Results for “large data sets” — Page 25

NASA NTRS2011

Scale Dependence of Spatiotemporal Intermittence of Rain

It is a common experience that rainfall is intermittent in space and time. This is reflected by the fact that the statistics of area- and/or time-averaged rain rate is described by a mixed distribution with a nonzero probability of having a sharp value zero. In this paper we have explored the dependence of the probability of zero rain on the averaging space and time scales in large multiyear data sets based on radar and rain gauge observations. A stretched exponential fannula fits the observed scale dependence of the zero-rain probability. The proposed formula makes it apparent that the space-time support of the rain field is not quite a set of measure zero as is sometimes supposed. We also give an ex.planation of the observed behavior in tenus of a simple probabilistic model based on the premise that rainfall process has an intrinsic memory.

Kundu, Prasun K.↗

NASA NTRS2009

Better Spectrometers, Beautiful Spectra and Confusion for All

The confluence of enormous improvements in submillimeter receivers and the development of powerful large scale observatories is about to force astrophysics and the sciences that support it to develop novel approaches for interpretation of data. The historical method of observing one or two lines and carefully analyzing them in the context of a simple model is now only applicable for distant objects where only a few lines are strong enough to be observable. Modern observatories collect many GHz of high signal-to-noise spectra in a single observation and in many cases, at sufficiently high spatial resolution to start resolving chemically distinct regions. The observatories planned for the near future and the inevitable upgrades of existing facilities will make large spectral data sets the rule rather than the exception in many areas of molecular astrophysics. The methodology and organization required to fully extract the available information and interpret these beautiful spectra represents a challenge to submillimeter astrophysics similar in magnitude to the last few decades of effort in improving receivers. The quality and abundance of spectra effectively prevents line-by-line analysis from being a time efficient proposition, however, global analysis of complex spectra is a science in its infancy. Spectroscopy at several other wavelengths have developed a number of techniques to analyze complex spectra, which can provide a great deal of guidance to the molecular astrophysics community on how to attack the complex spectrum problem. Ultimately, the challenge is one of organization, similar to building observatories, requiring teams of specialists combining their knowledge of dynamical, structural, chemical and radiative models with detailed knowledge in molecular physics and gas and grain surface chemistry to extract and exploit the enormous information content of complex spectra. This paper presents a spectroscopists view of the necessary elements in a tool for complex spectral analysis.

Spectral Analysis↗

NASA NTRS1989

Initial Scientific Assessment of the EOS Data and Information System (EOSDIS)

Crucial to the success of the Earth Observing System (Eos) is the Eos Data and Information System (EosDIS). The goals of Eos depend not only on its instruments and science investigations, but also on how well EosDlS helps scientists integrate reliable, large-scale data sets of geophysical and biological measurements made from Eos data, and on how successfully Eos scientists interact with other investigations in Earth System Science. Current progress in the use of remote sensing for science is hampered by requirements that the scientist understand in detail the instrument, the electromagnetic properties of the surface, and a suite of arcane tape formats, and by the immaturity of some of the techniques for estimating geophysical and biological variables from remote sensing data. These shortcomings must be transcended if remote sensing data are to be used by a much wider population of scientists who study environmental change at regional and global scales.

Source record↗

NASA NTRS2015

An Integrated Framework for Modeling Air Carrier Behavior, Policy, and Impacts in the U.S. Air Transportation System

The implementation of the Next Generation Air Transportation System (NextGen) in the United States is an ongoing challenge for policymakers due to the complexity of the air transportation system (ATS) with its broad array of stakeholders and dynamic interdependencies between them. The successful implementation of NextGen has a hard dependency on the active participation of U.S. commercial airlines. To assist policymakers in identifying potential policy designs that facilitate the implementation of NextGen, the National Aeronautics and Space Administration (NASA) and LMI developed a research framework called the Air Transportation System Evolutionary Simulation (ATS-EVOS). This framework integrates large empirical data sets with multiple specialized models to simulate the evolution of the airline response to potential future policies and explore consequential impacts on ATS performance and market dynamics. In the ATS-EVOS configuration presented here, we leverage the Transportation Systems Analysis Model (TSAM), the Airline Evolutionary Simulation (AIRLINE-EVOS), the Airspace Concept Evaluation System (ACES), and the Aviation Environmental Design Tool (AEDT), all of which enable this research to comprehensively represent the complex facets of the ATS and its participants. We validated this baseline configuration of ATS-EVOS against Airline Origin and Destination Survey (DB1B) data and subject matter expert opinion, and we verified the ATS-EVOS framework and agent behavior logic through scenario-based experiments that explored potential implementations of a carbon tax, congestion pricing policy, and the dynamics for equipage of new technology by airlines. These experiments demonstrated ATS-EVOS's capabilities in responding to a wide range of potential NextGen-related policies and utility for decision makers to gain insights for effective policy design.

