SEARCH · Search NASA

Results for “knowledge graphs”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 379 records · Page 21

All sources NASA NTRS DOE OSTI

NASA NTRS1999

Knowledge Discovery Process for Characterization of Materials Failure Mechanism

It is the intent of this project to provide a platform to visualize the various data collected from stress-strain testing of composite ceramic matrix materials. The data collected from the stress-strain tests are acoustic emissions (AE). As a material is subjected to a stress-strain test, various failure mechanisms occur in the material. The recorded sounds emitted during the test may correspond to various failure mechanisms. This project, thus, will give a possible way to visualize the data and data derived from the recorded AE. The stress-strain testing was performed on several composite matrix material combinations. Each of these tests produced anywhere from 1000 to 10,000+ AE events. For each AE event recorded, several characteristics in both the time and frequency domains are created. This project has two goals. First, this project will provide a summation page for a selected waveform. This page will include all of the characteristics determined from the AE event waveform along with graphs of the AE event waveform and its corresponding Power Spectrum. The other function of this project is to retrieve and display selected AE event waveforms for comparison.

Cios, Krzysztof J.↗

DOE OSTI2022

Detecting anomalous sequences in electronic health records using higher-order tensor networks

Detecting anomalous sequences is an integral part of building and protecting modern large-scale health information technology (HIT) systems. These HIT systems generate a large volume of records of patients’ state and significant events, which provide a valuable resource to help improve clinical decisions, patient care processes, and other issues. However, detecting anomalous sequences in electronic health records (EHR) remains a challenge in healthcare applications for several reasons, including imbalances in the data, complexity of relationships between events in the sequence, and the curse of dimensionality. Conventional anomaly detection methods use the finite sequence of events to discriminate sequences. They fail to incorporate salient event details under variable higher-order dependencies (e.g., duration between events) that can provide better discrimination of sequences in their models. To address this problem, we propose event sequence and subsequence anomaly detection algorithms that (1) use network-based representations of interactions in the data, (2) account for variable higher-order dependencies in the data, and (3) incorporate events duration for adequate discrimination of the data. The proposed approach identifies anomalies by monitoring the change in the graph after the test sequence is removed from the network. The change is quantified using graph distance metrics so that dramatic changes in the network can be attributed to the removed sequence. Furthermore, the proposed subsequence algorithm recommends plausible paths and salient information for the detected anomalous subsequences. Our results show that the proposed event sequence anomaly detection algorithm outperforms the baseline methods for both synthetic data and real-world EHR data.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

DOE OSTI2020

Hypergraph Analytics of Domain Name System Relationships

We report on the use of novel mathematical methods in hypergraph analytice over a large quantity of DNS data. Hypergraphs generalize graphs, as used in network science, to better model complex multiway relations in cyber data. Specifically, casting DNS data from Georgia Tech's ActiveDNS repository as hypergraphs allows us to fully represent the interactions between {\em collections} of domains and IP addresses. To facilitate large-scale analytics, we fielded an analytical pipeline of two capabilities. HyperNetX (HNX) is a Python package for the exploration and visualization of hypergraphs, acting as a frontend. For the backend, the Chapel HyperGraph Library (CHGL) is a library for high performance hypergraph analytics written in the exascale programming language Chapel. CHGL was used to process gigascale DNS data, performing compute-intensive calculations for data reduction and segmentation. Identified portions are then sent to HNX for both exploratory analysis and knowledge discovery targeting known tactics, techniques, and procedures.

