Search NASA⌕ Search

SEARCH · Search NASA

Results for “data representation”

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 1,477 records · Page 82
All sourcesNASA NTRSDOE OSTI
NASA NTRS1988

An improved error assessment for the GEM-T1 gravitational model

Several tests were designed to determine the correct error variances for the Goddard Earth Model (GEM)-T1 gravitational solution which was derived exclusively from satellite tracking data. The basic method employs both wholly independent and dependent subset data solutions and produces a full field coefficient estimate of the model uncertainties. The GEM-T1 errors were further analyzed using a method based upon eigenvalue-eigenvector analysis which calibrates the entire covariance matrix. Dependent satellite and independent altimetric and surface gravity data sets, as well as independent satellite deep resonance information, confirm essentially the same error assessment. These calibrations (utilizing each of the major data subsets within the solution) yield very stable calibration factors which vary by approximately 10 percent over the range of tests employed. Measurements of gravity anomalies obtained from altimetry were also used directly as observations to show that GEM-T1 is calibrated. The mathematical representation of the covariance error in the presence of unmodeled systematic error effects in the data is analyzed and an optimum weighting technique is developed for these conditions. This technique yields an internal self-calibration of the error model, a process which GEM-T1 is shown to approximate.

Lerch, F. J.↗
DOE OSTI2023

Convoluted filtering for process cycle modeling

Principles of materials science and engineering, physics, mathematics, and information science are used to extract knowledge and insights from the process-structure–property-performance relationships hidden in materials data. The process-structure modeling can be accelerated without loss of interpretability, with artificial intelligence tools that mimic the salient features of the process and process-structure relations. In this work, a novel convoluted model-filtering technique was exploited to build and successfully train the Convoluted Filter (CoFi) artifacts for Fe-based alloy heat treatment cycles. The artifacts were pre-trained to filter out deep models that change the surrogate microstructure state after the heat treatment at ambient conditions. Direct representation of the thermal cycle features within knowledge Graph facilitated development of meaningful data models for microstructure evolution, which reduce overfitting to limited datasets.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Efficient Clustering of Software Vulnerabilities using Self Organizing Map (SOM)

The common vulnerabilities and exposures (CVE) database was created with a mission to ``identify, define, and catalog publicly disclosed cybersecurity vulnerabilities''. This rich body of information can be used to enable rapid and efficient response to secure and defend cyber operations and protect critical cyber infrastructure. The main goal of this paper is to develop a visual analytics tool to enable deep analysis of CVEs using unsupervised clustering techniques. We enhance our analysis by first mapping CVEs to hierarchical-classes in Common Weakness Enumeration (CWE) using information in the National Vulnerability Database (NVD). Both the mapping and the numerical representation of CVEs are enabled by V2W-BERT, which uses natural language processing of the extensive information in NVD to generate a large tabular database of 137,226 CVE entries from 1999 to 2020, where each CVE is represented by a vector of 768 numerical features. The vectorized data is processed by Self-Organizing Maps (SOM), which is an unsupervised machine learning technique for dimensionality reduction, visual representation and clustering. Using a Torus map of 6417 units, we achieve ~10-fold data compression of ~140k CVEs using SOM. The trained map is further clustered using standard K-means clustering into 138 clusters of CVEs. We conducted a brief investigation of the rich mapping of CVEs to best-matching-units to K-means clusters, as well as CVEs to CWEs. For example, this novel mapping provided insight into the role of CWE-59 and CWE-264 in several CVEs that is otherwise hard to explore in the original data. We conclude that our this novel approach will not only enable deep analysis of the complex relationships between CVEs and CWEs, but also a mechanism to quickly respond to and design mitigation actions for rapidly evolving vulnerabilities that have not been mapped to existing CWEs.

Panchal, Khyati↗
NASA NTRS2020

Building a standardized Observing System Simulation Experiment (OSSE) framework for Mars

