoric uncertainties in a reacting flow model. In particular, we model the filtered progress variable scalar dissipation rate which plays a key role in the dynamics of turbulent premixed flames. We demonstrate that BNN models can provide unique insights about the structure of uncertainty of the data-driven closure models. We also propose a method for the incorporation of out-of-distribution information in a BNN, which can be used for out-of-distribution query detection. The efficacy of the model is demonstrated by a priori evaluation on a dataset consisting of a variety of flame conditions and fuels.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1994

An incremental database access method for autonomous interoperable databases

We investigated a number of design and performance issues of interoperable database management systems (DBMS's). The major results of our investigation were obtained in the areas of client-server database architectures for heterogeneous DBMS's, incremental computation models, buffer management techniques, and query optimization. We finished a prototype of an advanced client-server workstation-based DBMS which allows access to multiple heterogeneous commercial DBMS's. Experiments and simulations were then run to compare its performance with the standard client-server architectures. The focus of this research was on adaptive optimization methods of heterogeneous database systems. Adaptive buffer management accounts for the random and object-oriented access methods for which no known characterization of the access patterns exists. Adaptive query optimization means that value distributions and selectives, which play the most significant role in query plan evaluation, are continuously refined to reflect the actual values as opposed to static ones that are computed off-line. Query feedback is a concept that was first introduced to the literature by our group. We employed query feedback for both adaptive buffer management and for computing value distributions and selectivities. For adaptive buffer management, we use the page faults of prior executions to achieve more 'informed' management decisions. For the estimation of the distributions of the selectivities, we use curve-fitting techniques, such as least squares and splines, for regressing on these values.

Roussopoulos, Nicholas↗

NASA NTRS1991

An Object-oriented Query Processor that Produces Monotonically Improving Approximate Answers

The paper describes an object-oriented query processor that makes approximate answers available if there is not enough time to produce an exact answer or if part of the database is unavailable. The accuracy of the approximate result produces improves monotonically with the amount of data retrieved to produce the result. The query processing algorithm is based on an approximate relational data model and works within a standard relational algebra framework. The query processor maintains an object-oriented view on an underlying level and can be implemented on a relational database system with little change to the relational architecture. We show how a monotone query processing strategy can be implemented, making effective use of semantic information presented by the object-oriented view.

Vrbsky, S. V.↗

NASA NTRS2019

Biological CubeSats: What Have We Learned so Far and What Is Next?

Since Apollo 17 in 1972, NASA has sent no humans or other biological organisms outside of Earth's protective magnetosphere. Recently, NASA has set its sights on human exploration in deep space, with an ambitous plan to put astronauts back on the Moon by 2024 and to eventually land human missions on Mars. Such missions will require significant countermeasures, likely both technological and biomedical, to protect biology from chronic radiation exposure. CubeSats can inform these countermeasures by querying relevant space environments with model organisms.NASA has launched five biological CubeSat missions into low-Earth orbit (LEO). GeneSat-1 was launched in 2006 to study gene expression and increase our knowledge of how spaceflight affects microbes. Similar life-support technologies were then used in PharmaSat and O/OREOS, which launched in 2009 and 2010, respectively. PharmaSat contained optical systems to examine how yeast cells responded to an antifungal treatment. One of O/OREOS payloads, SESLO (Space Environment Survivability of Living Organisms), housed dormant microorganisms, which were rehydrated on orbit to track alterations to growth and metabolism induced by microgravity and radiation. In 2014, NASA launched SporeSat to study the mechanisms of plant cell gravity sensing using lab-on-a-chip devices. Most recently, in 2017, NASA launched EcAMSat (E. coli AntiMicrobial Satellite), which investigated the effects of microgravity on antibiotic resistance of a pathogenic bacterium. Each one of these missions increased our understanding of the biological effects of spaceflight in LEO, while refining technologies and imparting valuable lessons to the next generation of CubeSats.CubeSats housing translational biological models are therefore ideal for defining the hazards of deep space travel, as they can provide critical data over relevant durations. BioSentinel, a next-generation deep-space CubeSat, is planned to launch as a secondary payload on Artemis 1 in 2020. BioSentinel will study the DNA damage response to deep space radiation in yeast.

