SEARCH · Search NASA

Results for “scoring system”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

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

At least 181 records · Page 10

All sources NASA NTRS DOE OSTI

DOE OSTI2022

Estimate of the Mass and Radial Profile of the Orphan–Chenab Stream's Dwarf-galaxy Progenitor Using MilkyWay@home

We fit the mass and radial profile of the Orphan–Chenab Stream's (OCS) dwarf-galaxy progenitor by using turnoff stars in the Sloan Digital Sky Survey and the Dark Energy Camera to constrain N-body simulations of the OCS progenitor falling into the Milky Way on the 1.5 PetaFLOPS MilkyWay@home distributed supercomputer. We infer the internal structure of the OCS's progenitor under the assumption that it was a spherically symmetric dwarf galaxy composed of a stellar system embedded in an extended dark matter halo. We optimize the evolution time, the baryonic and dark matter scale radii, and the baryonic and dark matter masses of the progenitor using a differential evolution algorithm. The likelihood score for each set of parameters is determined by comparing the simulated tidal stream to the angular distribution of OCS stars observed in the sky. We fit the total mass of the OCS's progenitor to (2.0 ± 0.3) × 10 7 M ⊙ with a mass-to-light ratio of γ = 73.5 ± 10.6 and (1.1 ± 0.2) × 10 6 M ⊙ within 300 pc of its center. Within the progenitor's half-light radius, we estimate a total mass of (4.0 ± 1.0) × 10 5 M ⊙ . We also fit the current sky position of the progenitor's remnant to be (α, δ) = ((166.0 ± 0.9)°, (–11.1 ± 2.5)°) and show that it is gravitationally unbound at the present time. The measured progenitor mass is on the low end of previous measurements and, if confirmed, lowers the mass range of ultrafaint dwarf galaxies. Our optimization assumes a fixed Milky Way potential, OCS orbit, and radial profile for the progenitor, ignoring the impact of the Large Magellanic Cloud.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2026

A machine learning pipeline for identifying infiltration managed aquifer recharge locations from satellite imagery in the San Joaquin Valley, California

This study focuses on an agricultural region in California’s Central Valley, USA, where Managed Aquifer Recharge (MAR) is widely implemented to mitigate groundwater depletion under increasing water demand and climate variability. A deep learning and machine learning framework was developed to identify infiltration-MAR locations using satellite imagery and environmental data. The framework integrates surface water detection from Sentinel-2 imagery, geospatial delineation of water bodies, spatiotemporal tracking of water body dynamics, and supervised classification using meteorological, environmental, and topographic variables. The framework was applied to a 2379 km² study area southwest of Fresno, where 765 water bodies were detected, including 139 identified MAR sites based on publicly available datasets and expert knowledge. The classification model achieved an accuracy of 0.94 and an F1 score of 0.85. Feature importance analysis indicates that cropland, normalized difference vegetation index (NDVI), and evaporation are among the most influential predictors for infiltration-MAR. Notably, the framework suggests that engineered water management in infiltration-MAR systems can disrupt or even reverse the expected positive correlation between surface water extent and precipitation. These findings provide physically interpretable insights into the characteristics of existing infiltration-MAR facilities and demonstrate the potential of the proposed framework as a reproducible, interpretable, and potentially transferable tool for data-driven infiltration-MAR identification and inventory development under growing climatic and hydrological uncertainty.

Classification↗

DOE OSTI2025

Accelerating detector simulations with Celeritas: Profiling and performance optimizations

Celeritas is a GPU-optimized Monte Carlo (MC) particle transport code designed to meet the growing computational demands of next-generation high energy physics (HEP) experiments. It provides efficient simulation of electromagnetic (EM) physics processes in complex geometries with magnetic fields, detector hit scoring, and seamless integration into Geant4-driven applications to offload EM physics to GPUs. Recent efforts have focused on performance optimizations and expanding profiling capabilities. This paper presents some key advancements, including the integration of the Perfetto system profiling tool for detailed performance analysis and the development of track-sorting methods to improve computational efficiency.

