Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Datasets”

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 1,549 records · Page 86

CLM5 CAMELS Basins Ensemble

Land surface models such as Community Land Model Version 5 (CLM5) are essential tools for simulating the behaviors of the terrestrial system. Despite the extensive application of CLM5, limited attention has been paid to the underlying uncertainties associated with its hydrologic parameters and the implications that these uncertainties have on water resources applications. To address this long-standing issue, we conduct a comprehensive hydrologic parameter uncertainty characterization (UC) of CLM5 over the hydroclimatic gradients of the Conterminous United States using five meteorological datasets. Key datasets produced from the UC experiment include a benchmark dataset of CLM5 default hydrological performance, parameter sensitivity identified for 28 hydrological metrics, and large ensemble outputs for hydrological predictions. The presented datasets can assist CLM5 calibration and to support broad applications such as evaluating vulnerabilities to droughts and floods. The dataset can be used to identify under what hydroclimate conditions parametric uncertainties demonstrate substantial effects on hydrological predictions and clarify where further investigations are needed to understand how land runoff uncertainties interact with other Earth system processes. Please refer to the README.pdf for a description of the included files. Note that raw CLM5 model outputs for each forcing dataset are hosted on a Globus endpoint: https://app.globus.org/file-manager?destination_id=d22ef858-27b0-11ed-a910-fd3165076336.

Yan, Hongxiang↗

IM3 + EPRI Data Center Load Projections

This dataset contains scenarios of hourly total electricity demand with and without projected loads from data centers over the period 2022-2040. The root projections without data center demands are identical to those documented in Burleyson et al. 2024. In short, those projections encompass hourly electricity demands for 54 Balancing Authorities (BAs) in the United States across a range of eight of weather and socioeconomic scenarios. Refer to the root dataset and accompanying publication, Burleyson et al. 2025, for information about how those projections were generated. For this derivative dataset we used the base loads from the following scenarios: rcp45hotter_ssp3 rcp45hotter_ssp5 rcp85hotter_ssp3 rcp85hotter_ssp5 The root load projections did not reflect the drastic expansion of data centers that has occurred in the last several years to support artificial intelligence and cloud computing. To reflect growth in data center demand, a second set of load projections were created in which we layered in additional data center load projections based on the data center load growth scenarios described in a 2024 report by the Electric Power Research Institute (EPRI): "Powering Intelligence: Analyzing Artificial Intelligence and Data Center Energy Consumption". The EPRI projections from the report are included in this dataset (EPRI_2024_Projections.xlsx). That report contained annual state-level data center load projections for four year-over-year growth rates for data center demands: Low (3.71% annual growth) Moderate (5% annual growth) High (10% annual growth) Higher (15% annual growth) To homogenize the load projections with and without data centers we had to get them to a common scale. The first step was to take the EPRI annual state-level data center energy consumption values and convert them to 8760-hr loads for each year. We did that by assuming a flat (e.g., not weather- or time-sensitive) load profile and distributing the data center loads in each state evenly across all hours in a year. From there the loads were downscaled from the state-level to the county-level using 2019 county-level populations as weights. Finally, the county-level hourly data center loads were summed to the BA-level using the county-to-BA mapping underpinning the root load projections. The net result is 16 (4 weather and socioeconomic scenarios crossed with 4 data center load growth scenarios) unique load projections for the period 2022-2040. The file format follows that of the root dataset with a single additional column "Scaled_TELL_BA_Load_with_DC_MWh" that contains the hourly loads with the added data center loads for a given BA-year-scenario combination. Please refer to the readme file in the root dataset for more information on the file format.