Joslyn, Cliff A.↗

DOE OSTI2016

An Introduction to the FCRD Transmutation Fuels Handbook 2015

Transmutation of minor actinides such as Np, Am, and Cm in spent nuclear fuel is of international interest because of its potential for reducing the long-term health and safety hazards caused by the radioactivity of the spent fuel. For this reason, the DOE Fuel Cycle Research and Development (FCRD) Advanced Fuels Campaign (AFC) has been performing research on nuclear fuel technologies that could be used in conjunction with a future actinide transmutation mission. One important approach to transmutation involves incorporating the minor actinides into U-Pu-Zr alloys, which can be used as fuel in fast reactors. It is, therefore, important to understand the properties of U-Pu-Zr alloys. The Idaho National Laboratory has recently published a handbook intended to summarize key properties of these alloys for researchers. This handbook focuses on phases and key thermophysical properties of elements and alloys in the U-Pu-Zr system. It is envisioned as the first of a series, which will serve as a summary of current knowledge about important properties of transmutation fuels. Future volumes will include information about properties and materials not covered in the first edition, as well as updates to information in this edition of the handbook. The handbook is intended to serve two audiences. One audience is researchers, who may find it useful to know what has been measured, where it has been published, and what kinds of information are needed. A second audience is modelers, who need a concise summary of information about specific properties and the accuracy with which they are known. The two audiences have different needs, and the handbook is a compromise intended to be useful to both. Therefore, it includes summaries of research results and needs, but generally does not present the original data. It also includes numerous graphs and, where available, equations that provide convenient approximations to materials properties for modelers. It is important to understand that most of the equations provided in this handbook are derived by fitting polynomials to data and have no physical basis; while they can be used with caution for design studies, fuel modelers will probably want to use the original experimental data to develop or validate their own equations and/or models. Although the handbook includes some citations to research involving development of models, its primary focus is experimental data. Many of the measurements of the U-Pu-Zr system were made before 1980. Where possible, the handbook relies on previous reviews of experimental data rather than presenting new interpretations of the old information. It is expected that researchers will refer to the original literature for details that are not presented in the handbook. Metals and alloys in the U-Pu-Zr system are uniquely difficult to study for a number of reasons. Experimental designs may need to be modified to allow researchers to work with these hazardous materials safely. Kinetics of phase transformations are commonly sluggish, and it is highly unlikely that all of the samples in previous research had equilibrium phases and microstructures. Thermal cycling effects (changes in sample characteristics that are not fully reversed during cooling) are commonly reported and may be significant. Careful control of impurities (particularly oxygen) during sample fabrication and data collection is both crucial and difficult, and concentrations below 100 ppm in samples may significantly affect thermophysical properties. For all of these reasons, differences between measured values for similar alloys are commonly far larger than the estimated errors for individual measurements. Further research on well-characterized materials with careful control of impurities is needed for all of the alloys discussed here. The 2015 FCRD Handbook summarizes currently available information about U, Pu, Zr, and their binary and ternary alloys. It contains information about phase diagrams and related information (including phases and phase transformations); heat capacity, entropy, and enthalpy; thermal expansion; and thermal conductivity and diffusivity. In addition to presenting information about materials properties, it attempts to provide information about how well the property is known and how much variation exists between measurements. Although the handbook includes some references to publications about modeling, its primary focus is experimental data. (authors)

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

NASA NTRS2004

Advanced Technology Lifecycle Analysis System (ATLAS)

Developing credible mass and cost estimates for space exploration and development architectures require multidisciplinary analysis based on physics calculations, and parametric estimates derived from historical systems. Within the National Aeronautics and Space Administration (NASA), concurrent engineering environment (CEE) activities integrate discipline oriented analysis tools through a computer network and accumulate the results of a multidisciplinary analysis team via a centralized database or spreadsheet Each minute of a design and analysis study within a concurrent engineering environment is expensive due the size of the team and supporting equipment The Advanced Technology Lifecycle Analysis System (ATLAS) reduces the cost of architecture analysis by capturing the knowledge of discipline experts into system oriented spreadsheet models. A framework with a user interface presents a library of system models to an architecture analyst. The analyst selects models of launchers, in-space transportation systems, and excursion vehicles, as well as space and surface infrastructure such as propellant depots, habitats, and solar power satellites. After assembling the architecture from the selected models, the analyst can create a campaign comprised of missions spanning several years. The ATLAS controller passes analyst specified parameters to the models and data among the models. An integrator workbook calls a history based parametric analysis cost model to determine the costs. Also, the integrator estimates the flight rates, launched masses, and architecture benefits over the years of the campaign. An accumulator workbook presents the analytical results in a series of bar graphs. In no way does ATLAS compete with a CEE; instead, ATLAS complements a CEE by ensuring that the time of the experts is well spent Using ATLAS, an architecture analyst can perform technology sensitivity analysis, study many scenarios, and see the impact of design decisions. When the analyst is satisfied with the system configurations, technology portfolios, and deployment strategies, he or she can present the concepts to a team, which will conduct a detailed, discipline-oriented analysis within a CEE. An analog to this approach is the music industry where a songwriter creates the lyrics and music before entering a recording studio.

