Search NASA⌕ Search

SEARCH · Search NASA

Results for “Benchmark dataset”

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 325 records · Page 18
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

CISME report on experiments with HMX powder, PBX 9501 prills, and heated PBX 9501

The ability to predict post-ignition explosive response is relevant to explosives safety, particularly weapons assembly/disassembly operations that must operate under a sufficiently conservative safety basis to meet risk mitigation criteria for inadvertent nuclear detonation (IND). In particular, hazard determinations hinge on whether the PBX 9501 main charge can ultimately attain detonation from an initial, non-shock, ignition stimulus. The CISME experiment uses a spherical explosive charge, which is thermally ignited in the center using a fiber-delivered infrared laser pulse. This ignition mechanism - i.e. a localized thermal hotspot - is representative of the ignition-causing insults typical in accident scenarios, including low-velocity impact, drop, skid, and punch events. In fiscal year 2018 CISME experiments were conducted with pristine PBX 9501 spheres, confined and unconfined. Sub-detonative, low-violence reactions were observed. Here we report experiments conducted since 2018. The explosive charge was varied: experiments were conducted with room temperature pour-density HMX powder and prills of PBX 9501, and heated, thermally damaged PBX 9501. Experiments were conducted in a confined configuration, with two 4 mm-thick stainless-steel hemispherical shells bolted around the sphere. Detonation, via DDT (deflagration-to-detonation transition) was observed in the 3-inch diameter powdered HMX and the 6-inch diameter heated and thermally-damaged PBX 9501 tests. No transition to DDT was observed in smaller diameters for those configurations, and no DDT was observed for pour-density prills of PBX 9501 of any diameter. The original test series demonstrated that the response of pristine, undamaged PBX 9501 to a central ignition is relatively benign. This new test series shows that increased porosity, lack of polymer binders and thermal damage can greatly increase the violence of the post-ignition response, up to and including detonation. These results bridge the explosive response of PBX 9501 from sub-detonative through detonation as a function of diameter and provide valuable test cases for modeling efforts that strive to capture the DDT threshold. By exploring explosive response in a more representative 3D geometry, we can also benchmark these new results to more plentiful DDT datasets generated from testing in 1D tube confinement (the historical test configuration)–the configuration upon which almost all DDT models were developed.

42 ENGINEERING↗
DOE OSTI2026

AMVOS: Additive Manufacturing Video Object Segmentation Dataset

This dataset provides labeled video frames from four additive manufacturing (AM) processes for video object segmentation (VOS) tasks. It contains 90 video segments comprising 900 individually annotated frames across five AM datasets: laser hot-wire directed energy deposition (LHW-DED), tungsten inert gas wire arc additive manufacturing (TIG-WAAM), plasma arc welding (PAW), visible-light polymer extrusion (visPolymer), and near-infrared polymer extrusion (irPolymer). Each video segment consists of 10 contiguous frames with corresponding pixel-level object instance annotations. Depending on the process, two of four object classes are labeled per frame: Melt Pool, Feed Wire, Nozzle, or Material. Raw frames are provided as .jpg files and annotations as palettized .png files. The dataset follows the directory structure of established VOS benchmarks (DAVIS, YouTube-VOS, MOSE), enabling direct integration into VOS model training and evaluation pipelines for foundation model fine-tuning, domain adaptation, or zero-shot performance benchmarking. Data was collected at Oak Ridge National Laboratory's Manufacturing Demonstration Facility.

Wetzel, Jon [ORNL]↗
NASA NTRS1991

Navier-Stokes analysis of a liquid rocket engine disk cavity

This paper presents a Navier-Stokes analysis of hydrodynamic phenomena occurring in the aft disk cavity of a liquid rocket engine turbine. The cavity analyzed in the Space Shuttle Main Engine Alternate Turbopump currently being developed by NASA and Pratt and Whitney. Comparison of results obtained from the Navier-Stokes code for two rotating disk datasets available in the literature are presented as benchmark validations. The benchmark results obtained using the code show good agreement relative to experimental data, and the turbine disk cavity was analyzed with comparable grid resolution, dissipation levels, and turbulence models. Predicted temperatures in the cavity show that little mixing of hot and cold fluid occurs in the cavity and the flow is dominated by swirl and pumping up the rotating disk.

