Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “data diversity”

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 163 records · Page 9
All sourcesNASA NTRSDOE OSTI
DOE OSTI2014

Comparison of Mixed Layer Heights from Airborne High Spectral Resolution Lidar, Ground-based Measurements, and the WRP-Chem Model during CalNex and CARES

The California Research at the Nexus of Air Quality and Climate Change (CalNex) and Carbonaceous Aerosol and Radiative Effects Study (CARES) field campaigns during May and June 2010 provided a data set appropriate for studying characteristics of the planetary boundary layer (PBL). The NASA Langley Research Center (LaRC) airborne High Spectral Resolution Lidar (HSRL) was deployed to California onboard the NASA LaRC B-200 aircraft to aid incharacterizing aerosol properties during these two field campaigns. Measurements of aerosol extinction (532 nm), backscatter (532 and 1064 nm), and depolarization (532 and 1064 nm) profiles during 31 flights, many in coordination with other research aircraft and ground sites, constitute a diverse data set for use in characterizing the spatial and temporal distribution of aerosols, as well as the depth and variability of the daytime mixed layer (ML), which is a subset within the PBL. This work illustrates the temporal and spatial variability of the ML in the vicinity of Los Angeles and Sacramento, CA. ML heights derived from HSRL measurements are compared to PBL heights derived from radiosonde profiles, ML heights measured from ceilometers, and simulated PBL heights from the Weather Research and Forecasting Chemistry (WRF-Chem) community model. Comparisons between the HSRL ML heights and the radiosonde profiles in Sacramento result in a correlation coefficient value (R) of 0.93 (root7 mean-square (RMS) difference of 157 m and bias difference (HSRL radiosonde) of 5 m). HSRL ML heights compare well with those from the ceilometer in the LA Basin with an R of 0.89 (RMS difference of 108 m and bias difference (HSRL Ceilometer) of -9.7 m) for distances of up to 30 km between the B-200 flight track and the ceilometer site. Simulated PBL heights from WRF-Chem were compared with those obtained from all flights for each campaign, producing an R of 0.58 (RMS difference of 604 m and a bias difference (WRF-Chem HSRL) of -157 m) for CalNex and 0.59 (RMS difference of 689 m and a bias difference (WRF-Chem HSRL) of 220 m) for CARES. Aerosol backscatter simulations are also available from WRF15 Chem and are compared to those from HSRL to examine differences among the methods used to derive ML heights.

Scarino, Amy Jo↗
NASA NTRS2010

Lessons Learned from Performance Testing of Humans in Spacesuits in Simulated Reduced Gravity

Introduction: The overarching objective of the Integrated Suit Test (IST) series is to evaluate suited human performance using reduced-gravity analogs and learn what aspects of an EVA suit system affect human performance. For this objective to be successfully achieved, the testing methodology should be valid and reproducible, and the partial-gravity simulations must be as accurate and realistic as possible. Objectives: To highlight some of the key lessons learned about partial-gravity analogs and testing methodology, and to suggest considerations for optimizing the effectiveness and quality of results of future tests. Methods: Performance testing of suited and unsuited subjects was undertaken in different reduced-gravity analogs including the Space Vehicle Mockup Facility s Partial Gravity Simulator (POGO), parabolic flight on the C-9 aircraft, underwater environments including NASA s Extreme Environment Mission Operations (NEEMO) and the Neutral Buoyancy Lab (NBL), and in field analogs including Desert Research and Technology Studies (RATS), the Haughton Mars Project (HMP), and the JSC Rock Pile. Subjects performed level walking, incline/decline walking, running, shoveling, picking up and transferring rocks, kneeling/standing, and task boards. Lessons Learned Analogs: No single analog will properly simulate all aspects of the true partial-gravity environment. The POGO is an ideal environment from the standpoint that there are no time limits or significant volumetric constraints, but it does have several limitations. It allows only 2 translational degrees of freedom (DOF) and applies true partial-gravity offload only through the subject s center of gravity (CG). Also, when a subject is doing non-stationary tasks, significant overhead inertia from the lift column seems to have a negative impact on performance. Parabolic flight allows full translational and rotational DOF and applies offload to all parts of the body, but the simulation lasts less than 30 seconds. When this is coupled with the volumetric constraints of the plane, both task selection and data collection options are significantly limited. The underwater environments also allow all 6 DOF and allow off-loading to be applied throughout the body, but the data collection capabilities are limited to little more than subjective ratings. In addition, water drag negatively affects performance of tasks requiring dynamic motion. Field analogs provide the ability to simulate lunar terrain and more realistic mission-like objectives, but all of them operate at 1-g, so suited human performance testing generally must utilize a reduced-mass or "mockup" suit, depending on study objectives. In general, the ground-based overhead-suspension partial-gravity analogs like POGO allow the most diverse data collection methods possible while still simulating partial gravity. However, as currently designed, the POGO has significant limitations. Design of the Active Response Gravity Offload System (ARGOS) has begun and is focusing on adding full x,y,z translational DOF, improved offload accuracy, increased lift capacity, and active control of the x and y axes to minimize offload system inertia. Additionally, a new gimbal is being designed to reduce mass and inertia and to be able to work with different suits, as the current gimbal only supports suited testing with the Mark III Technology Demonstrator Suit (MKIII).