We advocate that the Decadal Survey recommends the NASA Science Mission Directorate to develop a rigorous Observing System Simulation Experiment (OSSE) framework for Mars, to optimize future atmospheric observations. Atmospheric conditions on Mars are a potential hazard source for landing missions. Errors in the estimates of atmospheric density profiles, inadequate knowledge of wind vertical structure and dust concentration as a function of height are likely causes of uncertainty at the landing site on the order of kilometers. An operational real-time weather forecasting capability for Mars would reduce such uncertainties, carrying enormous benefits to future robotic missions, and would be an invaluable prerequisite for human missions.A real-time forecasting capability relies upon three fundamental components: a critical mass of observing systems, a data assimilation system (DAS), and a global forecast model. The DAS allows the model to ingest the data effectively, optimizing the observational information content,and transforming them into a gridded representation of the atmosphere at a given time, called an ‘analysis’. The analysis is the best estimate of the atmospheric state for that time, and also represents a set of ‘initial conditions’ from which a global model can be initialized, to predict a future state of the atmosphere. The connection between analysis and forecast represents the foundation of modern weather forecasting. However, from the point of view of a forecast system,not all observations are equally impactful, partially because of the problem of “observational error correlation”, one important research topic in data assimilation development. For the Earth, partly due to the spontaneous and deregulated development of observations and forecast capabilities worldwide for more than half a century,the use of observations in contemporary operational forecast systems is suboptimal, with many potentially useful data being underutilized. On the contrary, Mars atmospheric scientists are in the unique situation of designing the next-generation observing systems by learning from the experience gathered on the Earth, so as to assure that the future instruments are specifically optimized to give the maximum benefit to a future weather forecast capability.An immensely powerful tool that has been firmly established by atmospheric scientists on the Earth is represented by a properly designed OSSE framework. A realistic OSSE framework cannot only quantify the benefit of future data types, be them surface based or space borne, but can also help design and optimize an entire observational network. Furthermore, OSSEs can provide deep insights into an atmosphere’s behavior, by addressing conceptual problems of its intrinsic predictability and delineating the regions or features of the atmosphere which are more sensitive to additional data and would benefit from a denser sampling. The difficulties posed by OSSEs are fundamentally different for Earth and Mars. For Earth, the enormous data volume imposes a tremendous constraint on any innovation in the observing systems: it is very hard for a single sensor to impact the skill. For Mars, the problem is the opposite: almost any additional instrument will exert some impact. However, OSSEs can help to evaluate the cost/benefit for every sensor and suggest optimal data configuration and density.The purpose of this white paper is to provide an introduction to a rigorously designed OSSE framework, explain the underlying problems and challenges, and engage the Mars community to collaborate with Earth Atmospheric scientists in order to develop a joint-OSSE framework for Mars with the largest consensual basis possible. An OSSE infrastructure would increase the understanding of the Martian atmosphere, would help NASA to optimize instrument specifications and orbit choice, providing the maximium benefit for a given expenditure of resources, and could even help establishing a roadmap for a future real-time weather forecasting capability.

Oreste Reale↗
DOE OSTI2022

Improving and testing machine learning methods for benchmarking soil carbon dynamics representation of land surface models

Representation of soil organic carbon (SOC) dynamics in Earth system models (ESMs) is a key source of uncertainty in predicting carbon climate feedbacks. The magnitude of this uncertainty can be reduced by accurate representation of environmental controllers of SOC stocks in ESMs. In this study, we used data of environmental factors, field SOC observations, ESM projections and machine learning approaches to identify dominant environmental controllers of SOC stocks and derive functional relationships between environmental factors and SOC stocks. Our derived functional relationships predicted SOC stocks with similar accuracy as the machine learning approach. We used the derived relationships to benchmark the coupled model intercomparison project phase six ESM representation of SOC stocks. We found divergent environmental control representation in ESMs in comparison to field observations. Representation of SOC in ESMs can be improved by including additional environmental factors and representing their functional relationships with SOC consistent with observations.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

CMIP7 data request: Earth system priorities and opportunities

This paper presents a comprehensive overview of the Coupled Model Intercomparison Project Phase 7 (CMIP7) request for data pertaining to Earth systems science, and provides justification for the resources needed to produce this data. Topics within the CMIP7 Earth System (CMIP7-ES) theme centre around tracking of flows of energy, carbon, water and other fluxes across domains, and constraining feedbacks between these cycles and the climate system. These topics are summarized in this paper as scientific “opportunities” describing specific model intercomparison experiments and use cases for next-generation Earth System Model (ESM) output. These opportunities were submitted by modelling groups and scientific consortia following an extended public consultation process. Contained within each opportunity are requests for groups of Climate & Forecasting (CF) variables, which are bundled into variable groups representing all data required to address the opportunities' needs. Novel opportunities in CMIP7 compared with previous phases will include running `emissions-driven' simulations that integrate carbon emissions and removal scenarios with updated representations of the global carbon cycle, expanded variable groups needed to model marine trophic interactions and biogeochemistry, and data needed to understand the risk of global tipping points, among others. The production of these variables will close key gaps and uncertainties identified during previous rounds of CMIP, and support the 7th Intergovernmental Panel on Climate Change Assessment Report (AR7). We argue that CMIP7-ES data will be broadly used by scientific, policy, governmental, industry, and other communities that rely on climate model projections for research and decision making. As an author group we also reflect on the evolution of the CMIP7-ES data request as a part of a deliberative process in support of the global CMIP program.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Leveraging Environmental Monitoring Results from Department of Energy Sites for Research on the Food-Energy-Water Nexus