Lund, Amanda [Argonne National Laboratory (ANL)]↗

DOE OSTI2021

Shotgun Immunoproteomic Approach for the Discovery of Linear B-Cell Epitopes in Biothreat Agents Francisella tularensis and Burkholderia pseudomallei

Peptide-based subunit vaccines are coming to the forefront of current vaccine approaches, with safety and cost-effective production among their top advantages. Peptide vaccine formulations consist of multiple synthetic linear epitopes that together trigger desired immune responses that can result in robust immune memory. The advantages of linear compared to conformational epitopes are their simple structure, ease of synthesis, and ability to stimulate immune responses by means that do not require complex 3D conformation. Prediction of linear epitopes through use of computational tools is fast and cost-effective, but typically of low accuracy, necessitating extensive experimentation to verify results. On the other hand, identification of linear epitopes through experimental screening has been an inefficient process that requires thorough characterization of previously identified full-length protein antigens, or laborious techniques involving genetic manipulation of organisms. In this study, we apply a newly developed generalizable screening method that enables efficient identification of B-cell epitopes in the proteomes of pathogenic bacteria. As a test case, we used this method to identify epitopes in the proteome of Francisella tularensis (Ft), a Select Agent with a well-characterized immunoproteome. Our screen identified many peptides that map to known antigens, including verified and predicted outer membrane proteins and extracellular proteins, validating the utility of this approach. We then used the method to identify seroreactive peptides in the less characterized immunoproteome of Select Agent Burkholderia pseudomallei (Bp). This screen revealed known Bp antigens as well as proteins that have not been previously identified as antigens. Although B-cell epitope prediction tools Bepipred 2.0 and iBCE-EL classified many of our seroreactive peptides as epitopes, they did not score them significantly higher than the non-reactive tryptic peptides in our study, nor did they assign higher scores to seroreactive peptides from known Ft or Bp antigens, highlighting the need for experimental data instead of relying on computational epitope predictions alone. The present workflow is easily adaptable to detecting peptide targets relevant to the immune systems of other mammalian species, including humans (depending upon the availability of convalescent sera from patients), and could aid in accelerating the discovery of B-cell epitopes and development of vaccines to counter emerging biological threats.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2025

Accelerating detector simulations with Celeritas: profiling and performance optimizations

Celeritas is a GPU-optimized MC particle transport code designed to meet the growing computational demands of next-generation HEP experiments. It provides efficient simulation of EM physics processes in complex geometries with magnetic fields, detector hit scoring, and seamless integration into Geant4-driven applications to offload EM physics to GPUs. Recent efforts have focused on performance optimizations and expanding profiling capabilities. This paper presents some key advancements, including the integration of the Perfetto system profiling tool for detailed performance analysis and the development of track-sorting methods to improve computational efficiency.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2021

Identifying schools at high-risk for elevated lead in drinking water using only publicly available data

Estimating the risk of lead contamination of schools' drinking water at the State level is a complex, important, and unexplored challenge. Variable water quality among water systems and changes in water chemistry during distribution affect lead dissolution rates from pipes and fittings. In addition, the locations of lead-bearing plumbing materials are uncertain. We tested the capability of six machine learning models to predict the likelihood of lead contamination of drinking water at the schools' taps using only publicly available datasets. The predictive features used in the models correspond to those with a proven correlation to the dominant, but commonly unavailable, factors that govern lead leaching: the presence of lead-bearing plumbing materials and water quality conducive to lead corrosion. By combining water chemistry data from public reports, socioeconomic information from the US census, and spatial features using Geographic Information Systems, we trained and tested models to estimate the likelihood of lead contaminated tap water in over 8,000 schools across California and Massachusetts. Our best-performing model was a Random Forest, with a 10-fold cross validation score of 0.88 for Massachusetts and 0.78 for California using the average Area Under the Receiver Operating Characteristic Curve (ROC AUC) metric. The model was then used to assign a lead leaching risk category to half of the schools across California (the other half was used for training). There was good agreement between the modeled risk categories and the actual lead leaching outcomes for every school; however, the model overestimated the lead leaching risk in up to 17% of the schools. This model is the first of its kind to offer a tool to predict the risk of lead leaching in schools at the State level. Further use of this model can help deploy limited resources more effectively to prevent childhood lead exposure from school drinking water.

