Search NASA⌕ Search

SEARCH · Search NASA

Results for “Language model”

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 649 records · Page 36

NeuroSymbolic Approaches as a Vector for Assured Artificial Intelligence

The deployment of artificial intelligence systems in critical applications requires higher levels of assurance for safety, security, and interpretability. While neurosymbolic (NESY) approaches combining neural networks with symbolic reasoning offer potential advantages for assured AI, existing differentiable neurosymbolic frameworks face significant limitations including computational overhead and performance constraints. This report investigates the ISED (InferSampleEstimateDescend) framework as an alternative approach that enables neurosymbolic learning without requiring endtoend differentiability. We evaluate ISED’s utility for geointelligence applications by comparing neurosymbolic models against standard neural networks on aircraft classification tasks using the RarePlanes and MTARSI imagery datasets. Our results demonstrate that while ISEDbased models achieve slightly lower accuracy (89.7% vs 92.1% on RarePlanes; 91.1% vs 92.5% on MTARSI), they provide critical explainability capabilities that enable tracing incorrect predictions back to specific attribute misclassifications. We also present an automated pipeline that generates both attributeclass mappings and neurosymbolic model architectures from natural language descriptions, significantly reducing the manual effort required for NESY model deployment. These findings suggest that ISED offers a promising direction for developing assured AI systems where interpretability and reasoning transparency are prioritized alongside performance.

97 MATHEMATICS AND COMPUTING↗

MPI + OpenACC: Accelerating radiation transport mini-application, minisweep, on heterogeneous systems

According to the article, architectures are rapidly evolving, and exascale machines are expected to offer billion-way concurrency. We need to rethink algorithms, languages and programming models among other components in order to migrate large scale applications and explore parallelism on these machines. Although directive-based programming models allow programmers to worry less about programming and more about science, expressing complex parallel patterns in these models can be a daunting task especially when the goal is to match the performance that the hardware platforms can offer. One such pattern is wavefront. This paper extensively studies a wavefront-based miniapplication for Denovo, a production code for nuclear reactor modeling. We parallelize the Koch–Baker–Alcouffe (KBA) parallel-wavefront sweep algorithm in the main kernel of Minisweep (the miniapplication) using CUDA 9.0, OpenMP 4.0 (SIMD) and OpenACC 2.6. Our OpenACC implementation running on NVIDIA’s next-generation Volta GPU boasts an 85.06x speedup over serial code, which is larger than CUDA’s 83.72x speedup over the same serial implementation. We also explore the scalability of our solution using MPI to decompose our simulation domain, allowing us to run on many nodes and accelerators present in state-of-the-art HPC systems. Our parallelization effort across platforms also motivated us to define an abstract parallelism model that is architecture independent, with a goal of creating software abstractions that can be used by applications employing the wavefront sweep motif.

Computer Science↗

The effective field theory of dark energy

We propose a universal description of dark energy and modified gravity that includes all single-field models. By extending a formalism previously applied to inflation, we consider the metric universally coupled to matter fields and we write in terms of it the most general unitary gauge action consistent with the residual unbroken symmetries of spatial diffeomorphisms. Our action is particularly suited for cosmological perturbation theory: the background evolution depends on only three operators. All other operators start at least at quadratic order in the perturbations and their effects can be studied independently and systematically. In particular, we focus on the properties of a few operators which appear in non-minimally coupled scalar-tensor gravity and galileon theories. In this context, we study the mixing between gravity and the scalar degree of freedom. We assess the quantum and classical stability, derive the speed of sound of fluctuations and the renormalization of the Newton constant. The scalar can always be de-mixed from gravity at quadratic order in the perturbations, but not necessarily through a conformal rescaling of the metric. We show how to express covariant field-operators in our formalism and give several explicit examples of dark energy and modified gravity models in our language. Finally, we discuss the relation with the covariant EFT methods recently appeared in the literature.