O'Neil, Daniel A.↗

DOE OSTI2015

Inter-Procedural Resource Sharing in High Level Synthesis through Function Proxies

Modular design is becoming increasingly important in High Level Synthesis (HLS) flows. Current HLS flows generate hierarchical and modular designs that mimic the structure and call graph of input specification translating functions into modules. Function calls are translated instantiating the callee module in the data-path of its caller, allowing for resource sharing when the same function is called multiple times. However, if two different callers invoke the same function, current HLS flows cannot share the instance of the module between the two callers, even if they invoke the function in a mutually exclusive way. In this paper, we propose a methodology that enables sharing of (sub)modules across modules boundaries. Sharing is obtained through function proxies, which act as forwarders of function calls in the original specification to shared modules without adding performance penalties. Building on the concept of function proxies, we propose a methodology and the related components to perform HLS of function calls through function pointers, without requiring complete static knowledge of the alias set (point-to set). We show that module sharing through function proxies provides valuable area savings without significant impacts on the execution delays, and that our synthesis approach for function pointers enables dynamic polymorphism.

HLS, function proxy, FPGA, modular HLS,↗

DOE OSTI2023

A Fine-grained Asynchronous Bulk Synchronous parallelism model for PGAS applications

The Partitioned Global Address Space (PGAS) model is well suited for executing irregular applications on cluster-based systems, due to its efficient support for short, one-sided messages. Separately, the actor model has been gaining popularity as a productive asynchronous message-passing approach for distributed objects in enterprise and cloud computing platforms, typically implemented in languages such as Erlang, Scala or Rust. To the best of our knowledge, there has been no past work on using the actor model to deliver both productivity and scalability to irregular PGAS applications with large number of small messages. In this paper, we introduce a new programming system for PGAS applications, in which point-to-point remote operations can be expressed as fine-grained asynchronous actor messages. In our approach, the programmer does not need to worry about programming complexities related to message aggregation and termination detection. Our approach can be viewed as extending the classical Bulk Synchronous Parallelism model with fine-grained asynchronous communications within a phase or superstep. Here, we believe that our approach offers a desirable point in the productivity-performance space for PGAS applications, with more scalable performance and higher productivity relative to past approaches. Specifically, for seven irregular mini-applications from the Bale Kernels and three graph kernels executed using 2048 cores in the NERSC Cori system, our approach shows geometric mean performance improvements of ≥ 20X relative to standard PGAS versions (UPC and OpenSHMEM) while maintaining comparable productivity to those versions.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2021

Deep Analysis Net with Causal Embedding for Coal-fired Power Plant Fault Detection and Diagnosis (DANCE4CFDD)