Norcross, Jason R.↗
DOE OSTI2025

Development of an ERT‐Based Framework for Bentonite Buffers Monitoring From Laboratory Tests: 2. Quantitative Moisture Dynamics Estimation Model

Abstract The long‐term containment of high‐level radioactive waste in geological disposal repositories relies on Engineered Barrier Systems (EBS), with bentonite clay emerging as a candidate material due to its unique properties. Understanding moisture dynamics within bentonite buffers is crucial for EBS performance, as it directly influences the material's swelling capacity, thermal and hydraulic conductivity, mechanical properties, and long‐term evolution under complex thermal‐hydrological‐mechanical (THM) processes. This study develops an advanced Electrical Resistivity Tomography (ERT)‐based framework to quantitatively monitor moisture dynamics under THM conditions. Our framework extends the Waxman‐Smits model to incorporate the coupled effects of temperature, water content, fluid chemistry, and mechanical changes on bentonite's electrical properties. Utilizing HotBENT‐Lab data from our companion paper, which includes electrical conductivity, CT density, and thermocouple measurements, this study offers a novel methodological framework bridging different scales of the model. Our results show that the extended model can estimate water content from ERT data, capturing spatial and temporal variations in moisture distribution within bentonite columns. However, the model tends to overestimate water content compared to CT density‐derived measurements. We address this discrepancy by incorporating a simplified swelling effect model, which improves agreement between ERT and CT density‐based water content estimates. We also discuss model limitations, including simplified treatment of swelling and micropore effects, and propose a conceptual framework for transitioning from laboratory to field applications, addressing challenges such as parameter scalability, field validation methods, and integration of diverse data sources. This ERT‐based framework can potentially advance real‐world moisture monitoring of bentonite‐based EBS in nuclear waste repositories. Plain Language Summary Safely containing high‐level radioactive waste depends on barriers made from materials like bentonite clay, which is effective because it swells and seals in the waste. To ensure these barriers work well over time, it's important to understand how moisture moves through the clay. Our study developed a new method using ERT to monitor moisture levels in bentonite under conditions that mimic those in actual storage sites, including changes in temperature, water content, and mechanical stress. This study improved an existing model to better account for how these factors affect the clay, allowing us to create more accurate moisture maps. Initially, the proposed model overestimated the amount of water in the clay, but its accuracy was improved by factoring in how the clay swells when wet. This study also identified some limitations of the model and suggested ways to adapt it for use in real‐world waste storage sites. This new approach could lead to better monitoring and safety checks for nuclear waste storage systems, helping to ensure long‐term containment. Key Points This work develops an ERT‐based framework extending the Waxman‐Smits model to monitor bentonite moisture dynamics during coupled THM processes The extended model accurately estimates water content from Electrical Resistivity Tomography data, incorporating swelling effects to improve precision This work proposes a conceptual framework for transitioning from laboratory to field applications, advancing EBS monitoring in nuclear waste repositories

Chen, Hang↗
DOE OSTI2025

Leveraging data mining, active learning, and domain adaptation for efficient discovery of advanced oxygen evolution electrocatalysts