Benjamin, Theodore G.↗
DOE OSTI2026

Intercomparison of flood inundation models across land use types and hydrological flood stages

Flood Inundation Mapping (FIM) model selection is a key operational decision because accurate, rapid mapping underpins early warning and resource allocation. FIM performance is context-dependent and can vary with hydrograph phase, land-use/land-cover (LULC), and the evaluation benchmark. Intercomparison studies typically assess a single near-peak snapshot against one reference dataset. Here, we provide a context-stratified intercomparison across (i) multiple hydrograph phases, (ii) LULC classes, and (iii) benchmark types, for five FIM approaches spanning a wide range of physical complexity and operational cost (TRITON, LISFLOOD-FP, HEC-RAS 2D, ARC-Curve2Flood, and OWP HAND-FIM). We use the Hurricane Matthew flood (2016) in the Neuse River Basin, North Carolina, USA, as a case study. Using high-resolution remote sensing-derived flood inundation maps, hand-labeled points, and building footprints, we assess model skill across two rising and two falling hydrograph limbs and across major LULC types. Results show that model rankings shift systematically across contexts: LISFLOOD-FP ranks highest in three of four flood phases, while TRITON leads during one rising limb phase; LISFLOOD-FP performs best in vegetated areas, whereas HEC-RAS improves relative performance in agricultural and urban areas; and benchmark choice influences conclusions, with LISFLOOD-FP performing best for flooded-building detection in the late falling limb, while TRITON ranks highest against hand-labeled points. We also report representative wall-clock runtimes for each workflow to provide use-case context for operational feasibility. Together, these results offer transferable guidance for model selection and for designing large-scale, benchmark-aware FIM intercomparison studies.

Nikrou, Parvaneh [University of Alabama]↗
DOE OSTI2021

Autotuning PolyBench benchmarks with LLVM Clang/Polly loop optimization pragmas using Bayesian optimization

Here, we develop a ytopt autotuning framework that leverages Bayesian optimization to explore the parameter space search and compare four different supervised learning methods within Bayesian optimization and evaluate their effectiveness. We select six of the most complex PolyBench benchmarks and apply the newly developed LLVM Clang/Polly loop optimization pragmas to the benchmarks to optimize them. We then use the autotuning framework to optimize the pragma parameters to improve their performance. The experimental results show that our autotuning approach outperforms the other compiling methods to provide the smallest execution time for the benchmarks syr2k, 3mm, heat-3d, lu, and covariance with two large datasets in 200 code evaluations for effectively searching the parameter spaces with up to 170,368 different configurations. We find that the Floyd-Warshall benchmark did not benefit from autotuning. To cope with this issue, we provide some compiler option solutions to improve the performance. Then we present loop autotuning without a user's knowledge using a simple mctree autotuning framework to further improve the performance of the Floyd-Warshall benchmark. We also extend the ytopt autotuning framework to tune a deep learning application.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2026

How efficiently can AI recognize Wireless Devices?

This poster presents a hardware benchmarking methodology for a 3-layer CNN waveform classifier deployed using ONNX Runtime on an NVIDIA Jetson AGX Orin. The dataset consist of 9 signal types, -30 to +30 dB SNR with 5dB increments. Benchmarking on the Jetson AGX Orin gave an accuracy of 91.9% and GPU throughput of 107,120 predictions/sec (23× faster than CPU). The Jetson GPU reached approximately 27M samples/sec with stable performance but fell below the 40 MHz rate needed for real-time radio feeds. Sustained testing of 5 minutes confirmed stable performance with no memory leaks, establishing a reproducible benchmarking baseline for future edge-deployment optimization.

99 - GENERAL AND MISCELLANEOUS↗
DOE OSTI2025

Fundamental limit of jet tagging

Identifying the origin of high-energy hadronic jets (jet tagging) has been a critical benchmark problem for machine learning in particle physics. Jets are ubiquitous at colliders and are complex objects that serve as prototypical examples of collections of particles to be categorized. Over the last decade, machine learning-based classifiers have replaced classical observables as the state of the art in jet tagging. Increasingly complex machine learning models are leading to increasingly more effective tagger performance. Our goal is to address the question of convergence—are we getting close to the fundamental limit on jet tagging or is there still potential for computational, statistical, and physical insights for further improvements? We address this question using state-of-the-art generative models to create a realistic, synthetic dataset with a known jet tagging optimum. Various state-of-the-art taggers are deployed on this dataset, showing that there is a significant gap between their performance and the optimum. Our dataset and software are made public to provide a benchmark task for future developments in jet tagging and other areas of particle physics.