The Annual Site Environmental Report (ASER) from a U.S. Department of Energy (DOE) Site summarizes environmental data; environmental management performance; compliance with applicable DOE, federal, state, and local regulations; and restoration and surveillance monitoring programs. The Savannah River Site (SRS) produces ASERs that include results of monitoring mercury levels in fish samples obtained in the vicinity of SRS. Mercury is a toxic trace metal and the methylated organic form is a neurotoxin that bioaccumulates in the food web, endangering humans and other organisms. In United States, power plants are the largest source of mercury emissions. Research Objective: To determine the patterns of mercury levels in fish samples reported in the SRS environmental monitoring reports. We developed box plot visualizations to make sense of the data as well as identify fish species, dates and location with outlier mercury content. The integration and visual representation of multi-year datasets can support decision making processes on environmental compliance and environmental sustainability conducted at U.S. DOE Sites. We are constructing datasets from textual, image and multivariable data sources in the multi-year ASERs of the U.S. DOE Savannah River Site (SRS https://www.srs.gov/general/pubs/ERsum/index.html). The Fish Surveillance for mercury presents a case study for the intersection of food, energy and water systems. The dataset of 864 records (2008 and 2009) of mercury levels includes water location of fish, fish species, collection date and mercury content of fish sample. The patterns of mercury levels in the fish species as well as locations provide knowledge for further investigations. A research area for future studies is the composition of microbial communities in fish guts of varying levels of mercury.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Internal conversion and intersystem crossing dynamics based on coupled potential energy surfaces with full geometry-dependent spin–orbit and derivative couplings. Nonadiabatic photodissociation dynamics of NH 3 (A) leading to the NH(X 3 Σ – , a 1 Δ) + H 2 channel

Here we simulate the photodissociation of NH 3 originating from its first excited singlet state S 1 into the NH 2 + H (radical) and NH + H 2 (molecular) channels. The states considered are the ground singlet state S 0 , the first excited singlet state S 1 and the lowest-lying triplet state T 1 , which permit for the first time a uniform treatment of the internal conversion and intersystem crossing. The simulations are based on a diabatic potential energy matrix (DPEM) of S 0 , S 1 coupled by a conical intersection seam, as well as a potential energy surface (PES) for T 1 coupled by spin-orbit coupling (SOC) to the two singlet states. The DPEM and PES are fitted to ab initio electronic structure data (ESD) including energies, energy gradients, and derivative couplings. The DPEM also defines an adiabatic to diabatic state (AtD) transformation, which is used to transform the singular adiabatic SOC into a smooth function of the nuclear coordinates in the diabatic representation, allowing the diabatic SOC to be fit to an analytical functional form. ESD and SOC data obtained from these surfaces can serve as input for either quantum or semi-classical characterization of the nonadiabatic dynamics. Using the SHARC suite of programs, nonadiabatic simulations based on over 40 000 semi-classical trajectories assess the convergence of our results. The production of NH + H 2 is not direct, but is only achieved through a quasi-statistical dissociation mechanism after internal conversion to the ground electronic state. This leads to a much lower yield comparing with the main NH 2 + H channel. The NH(X 3 Σ_) radical produced through the intersystem crossing from S 0 to T 1 is rare (~0.2%) compared to NH(a 1 Δ) due to the process being spin forbidden.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
NASA NTRS1994

SeaWiFS technical report series. Volume 15: The simulated SesWiFS data set, version 2