Developing advanced catalysts for acidic oxygen evolution reaction (OER) is crucial for sustainable hydrogen production. This study presents a multistage machine learning (ML) approach to streamline the discovery and optimization of complex multimetallic catalysts. Our method integrates data mining, active learning, and domain adaptation throughout the materials discovery process. Unlike traditional trial-and-error methods, this approach systematically narrows the exploration space using domain knowledge with minimized reliance on subjective intuition. Then, the active learning module efficiently refines element composition and synthesis conditions through iterative experimental feedback. The process culminated in the discovery of a promising Ru-Mn-Ca-Pr oxide catalyst. Our workflow also enhances theoretical simulations with domain adaptation strategy, providing deeper mechanistic insights aligned with experimental findings. By leveraging diverse data sources and multiple ML strategies, we demonstrate an efficient pathway for electrocatalyst discovery and optimization. This comprehensive, data-driven approach represents a paradigm shift and potentially benchmark in electrocatalysts research.

Science & Technology - Other Topics↗
NASA NTRSDate not supplied

Air Quality Forecasting at Sub-City Scale by Combining Models, Satellites, and Surface Measures

While there are a variety of sources for air quality information, no one source simultaneously allows for high accuracy, low bias, fine spatial resolution, wide spatial coverage, high temporal frequency, and the capability for near-term forecasting of air quality. Global models, like the NASA’s Goddard Earth Observing System -Composition Forecasting (GEOS-CF) model, provide global coverage and forecasting capabilities, but operate at relatively coarse spatial resolution and require ground-truthing with in-situ data. Polar-orbiting satellite data products, like those of the ESA TROPOspheric Monitoring Instrument (TROPOMI), provide higher-spatial-resolution remote sensing of atmospheric composition, but are limited by cloud cover and overpass times and report column-integrated quantities. Surface measurements, both from regulatory-grade monitors and low-cost networks, measure “nose-level” air quality, but may not represent concentration variability across large spatial domains, and (in the case of low-cost sensors) are subject to interference and biases. There exists a great potential to combine these diverse data sources together, using the strengths of some to offset the weaknesses of others to build a more comprehensive picture of air quality. This presentation will summarize results from ongoing efforts to produce such a combined forecast, with application case studies for surface-level Nitrogen Dioxide forecasting in several major US cities. Furthermore, we will examine the relative impacts and benefits of different data sources on the forecasting accuracy at different spatial and temporal scales. Finally, we will examine the potential for integrating low-cost sensors into such a system, both in terms of using these integrated air quality estimates as a baseline from which to calibrate networks of low-cost sensors in the field, and in terms of using dense networks of low-cost sensors to refine the spatial resolution of integrated air quality forecasts.

Air Quality↗
DOE OSTI2020

Generation of Synthetic Data for a Radiation Detection Algorithm Competition

This paper details the generation of synthetic radiation data using large-scale Monte Carlo transport models to evaluate radiation search detection algorithms. Modular 3-D Monte Carlo models spanning multiple city blocks were constructed, loosely based on downtown Knoxville, TN, containing buildings composed of multiple materials (brick, granite, and concrete), sidewalks, a four-lane road, side streets, parking lots, and grassy fields. Background and simulated source detector response calculations from these models were used to create synthetic list mode data sets for a 2"×4"×16" NaI(Tl) detector moving through a city street at a constant speed. For the background simulations, major isotopes were computed individually so that background composition and variability could be computed efficiently outside Monte Carlo. The source detector response included six simulated sources placed at 15 source locations. Detector response was developed to be periodic through the city street so that a detector path could begin at one end of the model and wrap around to the other. This framework allowed for the creation of diverse data sets, each with its own unique background and simulated source detector response. Synthetic data allows for high-quality labels, which are useful in developing data-driven radiation detection algorithms. This methodology was used to create synthetic data sets which were released as part of a public data competition to spur the development of new radiation detection algorithms for radiological search applications.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2026

From microbial diversity to functional potential using dimensionality reduction

The high dimensionality of microbial diversity data from ‘omics observations can be reduced using Machine Learning, with many recent studies showcasing ML utility for exploratory ecological feature finding and process prediction. Here, we compare the Self Organizing Map (SOM) dimensionality reduction method to the well-documented sample-based Principal Coordinate Analysis (PCoA) and taxa-based Weighted Gene Correlation Network Analysis (WGCNA) using near daily 16S rRNA gene amplicon sequencing data from the 2019 to 2020 MOSAiC International Arctic Drift Expedition. We then map k-means clustering outputs from each method to available metagenomes, extracting functionally distinct seasonal microbial ecotypes in the surface Arctic Ocean. Our results indicate the SOM method better represented expected seasonal transitions and identified a greater number of metabolically distinct functional groups than the more traditional PCoA ordination. Ultimately, we identified four community ecotypes with distinct taxonomic and functional cut-offs driven by seasonality, water mass, and substrate turnover, highlighting the importance of succession in functional diversity for the central Arctic Ocean. These results reinforce ML dimensionality reduction as a meaningful translator in the mining of historical amplicon datasets to address modern mechanistic questions and potentially provide ’omics informed ecotype diversity to leverage in mechanistic biogeochemical models.