Horio, Brant M.↗

NASA NTRS2016

Physical State and Distribution of Materials at the Surface of Pluto from New Horizons LEISA Imaging Spectrometer

From Earth based observations Pluto is known to be the host of N2, CH4 and CO ices and also a dark red material. Very limited spatial distribution information is available from rotational visible and near-infrared spectral curves obtained from hemispheric measurements. In July 2015 the New Horizons spacecraft reached Pluto and its satellite system and recorded a large set of data. The LEISA spectro-imager of the RALPH instruments are dedicated to the study of the composition and physical state of the materials composing the surface. In this paper we report a study of the distribution and physical state of the ices and non-ice materials on Pluto's illuminated surface and their mode and degree of mixing. Principal Component analysis as well as various specific spectral indicators and correlation plots are used on the first set of 2 high resolution spectro-images from the LEISA instrument covering the whole illuminated face of Pluto at the time of the New Horizons encounter. Qualitative distribution maps have been obtained for the 4 main condensed molecules, N2, CH4, CO, H2O as well as for the visible-dark red material. Based on specific spectral indicators, using either the strength or the position of absorption bands, these 4 molecules are found to indicate the presence of 3 different types of ices: N2-rich:CH4:CO ices, CH4-rich(:CO:N2?) ices and H2O ice. The mixing lines between these ices and with the dark red material are studied using scatter plots between the various spectral indicators. CH4 is mixed at the molecular level with N2, most probably also with CO, thus forming a ternary molecular mixture that follows its phase diagram with low solubility limits. The occurrence of a N2-rich - CH4-rich ices mixing line associated with a progressive decrease of the CO/CH4 ratio tells us that a fractionation sublimation sequence transforms one type of ice to the other forming either a N2-rich - CH4-rich binary mixture at the surface or an upper CH4-rich ice crust that may hide the N2-rich ice below. The strong CH4-rich - H2O mixing line witnesses the subsequent sublimation of the CH4-rich ice lag left behind by the N2:CO sublimation (N spring-summer), or a direct condensation of CH4 ice on the cold H2O ice (S autumn). The weak mixing line between CH4-containing ices and the dark red material and the very sharp spatial transitions between these ices and this non-volatile material are probably due to thermal incompatibility. Finally the occurrence of a H2O ice - red material mixing line advocates for a spatial mixing of the red material covering H2O ice, with possibly a small amount intimately mixed in water ice. From this analysis of the different materials distribution and their relative mixing lines, H2O ice appears to be the substratum on which other ices condense or non-volatile organic material is deposited from the atmosphere. N2-rich ices seem to evolve to CH4-dominated ices, possibly still containing traces of CO and N2, as N2 and CO sublimate away. The spatial distribution of these materials is very complex. The high spatial definition of all these composition maps, as well as those at even higher resolution that will be soon available, will allow us to compare them with Pluto's geologic features observed by LORRI panchromatic and MVIC multispectral imagers to better understand the geophysical processes in action at the surface of this astonishingly active frozen world.

Schmitt, B.↗

NASA NTRSDate not supplied

An Overview of Research in Nondestructive Evaluation at the National Aeronautics and Space Administration’s Langley Research Center

The primary focus of the nondestructive evaluation (NDE) effort at Langley Research Center (LaRC) is to pioneer advances in NDE and structural health monitoring (SHM) through fundamental scientific research, technology development, and transferring these to the scientific and aerospace communities. This research supports a variety of NASA missions in space operations, exploration and aeronautics. The work presented will focus on the development of advanced inspection systems to detect critical flaws in both metallic and non-metallic materials and structures for aerospace applications. The emphasis is on increasing the performance of inspection systems to provide defect detection and quantitative characterization of the material state. LaRC NDE utilizes expertise in computational ultrasonic, thermal and eddy current simulations to reduce measured responses to size and locations of flaws, establish technique limitations and optimize performance. This presentation will highlight research into five strategic areas: (1) The development of novel solutions using state-of-the-art NDE technologies such as eddy current, ultrasound, thermography and x-ray computed tomography; (2) Research in the development of unique NDE technologies such as terahertz, wavefield imaging and nonlinear ultrasound; (3) The application of both computational and analytic models to NDE problems; (4) The development of advanced analytic methods to interpret large complex data sets; and (5) Advanced methods of applying and interrogating sensors for structural health monitoring.