This document describes the second version of the simulated SeaWiFS data set. A realistic simulated data set is essential for mission readiness preparations and can potentially assist in all phases of ground support for a future mission. The second version improves on the first version primarily through additional realism and complexity. This version incorporates a representation of virtually every aspect of the flight mission. Thus, it provides a high-fidelity data set for testing several aspects of the ground system, including data acquisition, data processing, data transfers, calibration and validation, quality control, and mission operations. The data set is constructed for a seven-day period, 25-31 March 1994. Specific features of the data set include Global Area coverage (GAC), recorded Local Area Coverage (LAC), and realtime High Resolution Picture Transmission (HRPT) data for the seven-day period. A realistic orbit, which is propagated using a Brouwer-Lyddane model with drag, is used to simulate orbit positions. The simulated data corresponds to the command schedule based on the orbit for this seven-day period. It includes total (at-satellite) radiances not only for ocean, but for land, clouds, and ice. The simulation also utilizes a high-resolution land-sea mask. It includes the April 1993 SeaWiFS spectral responses and sensor saturation responses. The simulation is formatted according to July 1993 onboard data structures, which include corresponding telemetry (instrument and spacecraft) data. The methods are described and some examples of the output are given. The instrument response functions made available in April 1993 have been used to produce the Version 2 simulated data. These response functions will change as part of the sensor improvements initiated in July-August 1993.

Hooker, Stanford B.↗
NASA NTRSDate not supplied

Digital Lunar Exploration Sites (DLES)

It has been almost 50 years since humans last set foot on the Moon. With NASA’s Artemis program, the United States and its international and commercial partners are embarking on a new endeavor to explore the lunar surface. Before we return, we will have simulated every aspect of these future missions. Many of these models and simulations (M&S) will rely on well-known and commonly-used technologies, some of which trace their origins back to the Apollo program. However, M&S has advanced significantly, as have the underlying computational capabilities. As a result, we are able to model many more aspects of the Artemis vehicles and support systems with significantly improved detail and confidence. Accurately and efficiently modeling the lunar environment will be critical to simulating the Artemis elements and mission activities. This includes characterizing and modeling lunar topography, smaller craters, exposed surface rocks, lunar regolith, surface lighting, and ambient thermal environment. These are all necessary for understanding fundamental behaviors and performance of vehicles and support systems in the lunar environment and are often determining factors in the selection of exploration sites and defining mission profiles. The Astromaterials Research and Exploration Sciences (ARES) team in the Exploration Integration and Science Directorate at NASA’s Johnson Space Center (JSC) and the NASA Exploration Systems Simulations (NExSyS) team in the Simulation and Graphics Branch at JSC are developing and maintaining the Digital Lunar Exploration Sites (DLES) data, documentation, and software packages. This data is being fed directly into a diverse collection of graphics and simulation environments, where it is used to construct the closest known truth for numerous potential Lunar South Pole landing sites. DLES is available to projects across NASA and particularly the Artemis program to support coordinated digital representations of the lunar environment. This paper describes the fundamental need for DLES, the science data sets that are going into DLES, some of the processes used to integrate this data into DLES products, the basic products that constitute DLES, and some examples of DLES in use.

Lunar↗
DOE OSTI2021

Assimilation of Multiscale Data into Multifidelity Biogeochemical Models (Final Report)

Quantitative predictions of subsurface processes rely on computational models that capture, with different degrees of fidelity, complex interactions between hydrologic and biogeochemical processes. Molecular- and pore-scale models provide a high-fidelity representation of these processes but are impractical at the field scale. Reduced complexity (e.g., field-scale or data-driven) models sacrifice some degree of fidelity in favor of computational efficiency. Uncertainty and assimilation of data into model predictions, pose a question of model selection: Given a significant difference in computational cost, can a lower-fidelity model be preferable to its higher-fidelity counterpart? Since a predictive model must be computable in reasonable time it has to operate at the field scale, with molecular- and pore-scale data (obtained either from simulations or measurements) determining both the model's structure and parameters. Availability of such multi-resolution data raises a question hitherto undressed in hydrogeology: Can a coarse model dynamically ``learn'' its own structure (e.g., adjust the reaction pathways in its transport module) as more fine-scale data become available during simulations? Our results in multifidelity simulations, data assimilation, and machine learning led us to hypothesize that the answer to these questions is ``yes''. The overarching goal of this project was to confirm this hypothesis by developing scalable, computationally efficient tools for assimilation of data into multiscale models, in which fine-scale data and simulations dynamically inform and autonomously modify coarse-scale models. Our research led to nine manuscripts, three of which have been published and the other six are currently under review.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
NASA NTRS1993

Implementation and operation of three fractal measurement algorithms for analysis of remote-sensing data

Fractal geometry is increasingly becoming a useful tool for modeling natural phenomena. As an alternative to Euclidean concepts, fractals allow for a more accurate representation of the nature of complexity in natural boundaries and surfaces. The purpose of this paper is to introduce and implement three algorithms in C code for deriving fractal measurement from remotely sensed data. These three methods are: the line-divider method, the variogram method, and the triangular prism method. Remote-sensing data acquired by NASA's Calibrated Airborne Multispectral Scanner (CAMS) are used to compute the fractal dimension using each of the three methods. These data were obtained as a 30 m pixel spatial resolution over a portion of western Puerto Rico in January 1990. A description of the three methods, their implementation in PC-compatible environment, and some results of applying these algorithms to remotely sensed image data are presented.