Arctic Ocean↗
DOE OSTI2020

DPM: A deep learning PDE augmentation method with application to large-eddy simulation

A framework is introduced that leverages known physics to reduce overfitting in machine learning for scientific applications. The partial differential equation (PDE) that expresses the physics is augmented with a neural network that uses available data to learn a description of the corresponding unknown or unrepresented physics. Training within this combined system corrects for missing, unknown, or erroneously represented physics, including discretization errors associated with the PDE's numerical solution. For optimization of the network within the PDE, an adjoint PDE is solved to provide high-dimensional gradients, and a stochastic adjoint method (SAM) further accelerates training. Additionally, the approach is demonstrated for large-eddy simulation (LES) of turbulence. High-fidelity direct numerical simulations (DNS) of decaying isotropic turbulence provide the training data used to learn sub-filter-scale closures for the filtered Navier–Stokes equations. Out-of-sample comparisons show that the deep learning PDE method outperforms widely-used models, even for filter sizes so large that they become qualitatively incorrect. It also significantly outperforms the same neural network when a priori trained based on simple data mismatch, not accounting for the full PDE. Measures of discretization errors, which are well-known to be consequential in LES, point to the importance of the unified training formulation's design, which without modification corrects for them. For comparable accuracy, simulation runtime is significantly reduced. A relaxation of the typical discrete enforcement of the divergence-free constraint in the solver is also successful, instead allowing the DPM to approximately enforce incompressibility physics. Since the training loss function is not restricted to correspond directly to the closure to be learned, training can incorporate diverse data, including experimental data.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
NASA NTRS2016

Mineralogy of the Mercurian Surface

The MErcury Surface, Space ENvironment, GEochemistry, and Ranging (MESSENGER) spacecraft orbited Mercury for four years until April 2015, revealing its structure, chemical makeup, and compositional diversity. Data from the mission have confirmed that Mercury is a compositional end-member among the terrestrial planets. The X-Ray Spectrometer (XRS) and Gamma-Ray Spectrometer (GRS) on board MESSENGER provided the first detailed geochemical analyses of Mercury's surface. These instruments have been used in conjunction with the Neutron Spectrometer and the Mercury Dual Imaging System to classify numerous geological and geochemical features on the surface of Mercury that were previously unknown. Furthermore, the data have revealed several surprising characteristics about Mercury's surface, including elevated S abundances (up to 4 wt%) and low Fe abundances (less than 2.5 wt%). The S and Fe abundances were used to quantify Mercury's highly reduced state, i.e., between 2.6 and 7.3 log10 units below the Iron-Wustite (IW) buffer. This fO2 is lower than any of the other terrestrial planets in the inner Solar System and has important consequences for the thermal and magmatic evolution of Mercury, its surface mineralogy and geochemistry, and the petrogenesis of the planet's magmas. Although MESSENGER has revealed substantial geochemical diversity across the surface of Mercury, until now, there have been only limited efforts to understand the mineralogical and petrological diversity of the planet. Here we present a systematic and comprehensive study of the potential mineralogical and petrological diversity of Mercury.

Vander Kaaden, Kathleen E.↗
DOE OSTI2024

A semantics-driven framework to enable demand flexibility control applications in real buildings

Decarbonising and digitalising the energy sector requires scalable and interoperable Demand Flexibility (DF) applications. Semantic models are promising technologies for achieving these goals, but existing studies focused on DF applications exhibit limitations. These include dependence on bespoke ontologies, lack of computational methods to generate semantic models, ineffective temporal data management and absence of platforms that use these models to easily develop, configure and deploy controls in real buildings. This paper introduces a semantics-driven framework to enable DF control applications in real buildings. The framework supports the generation of semantic models that adhere to Brick and SAREF while using metadata from Building Information Models (BIM) and Building Automation Systems (BAS). The work also introduces a web platform that leverages these models and an actor and microservices architecture to streamline the development, configuration and deployment of DF controls. The paper demonstrates the framework through a case study, illustrating its ability to integrate diverse data sources, execute DF actuation in a real building, and promote modularity for easy reuse, extension, and customisation of applications. The paper also discusses the alignment between Brick and SAREF, the value of leveraging BIM data sources, and the framework's benefits over existing approaches, demonstrating a 75% reduction in effort for developing, configuring, and deploying building controls.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
NASA NTRSDate not supplied