Burleyson, Casey [Pacific Northwest National Labor↗

Tethys Water Demand Data

U.S. water demand varies sharply by sector and region as land use, population, weather patterns, and economic activity co-evolve. High-resolution water demand data is required to capture these dynamics, support integrated energy-water-land modeling, and local-to-regional water scarcity assessments. This dataset contains gridded (1/8 degree), monthly, multi-sector water demand dataset for the contiguous United States (CONUS) covering 1980-2100 across eight future scenarios of human-Earth system change. The dataset covers irrigation, thermoelectric, municipal (public-supply and domestic), livestock, manufacturing, and mining demands, separately for withdrawals and consumption, and includes per-cell renewable vs. non-renewable water source attributions. The dataset is validated against the latest USGS 2010-2020 water-use data for the three largest water demand sectors (Domestic, Electricity, and Irrigation), with correlations ranging from 0.73-0.95 at the HUC6 scale. The two datasets largely agree on an aggregate basis with per-sector bias falling within +/-7%, but they disagree on the spatial allocation of water with individual HUC6 basins having normalized RMSE from 68-171% and median absolute percent difference from 37-86%. This dataset advances prior global products by combining state-resolved sectoral demands from GCAM-USA, future power-plant siting from the CERF model, and scenario-consistent high-resolution climate and population forcing data across the eight scenarios.

GCAM-USA↗

Sharing the Sun: Community Solar Deployment and Subscriptions (As of January 2026)

The community solar market analysis presented here is based primarily on data collected through Sharing the Sun, an initiative of the National Community Solar Partnership+ (NCSP+). Sharing the Sun data collection and analysis are conducted by the National Laboratory of the Rockies (NLR) as part of its support for implementation of NCSP+. NLR first released a dataset of community solar projects in 2018 and updates it biannually. The January 2026 dataset, data collection methodology, and all the previous datasets are available from NLR's Data Catalog: https://data.nlr.gov/submissions/244. The dataset presents project-level information including location, capacity, operating utility, and year of interconnection. The dataset is created from multiple data sources such as utility data, public utility commissions, project developer websites, media releases, primary data collection by NLR, and data provided by developers under nondisclosure agreements. This presentation builds on a previous analysis of the community solar project dataset, Sharing the Sun: Community Solar Deployment and Subscriptions (as of June 2024). Dr. Gabriel Chan and his team at the University of Minnesota contribute to this effort. NCSP+ is led and funded by U.S. Department of Energy's Integrated Energy Systems Office (IESO).

14 SOLAR ENERGY↗

Public Reference Data for Megawatt-Scale Hydrogen Electrolysis – Simulated Wind

The U.S. Department of Energy and the National Laboratory of the Rockies (NLR) demonstrate hydrogen electrolysis, hydrogen compression and storage, and variable hydrogen fuel cell power production using megawatt-scale equipment at NLR’s Flatirons Campus as part of the Advanced Research on Integrated Energy Systems (ARIES) initiative. This dataset represents part of that effort and is intended for academic, national laboratory, industrial, and other stakeholders to plan, design, and validate models of megawatt-scale hydrogen technologies and diverse energy infrastructure nationwide. These data provide a baseline for how existing hydrogen electrolysis technologies perform when coupled with various energy technologies. Future datasets will demonstrate how existing hydrogen fuel cell technologies can provide controllable, dispatchable, and variable power output for artificial intelligence (AI) data centers and other variable loads. This dataset entry describes hydrogen production using a single, simulated wind turbine. The electrolyzer is a 1.25-MW proton exchange membrane type MC250 system manufactured by Nel Hydrogen . While the unit supports up to 2.5 MW of electrolysis, NLR only has a single 1.25-MW electrolysis stack. For the simulated wind energy profiles, NLR used OpenFAST to simulate a 3.4-MW International Energy Agency (IEA) reference wind turbine. The hour-long wind energy profiles varied over wind turbulence intensity (Class A or Class C) and average wind speed (5, 7, or 9 m/s). To match the power limits of the 1.25-MW electrolyzer and 3.4-MW IEA wind turbine most effectively and to maximize the efficiency of hydrogen production at a given average wind speed, the profiles were sometimes scaled by two times. This means that, in some cases, the experimental setup assumed two 1.25-MW electrolyzers were coupled with the wind turbine, representing a total maximum electrolysis load of 2.5 MW. Finally, NLR experimented with two settings for the electrolyzer power supply minimum and maximum current ramp rates (gain and slew): 200 and 400 amperes per second. The simulated profiles were translated from power (kilowatts) to current (amperes) using a curve fit with calibration data and sent to the electrolyzer power supply at 1-Hz frequency. These datasets report relevant hydrogen balance-of-plant and system data, all captured at 1 Hz, including hydrogen mass production measured with an Emerson Coriolis flow meter. Each .zip file represents a single wind turbine electrolysis experiment and is formatted as follows: {technology}-{average wind speed}-{turbulence class}_{number of 1.25 MW electrolyzers connected}-{electrolyzer ramp rate in amperes/second} For instance, “windIEA3.4-5ms-C_2-400.zip” represents the hour-long experiment using the IEA 3.4-MW turbine, subjected to an average wind speed of 5 m/s and Class C wind turbulence, and connected to two 1.25-MW electrolyzers with the power supply set to a maximum current ramp rate (gain and slew) of 400 A/s. Each .zip folder contains the following files: A .csv file containing raw data. An .xlsx file explaining all the fields in the raw data. A .png plot showing the time series of hydrogen production in kilograms per hour, electrolysis power consumption, and input wind turbine power. An experiment labeled “characterization_200.zip” demonstrates the MC250 electrolyzer steady-state response with 30 minute load steps for a total duration of 5 hours. Finally, a .csv file is provided with all simulated wind experiments combined into one dataset labeled "combined_wind_experiments.csv". NLR also built an AI/machine-learning predictive model based on these datasets. The model ingests the electrolyzer current command in amperes, as well as various pressures and temperatures across the system, and predicts hydrogen output in kilograms per hour. The complete model can be found at https://huggingface.co/NatLabRockies/ptmelt-hydrogen-electrolysis .