63 RADIATION, THERMAL, AND OTHER ENVIRON. POLLUTAN↗

DOE OSTI2021

A meta-learning based distribution system load forecasting model selection framework

This paper presents a meta-learning based, automatic distribution system load forecasting model selection framework. Furthermore, the framework includes the following processes: feature extraction, candidate model preparation and labeling, offline training, and online model recommendation. Using load forecasting needs and data characteristics as input features, multiple metalearners are used to rank the candidate load forecast models based on their forecasting accuracy. Then, a scoring-voting mechanism is proposed to weights recommendations from each meta-leaner and make the final recommendations. Heterogeneous load forecasting tasks with different temporal and technical requirements at different load aggregation levels are set up to train, validate, and test the performance of the proposed framework. Simulation results demonstrate that the performance of the meta-learning based approach is satisfactory in both seen and unseen forecasting tasks.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2025

Corral Summit Pumped Storage Hydropower Hybrid: Site Suitability Assessment

In 2024, Idaho National Laboratory (INL) and Pacific Northwest National Laboratory (PNNL) initiated a technical-assistance project to support Cat Creek Energy, LLC, (CCE) in evaluating site suitability for the proposed Corral Summit Pumped Storage Hydropower (PSH) project in south-central Idaho near Mackay Reservoir. The Corral Summit facility incorporates battery storage and photovoltaic (PV) solar arrays in a Trybrid configuration to deliver large-volume long-duration (LVLD) storage solutions for rural electric cooperatives in eastern Idaho. The evaluation process focused on determining the most-suitable location for the upper reservoir of the PSH system, guided by a comprehensive assessment framework spanning multiple categories, including physical characteristics, environmental constraints, building infrastructure, regulatory constraints, cultural resources and sensitivity, social factors, and power market and grid integration. Each site was analyzed based on a ranking scale (0–1), which scores ranging from “severely disfavored” to “highly favored,” allowing detailed comparisons of site-specific conditions. Categories such as hydraulic head, utilities corridor, land ownership, and transmission-grid limitations emerged as key contributors to the overall assessment. Site 2 (Idaho Trust) demonstrated a slight advantage over Site 1 (Bureau of Land Management) primarily due to favorable outcomes in regulatory constraints, building infrastructure, and power-market integration. However, Site 1 outperformed Site 2 in factors related to physical characteristics and social factors. The report emphasizes the need for further evaluation of both sites before clear determination of which site is preferred, due to the limited information available on either site at the time of this report. Key areas of evaluation to clearly define the preferred site are ecological impacts, cultural-resource surveys, and economic-feasibility assessments. For successful project execution, recommended follow-up actions include seismic and geotechnical surveys, groundwater and habitat monitoring, regulatory reviews of water rights and right-of-way agreements, cultural engagement with local tribal governments, and enhanced stakeholder strategies. These efforts will ensure the Corral Summit Trybrid facility meets local energy needs while balancing environmental, social, and regulatory responsibilities.