Earth System Digital Twins (ESDT) Technology for NASA Earth Science

For NASA's Advanced Information Systems Technology (AIST) Program, an Earth System Digital Twin (ESDT) is defined as an interactive and integrated multidomain, multiscale, digital replica of the state and temporal evolution of Earth systems. It dynamically integrates: relevant Earth system models and simulations; other relevant models (e.g., related to the world's infrastructure); continuous and timely (including near real time and direct readout) observations (e.g., space, air, ground, over/underwater, Internet of Things (IoT), socioeconomic); long-time records; as well as analytics and artificial intelligence tools. Effective ESDTs enable users to run hypothetical scenarios to improve the understanding, prediction of and mitigation/response to Earth system processes, natural phenomena and human activities as well as their many interactions. An ESDT is a type of integrated information system that, for example, enables continuous assessment of impact from naturally occurring and/or human activities on physical and natural environments. AIST ESDT strategic goals are to: 1. Develop information system frameworks to provide continuous and accurate representations of systems as they change over time; 2. Mirror various Earth Science systems and utilize the combination of Data Analytics, Artificial Intelligence, Digital Thread, and state-of-the-art models to help predict the Earth’s response to various phenomena; 3. Provide the tools to conduct "what if" investigations that can result in actionable predictions. The AIST ESDT thrust is developing capabilities toward the development of future digital twins of the Earth or of subcomponents of the Earth. This will enable the development of an overarching framework that will integrate New Observing Strategies (NOS) to enable new observation measurements, i.e., multi-source, coordinated, dynamic and responsive to needs and requests defined by Analytic Collaborative Frameworks (ACF) that enable agile science investigations fusing and analyzing very large amounts of diverse data. NOS and ACF capabilities along with open access to various science, infrastructure and human data, interconnected modeling, data assimilation, simulations, surrogate modeling, high-performance computing and advanced visualization, will define a powerful framework that could be utilized for local, regional or global and/or thematic digital twins. This presentation will describe a general overview of the AIST ESDT vision including prior work done in the areas of NOS and ACF as well as current and upcoming ESDT projects.

Jacqueline Le Moigne↗
NASA NTRS2014

Introducing Multisensor Satellite Radiance-Based Evaluation for Regional Earth System Modeling

Earth System modeling has become more complex, and its evaluation using satellite data has also become more difficult due to model and data diversity. Therefore, the fundamental methodology of using satellite direct measurements with instrumental simulators should be addressed especially for modeling community members lacking a solid background of radiative transfer and scattering theory. This manuscript introduces principles of multisatellite, multisensor radiance-based evaluation methods for a fully coupled regional Earth System model: NASA-Unified Weather Research and Forecasting (NU-WRF) model. We use a NU-WRF case study simulation over West Africa as an example of evaluating aerosol-cloud-precipitation-land processes with various satellite observations. NU-WRF-simulated geophysical parameters are converted to the satellite-observable raw radiance and backscatter under nearly consistent physics assumptions via the multisensor satellite simulator, the Goddard Satellite Data Simulator Unit. We present varied examples of simple yet robust methods that characterize forecast errors and model physics biases through the spatial and statistical interpretation of various satellite raw signals: infrared brightness temperature (Tb) for surface skin temperature and cloud top temperature, microwave Tb for precipitation ice and surface flooding, and radar and lidar backscatter for aerosol-cloud profiling simultaneously. Because raw satellite signals integrate many sources of geophysical information, we demonstrate user-defined thresholds and a simple statistical process to facilitate evaluations, including the infrared-microwave-based cloud types and lidar/radar-based profile classifications.