08 HYDROGEN↗

Public Reference Data for Megawatt-Scale Hydrogen Electrolysis - Simulated Wave

The U.S. Department of Energy and the National Laboratory of the Rockies (NLR) demonstrate hydrogen electrolysis, hydrogen compression and storage, and variable hydrogen fuel cell power production using megawatt-scale equipment at NLR’s Flatirons Campus as part of the Advanced Research on Integrated Energy Systems (ARIES) initiative. This dataset represents part of that effort and is intended for academic, national laboratory, industrial, and other stakeholders to plan, design, and validate models of megawatt-scale hydrogen technologies and diverse energy infrastructure nationwide. These data provide a baseline for how existing hydrogen electrolysis technologies perform when coupled with various energy technologies. Future datasets will demonstrate how existing hydrogen fuel cell technologies can provide controllable, dispatchable, and variable power output for artificial intelligence (AI) data centers and other variable loads. This dataset entry describes hydrogen production using a single, simulated wave energy conversion device. The electrolyzer is a 1.25-MW proton exchange membrane type MC250 system manufactured by Nel Hydrogen. While the unit supports up to 2.5 MW of electrolysis, NLR only has a single 1.25-MW electrolysis stack. For the wave energy, NLR used a wave energy converter model from PacWave. These devices can be equipped with accumulators and pressure relief values to smooth the power output by storing and releasing hydraulic energy. Using a peak power output of 10 MW, the model created two 25-minute profiles: one with and one without the accumulators and pressure relief valves. To down select the profile data from the native resolution of 20 Hz to 1 Hz, NLR took the mean of every 20 data points. NLR experimented with two simulated wave energy power plants: one that peaks at 10 MW, and one that peaks at 5 MW. These profiles were scaled for the physical 1.25 MW electrolyzer by multiplying the original profiles by one eighth and one quarter, respectively. The first profile matches the capacity rating of eight of the 1.25 MW electrolyzers, while the second matches four electrolyzers. Finally, NLR experimented with two settings for the electrolyzer power supply minimum and maximum current ramp rates (gain and slew): 200 and 400 amperes per second. The simulated profiles were translated from power (kilowatts) to current (amperes) using a curve fit with calibration data and sent to the electrolyzer power supply at 1-Hz frequency. These datasets report relevant hydrogen balance-of-plant and system data, all captured at 1 Hz, including hydrogen mass production measured with an Emerson Coriolis flow meter. Each .zip file represents a single wave electrolysis experiment and is formatted as follows: {technology}-{accumulator?}_{number of 1.25 MW electrolyzers connected}-{electrolyzer ramp rate in amperes/second} For instance, “wavePacWave-Noacc_4-400.zip” represents the 25 minute-long experiment using the PacWave’s wave energy converter model, equipped with no accumulator, connected to four 1.25-MW electrolyzers with their power supplies set to a maximum current ramp rate (gain and slew) of 400 A/s. Each .zip folder contains the following files: A .csv file containing raw data. An .xlsx file explaining all the fields in the raw data. A .png plot showing the time series of hydrogen production in kilograms per hour, electrolysis power consumption, and input wave power. An experiment, labeled “characterization_200.zip”, demonstrates the MC250 electrolyzer steady-state response with 30 minute load steps for a total duration of 5 hours. Finally, a .csv file is provided with all wave profiles combined into one dataset labeled "combined_wave_experiments.csv". NLR also built an AI/machine-learning predictive model based on these datasets. The model ingests the electrolyzer current command in amperes, as well as various pressures and temperatures across the system, and predicts hydrogen output in kilograms per hour. The complete model can be found at https://huggingface.co/NatLabRockies/ptmelt-hydrogen-electrolysis.