K Elliott Cramer↗

NASA NTRSDate not supplied

An Overview of Research in Nondestructive Evaluation at the National Aeronautics and Space Administration’s Langley Research Center

The primary focus of the nondestructive evaluation (NDE) effort at Langley Research Center (LaRC) is to pioneer advances in NDE and structural health monitoring (SHM) through fundamental scientific research, technology development, and transferring these to the scientific and aerospace communities. This research supports a variety of NASA missions in space operations, exploration and aeronautics. The work presented will focus on the development of advanced inspection systems to detect critical flaws in both metallic and non-metallic materials and structures for aerospace applications. The emphasis is on increasing the performance of inspection systems to provide defect detection and quantitative characterization of the material state. LaRC NDE utilizes expertise in computational ultrasonic, thermal and eddy current simulations to reduce measured responses to size and locations of flaws, establish technique limitations and optimize performance. This presentation will highlight research into five strategic areas: (1) The development of novel solutions using state-of-the-art NDE technologies such as eddy current, ultrasound, thermography and x-ray computed tomography; (2) Research in the development of unique NDE technologies such as terahertz, wavefield imaging and nonlinear ultrasound; (3) The application of both computational and analytic models to NDE problems; (4) The development of advanced analytic methods to interpret large complex data sets; and (5) Advanced methods of applying and interrogating sensors for structural health monitoring.

NDE↗

NASA NTRSDate not supplied

Clinical Decision Support - Concepts of Operation

We are entering a new era in space exploration to return to the moon and explore Mars. These ambitious goals will require significant changes to in-flight and habitat medical care due to constraints on mass, volume, power, crew time and medical evacuation capabilities. These constraints make it absolutely necessary to develop transformative solutions using new technologies. The Exploration Medical Capability (ExMC) Element of the Human Research Program (HRP) pushes the boundary of space medical systems to advance the care of astronauts on future exploration missions beyond low Earth orbit by identifying and testing next-generation medical care and crew health maintenance technologies. The Clinical Decision Support (CDS) project addresses the gap Medical-701 within the Inflight Medical Conditions risk: Enhance medical capabilities within an exploration medical system. For long-duration, deep space missions, computational and data resources will play an important role in maintaining crew health, wellness and performance where the crew will need to be more self-reliant. The aim of the CDS project is to develop and provide recommended requirements for an in-vehicle CDSS that acts as an assistant for delivering optimal health and performance and medical care during exploration missions. The CDSS is envisioned as a software-based tool that will augment a crewmembers’ knowledge, skills and abilities to assist in decision-making and crew health and performance (CHP) management thus increasing CHP systems capabilities. The human interface will be context aware and lessen the cognitive load to assimilate and use information as well as combine large disparate data sets in such a manner that provides the crew with actionable insight to decisions related to crew medical, health and performance management. Crew autonomy will be provided through a CDS that presents knowledge and data in a context aware manner to augment a crew members’ knowledge, skills and abilities during the process of observation, orientation, decisions and action. The CDS project addresses the need for crew members to operate independently during long duration space exploration missions that require medical Levels of Care (LoC) V, the highest level specified by NASA-STD-3001 and described in more detail by the ExMC interpretation of LoC document (NASA/TM-2017-219290), where significant changes to in-flight and habitat medical care necessitate increasing crew autonomy in decision making and task performance. The CDS project will develop and test a series of iterative and increasingly more complex system prototypes. These annual demonstrations of the data system integration with the crew health and performance domain will inform exploration medical system requirements for an on-board Clinical Decision Support System (CDSS) through a series of use cases that guide CDS prototype functionality. CDS concepts are based on ExMC Concept of Operations documents (presented separately) and will highlight architecture extensibility to other more complex analyses and tests using core crew health and performance integrated data management, processing and visualization capabilities. This approach also establishes how externally developed analyses and approaches could be added to expand a clinical decision support system and thus highlight how a comprehensive system can be commercially and/or globally developed. The CDS project will build upon the concept of an integrated data management approach based on the Medical Data Architecture (MDA) project to more fully address challenges associated with in-flight and habitat medical, health and performance care due to constraints on mass, volume, power, crew time and medical evacuation capabilities required for medical LoC V. These requirements will be derived through systems engineering approaches and software prototype developments over the course of the multi-year CDS project to address crew health and performance decision-making and task performance, often autonomously executed by the crew, in a manner that is consistent with the appropriate medical level of care for the mission. This presentation will provide an overview of the vision for the CDS project and highlight the initial accomplishments in project planning, implementation and requirements identification in fiscal year 2020.