79 ASTRONOMY AND ASTROPHYSICS↗

Characterizing Quantum Classifier Utility in Natural Language Processing Workflows

Quantum Natural Language Processing (QNLP) develops natural language processing (NLP) models for deployment on quantum computers. We explore feature and data prototype selection techniques to address challenges posed by encoding high dimensional features. Our study builds quantum circuit classifiers that includes classical feature pre-processing, quantum embedding and quantum model training. The quantum models are built on 4 or 6 qubits and the quantum neural network (QNN) uses the established bricklayer design. We compare the dependence of model performance (in terms of accuracy and F1 scores) on feature length, embedding gates and parameterized unitary design. We compare the performance of quantum machine learning models to classical convolution neural network model (CNN) on binary and multi-class classification tasks using two datasets of synthetic features and labels. The first is the ECP-CANDLE P3B3 dataset a corpus of synthetically generated cancer pathology reports. The second dataset is extracted from well-known benchmark dataset (MADELON) - features are generated with a combination of informative, repeated and uninformative features. Both datasets are used for binary classification and multi-class classification with 3 classes. We observe robust, accurate performance from all models on the binary classification tasks, but multiclass classification is a challenge for the quantum models-there is a notable decrease in accuracy when using 3 classes. Overall the performance is comparable in terms of recall and accuracy between QNNs and CNNs, even with large datasets. These results provide a point of comparison between quantum and classical models on real-world datasets.

Hamilton, Kathleen↗

Abstractions and Directives for Adapting Wavefront Algorithms to Future Architectures

Architectures are rapidly evolving, and exascale machines are expected to offer billion-way concurrency. We need to rethink algorithms, languages and programming models among other components in order to migrate large scale applications and explore parallelism on these machines. Although directive-based programming models allow programmers to worry less about programming and more about science, expressing complex parallel patterns in these models can be a daunting task especially when the goal is to match the performance that the hardware platforms can offer. One such pattern is wavefront. This paper extensively studies a wavefront-based miniapplication for Denovo, a production code for nuclear reactor modeling. We parallelize the Koch-Baker-Alcouffe (KBA) parallel-wavefront sweep algorithm in the main kernel of Minisweep (the miniapplication) using CUDA, OpenMP and OpenACC. Our OpenACC implementation running on NVIDIA's next-generation Volta GPU boasts an 85.06x speedup over serial code, which is larger than CUDA's 83.72x speedup over the same serial implementation. Our experimental platform includes SummitDev, an ORNL representative architecture of the upcoming Summit supercomputer. Our parallelization effort across platforms also motivated us to define an abstract parallelism model that is architecture independent, with a goal of creating software abstractions that can be used by applications employing the wavefront sweep motif.

Searles, Robert↗

Modelica Builder (ModBuild)

Modelica is a modeling and simulation language similar to Matlab/Simulink. Modelica has many advantages, which will not be discussed here, over conventional software. The software project implements a parser of the Modelica language allowing for easy-to-implement transformations of Modelica files.

Long, Nicholas↗

pnnl/SciTune

Scientific multimodal instruction tuning with large language and vision models.

Horawalavithana, Sameera [Pacific Northwest Nation↗

Osprey Framework v0.2.2

The Alpha Berkeley Framework is a software architecture for building agentic AI systems that coordinate multi-step workflows in scientific and industrial environments. It is based on a plan-first orchestration model, where natural language requests are translated into execution plans with explicit dependencies and optional human approval. The framework includes capability classification, which selects relevant tools on a per-task basis to keep orchestration efficient as the number of available tools grows. It incorporates task extraction methods that compress conversational context and integrate external resources such as databases, APIs, and knowledge bases into structured, machine-readable tasks. Execution is supported by modular services with checkpointing, artifact management, and error handling, allowing workflows to be paused, inspected, and resumed. The system is designed for deployment in production environments, supporting both local and containerized execution as well as integration with HPC clusters. Interfaces include command-line tools, browser-based workflows, and containerized services. The framework has been demonstrated in tutorial examples and deployed at the Advanced Light Source, where it coordinates accelerator control and analysis workflows.

Hellert, Thorsten [Lawrence Berkeley National Labo↗

AEDAM: Whole Program Adaptive Error Detection and Mitigation—Year 3 Report

In Year 3, MIT was primarily responsible for the effort on Software Characterization, with the following milestones: 1. Completed design of domain-specific language for fault models 2. Completed design of program logic for verification 3. Completed evaluation of relational verification system for jacobi, steepest descent, and conjugate gradient 4. Completed development of relational verification system 5. Completed evaluation of relational verification system

97 MATHEMATICS AND COMPUTING↗

Standardization of Smart Contracts for Energy Markets and Operation

This work presents a formal review of smart contracts, including definitions, technical requirements, and potential power and energy-related use cases. This includes in-depth discussions covering cybersecurity, legality and interoperability goals that must be taken into consideration by potential end-users. The paper presents a first attempt towards the standardization of smart contracts (SCs) within the field of power and energy as a work in progress activity under the IEEE Standards Association (IEEE SA) P2418.5 Working Group. This work also proposes a holistic, language-agnostic reference model that is intended to accelerate the adoption of Distributed Ledger Technology (DLT) by industry stakeholders by providing standardized processes. Finally, the paper discusses key takeaways that must continue to be developed to increase SC usage within the energy industry.