08 HYDROGEN↗

Public Reference Data for Megawatt-Scale Hydrogen Electrolysis - NLR Historical Wind

The U.S. Department of Energy and the National Laboratory of the Rockies (NLR) demonstrate hydrogen electrolysis from variable sources, hydrogen compression and storage, and hydrogen fuel cell power production using megawatt-scale equipment at NLR’s Flatirons Campus as part of the Advanced Research on Integrated Energy Systems (ARIES) initiative. This dataset represents part of that effort and is intended for academic, national laboratory, industrial, and other stakeholders to plan, design, and validate models of megawatt-scale hydrogen technologies and diverse energy infrastructure nationwide. These data provide a baseline for how existing hydrogen electrolysis technologies perform when coupled with various energy technologies. Future datasets will demonstrate how existing hydrogen fuel cell technologies can provide controllable, dispatchable, and variable power output for artificial intelligence (AI) data centers and other variable loads. This dataset entry describes hydrogen production by conducting a statistical analysis of historical wind data over a five-year period (2020-2025) from a single 1.5MW turbine manufactured by General Electric (GE) located at NLR’s Flatirons Campus, to generate an experimental test profile that was deployed on a 1.25-MW proton exchange membrane type MC250 electrolyzer system manufactured by Nel Hydrogen . [1] While the electrolyzer balance-of-plant supports up to 2.5 MW of electrolysis, NLR only has a single 1.25-MW electrolysis stack. The historical wind data provided several metrics, however, the analysis particularly focused on the measured power output by the wind turbine. The power output time series of data for each day was categorized by total energy generation and standard deviation, and the day that represented the highest combination of these two metrics was chosen – December 25th, 2022. This process was then repeated for a moving four-hour window within this day to identify the most statistically variable period. Finally, this four-hour period was scaled by 65% to match the 1.25 MW electrolyzer. The electrolysis system controls hydrogen production by varying DC current applied to the stack, from a maximum of 3000 A to a minimum safe operation of 300 A, or 10%. Because the current – voltage characteristic changes as the stack ages and efficiency degrades, the actual minimum safe operating power changes over time. The historical wind profiles were translated from power (kilowatts) to current (amperes) using a curve fit with calibration data and sent to the electrolyzer power supply at 1 Hz frequency. For more details on the statistical analysis process, see the presentation labeled “ Public Reference Data for Megawatt-Scale Hydrogen Electrolysis” provided with each data entry. These datasets report relevant hydrogen balance-of-plant and system data, all captured at 1 Hz, including hydrogen mass production measured with an Emerson Coriolis flow meter. Each .zip file represents a single wind turbine electrolysis experiment and is formatted as follows: {technology}_{scaling factor}-{electrolyzer ramp rate in amperes/second} For instance, “wind-GE1.5MW_0.65-400.zip” represents the hour-long experiment using historical data from the wind-GE1.5MW turbine, scaled to 65%, with the electrolyzer power supply set to a maximum ramp rate (gain and slew) of 400 A/s. Each .zip folder contains the following files: A .csv file containing raw data An .xlsx file explaining all the fields in the raw data. A .png plot showing the time series of hydrogen production, electrolysis power consumption, and wind power input. A PDF file detailing the historical wind data statistical analysis used to generate the wind profile. An experiment labeled “characterization_200.zip” demonstrates the MC250 electrolyzer steady-state response with 30-minute load steps for a total duration of 5 hours. Finally, a .csv file is provided with all simulated wind experiments combined into one dataset labeled "combined_historical_wind_experiments.csv". NLR also built an AI/machine-learning predictive model based on these datasets. The model ingests the electrolyzer current command in amperes, as well as various pressures and temperatures across the system, and predicts hydrogen output in kilograms per hour. The complete model can be found at https://huggingface.co/NatLabRockies/ptmelt-hydrogen-electrolysis [1] nelhydrogen.com/product/mc-series-electrolyser .