clinical decision support↗

NASA NTRSDate not supplied

Clinical Decision Support - Overview and Update

We are entering a new era in space exploration to return to the moon and explore Mars. These ambitious goals will require significant changes to in-flight and habitat medical care due to constraints on mass, volume, power, crew time and medical evacuation capabilities. These constraints make it absolutely necessary to develop transformative solutions using new technologies. The Exploration Medical Capability (ExMC) Element of the Human Research Program (HRP) pushes the boundary of space medical systems to advance the care of astronauts on future exploration missions beyond low Earth orbit by identifying and testing next-generation medical care and crew health maintenance technologies. The Clinical Decision Support (CDS) project addresses the gap Medical-701 within the Inflight Medical Conditions risk: Enhance medical capabilities within an exploration medical system. For long-duration, deep space missions, computational and data resources will play an important role in maintaining crew health, wellness and performance where the crew will need to be more self-reliant. The aim of the CDS project is to develop and provide recommended requirements for an in-vehicle CDSS that acts as an assistant for delivering optimal health and performance and medical care during exploration missions. The CDSS is envisioned as a software-based tool that will augment a crewmembers’ knowledge, skills and abilities to assist in decision-making and crew health and performance (CHP) management thus increasing CHP systems capabilities. The human interface will be context aware and lessen the cognitive load to assimilate and use information as well as combine large disparate data sets in such a manner that provides the crew with actionable insight to decisions related to crew medical, health and performance management. Crew autonomy will be provided through a CDS that presents knowledge and data in a context aware manner to augment a crew members’ knowledge, skills and abilities during the process of observation, orientation, decisions and action. The CDS project addresses the need for crew members to operate independently during long duration space exploration missions that require medical Levels of Care (LoC) V, the highest level specified by NASA-STD-3001 and described in more detail by the ExMC interpretation of LoC document (NASA/TM-2017-219290), where significant changes to in-flight and habitat medical care necessitate increasing crew autonomy in decision making and task performance. The CDS project will develop and test a series of iterative and increasingly more complex system prototypes. These annual demonstrations of the data system integration with the crew health and performance domain will inform exploration medical system requirements for an on-board Clinical Decision Support System (CDSS) through a series of use cases that guide CDS prototype functionality. CDS concepts are based on ExMC Concept of Operations documents (presented separately) and will highlight architecture extensibility to other more complex analyses and tests using core crew health and performance integrated data management, processing and visualization capabilities. This approach also establishes how externally developed analyses and approaches could be added to expand a clinical decision support system and thus highlight how a comprehensive system can be commercially and/or globally developed. The CDS project will build upon the concept of an integrated data management approach based on the Medical Data Architecture (MDA) project to more fully address challenges associated with in-flight and habitat medical, health and performance care due to constraints on mass, volume, power, crew time and medical evacuation capabilities required for medical LoC V. These requirements will be derived through systems engineering approaches and software prototype developments over the course of the multi-year CDS project to address crew health and performance decision-making and task performance, often autonomously executed by the crew, in a manner that is consistent with the appropriate medical level of care for the mission. This presentation will provide an overview of the vision for the CDS project and highlight the initial accomplishments in project planning, implementation and requirements identification in fiscal year 2020.

clinical decision support system↗

NASA NTRS1993

Lithologic Discrimination and Alteration Mapping from AVIRIS Data, Socorro, New Mexico

Geologic maps are, by their very nature, interpretive documents. In contrast, images prepared from AVIRIS data can be used as uninterpreted, and thus unbiased, geologic maps. We are having significant success applying AVIRIS data in this non-quantitative manner to geologic problems. Much of our success has come from the power of the Linked Windows Interactive Data System. LinkWinds is a visual data analysis and exploration system under development at JPL which is designed to rapidly and interactively investigate large multivariate data sets. In this paper, we present information on the analysis technique, and preliminary results from research on potassium metasomatism, a distinctive and structurally significant type of alteration associated with crustal extension.