Santa Maria, Sergio R.↗

NASA NTRSDate not supplied

Developing Technologies for Biological Experiments in Deep Space

NASA Ames Research Center is the leader in developing autonomous nanosatellites or CubeSats to address strategic knowledge gaps about the effects of space travel on biological organisms, including GeneSat, PharmaSat, and EcAMSat. Now that NASA has set its sights on human exploration in deep space, such missions require significant technological and biomedical countermeasures to protect astronauts from chronic radiation exposure. CubeSats can inform these countermeasures by querying relevant space environments with model organisms and/or biosensors. BioSentinel will be the first interplanetary CubeSat to study the biological response to space radiation outside low Earth orbit in almost 50 years. BioSentinel is an autonomous platform able to support biology and to investigate the effects of space radiation on a model organism in interplanetary deep space. It will fly onboard Artemis-1, from which it will be deployed on a lunar fly-by trajectory and into a heliocentric orbit. BioSentinel, a 6U CubeSat (1U = 10-cm cube), will measure the DNA damage response to ambient space radiation in a model organism, which will be compared to information provided by an onboard radiation spectrometer and to data obtained on the ISS and on Earth. Even though the primary objective of the mission is to develop an autonomous spacecraft capable of conducting biological experiments in deep space, the 4U BioSensor science payload contained within the free-flyer is an adaptable instrument that can perform bio measurements with different microorganisms and in multiple space environments, including the ISS, lunar gateway, and on the surface of the Moon. Thus, nanosatellites like BioSentinel can be used to study the effects of both reduced gravity and space radiation and can house different organisms to answer specific science questions. In addition to their flexibility, nanosatellites also provide a low-cost alternative to more complex and larger missions, and require minimal crew support, if any

biosenses↗

NASA NTRSDate not supplied

Developing Technologies for Biological Experiments in Deep Space

NASA Ames Research Center is the leader in developing autonomous nanosatellites or CubeSats to address strategic knowledge gaps about the effects of space travel on biological organisms, including GeneSat, PharmaSat, and EcAMSat. Now that NASA has set its sights on human exploration in deep space, such missions require significant technological and biomedical countermeasures to protect astronauts from chronic radiation exposure. CubeSats can inform these countermeasures by querying relevant space environments with model organisms and/or biosensors. BioSentinel will be the first interplanetary CubeSat to study the biological response to space radiation outside low Earth orbit in almost 50 years. BioSentinel is an autonomous platform able to support biology and to investigate the effects of space radiation on a model organism in interplanetary deep space. It will fly onboard Artemis-1, from which it will be deployed on a lunar fly-by trajectory and into a heliocentric orbit. BioSentinel, a 6U CubeSat (1U = 10-cm cube), will measure the DNA damage response to ambient space radiation in a model organism, which will be compared to information provided by an onboard radiation spectrometer and to data obtained on the ISS and on Earth. Even though the primary objective of the mission is to develop an autonomous spacecraft capable of conducting biological experiments in deep space, the 4U BioSensor science payload contained within the free-flyer is an adaptable instrument that can perform bio measurements with different microorganisms and in multiple space environments, including the ISS, lunar gateway, and on the surface of the Moon. Thus, nanosatellites like BioSentinel can be used to study the effects of both reduced gravity and space radiation and can house different organisms to answer specific science questions. In addition to their flexibility, nanosatellites also provide a low-cost alternative to more complex and larger missions, and require minimal crew support, if any.

biosenses↗

NASA NTRS2022

Evolution of Biological Satellites: From Low Earth Orbit to NASA’s BioSentinel Deep Space Mission