13 - HYDRO ENERGY↗

DOE OSTI2026

Fine-Grained Power and Energy Attribution on AMD GPU/APU-Based Exascale Nodes

Modern exascale GPU- and APU-based systems provide multiple power and energy sensors, but differences in scope, update rate, timing, and filtering complicate the attribution of short-lived accelerator activity. This paper presents a methodology to characterize and correct these effects on Cray EX systems with AMD Instinct MI250X GPUs (Frontier) and MI300A APUs (Portage). Using controlled square-wave workloads, we quantify update intervals, delay, aliasing, and variability across up to 512 GPUs and 480 APUs with on-chip (rocm-smi/amd-smi) and off-chip Cray Power Management sensors. We reconstruct power from cumulative energy counters to achieve faster response times, validate it against on-chip, off-chip, and node-level sensors, and integrate the resulting streams into a Score-P/PAPI-based tool for time-aligned, phase-level attribution. Applied to rocHPL, rocHPL-MxP, and HPG-MxP, the method separates energy savings due to reduced runtime from changes in power. Mixed precision reduces node energy on Frontier by 79% for rocHPL-MxP and 31% for HPG-MxP, with similar trends on Portage. These results provide portable guidance for sensor validation and power-aware optimization on current and future exascale systems.

Mcdaniel, Adam [ORNL] (ORCID:000000016926028X)↗

DOE OSTI2023

Artificial intelligence-empowered cellular morphometric risk score improves prognostic stratification of cutaneous squamous cell carcinoma

Abstract Background Risk stratification of cutaneous squamous cell carcinoma (cSCC) is essential for managing patients. Objectives To determine if artificial intelligence and machine learning might help to stratify patients with cSCC by risk using more than solely clinical and histopathological factors. Methods We retrieved a retrospective cohort of 104 patients whose cSCCs had been excised with clear margins. Clinical and histopathological risk factors were evaluated. Haematoxylin and eosin-stained slides were scanned and analysed by an algorithm based on the stacked predictive sparse decomposition technique. Cellular morphometric biomarkers (CMBs) were identified via machine learning and used to derive a cellular morphometric risk score (CMRS) that classified cSCCs into clusters of differential prognoses. Concordance analysis, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and accuracy were calculated and compared with results obtained with the Brigham and Women’s Hospital (BWH) staging system. The performance of the combination of the BWH staging system and the CMBs was also analysed. Results There were no differences among the CMRS groups in terms of clinical and histopathological risk factors and T-stage assignment, but there were significant differences in prognosis. Combining the CMRS with BWH staging systems increased distinctiveness and improved prognostic performance. C-indices were 0.91 local recurrence and 0.91 for nodal metastasis when combining the two approaches. The NPV was 94.41% and 96.00%, the PPV was 36.36% and 41.67%, and accuracy reached 86.75% and 89.16%, respectively, with the combined approach. Conclusions CMRS is helpful for cSCC risk stratification beyond classic clinical and histopathological risk features. Combining the information from the CMRS and the BWH staging system offers outstanding prognostic performance for patients with high-risk cSCC.

Pérez-Baena, Manuel J.↗

DOE OSTI2023

Trust Model System for the Energy Grid of Things Network Communications

Network communication is crucial in the Energy Grid of Things (EGoT). Without a network connection, the energy grid becomes just a power grid where the energy resources are available to the customer uni-directionally. A mechanism to analyze and optimize the energy usage of the grid can only happen through a medium, a communications network, that enables information exchange between the grid participants and the service provider. Security implementers of EGoT network communication take extraordinary measures to ensure the safety of the energy grid, a critical infrastructure, as well as the safety and privacy of the grid participants. With the dynamic nature of network communication of the EGoT, the information provided by the customer or the service provider can be falsified by a malicious attacker. Therefore, a trust model is necessary to monitor any abnormal activities. This paper describes a distributed trust model system that meets the need of the EGoT. This paper describes methods for evaluating and improving the distributed trust model using standard hypothesis testing metrics such as true positive, false positive, true negative, false negative, equal error rate, and F1 score. Example calculations are shown based on generated sample data.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2025

Automating Bug Report Classification with Few Shot Learning

Orthogonal defect classification (ODC) is a method used to categorize software defects, providing valuable insights into the development process. This study focuses on automating the classification of software bug reports into different ODC defect types using few shot learning, a machine learning approach that requires minimal labeled data. Previous research has manually classified bug reports or used traditional machine learning algorithms like linear support vector machine, achieving limited success. Our approach uses few shot learning to improve classification accuracy and efficiency. The results show a harmonic mean of recall and precision (i.e., the F1 score) of around 0.6 which is a performance improvement over previous methods. The results highlight the potential benefit of few shot learning techniques and their application in enhancing the safety and reliability of nuclear digital instrumentation and control (DI&C) systems. Future work will explore incorporating advanced techniques to supplement the model's training data and achieve better results.