Chapin, C. E.↗

NASA NTRS2018

The Surface Water and Ocean Topography Mission

The SWOT mission is a partnership between two communities, physical oceanography and hydrology, to share high vertical accuracy and high spatial resolution topography data produced by the science payload, whose principal instrument is a Ka-band radar Interferometer. The SWOT mission will provide large-scale data sets of ocean sea-surface height resolving scales of 15km (in wavelength) and larger, allowing the characterization of ocean mesoscale and submesoscale circulation. Present altimeter constellations can only resolve the ocean circulation at wavelengths larger than 200km. SWOT will address fundamental questions on the dynamics of ocean variability at wavelengths shorter than 200km, which encompasses mesoscale and submesoscale processes such as the formation, evolution, and dissipation of eddy variability (including narrow currents, fronts, and quasi-geostrophic turbulence) and their role in air-sea interaction.

Zohar, Guy↗

NASA NTRS2020

ZTF Early Observations of Type Ia Supernovae. II. First Light, the Initial Rise, and Time to Reach Maximum Brightness

While it is clear that Type Ia supernovae (SNe) are the result of thermonuclear explosions in C/O white dwarfs (WDs), a great deal remains uncertain about the binary companion that facilitates the explosive disruption of the WD. Here, we present a comprehensive analysis of a large, unique data set of 127 SNe Ia with exquisite coverage by the Zwicky Transient Facility (ZTF). High-cadence (six observations per night) ZTF observations allow us to measure the SN rise time and examine its initial evolution. We develop a Bayesian framework to model the early rise as a power law in time, which enables the inclusion of priors in our model. For a volume-limited subset of normal SNe Ia, we find that the mean power-law index is consistent with 2 in the r(ZTF)-band (a(r) = 2.01 ± 0.02), as expected in the expanding fireball model. There are, however, individual SNe that are clearly inconsistent with a(r) = 2. We estimate a mean rise time of 18.9 days (with a range extending from ∼15 to 22 days), though this is subject to the adopted prior. We identify an important, previously unknown, bias whereby the rise times for higher redshift SNe within a flux-limited survey are systematically underestimated. This effect can be partially alleviated if the power-law index is fixed to α = 2, in which case we estimate a mean rise time of 21.7 days (with a range from ∼18 to 23 days). The sample includes a handful of rare and peculiar SNe Ia. Finally, we conclude with a discussion of lessons learned from the ZTF sample that can eventually be applied to observations from the Vera C. Rubin Observatory.

A. A. Miller↗

NASA NTRS2020

Efficient Active Learning for New Domains

The promise of active learning is to reduce the number of labeled examples required by supervised machine learning algorithms. The largest potential benefits lie in entirely new domains, for which no labeled examples yet exist. Yet to date, most active learning studies are retroactive and demonstrate the benefits that could have been gained if active learning had been used. What are the barriers to true adoption and utilization of active learning? We focus on two: (1) the cold start or class discovery problem, in which active learning methods may struggle to make progress with zero labeled examples, and (2) the cost of having the classifier in the loop to select the next example to be labeled. We assess different active learning approaches in the context of these two barriers and conclude with recommendations for how to employ active learning in new domains. As an example, we report on the use of active learning on a large, novel data set of Mars surface images.

Lu, Steven↗

NASA NTRS2023

Machine Intelligence for Radiation Science: Summary of the Radiation Research Society 67th Annual Meeting Symposium

The era of high-throughput techniques created big data in the medical field and research disciplines. Machine intelligence (MI) approaches can overcome critical limitations on how those large-scale data sets are processed, analyzed, and interpreted. The 67 th Annual Meeting of the Radiation Research Society featured a symposium on MI approaches to highlight recent advancements in the radiation sciences and their clinical applications. This article summarizes three of those presentations regarding recent developments for metadata processing and ontological formalization, data mining for radiation outcomes in pediatric oncology, and imaging in lung cancer.

radiation↗

NASA NTRSDate not supplied

Hydrological Data at the NASA GES DISC: Current Capabilities and New Opportunities