Jaggi, S.↗
DOE OSTI2020

Tensor Basis Gaussian Process Models of Hyperelastic Materials

In this study, we develop Gaussian process regression (GPR) models of isotropic hyperelastic material behavior. First, we consider the direct approach of modeling the components of the Cauchy stress tensor as a function of the components of the Finger stretch tensor in a Gaussian process. We then consider an improvement on this approach that embeds rotational invariance of the stress-stretch constitutive relation in the GPR representation. This approach requires fewer training examples and achieves higher accuracy while maintaining invariance to rotations exactly. Finally, we consider an approach that recovers the strain-energy density function and derives the stress tensor from this potential. Although the error of this model for predicting the stress tensor is higher, the strain-energy density is recovered with high accuracy from limited training data. The approaches presented here are examples of physics-informed machine learning. They go beyond purely data-driven approaches by embedding the physical system constraints directly into the Gaussian process representation of materials models.

36 MATERIALS SCIENCE↗
DOE OSTI2025

ARCH: Large-scale knowledge graph via aggregated narrative codified health records analysis

Objective: Electronic health record (EHR) systems contain a wealth of clinical data stored as both codified data and free-text narrative notes (NLP). The complexity of EHR presents challenges in feature representation, information extraction, and uncertainty quantification. Here, to address these challenges, we proposed an efficient Aggregated naRrative Codified Health (ARCH) records analysis to generate a large-scale knowledge graph (KG) for a comprehensive set of EHR codified and narrative features. Methods: Using data from 12.5 million Veterans Affairs patients, ARCH first derives embedding vectors and generates similarities along with associated p-values to measure the strength of relatedness between clinical features with statistical certainty quantification. Next, ARCH performs a sparse embedding regression to remove indirect linkage between features to build a sparse KG. Finally, ARCH was validated on various clinical tasks, including detecting known relationships between entity pairs, predicting drug side effects, disease phenotyping, as well as sub-typing Alzheimer’s disease patients. Results: ARCH produces high-quality clinical embeddings and KG for over 60,000 codified and narrative EHR concepts. The KG and embeddings are visualized in the R-shiny powered web-API.3 ARCH achieved high accuracy in detecting EHR concept relationships, with AUCs of 0.926 (codified) and 0.861 (NLP) for similar EHR concepts, and 0.810 (codified) and 0.843 (NLP) for related pairs. It detected drug side effects with a 0.723 AUC, which improved to 0.826 after fine-tuning. Using both codified and NLP features, the detection power increased significantly. Compared to other methods, ARCH has superior accuracy and enhances weakly supervised phenotyping algorithms’ performance. Notably, it successfully categorized Alzheimer’s patients into two subgroups with varying mortality rates. Conclusion: The proposed ARCH algorithm generates large-scale high-quality semantic representations and knowledge graph for both codified and NLP EHR features, useful for a wide range of predictive modeling tasks.

Electronic health records↗
DOE OSTI2019

Lidar Mapping and Surveillance of Nuclear Infrastructure

Wear is unavoidable, whether it occurs in a nuclear facility or abridge on the highway its detection is crucial to preventing the failure of a system. While tools capable of detecting localized damage exist, industry lacks methods to evaluate the health of larger infrastructure. Routine inspection of nuclear facilities must be undertaken to ensure the safety of personnel and proper containment of nuclear materials. Most systems in a nuclear facility are designated as radioactive and confined spaces. To constantly monitor such systems in person would be hazardous but with a remote inspection tool it can be done in a safer and easier way. Lidar: Operates by emitting a laser pulse and looking for the reflected light. Allows user to gain 3D information of the environment. Project Objective: To develop an inspection tool for evaluating the health of large scale infrastructure using Lidar and machine learning. Autonomous Platform + Lidar + Data Fusion + Big Data. Use SLAM to build a 2D map of the environment. Point cloud created by transforming the points between reference frames. Point cloud to Surface: Inherent representation of surface geometry; Difficult to process with conventional techniques. Point cloud to Image: Easily processed by conventional machine learning algorithms. The quantity of data generated will necessitate a big data framework to manage the data for processing. Additional Sensors: Detecting the temperature (a) chemical makeup (b) and radiation emission (c) of a surface could assist in detecting problems. Human inspection can detect irregularities in both physical objects and their point-cloud representations. This is a good indication that mapping nuclear sites using Lidar will provide qualitative insight into the health of the facility. If deep learning can be used to automatically identify problem areas then the completed tool could become an invaluable asset.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2024