42 - ENGINEERING↗

DOE OSTI2025

Corral Summit Pumped Storage Hydropower Hybrid Site Suitability Assessment (Rev.1)

13 - HYDRO ENERGY↗

DOE OSTI2022

Survival analysis of localized prostate cancer with deep learning

In recent years, data-driven, deep-learning-based models have shown great promise in medical risk prediction. By utilizing the large-scale Electronic Health Record data found in the U.S. Department of Veterans Affairs, the largest integrated healthcare system in the United States, we have developed an automated, personalized risk prediction model to support the clinical decision-making process for localized prostate cancer patients. This method combines the representative power of deep learning and the analytical interpretability of parametric regression models and can implement both time-dependent and static input data. To collect a comprehensive evaluation of model performances, we calculate time-dependent C-statistics C td over 2-, 5-, and 10-year time horizons using either a composite outcome or prostate cancer mortality as the target event. The composite outcome combines the Prostate-Specific Antigen (PSA) test, metastasis, and prostate cancer mortality. Our longitudinal model Recurrent Deep Survival Machine (RDSM) achieved C td 0.85 (0.83), 0.80 (0.83), and 0.76 (0.81), while the cross-sectional model Deep Survival Machine (DSM) attained C td 0.85 (0.82), 0.80 (0.82), and 0.76 (0.79) for the 2-, 5-, and 10-year composite (mortality) outcomes, respectively. In addition to estimating the survival probability, our method can quantify the uncertainty associated with the prediction. The uncertainty scores show a consistent correlation with the prediction accuracy. We find PSA and prostate cancer stage information are the most important indicators in risk prediction. Our work demonstrates the utility of the data-driven machine learning model in prostate cancer risk prediction, which can play a critical role in the clinical decision system.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2021

Photometric redshifts for the S-PLUS Survey: Is machine learning up to the task?

The Southern Photometric Local Universe Survey (S-PLUS) is a novel project that aims to map the Southern Hemisphere using a twelve filter system, comprising five broad-band SDSS-like filters and seven narrow-band filters optimized for important stellar features in the local universe. In this paper we use the photometry and morphological information from the first S-PLUS data release (S-PLUS DR1) cross-matched to unWISE data and spectroscopic redshifts from Sloan Digital Sky Survey DR15. We explore three different machine learning methods (Gaussian Processes with GPz and two Deep Learning models made with TensorFlow) and compare them with the currently used template-fitting method in the S-PLUS DR1 to address whether machine learning methods can take advantage of the twelve filter system for photometric redshift prediction. Using tests for accuracy for both single-point estimates such as the calculation of the scatter, bias, and outlier fraction, and probability distribution functions (PDFs) such as the Probability Integral Transform (PIT), the Continuous Ranked Probability Score (CRPS) and the Odds distribution, we conclude that a deep-learning method using a combination of a Bayesian Neural Network and a Mixture Density Network offers the most accurate photometric redshifts for the current test sample. In conclusion, it achieves single-point photometric redshifts with scatter (σ NMAD ) of 0.023, normalized bias of -0.001, and outlier fraction of 0.64% for galaxies with r_auto magnitudes between 16 and 21.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2025

Abbreviated Report for 25-FS-011: Switch and Stitch Similar Subgraph Synthesizer

Government institutions utilize software from a wide array of development sources, including those written by large software companies, government contractors, and open-source repositories. Avoiding installation of malicious software components is an important national security endeavor. Automated analysis of previously unseen software is an active research area, and there is much research in the design of systems that compare new software artifacts to a large set of previously seen software records organized by various behaviors they contain. One attractive approach is to turn each compiled software binary into a graph representation and apply a graph similarity model that scores pairs of binaries by their relative similarity. When a pair is deemed similar, it is useful to know why, in the sense of providing explanations to security analysts regarding which portions of the software they should look into further.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗

