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 397 records · Page 22
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Enhancing Solar Power Forecasting with Regularized Constrained Quantile Regression Averaging and Bootstrapping Techniques

Probabilistic solar power forecasting (SPF) plays an essential role in optimizing power-grid operations by quantifying the forecast uncertainty. To improve the accuracy and robustness of probabilistic SPF, this paper introduces the regularized constrained quantile regression averaging (rCQRA) method to combine outputs from multiple PSPF models. In addition, a bootstrapping method was used to quantify model uncertainty, providing insights into the reliability and significance of each ensemble component. To evaluate its efficacy, the proposed rCQRA method is used to integrate four PSPF methods. The resulting SPF models are trained and validated using a real-world six-year dataset from a rooftop solar plant in the USA. The performance of the proposed rCQRA method is evaluated and compared with two benchmark methods under three categories of weather conditions. It is shown that the rCQRA method has superior performance in its forecast reliability, sharpness, and accuracy.

Ensemble learning, probabilistic solar power forec↗
DOE OSTI2021

Cumulative $\chi^2$ Metric for VALID for ENDF/B-VII.1 and ENDF/B-VIII.0 in SCALE 6.3b9

Nuclear data testing is generally performed in a manner similar to validation: a series of critical benchmark experiments is modeled, and the differences between calculated and expected results are examined to understand the performance of a code and cross section set. This process is repeated for multiple sets of experiments with different transport codes and sometimes with different datasets. Occasionally, data processing differences are also important in understanding the differences in calculated results. Relevant experts then meet periodically to compare results and set priorities for improvement in the next round of data updates. This process has been largely effective, despite the confounding factors of different benchmark sets, application areas, sponsors, nationalities, and the resulting different priorities.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2021

International collaboration framework for the calculation of performance loss rates: Data quality, benchmarks, and trends (towards a uniform methodology)

Abstract The IEA PVPS Task 13 group, experts who focus on photovoltaic performance, operation, and reliability from several leading R&D centers, universities, and industrial companies, is developing a framework for the calculation of performance loss rates of a large number of commercial and research photovoltaic (PV) power plants and their related weather data coming across various climatic zones. The general steps to calculate the performance loss rate are (i) input data cleaning and grading; (ii) data filtering; (iii) performance metric selection, corrections, and aggregation; and finally, (iv) application of a statistical modeling method to determine the performance loss rate value. In this study, several high‐quality power and irradiance datasets have been shared, and the participants of the study were asked to calculate the performance loss rate of each individual system using their preferred methodologies. The data are used for benchmarking activities and to define capabilities and uncertainties of all the various methods. The combination of data filtering, metrics (performance ratio or power based), and statistical modeling methods are benchmarked in terms of (i) their deviation from the average value and (ii) their uncertainty, standard error, and confidence intervals. It was observed that careful data filtering is an essential foundation for reliable performance loss rate calculations. Furthermore, the selection of the calculation steps filter/metric/statistical method is highly dependent on one another, and the steps should not be assessed individually.

14 SOLAR ENERGY↗
DOE OSTI2024

Decomprolute is a benchmarking platform designed for multiomics-based tumor deconvolution

Tumor deconvolution is a reliable way to disentangle the diverse cell types that comprise solid tumors. To date, however, both the algorithms developed to deconvolve tumor samples, and the gold standard datasets used to assess the algorithms are geared toward the analysis of gene expression (e.g., RNA-seq) rather than protein levels in tumor cells. While gene expression is less expensive to measure, protein levels provide a more accurate view of immune markers. To facilitate the development as well as improve the reproducibility and reusability of multi-omic deconvolution algorithms, we introduce Decomprolute, a Common Workflow Language framework that leverages containerization to compare tumor deconvolution algorithms across multiomic data sets. Decomprolute incorporates the large-scale multiomic data sets produced by the Clinical Proteomic Tumor Analysis Consortium (CPTAC), which include matched mRNA expression and proteomic data from thousands of tumors across multiple cancer types to build a fully open-source, containerized proteogenomic tumor deconvolution benchmarking platform. The platform consists of modular architecture and it comes with well-defined input and output formats at each module. As a result, it is robust and extendable easily with additional algorithms or analyses. The platform is available for access and use at http://pnnl-compbio.github.io/decomprolute.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