Blockchain, smart contracts, DLT↗

AI-powered topic modeling: comparing LDA and BERTopic in analyzing opioid-related cardiovascular risks in women

Topic modeling is a crucial technique in natural language processing (NLP), enabling the extraction of latent themes from large text corpora. Traditional topic modeling, such as Latent Dirichlet Allocation (LDA), faces limitations in capturing the semantic relationships in the text document although it has been widely applied in text mining. BERTopic, created in 2022, leveraged advances in deep learning and can capture the contextual relationships between words. In this work, we integrated Artificial Intelligence (AI) modules to LDA and BERTopic and provided a comprehensive comparison on the analysis of prescription opioid-related cardiovascular risks in women. Opioid use can increase the risk of cardiovascular problems in women such as arrhythmia, hypotension etc. 1,837 abstracts were retrieved and downloaded from PubMed as of April 2024 using three Medical Subject Headings (MeSH) words: “opioid,” “cardiovascular,” and “women.” Machine Learning of Language Toolkit (MALLET) was employed for the implementation of LDA. BioBERT was used for document embedding in BERTopic. Eighteen was selected as the optimal topic number for MALLET and 23 for BERTopic. ChatGPT-4-Turbo was integrated to interpret and compare the results. The short descriptions created by ChatGPT for each topic from LDA and BERTopic were highly correlated, and the performance accuracies of LDA and BERTopic were similar as determined by expert manual reviews of the abstracts grouped by their predominant topics. The results of the t-SNE (t-distributed Stochastic Neighbor Embedding) plots showed that the clusters created from BERTopic were more compact and well-separated, representing improved coherence and distinctiveness between the topics. Our findings indicated that AI algorithms could augment both traditional and contemporary topic modeling techniques. In addition, BERTopic has the connection port for ChatGPT-4-Turbo or other large language models in its algorithm for automatic interpretation, while with LDA interpretation must be manually, and needs special procedures for data pre-processing and stop words exclusion. Therefore, while LDA remains valuable for large-scale text analysis with resource constraints, AI-assisted BERTopic offers significant advantages in providing the enhanced interpretability and the improved semantic coherence for extracting valuable insights from textual data.

Research & Experimental Medicine↗

Using Topic Modeling and Text Embeddings to Predict Deleted Tweets

Predictive models for tweet deletion have been a relatively unexplored area of Twitter-related computational research. We first approach the deletion of tweets as a spam detection problem, applying a small set of handcrafted features to improve upon the current state-of-the- art in predicting deleted tweets. Next, we apply our approach to a dataset of deleted tweets that better reflects the current deletion rate. Since tweets are deleted for reasons beyond just the presence of spam, we apply topic modeling and text embeddings in order to capture the semantic content of tweets that can lead to tweet deletion. Our goal is to create an effective model that has a low-dimensional feature space and is also language-independent. A lean model would be computationally advantageous processing high-volumes of Twitter data, which can reach 9,885 tweets per second. Our results show that a small set of spam-related features combined with word topics and character-level text embeddings provide the best f1 when trained with a random forest model. The highest precision of the deleted tweet class is achieved by a modification of paragraph2vec to capture author identity.

Potash, Peter J.↗

Kitaev model on a quantum computer using VQE with Majorana fermions

We study the simulation of the Kitaev spin model on quantum computers. In particular we focus on the models defined on the honeycomb, and square-octagon lattices. Using a fermionic language to describe these models reveals a region of the parameter space that is exactly solvable. We explore an ansatz that is capable of expressing the ground state in the exactly solvable region of the parameter space and extend it outside this region with good accuracy. Doing the calculation using fermions, while requiring the introduction of a non-local map from the fermionic Hilbert space to that of qubits, offers the potentially interesting application of realizing non-abelian anyons on quantum computers, and can also lead to a reduction in the number of qubits required by half.

Jahin, Ammar↗

Latent Variable Network Modeling

lvnm Is a library for fitting latent variable network models within the R programming language. The code focuses on the Stochastic Block Model, Weighted Stochastic Block Model, and Dynamic Stochastic Block Model. Features include simulation methods, estimation methods, diagnostic plots and anomaly detection routines for network data.