The NASA Goddard Earth Sciences Data and Information Services Center (GES DISC) is one of twelve NASA Earth science data centers that document, process, archive and distribute data from Earth observation missions and projects. GES DISC maintains an archive of several hydrology datasets, including the Land Data Assimilation Systems (LDAS) and the Gravity Recovery and Climate Experiment (GRACE) Data Assimilation for Drought Monitoring (GRACE-DA-DM) data products. These datasets include model output of heat fluxes, rain, snow, soil temperature, soil moisture, and runoff; and observational forcing data, including surface pressure, temperature, precipitation, downward shortwave and longwave radiation, humidity, and wind. The temporal resolution of the hydrology data at GES DISC ranges from hourly to monthly, and spatial resolutions range from 0.1° to 1.0°. The GES DISC provides services which enable users to aggregate, temporally and spatially subset, regrid, and visualize archived data including the GES DISC Subsetter, Hydrology Data Rods, and the Geospatial Interactive Online Visualization and Analysis Infrastructure (GIOVANNI). The Hydrology Data Rods service optimally reorganizes large hydrological data sets as extended time series, providing more efficient access for the hydrological community. The time series data (aka “data rods”) were integrated into hydrology community tools, such as the Data Rods Explorer on HydroShare. Furthermore, the GES DISC is in the process of migrating its data and services to the cloud. Hydrological data available at the GES DISC are now available in the Amazon Web Services (AWS) cloud (us-west-2 region) providing users Direct S3 data access and the capability for cloud computing operations. In this presentation, the hydrology data products and services currently available at the GES DISC will be summarized. Also discussed are the migration to the cloud, user support through this transition, and the status of migrating the data rods service to the cloud.

Ashley Heath↗

DOE OSTI2020

Parallel Particle Advection Bake-Off for Scientific Visualization Workloads

There are multiple algorithms for parallelizing particle advection for scientific visualization workloads. While many previous studies have contributed to the understanding of individual algorithms, our study aims to provide a holistic understanding of how algorithms perform relative to each other on various workloads. To accomplish this, we consider four popular parallelization algorithms and run a “bake-off” study (i.e., an empirical study) to identify the best matches for each. The study includes 216 tests, going to a concurrency of up to 8192 cores and considering data sets as large as 34 billion cells with 300 million particles. Overall, our study informs three important research questions: (1) which parallelization algorithms perform best for a given workload?, (2) why?, and (3) what are the unsolved problems in parallel particle advection? In terms of findings, we find that the seeding box is the most important factor in choosing the best algorithm, and also that there is a significant opportunity for improvement in execution time, scalability, and efficiency.

Pugmire, Dave↗

DOE OSTI2021

Report on Mowry Shale Thermal Maturity Mapping in the Powder River Basin, Wyoming

The Enhanced Oil Recovery Institute (EORI) has completed a map of thermal maturity of the Mowry Shale in the Powder River Basin (PRB). Thermal maturity, the degree to which the total organic carbon in a formation has been transformed from kerogen to producible hydrocarbons due to heat and pressure, is an important measure for not just the quality of a source rock, but also helps for delineating areas more favorable for unconventional drilling. There is a dearth of published Mowry maturity maps available for the PRB and this publication endeavors to provide a detailed map based on a large, public data set covering the Wyoming portion of the PRB. Additional data, currently held confidential by operators in the basin, would be of benefit to future iterations of this map.

58 GEOSCIENCES↗

DOE OSTI2023

Machine Learning Prediction of Fracture Toughness in Hydrogen-charged Stainless Steels

Austenitic stainless steels are structural materials utilized in tritium gas pressure boundaries since they are resistant to hydrogen isotope embrittlement [1-3]. However, exposure to tritium over long periods of time leads to tritium uptake which decays to result in helium ingrowth. This helium ingrowth results in further embrittlement effects which are synergistic with that from the hydrogen isotope [4]. Therefore, it is important for tritium facilities to understand the material limitations of stainless steel in this environment. The Savannah River National Laboratory (SRNL) has available a large experimental data set of austenitic stainless steels which have been exposed to tritium environments for various lengths of time. With the availability of this data set, machine learning (ML) algorithms provide an opportunity to model the embrittlement of stainless steel due to the algorithm’s ability to identify patterns in data sets that are difficult and costly to identify in other manners [5]. Ultimately, the amount and quality of the available data is one defining force in the ability of a ML model to accurately predict the desired outputs. The models developed herein will illustrate the ability for the various algorithms to predict the change in fracture toughness in stainless steels due to hydrogen-isotope embrittlement.

Hoar, Eric T.↗