Spatially distributed atmospheric boundary layer properties in Houston – A value-added observational dataset

Abstract In 2022, Houston, TX became a nexus for field campaigns aiming to further our understanding of the feedbacks between convective clouds, aerosols and atmospheric boundary layer (ABL) properties. Houston’s proximity to the Gulf of Mexico and Galveston Bay motivated the collection of spatially distributed observations to disentangle coastal and urban processes. This paper presents a value-added ABL dataset derived from observations collected by eight research teams over 46 days between 2 June - 18 September 2022. The dataset spans 14 sites distributed within a ~80-km radius around Houston. Measurements from three types of instruments are analyzed to objectively provide estimates of nine ABL parameters, both thermodynamic (potential temperature, and relative humidity profiles and thermodynamic ABL depth) and dynamic (horizontal wind speed and direction, mean vertical velocity, updraft and downdraft speed profiles, and dynamical ABL depth). Contextual information about cloud occurrence is also provided. The dataset is prepared on a uniform time-height grid of 1 h and 30 m resolution to facilitate its use as a benchmark for forthcoming numerical simulations and the fundamental study of atmospheric processes.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Estimates of Southern Hemispheric Gravity Wave Momentum Fluxes across Observations, Reanalyses, and Kilometer-Scale Numerical Weather Prediction Model

Abstract Gravity waves (GWs) are among the key drivers of the meridional overturning circulation in the mesosphere and upper stratosphere. Their representation in climate models suffers from insufficient resolution and limited observational constraints on their parameterizations. This obscures assessments of middle atmospheric circulation changes in a changing climate. This study presents a comprehensive analysis of stratospheric GW activity above and downstream of the Andes from 1 to 15 August 2019, with special focus on GW representation ranging from an unprecedented kilometer-scale global forecast model (1.4 km ECMWF IFS), ground-based Rayleigh lidar (CORAL) observations, modern reanalysis (ERA5), to a coarse-resolution climate model (EMAC). Resolved vertical flux of zonal GW momentum (GWMF) is found to be stronger by a factor of at least 2–2.5 in IFS compared to ERA5. Compared to resolved GWMF in IFS, parameterizations in ERA5 and EMAC continue to inaccurately generate excessive GWMF poleward of 60°S, yielding prominent differences between resolved and parameterized GWMFs. A like-to-like validation of GW profiles in IFS and ERA5 reveals similar wave structures. Still, even at ∼1 km resolution, the resolved waves in IFS are weaker than those observed by lidar. Further, GWMF estimates across datasets reveal that temperature-based proxies, based on midfrequency approximations for linear GWs, overestimate GWMF due to simplifications and uncertainties in GW wavelength estimation from data. Overall, the analysis provides GWMF benchmarks for parameterization validation and calls for three-dimensional GW parameterizations, better upper-boundary treatment, and vertical resolution increases commensurate with increases in horizontal resolution in models, for a more realistic GW analysis. Significance Statement Gravity wave–induced momentum forcing forms a key component of the middle atmospheric circulation. However, complete knowledge of gravity waves, their atmospheric effects, and their long-term trends are obscured due to limited global observations, and the inability of current climate models to fully resolve them. This study combines a kilometer-scale forecast model, modern reanalysis, and a coarse-resolution climate model to first compare the resolved and parameterized momentum fluxes by gravity waves generated over the Andes, and then evaluate the fluxes using a state-of-the-art ground-based Rayleigh lidar. Our analysis reveals shortcomings in current model parameterizations of gravity waves in the middle atmosphere and highlights the sensitivity of the estimated flux to the formulation used.