Multi-Agent Graph-Attention Deep Reinforcement Learning for Post-Contingency Grid Emergency Voltage Control

Grid emergency voltage control (GEVC) is paramount in electric power systems to improve voltage stability and prevent cascading outages and blackouts in case of contingencies. While most deep reinforcement learning (DRL)-based paradigms perform single agents in a static environment, real-world agents for GEVC are expected to cooperate in a dynamically shifting grid. Moreover, due to high uncertainties from combinatory natures of various contingencies and load consumption, along with the complexity of dynamic grid operation, the data efficiency and control performance of the existing DRL-based methods are challenged. To address these limitations, we propose a multi-agent graph-attention (GATT)-based DRL algorithm for GEVC in multi-area power systems. Here, we develop graph convolutional network (GCN)-based agents for feature representation of the graph-structured voltages to improve the decision accuracy in a data-efficient manner. Furthermore, a cutting-edge attention mechanism concentrates on effective information sharing among multiple agents, synergizing different-sized subnetworks in the grid for cooperative learning. We address several key challenges in the existing DRL-based GEVC approaches, including low scalability and poor stability against high uncertainties. Test results in the IEEE benchmark system verify the advantages of the proposed method over several recent multi-agent DRL-based algorithms.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS2015

Evalution of a DE-Identification Process for Ocular Imaging

Medical privacy of NASA astronauts requires an organized and comprehensive approach when data are being made available outside NASA systems. A combination of factors, including the uniquely small patient population, the extensive medical testing done on these individuals, and the relative cultural popularity of the astronauts puts them at a far greater risk to potential exposure of personal information than the general public. Therefore, care must be taken to ensure that the astronauts' identities are concealed. Magnetic Resonance Imaging (MRI) medical data is a recent source of interest to researchers concerned with the development of Visual Impairment due to Intracranial Pressure (VIIP) in the astronaut population. Each vision MRI scan of an astronaut includes 176 separate sagittal images that are saved as an "image series" for clinical use. In addition to the medical information these image sets provide, they also inherently contain a substantial amount of non-medical personally identifiable information (PII) such as-name, date of birth, and date of exam. We have shown that an image set of this type can be rendered, using free software, to give an accurate representation of the patient's face. This currently restricts NASA from dispensing MRI data to researchers in a deidentified format. Automated software programs, such as the Brain Extraction Tool, are available to researchers who wish to de-identify MRI sagittal brain images by "erasing" identifying characteristics such as the nose and jaw on the image sets. However, this software is not useful to NASA for vision research because it removes the portion of the images around the eye orbits, which is the main area of interest to researchers studying the VIIP syndrome. The Lifetime Surveillance of Astronaut Health program has resolved this issue by developing a protocol to de-identify MRI sagittal brain images using Showcase Premier, a DICOM (Digital Imaging and Communications in Medicine) software package. The software allows manual editing of one image from a patient's image set to be automatically applied to the entire image series. This new approach would allow a new level of access to untapped medical imaging data relating to VIIP that can be utilized by researchers while protecting the privacy of the astronauts. In the next step toward finalizing this technique, NASA clinical radiology consultants will test the images to verify removal of all metadata and PII.

LaPelusa, Michael B.↗
DOE OSTI2024

Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Models

Abstract We propose masked particle modeling (MPM) as a self-supervised method for learning generic, transferable, and reusable representations on unordered sets of inputs for use in high energy physics (HEP) scientific data. This work provides a novel scheme to perform masked modeling based pre-training to learn permutation invariant functions on sets. More generally, this work provides a step towards building large foundation models for HEP that can be generically pre-trained with self-supervised learning and later fine-tuned for a variety of down-stream tasks. In MPM, particles in a set are masked and the training objective is to recover their identity, as defined by a discretized token representation of a pre-trained vector quantized variational autoencoder. We study the efficacy of the method in samples of high energy jets at collider physics experiments, including studies on the impact of discretization, permutation invariance, and ordering. We also study the fine-tuning capability of the model, showing that it can be adapted to tasks such as supervised and weakly supervised jet classification, and that the model can transfer efficiently with small fine-tuning data sets to new classes and new data domains.

Heinrich, Lukas (ORCID:0000000240487584)↗