Fault detection and diagnosis is critical to power plant operation to ensure attaining high reliability while reducing operation cost. As more renewable power is introduced to the power grid, traditional fossil power plants take on the extra burden of excessive load cycling to compensate the generation variability from renewable power. Such load cycling will pose more reliability challenges to power plant operation. There are a number of challenges faced by today’s asset health management system in coal- fired (or gas) power plants: 1) high-dimensional nonlinear interaction among multiple time series measurements; 2) high measurement variance induced by operational conditions/modes; 3) variation among asset types and plant configurations; and 4) a small number of faulty events to learn from. To cope with these challenges, today’s fielded asset health management systems rely heavily on manual efforts from domain experts and hand-crafted features or rules based on domain knowledge. Despite its role in plant reliability, such a practice is costly and hinders its scalability and sustainability, particularly when a plant undergoes modifications. The objective of this project is to develop a novel end-to-end AI learning system that is trainable (i.e., the AI representation of a complex system behavior can be directly learned from properly labeled data) for accurate fault detection and root cause analysis. The ability to create a fault detection model directly from time series could alleviate the efforts associated with today’s asset management solution development. In the course of this project, we have achieved the following: Created an AI model development environment incorporating state-of-the-art neural network architectures for rapid model development and evaluation; Developed novel learning strategies for training of fault detection model; Developed special-purpose neural network architecture embedded with variable association graph aiming for better interpretability; Developed a learning strategy to leverage a small number of faulty events for enhanced fault detection capability; Conducted detailed experimental study based on public benchmark datasets and demonstrated the effectiveness of the proposed solution; and Validated the developed system with data from both a coal-fired plant boiler dynamic simulation model and real-world coal-fired power plant covering multiple asset and fault types. Overall, the project attained a technology readiness level of TRL 5 from TRL 2 at the beginning of the project.

20 FOSSIL-FUELED POWER PLANTS↗

DOE OSTI2018

Quickest Detection for Changes in Maximal kNN Coherence of Random Matrices

This paper addresses the problem of quickest detection of a change in the maximal coherence between columns of a n p random matrix based on a sequence of matrix observations having a single unknown change point. The random matrix is assumed to have identically distributed rows and the maximal coherence is defined as the largest of the ( 2 p) correlation coefficients associated with any row. Likewise the κ nearest neighbor (kNN) coherence is defined as the κ-th largest of these correlation coefficients. The forms of the preand postchange distributions of the observed matrices are assumed to belong to the family of elliptically contoured densities with sparse dispersion matrices but are otherwise unknown. A nonparametric stopping rule is proposed that is based on the maximal kNN sample coherence between columns of each observed random matrix. This is a summary statistic that is related to a test of existence of a hub vertex in a sample correlation graph having degree at least κ. Performance bounds on the delay and false alarm performance of the proposed stopping rule are obtained in the purely high-dimensional regime where p → ∞ and n is fixed. When the prechange dispersion matrix is diagonal it is shown that, among all functions of the proposed summary statistic, the proposed stopping rule is asymptotically optimal under a minimax quickest change detection model as the stopping threshold approaches infinity. Furthermore, the theory developed also applies to sequential hypothesis testing and fixed sample size tests.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

NASA NTRS2008

Population Simulation, AKA: Grahz, Rahbitz and Fawkzes

In an effort to give students a more visceral experience of science and instill a deeper working knowledge of concepts, activities that utilize hands-on, laboratory and simulated experiences are recommended because these activities have a greater impact on student learning, especially for Native American students. Because it is not usually feasible to take large and/or multiple classes of high school science students into the field to count numbers of organisms of a particular species, especially over a long period of time and covering a large area of an environment, the population simulation presented in this paper was created to aid students in understanding population dynamics by working with a simulated environment, which can be done in the classroom. Students create an environment and populate the environment with imaginary species. Then, using a sequence of "rules" that allow organisms to eat, reproduce, move and age, students see how the population of a species changes over time. In particular, students practice collecting data, summarizing information, plotting graphs, and interpreting graphs for such information as carrying capacity, predator prey relationships, and how specific species factors impact population and the environment. Students draw conclusions from their results and suggest further research, which may involve changes in simulation parameters, prediction of outcomes, and testing predictions. The population Simulation has demonstrated success in the above student activities using a "board game" version of the population simulation. A computer version of the population simulation needs more testing, but preliminary runs are promising. A second - and more complicated - computer simulation will simulate the same things and will add simulated population genetics.