Artificial intelligence↗
DOE OSTI2025

Cross-functional transferability in foundation machine learning interatomic potentials

The rapid development of foundation potentials (FPs) in machine learning interatomic potentials demonstrates the possibility for generalizable learning of the universal potential energy surface. The accuracy of FPs can be further improved by bridging the model from lower-fidelity datasets to high-fidelity ones. In this work, we analyze the challenge of this transfer learning (TL) problem within the CHGNet framework. We show that significant energy scale shifts and poor correlations between GGA and r 2 SCAN hinder cross-functional transferability. By benchmarking different TL approaches on the MP-r 2 SCAN dataset, we demonstrate the importance of elemental energy referencing in the TL of FPs. By comparing the scaling law with and without the pre-training on a low-fidelity dataset, we show that significant data efficiency can still be achieved through TL, even with a target dataset of sub-million structures. We highlight the importance of proper TL and multi-fidelity learning in creating next-generation FPs on high-fidelity data.

Huang, Xu [University of California, Berkeley, CA ↗
NASA NTRS2023

AgMIP-Wheat Multi-Model Simulations on Climate Change Impact and Adaptation for Global Wheat

The climate change impact and adaptation simulations from the Agricultural Model Intercomparison and Improvement Project (AgMIP) for wheat provide a unique dataset of multi-model ensemble simulations for 60 representative global locations covering all global wheat mega environments. The multi-model ensemble reported here has been thoroughly benchmarked against a large number of experimental data, including different locations, growing season temperatures, atmospheric CO2 concentration, heat stress scenarios, and their interactions. In this paper, we describe the main characteristics of this global simulation dataset. Detailed cultivar, crop management, and soil datasets were compiled for all locations to drive 32 wheat growth models. The dataset consists of 30-year simulated data including 25 output variables for nine climate scenarios, including Baseline (1980-2010) with 360 or 550 ppm CO2, Baseline +2oC or +4oC with 360 or 550 ppm CO2, a mid-century climate change scenario (RCP8.5, 571 ppm CO2), and 1.5°C (423 ppm CO2) and 2.0oC (487 ppm CO2) warming above the pre-industrial period (HAPPI). This global simulation dataset can be used as a benchmark from a well-tested multi-model ensemble in future analyses of global wheat. Also, resource use efficiency (e.g., for radiation, water, and nitrogen use) and uncertainty analyses under different climate scenarios can be explored at different scales. The DOI for the dataset is 10.5281/zenodo.4027033 (AgMIP-Wheat, 2020), and all the data are available on the data repository of Zenodo (http://doi.org/10.5281/zenodo.4027033). Two scientific publications have been published based on some of these data here.

Agricultural Model Intercomparison and Improvement↗
DOE OSTI2020

Automated detection of part quality during two-photon lithography via deep learning

Two-photon lithography (TPL) is an additive manufacturing technique for fabricating three-dimensional objects with nanoscale features. A main challenge of TPL is the routine and labor-intensive task of finding suitable light dosage parameters, i.e. writing speed and laser intensity that induce photo-polymerization within a wide variety of candidate photo-curing polymers. Another challenge is the monitoring required during fabrication. In this work, we apply machine learning (ML) models to accelerate the process of identifying optimal light dosage parameters and automate the detection of part quality. We curate TPL videos of different parts fabricated under a range of light dosage parameters using different resins and train spatial-temporal ML models on this data. Our results show that ML models can detect TPL part quality with a 95.1% accuracy in milliseconds. We also evaluate classification failures and identify two operating modes: parameter optimization and part quality detection. Last but not least, we publicly release this labelled dataset so that it may serve as a useful benchmark to the community. Our approach to process optimization and part quality detection addresses important aspects of TPL industrialization, is applicable beyond TPL and should benefit other additive manufacturing techniques with similar barriers to operating at industrial scale.

36 MATERIALS SCIENCE↗
DOE OSTI2022

A three-year dataset supporting research on building energy management and occupancy analytics

Abstract This paper presents the curation of a monitored dataset from an office building constructed in 2015 in Berkeley, California. The dataset includes whole-building and end-use energy consumption, HVAC system operating conditions, indoor and outdoor environmental parameters, as well as occupant counts. The data were collected during a period of three years from more than 300 sensors and meters on two office floors (each 2,325 m 2 ) of the building. A three-step data curation strategy is applied to transform the raw data into research-grade data: (1) cleaning the raw data to detect and adjust the outlier values and fill the data gaps; (2) creating the metadata model of the building systems and data points using the Brick schema; and (3) representing the metadata of the dataset using a semantic JSON schema. This dataset can be used in various applications—building energy benchmarking, load shape analysis, energy prediction, occupancy prediction and analytics, and HVAC controls—to improve the understanding and efficiency of building operations for reducing energy use, energy costs, and carbon emissions.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