Meteorology & Atmospheric Sciences↗
DOE OSTI2021

Battle of the Defaults: Extracting Performance Characteristics of HDF5 under Production Load

Popular parallel I/O libraries, such as HDF5, provide tuning parameters to obtain superior performance. However, the selection of effective parameters on production systems is complex due to the interdependence of I/O software and file system layers. Hence, application developers typically use the default parameters and often experience poor I/O performance. This work conducts a benchmarking-based analysis on the HDF5 behaviors with a wide variety of I/O patterns to extract performance characteristics under the production workload. To make the analysis well controlled, we exercise I/O benchmarks on POSIX-IO, MPI-IO, and HDF5 using the same I/O patterns and in the same jobs. To address high performance variability in production environments, we repeat the benchmarks across I/O patterns, storage devices, and time intervals. Based on the results, we identified consistent HDF5 behaviors that appropriate configurations and operations on dataset layout and file-metadata placement can improve performance significantly. We apply our findings and evaluate the tuned I/O library on two supercomputers: Summit and Cori. The results show that our tuned parameters can achieve more than 10× I/O performance speedup than that with default parameters on both systems, suggesting the effectiveness, stability, and generality of our solution.

Xie, Bing↗
DOE OSTI2024

RUBISCO Soil Moisture Working Group (SMWG) Mini-Workshop Report

The RUBISCO Soil Moisture Working Group (SMWG), an initiative bolstered by the DOE RUBISCO Science Focus Area project, is committed to unraveling the intricacies of soil moisture and its profound impact on global hydrology, energy, and biogeochemical cycles. Confronted with the complex challenges in multi-scale SM data development, feedback analysis, and model benchmarking, the SMWG aims to catalyze advancements in the field through a synergistic approach that engages leaders in soil moisture research and encompasses diverse datasets and novel analytical techniques.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

FATHOMS-RAG: A Framework for the Assessment of Thinking and Observation in Multimodal Systems that use Retrieval Augmented Generation

Retrieval-augmented generation (RAG) has emerged as a promising paradigm for improving factual accuracy in large language models (LLMs). We introduce a benchmark designed to evaluate RAG pipelines as a whole, evaluating a pipelines ability to ingest several modalities of information. We present (1) a curated dataset of 93 questions designed to evaluate a pipeline's ability to ingest textual data, tables, images, multimodal data, and cross-document multimodal data; (2) a phrase-level recall metric for correctness; (3) a nearest-neighbor embedding classifier in an attempt to classify pipeline hallucinations; (4) a comparative evaluation of 2 pipelines built with open-source retrieval mechanisms and 4 closed-source foundational models; and (5) a third-party human evaluation of the alignment of our correctness and hallucination metrics. We find that closed-source pipelines significantly outperform open-source pipelines in both the correctness and halucination metrics, with a wider performance gap in questions relying on multimodal and cross-document information. We also find after a human evaluation of our correctness and hallucination metric compared with our questions and pipeline responses, average agreement was 4.62 for correctness 4.53 for hallucination detection on a 1-5 Likert scale with 5 being strongly agree with our determination.

Hildebrand, Samuel [ORNL] (ORCID:0009000465963104)↗
DOE OSTI2026

smol_model_benchmark

Machine learning models for protein–small molecule binding prediction using graph (GAT), image-based (ResNet), and transformer-based SMILES approaches (ChemBERTa and MIST). The code includes training pipelines and experiments on the dataset from the BELKA Kaggle competition.

Gibson, Kaetlyn [Los Alamos National Lab]↗
DOE OSTI2022

Uncovering novel mutational signatures by de novo extraction with SigProfilerExtractor

Mutational signature analysis is commonly performed in cancer genomic studies. Here, we present SigProfilerExtractor, an automated tool for de novo extraction of mutational signatures, and benchmark it against another 13 bioinformatics tools by using 34 scenarios encompassing 2,500 simulated signatures found in 60,000 synthetic genomes and 20,000 synthetic exomes. For simulations with 5% noise, reflecting high-quality datasets, SigProfilerExtractor outperforms other approaches by elucidating between 20% and 50% more true-positive signatures while yielding 5-fold less false-positive signatures. Applying SigProfilerExtractor to 4,643 whole-genome- and 19,184 whole-exome-sequenced cancers reveals four novel signatures. Two of the signatures are confirmed in independent cohorts, and one of these signatures is associated with tobacco smoking. In summary, this report provides a reference tool for analysis of mutational signatures, a comprehensive benchmarking of bioinformatics tools for extracting signatures, and several novel mutational signatures, including one putatively attributed to direct tobacco smoking mutagenesis in bladder tissues.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2026