Planetary Boundary Layer↗
NASA NTRS1992

The Global Ocean Observing System

A Global Ocean Observing System (GOOS) should be established now with international coordination (1) to address issues of global change, (2) to implement operational ENSO forecasts, (3) to provide the data required to apply global ocean circulation models, and (4) to extract the greatest value from the one billion dollar investment over the next ten years in ocean remote sensing by the world's space agencies. The objectives of GOOS will focus on climatic and oceanic predictions, on assessing coastal pollution, and in determining the sustainability of living marine resources and ecosystems. GOOS will be a complete system including satellite observations, in situ observations, numerical modeling of ocean processes, and data exchange and management. A series of practical and economic benefits will be derived from the information generated by GOOS. In addition to the marine science community, these benefits will be realized by the energy industries of the world, and by the world's fisheries. The basic oceanic variables that are required to meet the oceanic and predictability objectives of GOOS include wind velocity over the ocean, sea surface temperature and salinity, oceanic profiles of temperature and salinity, surface current, sea level, the extent and thickness of sea ice, the partial pressure of CO2 in surface waters, and the chlorophyll concentration of surface waters. Ocean circulation models and coupled ocean-atmosphere models can be used to evaluate observing system design, to assimilate diverse data sets from in situ and remotely sensed observations, and ultimately to predict future states of the system. The volume of ocean data will increase enormously over the next decade as new satellite systems are launched and as complementary in situ measuring systems are deployed. These data must be transmitted, quality controlled, exchanged, analyzed, and archived with the best state-of-the-art computational methods.

Kester, Dana↗
DOE OSTI2023

Integrated Research Infrastructure Architecture Blueprint Activity (Final Report 2023)

The complexity of scientific pursuits is increasing rapidly with aspects that require dynamic integration of experiment, observation, theory, modeling, simulation, visualization, machine learning (ML), artificial intelligence (AI), and analysis. Research projects across the Department of Energy (DOE) are increasingly data and compute intensive. Innovative research teams are accelerating the pace of discovery by using high-performance computational and data tools in their research workflows and leveraging multiple research infrastructures. Additionally, several recent high-level U.S. government reports underscore the necessity of a new advanced computing ecosystem for international competitiveness and national security. International competitors are moving forward with major research infrastructure integration efforts that seek to capture a competitive advantage in the global innovation race. Owing to its unparalleled constellation of world-class experimental and observational facilities and high-performance and extreme-scale computational, data, and networking infrastructure, DOE is positioned to be a global leader in this new era of integrated science. However, this new integration paradigm will demand continuing evolution to ensure the U.S. remains a global leader in research and innovation. The DOE Office of Science (SC) has seized on the strategic importance of integration and has adopted a vision for Integrated Research Infrastructure (IRI): To empower researchers to meld DOE’s world-class research tools, infrastructure, and user facilities seamlessly and securely in novel ways to radically accelerate discovery and innovation. To respond to the evolving computational requirements of research and the competitive international innovation landscape, experimental facilities could be connected with high performance computing resources for near real-time analysis, and resources should be provided for merging enormous and diverse data for AI/ML techniques and analysis.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

A Multiyear Gridded Data Ensemble of Surface Biogenic Carbon Fluxes for North America: Evaluation and Analysis of Results

Accurate and fine-scale estimates of biogenic carbon fluxes are critical for measuring and monitoring the biosphere's responses and feedback to the climate system. Currently available data products from flux towers and model-intercomparison projects struggle to adequately represent spatiotemporal dynamics of surface biogenic carbon fluxes, and to quantify their uncertainties, which also are crucial to atmospheric inversion systems. To address these gaps, we introduce a new perturbed-parameter model ensemble with the CASA model to estimate surface biogenic carbon fluxes at monthly and 3-hourly scales for North America at ~500-m and 5-km resolutions. We first use the Extended Fourier Amplitude Sensitivity Testing to choose the three most sensitive parameters to be perturbed, maximum light use efficiency (E max ), optimal temperature of photosynthesis (T opt ), and temperature response of respiration (Q 10 ). The initial range for each parameter is broadly sampled for the L1 ensemble, but then we pruned E max with site-level primary productivity to derive an L2 ensemble with narrower uncertainty ranges. Ensembles are strongly correlated with site-level results at both monthly and 3-hourly scales, and the spread across L1/L2 ensemble members encompasses the range of AmeriFlux observations. Monthly variability in the L2 ensemble mean is 85% of the observed variability. The L2 ensemble outperforms diverse data products with the highest Taylor skill scores at diurnal to annual scales. Finally, the ensemble's seasonality agrees well with other models for most biome types and in high and middle latitudes, but inconsistencies are found in subtropical and tropical ecoregions and for annual totals over North America.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Scalable training of trustworthy and energy-efficient predictive graph foundation models for atomistic materials modeling: a case study with HydraGNN