A global dataset of terrestrial biological nitrogen fixation

Biological nitrogen fixation (BNF) is the main natural source of new nitrogen inputs in terrestrial ecosystems, supporting terrestrial productivity, carbon uptake, and other Earth system processes. We assembled a comprehensive global dataset of field measurements of BNF in all major N-fixing niches across natural terrestrial biomes derived from the analysis of 376 BNF studies. The dataset comprises 32 variables, including site location, biome type, N-fixing niche, sampling year, quantification method, BNF rate (kg N ha −1 y −1 ), the percentage of nitrogen derived from the atmosphere (%N dfa ), N fixer or N-fixing substrate abundance, BNF rate per unit of N fixer abundance, and species identity. Overall, the dataset combines 1,207 BNF rates for trees, shrubs, herbs, soil, leaf litter, woody litter, dead wood, mosses, lichens, and biocrusts, 152 herb %N dfa values, 1,005 measurements of N fixer or N-fixing substrate abundance, and 762 BNF rates per unit of N fixer abundance for a total of 424 species across 66 countries. This dataset facilitates synthesis, meta-analysis, upscaling, and model benchmarking of BNF fluxes at multiple spatial scales.

Reis Ely, Carla R. [Oregon State Univ., Corvallis,↗
DOE OSTI2021

Fast convolutional neural networks on FPGAs with hls4ml

We introduce an automated tool for deploying ultra low-latency, low-power deep neural networks with convolutional layers on field-programmable gate arrays (FPGAs). By extending the hls4ml library, we demonstrate an inference latency of 5 µs using convolutional architectures, targeting microsecond latency applications like those at the CERN Large Hadron Collider. Considering benchmark models trained on the Street View House Numbers Dataset, we demonstrate various methods for model compression in order to fit the computational constraints of a typical FPGA device used in trigger and data acquisition systems of particle detectors. In particular, we discuss pruning and quantization-aware training, and demonstrate how resource utilization can be significantly reduced with little to no loss in model accuracy. We show that the FPGA critical resource consumption can be reduced by 97% with zero loss in model accuracy, and by 99% when tolerating a 6% accuracy degradation.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

Towards philosophical reasoning with agentic LLMs: Socratic method for scientific assistance

As large language models (LLMs) become central tools in science, improving their reasoning capabilities is critical for meaningful and trustworthy applications. We introduce a Socratic agent for scientific reasoning, implemented through a structured system prompt that guides LLMs via classical principles of inquiry. Unlike typical prompt engineering or retrieval-based methods, our approach leverages definition, analogy, hypothesis elimination, and other Socratic techniques to generate more coherent, critical, and domain-aware responses. We evaluate the agent across diverse scientific domains and benchmark it on the abstraction and reasoning corpus challenge dataset, achieving 97.15% under a fixed prompting protocol and without fine-tuning or external tools. Expert evaluation shows improved reasoning depth, clarity, and adaptability over conventional LLM outputs, suggesting that structured prompting rooted in philosophical reasoning can improve the scientific utility of language models.

LLM reasoning↗
DOE OSTI2025

Structure refinement and anisotropic atomic displacement parameters of 1M Illite: Rietveld and pair distribution function analysis using synchrotron X-ray radiation

Illite, a widespread clay mineral, plays a pivotal role in geological processes, notably as an indicator in diagenetic and hydrothermal alteration environments, and possesses significant industrial relevance in applications including ceramics, construction and catalysis. However, challenges including its nanoscale crystallinity, structural disorder and frequent interstratification with other clay minerals have hindered detailed structural characterization using conventional X-ray diffraction (XRD) techniques. This study employs integrated synchrotron XRD and pair distribution function (PDF) analysis to elucidate the crystal structure of the 1M illite polytype, yielding the first determination of its anisotropic atomic displacement parameters (U aniso ). TheseU aniso parameters provide critical insights into atomic dynamics and static disorder within the structure, enabling a more refined understanding of structure–property relationships. This integrated approach, combining synchrotron XRD, Rietveld refinement and PDF analysis, yields a comprehensive structural characterization, capturing both average crystallographic and local atomic arrangements. Considering illite's widespread geological occurrence and industrial importance, this high-precision structural dataset, especially the determinedU aniso values, provides a crucial benchmark for future modeling and simulation efforts targeting accurate prediction of its physicochemical behavior.