Bangert, Tyler R.↗

DOE OSTI2016

Initial study of Schroedinger eigenmaps for spectral target detection

Spectral target detection refers to the process of searching for a specific material with a known spectrum over a large area containing materials with different spectral signatures. Traditional target detection methods in hyperspectral imagery (HSI) require assuming the data fit some statistical or geometric models and based on the model, to estimate parameters for defining a hypothesis test, where one class (i.e., target class) is chosen over the other classes (i.e., background class). Nonlinear manifold learning methods such as Laplacian eigenmaps (LE) have extensively shown their potential use in HSI processing, specifically in classification or segmentation. Recently, Schroedinger eigenmaps (SE), which is built upon LE, has been introduced as a semisupervised classification method. In SE, the former Laplacian operator is replaced by the Schroedinger operator. The Schroedinger operator includes by definition, a potential term V that steers the transformation in certain directions improving the separability between classes. In this regard, we propose a methodology for target detection that is not based on the traditional schemes and that does not need the estimation of statistical or geometric parameters. This method is based on SE, where the potential term V is taken into consideration to include the prior knowledge about the target class and use it to steer the transformation in directions where the target location in the new space is known and the separability between target and background is augmented. An initial study of how SE can be used in a target detection scheme for HSI is shown here. Inscene pixel and spectral signature detection approaches are presented. Finally, the HSI data used comprise various target panels for testing simultaneous detection of multiple objects with different complexities.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS2021

Perceptions of Climate Risk and Use of Climate Risk Information by Natural Resource Conservation Stakeholders Participating in ADVANCE Projects in Asia and Latin America

Integrating climate risk information into resilience-building activities in the field is important to ensure that adaptation is based on the best available science. Despite this, many challenges exist when developing, communicating, and incorporating climate risk information. There are limited resources on how stakeholders perceive risks, use risk information, and what barriers exist to limit knowledge integration. This paper seeks to define the following: 1) What do conservation stakeholders consider to be the most significant climate risks they face now and possibly in the future? 2) What have been the most significant barriers to their using climate risk information? 3) What sources and types of knowledge would be most useful for these managers to overcome these barriers? A survey was conducted among stakeholders (n = 224) associated with World Wildlife Fund projects in tropical and subtropical countries. A very high proportion of stakeholders used climate risk information and yet faced integration-related challenges, which included too much uncertainty and the lack of a relevant scale for planning. The main factors preventing the use of climate risk information in decision-making were unavailability of climate risk information, no or limited financial or human resources available to respond, lack of organizational mandate or support, and no or limited institutional incentives. Comparing perceived current and future risks revealed a decline in concern for some future climate hazards. Survey respondents identified scientific reports, climate scientists, and online sources as the most useful information sources of climate risk information, while (i) maps and illustrations; (ii) scenarios format; and (iii) data tables, graphs, and charts were identified as user-friendly formats.