We present our work on developing and training scalable, trustworthy, and energy-efficient predictive graph foundation models (GFMs) using HydraGNN, a multi-headed graph convolutional neural network architecture. HydraGNN expands the boundaries of graph neural network (GNN) computations in both training scale and data diversity. It abstracts over message passing algorithms, allowing both reproduction of and comparison across algorithmic innovations that define nearest-neighbor convolution in GNNs. This work discusses a series of optimizations that have allowed scaling up the GFMs training to tens of thousands of GPUs on datasets consisting of hundreds of millions of graphs. Our GFMs use multitask learning (MTL) to simultaneously learn graph-level and node-level properties of atomistic structures, such as energy and atomic forces. Using over 154 million atomistic structures for training, we illustrate the performance of our approach along with the lessons learned on two state-of-the-art US Department of Energy (US-DOE) supercomputers, namely the Perlmutter petascale system at the National Energy Research Scientific Computing Center and the Frontier exascale system at Oak Ridge Leadership Computing Facility. The HydraGNN architecture enables the GFM to achieve near-linear strong scaling performance using more than 2000 GPUs on Perlmutter and 16,000 GPUs on Frontier.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

Automatic detection of small bowel tumors in wireless capsule endoscopy images using ensemble learning

Purpose Wireless Capsule Endoscopy (WCE) is a minimally invasive diagnosis tool for lesion detection in the gastrointestinal tract, reaching places where conventional endoscopy is unable to. However, the significant amount of acquired data leads to difficulties in the diagnosis by the physicians; which can be eased with computer assistance. This paper addresses a method for the automatic detection of tumors in WCE by using a two‐step based procedure: region of interest selection and classification. Methods The first step aims to separate abnormal from normal tissue by using automatic segmentation based on a Gaussian Mixture Model (GMM). A modified version of the Anderson method for convergence acceleration of the expectation–maximization (EM) algorithm is proposed. The proposed features for both segmentation and classification are based on the CIELab color space, as a way of bypassing lightness variations, where the L component is discarded. Tissue variability among subjects, light inhomogeneities and even intensity differences among different devices can be overcome by using simultaneously features from both regions. In the second step, an ensemble system with partition of the training data with a new training scheme is proposed. At this stage, the gating network is trained after the experts have been trained decoupling the joint maximization of both modules. The partition module is also used at the test step, leading the incoming data to the most likely expert allowing incremental adaptation by preserving data diversity. Results This algorithm outperforms others based on texture features selected from Wavelets and Curvelets transforms, classified by a regular support vector machine (SVM) in more than 5%. Conclusions This work shows that simpler features can outperform more elaborate ones if appropriately designed. In the current case, luminance was discarded to cope with saturated tissue, facilitating the color perception. Ensemble systems remain an open research field. In the current case, changes in both topology and training strategy have led to significant performance improvements. A system with this level of performance can be used in current clinical practice.

Vieira, Pedro M.↗
DOE OSTI2021

Italian prototype building models for urban scale building performance simulation

Urban building energy modeling (UBEM) seeks to evaluate strategies to optimize building energy use at urban scale to support a city's building energy goals. Prototype building models are usually developed to represent typical urban building characteristics of a specific use type, construction year, and climate zone, as detailed characteristics of individual buildings at urban scale are difficult to obtain. This study investigated the Italian building stock, developing 46 building prototypes, based on construction year, for residential and office buildings. The study included 16 single-family buildings, 16 multi-family buildings, and 14 office buildings. Building envelope properties and heating, ventilation, and air conditioning system characteristics were defined according to existing building energy codes and standards for climatic zone E, which covers about half the Italian municipalities. Novel contributions of this study include (1) detailed specifications of prototype building energy models for Italian residential and office buildings that can be adopted by UBEM tools, and (2) a dataset in GeoJSON format of Italian urban buildings compiled from diverse data sources and national standards. Finally, the developed prototype building specifications, the building dataset, and the workflow can be applied to create other building prototypes and to support Italian national building energy efficiency and environmental goals.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