Chemistry↗
DOE OSTI2025

RingX: Scalable Parallel Attention for Long-Context Learning on HPC

The attention mechanism has become foundational for remarkable AI breakthroughs since the introduction of the Transformer, driving the demand for increasingly longer context to power frontier models such as large-scale reasoning language models and high-resolution image/video generators. However, its quadratic computational and memory complexities present substantial challenges. Current state-of-the-art parallel attention methods, such as ring attention, are widely adopted for long-context training but utilize a point-to-point communication strategy that fails to fully exploit the capabilities of modern HPC network architectures. In this work, we propose ringX, a scalable family of parallel attention methods optimized explicitly for HPC systems. By enhancing workload partitioning, refining communication patterns, and improving load balancing, ringX achieves up to 3.4 × speedup compared to conventional ring attention on the Frontier supercomputer. Optimized for both bi-directional and causal attention mechanisms, ringX demonstrates its effectiveness through training benchmarks of a Vision Transformer (ViT) on a climate dataset and a Generative Pre-Trained Transformer (GPT) model, Llama3 8B. Our method attains an end-to-end training speedup of approximately 1.5 × in both scenarios. To our knowledge, the achieved 38% model FLOPs utilization (MFU) for training Llama3 8B with a 1M-token sequence length on 4,096 GPUs represents one of the highest training efficiencies reported for long-context learning on HPC systems. Our code implementation is available at https://github.com/jqyin/ringX-attention.

Yin, Junqi [ORNL] (ORCID:0000000338435520)↗
DOE OSTI2020

Fabricated ecosystem workshop: bridging laboratory to field science. Workshop report.

Lawrence Berkeley National Laboratory (Berkeley Lab) scientists held a workshop at the DOE BER Genomic Sciences PI meeting on the use of Fabricated Ecosystems in Washington D.C. on February 25th, 2020. Ecosystem fabrication is an approach to creating controlled microbial, soil and plant ecologies within a laboratory setting that enable discovery and dissection of environmental variables, activities, and interactions. At Berkeley Lab, we are developing two systems which span spatial and temporal scales — the EcoFAB and the EcoPOD. The participants of the workshop discussed the potential applications and challenges of using fabricated ecosystems as tools to tackle BER-relevant scientific questions. Specifically, they identified (1) research challenges that would benefit from ready access to this infrastructure (2) identified and prioritized technical challenges that currently limit these systems and (3) discussed how to use them to bridge the gap between lab and field research. To ensure that the fabricated ecosystems , in particular the larger-scale EcoPODs, are of use to as much of the BER community as possible, the workshop participants made the following recommendations: 1. Produce publicly available datasets for a set of control variables. Use for benchmarking, and assessing reproducibility between systems. 2. Implement data standards. 3. Develop/leverage nano/micro sensors and in situ root imaging. 4. Encourage the development of interdisciplinary teams to develop EcoPOD experiments. 5. Develop fabricated ecosystems with size and complexity that sits between the EcoFAB and EcoPOD to accelerate use and access.

42 ENGINEERING↗
DOE OSTI2024

An ML-based terrestrial data fusion and augmentation framework to enable advanced understanding of the terrestrial carbon and water interactions

Soil moisture is essential to the terrestrial carbon and water cycles and land–atmosphere interactions. There are various types of soil moisture data, and each type has the distinct spatiotemporal strengths and limitations, depending on the diverse applications and retrieval methodologies of different data types (Li et al., in review; The PNNL-82151 FY23 Report). However, the limitations of different soil moisture data in terms of accuracy and spatiotemporal coverage hinder our ability to further understand the soil moisture dynamics across scales. To have a gap free soil moisture data product with a fine spatiotemporal coverage and vertical profiles, we train extreme gradient boosting (XGBoost) models by using (1) in-situ soil moisture measurements from the International Soil Moisture Network (ISMN), (2) soil moisture from the ECMWF reanalysis (ERA) at the 9 km and sub-daily spatiotemporal resolution, (3) the Daymet meteorological fields, and (4) data products that characterize surface conditions, including soil texture, organic content, topography, vegetation type, and rooting depth. We use the trained XGBoost models that have consistent performance across seven soil layers, i.e., 0–5 cm, 5–10 cm, 10–20 cm, 20–40 cm, 40–60 cm, 60–100 cm, and 100–200 cm, and the gridded model predictors to generate a soil moisture data at the 1 km and daily spatiotemporal resolution for the Continental United States (CONUS) from 2001–2020. This dataset can be broadly used for Earth system model benchmark, monitoring extreme weathers, making informed decisions regarding agriculture, water resource management, climate change mitigation, and ecosystem preservation.

58 GEOSCIENCES↗