Climate risk↗

DOE OSTI2018

Evaluation of Visualization Heuristics

Heuristics have been used since the early 1990's in the Human Computer Interaction (HCI) domain, for evaluating user interfaces. Most notably, heuristics developed by Nielsen and Molich (1990) have been used by the HCI community. Forsell and Johansson (2010) used the same methodology as Nielsen and Molich and developed a set of 10 heuristics for information visualization. Currently, neither the information visualization or the visual analytics community has adopted these heuristics. However, several studies have been conducted using heuristics. Hearst et al. (2015) found that using the heuristics for visualizations along with asking questions about the data resulted in complementary results as the questions about the data could compensate for heuristics that were difficult to understand and apply. Heli Väätäjä et al. (2016) found that heuristics related to interaction, veracity, and aesthetics needed to be added to the Forsell and Johansson (2010) set. They also noted that a lack of domain knowledge caused the evaluators issues in conducting a heuristic evaluation. We conducted a controlled experiment to determine what factors might impact the expert evaluators' capability to conduct a heuristic evaluation of a static information visualization. In particular, we wanted to understand how their familiarity with the visualizations and their experience in conducting heuristic evaluations impacted their evaluations of visualizations. We recruited 10 participants who were domain experts in the visualization field each having experience with one of more of the following: user experience design or research, user interface development, and human computer interaction research. We used a heuristic set proposed by Forsell and Johansson. Participants were also asked to complete a demographic survey in which they rated their experience with each visualization type generally, their experience conducting heuristic evaluations, their experience using each visualization type to extract information, and their experience developing and creating each visualization type. The participants were shown a series of 5 common visualizations (Scatterplots, Sunbursts, Tree Maps, Parallel Sets, and Area Graphs) all displaying the VAST 2008 Mini Challenge Two- Migrant Boats data . Participants were given a suggested analytical question related to each visualization to keep in mind as they applied the 10 heuristics to each visualization. They were asked if they could find any usability problems in the visualizations and which heuristic(s) helped them to identify these problems. The participants were asked to rate how relevant each heuristic was for evaluating each visualization along with rating how confident they felt in their ability to apply the heuristic to evaluate each visualization. At the conclusion of the study, participants provided qualitative feedback on the usability issues of each visualization. Additionally, we collected eye tracking data on 6 of the 10 participants. We will be using this data to determine how long participants looked at the various visualizations and what parts of the visualizations they focused on. We had two hypotheses for this empirical evaluation: 1.The Forsell and Johansson heuristics of Orientation and help, Data set reduction, and Prompting are less useful for static visualizations because they require some interaction in order to test completely. 2.Participants that do not have experience with heuristic evaluation will provide lower evaluation scores for the heuristics compared to those that have experience. Related to hypothesis 1, as our study used only static visualizations, interaction-related usability challenges should be harder to identify. This should result in lower usefulness ratings for those heuristics. Preliminary results indicate that participants found it more difficult to apply heuristics to unfamiliar visualizations.

Williams, Ryan G.↗

NASA NTRS2021

A Mathematical Analysis of an Example Delay Tolerant Network using the Theory of Sheaves

NASA’s High-Data Rate Architecture (HiDRA) project is working towards a general yet practical toolkit and knowledge base to help usher in the era of new technologies for space systems communications, such as optical links. The High-Rate Delay Tolerant Networking (HDTN) implementation falls under the umbrellas of both the toolkit and the knowledge base, as its advancements illuminate more general areas of Delay Tolerant Networking (DTN) that need growth. The goal of this paper is to explore the usage of particular mathematical machineries, namely temporal flow networks and sheaves, to identify fundamental, underlying structures in DTN for space systems. Satellites, space assets, ground stations, etc. give rise to a disconnected network, and it is the goal of DTN to glue disparate links together into a cohesive system, that is, a network. Depending on a given link, the latencies might be beyond that which the Transmission Control Protocol (TCP) can handle, and contact times might have one-way light times in excess of minute (sometimes significantly longer). Some links might be periodic (say, due to orbital mechanics) or they might not be. This diversity has made it difficult to probe the underlying structure. An immediate consequence is that DTNs in practice today are controlled by globally distributed contact plans (schedules), which are the input to the contact graph routing (CGR) algorithm. While this is effective for smaller networks, it will be very difficult to scale for future networks. Deeper and more rigorous theory is needed to bring DTN to the next evolutionary step. To this end, this paper introduces and suggests a mathematical framework for DTN, and applies it to a space network that is simulated using an orbital analysis toolkit. The tag-line for the structure known as sheaves is that they are the mathematically precise way of gluing local data together into unique, global data. If we consider routing, we see that networking is a “sheafy” science. We then discuss a simplified sheaf model, known as the cellular sheaf. The sheaf-theoretic analysis is presented and discussed, as it is hoped that this and related papers will help form the primordial ooze of DTN theory. Finally there is a section of future work suggesting follow-on research.