DOE OSTI2024

Imitating the “breeder's eye”: Predicting grain yield from measurements of non‐yield traits

Abstract Plant breeding relies on information gathered from field trials to select promising new crop varieties for release to farmers and to develop genomic prediction models that can enhance the efficiency of genetic improvement in future breeding cycles. However, generating the genetic marker data required to apply genomic prediction at the early stages of a breeding program remains costly for many public‐sector breeding programs as well as for many plant breeders operating in developing countries. As the pace of climate change intensifies, the time lag of developing and deploying new crop varieties requires plant breeders to make selection decisions without knowing the future environments those crop varieties will encounter in farmers’ fields. Therefore, both lower cost and higher accuracy methods for prediction of crop performance are essential for creating and maintaining resilient agricultural systems in the latter half of the 21 st century. To address this challenge, we conducted linked yield trials of 752 public maize ( Zea mays ) genotypes in two distinct environments. We developed and trained a phenotypic prediction model to predict yield from manually scored plant traits. The phenotypic prediction approach we employed outperformed genomic prediction in predicting yields in a second environment, with 8.7%–63% higher R 2 and 4%–13% less root mean square error than the genomic prediction. The phenotypic prediction has the potential to be applied to a wider range of breeding programs, including those that lack the resources to genotype large populations, such as programs in the developing world, breeding programs for specialty crops, and public sector programs.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2025

Analyzing and Exploring Training Recipes for Large-Scale Transformer-Based Weather Prediction

Abstract The rapid rise of deep learning (DL) in numerical weather prediction (NWP) has led to a proliferation of models which forecast atmospheric variables with comparable or superior skill than traditional physics-based NWP. However, among these leading DL models, there is a wide variance in both the training settings and architecture used. Further, the lack of thorough ablation studies makes it hard to discern which components are most critical to success. In this work, we show that it is possible to attain high forecast skill even with relatively off-the-shelf architectures, simple training procedures, and moderate compute budgets. Specifically, we train a minimally modified Swin Transformer V2 (SwinV2) on ERA5 data and find that it attains superior skill in terms of mean-square errors of deterministic forecasts when compared against the European Centre for Medium-Range Weather Forecasts’ Integrated Forecasting System (IFS). Almost all DL–NWP systems share a core set of hyperparameters and design decisions. To aid and expedite future DL–NWP research, we present an in-depth, systematic exploration of different loss functions, model sizes and depths, patch sizes, and multistep training objectives. We also examine the model performance with metrics beyond the typical accuracy (ACC) and RMSE and investigate how the performance scales with model size. Through our open-source code, scoring pipelines, and models, we share our findings on key aspects of the training pipeline. These ablations reduce the necessity for expensive hyperparameter tuning and lower the barrier to entry for future DL–NWP research. Significance Statement This study investigates the potential of using large-scale transformer-based models for weather prediction, showing that it is possible to achieve high forecast accuracy with simpler, off-the-shelf architectures. By training a minimally modified SwinV2 transformer on ERA5 data, we show that the model achieves competitive forecast skill in terms of mean-square error for key variables, outperforming the European Centre for Medium-Range Weather Forecasts’ Integrated Forecasting System (IFS) at all lead times. Our findings suggest that effective training strategies, such as multistep fine-tuning and channel-weighted losses, significantly enhance the model’s performance. However, we also highlight that these improvements come with trade-offs in other areas, such as ensemble spread and high-frequency spatial detail. This work highlights the promise of deep learning in improving weather forecasts, which could lead to better preparedness and response to weather events, ultimately benefiting society by providing more reliable weather predictions.

Willard, Jared D. [Lawrence Berkeley National Labo↗