Dabbs, Beau↗

Selective Information Extraction Strategies for Cancer Pathology Reports with Convolutional Neural Networks

To trust model predictions, it is important to ensure new data scored by the model comes from the same population used for model training. If the model is used to score new data different than the model’s training data, then predictions and model performance metrics cannot be trusted. Identifying and excluding these anomalous data points is an important task when using models in the real world. Traditional machine learning algorithms and classifiers don’t have the capability to abstain in this case. Here we propose a data-novelty detection algorithm for the Convolutional Neural Network classifier, yielding a rejection score for each new data point scored. It is a post-modeling procedure which examines the distribution of convolution filters to determine if the prediction should be trusted. We apply this algorithm to an information extraction model for a natural language text corpus. We evaluated the algorithm performance using a primary cancer site classification model applied to cancer pathology reports. Results demonstrate that the algorithm is an effective way to exclude cancer pathology reports from model scoring when they do not contain the expected information necessary to accurately classify the primary cancer type.

Yoon, Hong-Jun↗

Designing a unified programming model for heterogeneous machines

While high-efficiency machines are increasingly embracing heterogeneous architectures and massive multithreading, contemporary mainstream programming languages reflect a mental model in which processing elements are homogeneous, concurrency is limited, and memory is a flat undifferentiated pool of storage. Moreover, the current state of the art in programming heterogeneous machines tends towards using separate programming models, such as OpenMP and CUDA, for different portions of the machine. Both of these factors make programming emerging heterogeneous machines unnecessarily difficult. We describe the design of the Phalanx programming model, which seeks to provide a unified programming model for heterogeneous machines. It provides constructs for bulk parallelism, synchronization, and data placement which operate across the entire machine. Our prototype implementation is able to launch and coordinate work on both CPU and GPU processors within a single node, and by leveraging the GASNet runtime, is able to run across all the nodes of a distributed-memory machine.

Garland, Michael↗

Virtual Engineering Software Framework for Integrated Biomass Conversion Modeling

This presentation covers the design and implementation of a software tool to systematically connect computational models of unit operations to simulate an integrated process of low-temperature conversion of biomass to fuel. This virtual engineering (VE) software was designed with the overarching goal of connecting unit models written in various programming languages and requiring different computational resources within a single, flexible framework. The models and features currently considered for the VE library include mechanistic models for pretreatment, enzymatic hydrolysis, and aerobic bioreaction; high-fidelity computational fluid dynamics (CFD) simulations for enzymatic hydrolysis and aerobic bioreaction; and the capability to perform techno-economic analyses (TEA) using Aspen Plus, a commercial software package. The CFD models require access to high-performance computing (HPC) resources, so in addition to handling multiple programming languages and interfaces, the VE software must also be capable of interacting with an HPC scheduler to submit, run, and post-process jobs. Using the Python programming language, a new VE software package has been developed that contains functionality to manage the input-output communication between various unit models, schedule simulations to run on NREL's HPC and analyze those results, and interface with existing TEA software workflows. A Jupyter-notebook GUI was also created to solicit user input and provide documentation. In cases where multiple models for a particular unit-operation exist, selection between models is accomplished through a simple checkbox, with the appropriate inputs and outputs being parsed and converted seamlessly in the background. Each operation makes use of a different programming language, but the flow of information from pretreatment to enzymatic hydrolysis to bioreaction is managed with an intuitive, centralized file-communication strategy. In this talk, the programming approach and implementation details of the notebook are presented for multiple possibilities of the conversion process, including a demonstration of the ability to manage HPC resources. Additionally, an example of a sensitivity study of treatment parameters governing the overall conversion outcome is shown which highlights the ease of defining new problems using the VE Notebook workflow and leads into a discussion of ongoing work to enable outer-loop optimization studies.

biofuel↗

Symplectic multi-particle tracking on GPUs

A symplectic multi-particle tracking model is implemented on the Graphic Processing Units (GPUs) using the Compute Unified Device Architecture (CUDA) language. The symplectic tracking model can preserve phase space structure and reduce non-physical effects in long term simulation, which is important for beam property evaluation in particle accelerators. Though this model is computationally expensive, it is very suitable for parallelization and can be accelerated significantly by using GPUs. In this paper, we optimized the implementation of the symplectic tracking model on both single GPU and multiple GPUs. Using a single GPU processor, the code achieves a factor of 2-10 speedup for a range of problem sizes compared with the time on a single state-of-the-art Central Processing Unit (CPU) node with similar power consumption and semiconductor technology. It also shows good scalability on a multi-GPU cluster at Oak Ridge Leadership Computing Facility. In an application to beam dynamics simulation, the GPU implementation helps save more than a factor of two total computing time in comparison to the CPU implementation.

43 PARTICLE ACCELERATORS↗