Delay Tolerant Networking↗

DOE OSTI2021

Neuromorphic Graph Algorithms

Graph algorithms enable myriad large-scale applications including cybersecurity, social network analysis, resource allocation, and routing. The scalability of current graph algorithm implementations on conventional computing architectures are hampered by the demise of Moore’s law. We present a theoretical framework for designing and assessing the performance of graph algorithms executing in networks of spiking artificial neurons. Although spiking neural networks (SNNs) are capable of general-purpose computation, few algorithmic results with rigorous asymptotic performance analysis are known. SNNs are exceptionally well-motivated practically, as neuromorphic computing systems with 100 million spiking neurons are available, and systems with a billion neurons are anticipated in the next few years. Beyond massive parallelism and scalability, neuromorphic computing systems offer energy consumption orders of magnitude lower than conventional high-performance computing systems. We employ our framework to design and analyze new spiking algorithms for shortest path and dynamic programming problems. Our neuromorphic algorithms are message-passing algorithms relying critically on data movement for computation. For fair and rigorous comparison with conventional algorithms and architectures, which is challenging but paramount, we develop new models of data-movement in conventional computing architectures. This allows us to prove polynomial-factor advantages, even when we assume a SNN consisting of a simple grid-like network of neurons. To the best of our knowledge, this is one of the first examples of a rigorous asymptotic computational advantage for neuromorphic computing.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

NuGraph2: A Graph Neural Network for Neutrino Event Reconstruction

Neutrino experiments are set to probe some of the most important open questions in physics, from CP violation and the nature of dark matter. The technology of choice for many of these experiments is the liquid argon time projection chamber (LArTPC). In current LArTPC experiments, reconstruction performance often represents a limiting factor for the sensitivity. New developments are therefore needed to unlock the full potential of LArTPC experiments. NuGraph2 is a state of the art Graph Neural Network for reconstruction of data in LArTPC experiments. NuGraph2 utilizes a heterogeneous graph structure, with separate subgraphs of 2D nodes (hits in each plane) connected across planes via 3D nodes (space points). The model provides a consistent description of the neutrino interaction across all planes. NuGraph2 is a multi-purpose network, with a common message-passing attention engine connected to multiple decoders with different classification or regression tasks. These include the classification of detector hits according to the particle type that produced them (semantic segmentation) and the separation of hits from the neutrino interaction from hits due to noise or cosmic-ray background. Additional decoders are being developed, performing tasks such as the regression of the neutrino interaction vertex position. Performance results will be presented based on publicly available samples from MicroBooNE. These include both physics performance metrics, achieving 95% accuracy for semantic segmentation and 98% classification of neutrino hits, as well as computational metrics for training and for inference on CPU or GPU. The status of the NuGraph integration in the LArSoft software framework will be presented, as well as initial studies about model interpretability and injection of domain knowledge.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2024

NuGraph2: A Graph Neural Network for Neutrino Event Reconstruction

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2024

NuGraph2: A Graph Neural Network for Neutrino Event Reconstruction

Neutrino experiments are set to probe some of the most important open questions in physics, from CP violation and the nature of dark matter. The technology of choice for many of these experiments is the liquid argon time projection chamber (LArTPC). In current LArTPC experiments, reconstruction performance often represents a limiting factor for the sensitivity. New developments are therefore needed to unlock the full potential of LArTPC experiments. NuGraph2 is a state of the art Graph Neural Network for reconstruction of data in LArTPC experiments [https://arxiv.org/abs/2403.11872]. NuGraph2 utilizes a heterogeneous graph structure, with separate subgraphs of 2D nodes (hits in each plane) connected across planes via 3D nodes (space points). The model provides a consistent description of the neutrino interaction across all planes. NuGraph2 is a multi-purpose network, with a common message-passing attention engine connected to multiple decoders with different classification or regression tasks. These include the classification of detector hits according to the particle type that produced them (semantic segmentation) and the separation of hits from the neutrino interaction from hits due to noise or cosmic-ray background. Additional decoders are being developed, performing tasks such as the regression of the neutrino interaction vertex position. Performance results will be presented based on publicly available samples from MicroBooNE. These include both physics performance metrics, achieving 95% accuracy for semantic segmentation and 98% classification of neutrino hits, as well as computational metrics for training and for inference on CPU or GPU. The status of the NuGraph integration in the LArSoft software framework will be presented, as well as initial studies about model interpretability and injection of domain knowledge.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