Optimal invariant sets for atomistic machine learning

The representation of atomic configurations for machine learning models has led to numerous sets of descriptors. However, many descriptor sets are incomplete and/or functionally dependent. Incomplete sets cannot faithfully represent atomic environments. Yet complete constructions often suffer from a high degree of functional dependence, where some descriptors are functions of others. These redundant descriptors do not improve discrimination between atomic environments. We employ pattern recognition techniques to remove dependent descriptors to produce the smallest possible set that satisfies completeness. We apply this in two ways: First, we refine an existing description, the atomic cluster expansion. Second, we augment an incomplete construction, yielding a new message-passing neural network architecture that can recognize up to 5-body patterns. This architecture shows strong accuracy on state-of-the-art benchmarks while retaining low computational cost. Our results demonstrate the utility of this strategy to optimize descriptor sets across a range of descriptors and application datasets.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

ASDFL: An adaptive super‐pixel discriminative feature‐selective learning for vehicle matching

Abstract There are a large number of cameras in modern transportation system that capture numerous vehicle images continuously. Therefore, automatic analysis of these vehicle images is helpful for traffic flow management, criminal investigations and vehicle inspections. Vehicle matching, which aims to determine whether two input images depict an identical vehicle, is one of the core tasks in vehicle analysis. Recent relevant studies have focused on local feature extraction instead of global extraction, since local details can provide crucial cues to distinguish between cars. However, these methods do not select local features; that is, they do not assign weights to local features. Therefore, in this research, we systematically study the vehicle matching task, and present a novel annotation‐free local‐based deep learning method called Adaptive super‐pixel discriminative feature‐selective learning (ASDFL) to address this issue. In ASDFL, vehicle images are segmented into clusters of super‐pixels of similar size by considering the location and colour similarities of pixels without using any component‐level annotation. These super‐pixels are deemed to be the virtual components of vehicles. Moreover, a convolutional neural network is used to extract the deep features of these virtual components. Thereafter, an instance‐specific mask generation module driven by the extracted global features is enhanced to produce a mask to select the most distinctive virtual components of each vehicle image pair in the feature space. Finally, the vehicle matching task is accomplished by classifying the selected virtual component features of each imaged vehicle pair. Extensive experiments on two popular vehicle identification benchmarks demonstrate that our method is 1.57% and 0.8% more accurate than the previous baselines in a vehicle matching task on the VeRi and VehicleID datasets, respectively, which demonstrates the effectiveness of our method.

Qin, Rong↗
DOE OSTI2020

CMDV (CM)4 Project - University of Washington contribution. Final report

The original goal of this project was to diagnose and improve CLUBB, the turbulence and cloud fraction parameterization used in DOE’s E3SM model. For this purpose, we planned to use large-eddy simulation (LES) and ARM observations from the NE Pacific Ocean and the SGP site, in coordination with ARM’s LASSO program. It was determined that for these cloud regimes, many of the turbulent ‘moment closures’ which underlie CLUBB’s mathematical formulation are inconsistent with LES, which is an appropriate benchmark for testing this. The research assistant found that these closures could be more accurately formulated using machine learning using the LES as a training dataset. However the resulting parameterization proved to quickly drift away from physical plausibility. A novel machine-learning based boundary layer parameterization called MARBLE based on matching the time evolution of a parameterized cloud-topped boundary layer to reanalysis was then developed and published.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

A new metrics framework for quantifying and intercomparing atmospheric rivers in observations, reanalyses, and climate models