NASA has set its sights on human exploration in deep space with the Artemis missions, with an ambitious plan to put astronauts back on the Moon and to eventually land human missions on Mars. Such missions will require significant countermeasures, likely both technological and biomedical, to protect biology from chronic radiation exposure. Small satellites like CubeSats can inform these countermeasures by querying relevant space environments with model organisms over relevant durations. NASA has launched five biological CubeSats into low Earth orbit (LEO) from GeneSat in 2006 to EcAMSat in 2017. Each one of these missions increased our understanding of the effects of spaceflight, while refining technologies and imparting valuable lessons to the next generation of CubeSats. The Artemis I rocket will carry ten CubeSats, each of them with its own objective. One in particular, BioSentinel, will conduct the first study of the biological response to interplanetary space radiation beyond LEO since Apollo 17. Once it reaches its heliocentric orbit – after a short lunar fly-by – BioSentinel will measure the DNA damage response to ambient radiation in a model organism, the budding yeast Saccharomyces cerevisiae, which will be compared to information provided by an onboard radiation sensor and to data obtained in LEO (on ISS) and on Earth. Once in interplanetary space, fluidic cards containing desiccated yeast cells will be activated by growth medium addition at different time points throughout the mission. Growth and metabolic activity will be tracked continuously via optical density. BioSentinel is a complete, autonomous spacecraft capable of conducting experiments in deep space. Its 4U BioSensor payload is a fully automated and adaptable platform that can perform biological measurements with a range of microorganisms in multiple space environments, including the ISS, free flyers, and other platforms like the Lunar Gateway and lander vehicles.

Sergio R Santa Maria↗

NASA NTRSDate not supplied

Dragonfly Rotor Optimization using Machine Learning Applied to an OVERFLOW Generated Airfoil Database

NASA’s 4th New Frontiers Mission is the Titan Dragonfly relocatable lander. This coaxial quadrotor vehicle will be launched on a rocket to Titan in 2028. Following a gravity assisted Earth flyby and an approximate 6-year transit, Dragonfly will enter the Titan atmosphere around 2034 with the goal of exploring Titan’s pre-biotic chemistry and habitability. The multirotor design for this unique application has continually evolved since 2016 with constraints such as Titan’s cryogenic atmosphere at 95 Kelvin (-288 F), gravity 14% that of Earth’s, atmospheric density 440% of standard sea-level air, and the inability to test the entire system together under all these conditions until the first flight on Titan. This paper focuses on rotor design aspects of the Dragonfly lander and introduces a novel framework for multirotor design optimization considering multiple flight conditions. The methodology leverages machine learning methods and is demonstrated in the context of Dragonfly. A new OVERFLOW Machine Learning Airfoil Performance (PALMO) database is first presented. PALMO is then wrapped inside a Bayesian optimization framework and applied to a 4-rotor system (one side of the Dragonfly lander). Training data is generated on each iteration of the optimization using the CAMRAD-II comprehensive analysis software to evaluate successive rotor designs in multiple relevant flight conditions. An optimal design for the 4-rotor system was found with approximately 900 rotor designs analyzed in CAMRAD-II, which required 9 million queries of the PALMO surrogate models. This demonstration case evaluated 10,000,000 potential candidate rotor designs in 5.5 hours on 114 CPU cores using uniform inflow, and in 27.8 hours using the prescribed wake model. This work thus enables mid-fidelity rotor design optimization without requiring access to high-performance computing.

Dragonfly↗

DOE OSTI2026

BrickQA: Bridging the Semantic Gap in Building Operations with Dynamic Graph Exploration

While standardized ontologies like the Brick schema address data heterogeneity in Building Automation Systems (BAS), accessing this semantic data remains a challenge as domain experts often lack the expertise to formulate complex SPARQL queries. To bridge this gap, we present BrickQA, a Large Language Model (LLM)-based framework that translates natural language into executable SPARQL queries through structured query decomposition, dynamic schema exploration, and inline validation. BrickQA utilizes an iterative reasoning agent to actively navigate graph topology through dynamic exploration actions without requiring exhaustive context injection or model fine-tuning. This approach effectively mitigates hallucinations, particularly in large-scale building knowledge graphs. Empirical evaluation on BuildingQA, a standardized benchmark, demonstrates that BrickQA significantly outperforms ReAct baselines, delivering a 0.291–0.355 absolute F1 improvement while achieving 3 × –12.7 × higher token cost-efficiency. Beyond these metrics, the framework maintains structural fidelity across heterogeneous buildings and remains resilient to ambiguous queries without requiring site-specific fine-tuning. Furthermore, a case study on operational analytics validates the framework’s capability to handle temporal and aggregation constraints, effectively transforming abstract semantic models into actionable facility management insights.1

Ko, Yun-Dam↗