We present a new atmospheric river (AR) analysis and benchmarking tool, namely Atmospheric River Metrics Package (ARMP). It includes a suite of new AR metrics that are designed for quick analysis of AR characteristics via statistics in gridded climate datasets such as model output and reanalysis. This package can be used for climate model evaluation in comparison with reanalysis and observational products. Integrated metrics such as mean bias and spatial pattern correlation are efficient for diagnosing systematic AR biases in climate models. For example, the package identifies the fact that, in CMIP5 and CMIP6 (Coupled Model Intercomparison Project Phases 5 and 6) models, AR tracks in the South Atlantic are positioned farther poleward compared to ERA5 reanalysis, while in the South Pacific, tracks are generally biased towards the Equator. For the landfalling AR peak season, we find that most climate models simulate a completely opposite seasonal cycle over western Africa. This tool can also be used for identifying and characterizing structural differences among different AR detectors (ARDTs). For example, ARs detected with the Mundhenk algorithm exhibit systematically larger size, width, and length compared to the TempestExtremes (TE) method. The AR metrics developed from this work can be routinely applied for model benchmarking and during the development cycle to trace performance evolution across model versions or generations and set objective targets for the improvement of models. They can also be used by operational centers to perform near-real-time climate and extreme event impact assessments as part of their forecast cycle.

58 GEOSCIENCES↗
DOE OSTI2026

scPlantAnnotate: an accurate and robust transformer-based model for plant cell type annotation

Accurate cell type annotation remains a major bottleneck in plant single-cell RNA sequencing (scRNA-seq), where existing tools are often adapted from animal studies and perform sub-optimally on plant data. The lack of plant-specific computational frameworks limits the construction of plant cell atlases and downstream biological discovery. We develop and evaluate scPlantAnnotate, a Transformer-based reference annotation framework tailored for plant scRNA-seq data, and benchmark it against state-of-the-art deep learning and conventional methods across multiple plant species. Species-specific scPlantAnnotate models were trained using curated datasets from Arabidopsis thaliana, Zea mays, Oryza sativa, and Glycine max. We compared scPlantAnnotate with leading baselines under both standard random-split evaluation and a more stringent leave-one-dataset-out setting, which tests robustness to completely unseen datasets and tissue types. scPlantAnnotate consistently outperforms existing approaches across all four species under random-split evaluation. In the leave-one-dataset-out setting for A. thaliana, where performance drops markedly for all methods due to strong batch effects and dataset heterogeneity, scPlantAnnotate nonetheless achieves the highest Accuracy, Macro-F1, Balanced Accuracy, and Macro-AUROC on average and ranks first on most held-out datasets. These results demonstrate improved robustness to dataset shifts, a critical yet underexplored challenge in plant scRNA-seq analysis. A freely accessible web server enables users to annotate their own datasets using pretrained models. scPlantAnnotate provides a plant-specific, Transformer-based framework for single-cell annotation that delivers state-of-the-art performance and enhanced robustness to unseen datasets. By addressing limitations of existing tools and enabling scalable reference-based annotation, scPlantAnnotate supports the development of comprehensive plant cell atlases and facilitates broader use of single-cell genomics in plant biology.

Bioinformatics↗
DOE OSTI2023

Neural Image Compression: Generalization, Robustness, and Spectral Biases

Recent advances in neural image compression (NIC) have resulted in models which are starting to outperform traditional codecs. While this has led to growing excitement about using these methods in real-world applications, the successful adoption of any machine learning system (including NIC) in the wild requires it to generalize (and be robust) to unseen distribution shifts at deployment time. Unfortunately, current research lacks comprehensive datasets and informative tools to evaluate and understand compression performance in real-world settings. To bridge this crucial gap, first, this paper presents a comprehensive benchmark suite to evaluate the out-of-distribution (OOD) performance of image compression methods. Specifically, we design CLIC-C and Kodak-C by introducing 15 common corruptions to popular CLIC and Kodak benchmarks. Next, we propose spectrally inspired introspection tools to gain a deeper understanding of errors introduced by image compression methods as well as their OOD performance. To this end, we carry out a detailed performance comparison of the classical codec with various variants of NIC (e.g., original, variable rate, pruned), revealing intriguing findings that challenge our current understanding of the strengths and limitations of NIC. Finally, we corroborate our empirical findings with theoretical analysis, providing an in-depth view of the OOD performance of NIC. Our benchmarks, spectral introspection tools, and findings provide a crucial bridge to the real-world adoption of NIC. We hope that our work will propel future efforts in designing more robust and generalizable NIC methods.

neural networks, Variational Autoencoder, robustne↗