08 HYDROGEN↗

Analyzing How We Do Analysis and Consume Data, Results from the SciDAC-Data Project

One of the main goals of the Dept. of Energy funded SciDAC-Data project is to analyze the more than 410,000 high energy physics datasets that have been collected, generated and defined over the past two decades by experiments using the Fermilab storage facilities. These datasets have been used as the input to over 5.6 million recorded analysis projects, for which detailed analytics have been gathered. The analytics and meta information for these datasets and analysis projects are being combined with knowledge of their part of the HEP analysis chains for major experiments to understand how modern computing and data delivery is being used. We present the first results of this project, which examine in detail how the CDF, D0, NOvA, MINERvA and MicroBooNE experiments have organized, classified and consumed petascale datasets to produce their physics results. The results include analysis of the correlations in dataset/file overlap, data usage patterns, data popularity, dataset dependency and temporary dataset consumption. The results provide critical insight into how workflows and data delivery schemes can be combined with different caching strategies to more efficiently perform the work required to mine these large HEP data volumes and to understand the physics analysis requirements for the next generation of HEP computing facilities. In particular we present a detailed analysis of the NOvA data organization and consumption model corresponding to their first and second oscillation results (2014-2016) and the first look at the analysis of the Tevatron Run II experiments. We present statistical distributions for the characterization of these data and data driven models describing their consumption

Ding, P.↗

Semi-Supervised Domain Adaptation for Cross-Survey Galaxy Morphology Classification and Anomaly Detection

In the era of big astronomical surveys, our ability to leverage artificial intelligence algorithms simultaneously for multiple datasets will open new avenues for scientific discovery. Unfortunately, simply training a deep neural network on images from one data domain often leads to very poor performance on any other dataset. Here we develop a Universal Domain Adaptation method DeepAstroUDA, capable of performing semi-supervised domain alignment that can be applied to datasets with different types of class overlap. Extra classes can be present in any of the two datasets, and the method can even be used in the presence of unknown classes. For the first time, we demonstrate the successful use of domain adaptation on two very different observational datasets (from SDSS and DECaLS). We show that our method is capable of bridging the gap between two astronomical surveys, and also performs well for anomaly detection and clustering of unknown data in the unlabeled dataset. We apply our model to two examples of galaxy morphology classification tasks with anomaly detection: 1) classifying spiral and elliptical galaxies with detection of merging galaxies (three classes including one unknown anomaly class); 2) a more granular problem where the classes describe more detailed morphological properties of galaxies, with the detection of gravitational lenses (ten classes including one unknown anomaly class).

79 ASTRONOMY AND ASTROPHYSICS↗

Quantifying Rates of Erosion Using Historical Aerial Photos - 19478

Erosion can play an important role in the fate and transport of waste at sites where disposal of long-lived waste is anticipated. The statistical characterization of key processes related to erosion is essential to the understanding of site stability through time. In this work multi-temporal historical aerial images are analyzed in conjunction with orthophotography and Lidar data to develop probability distributions for variables representing important erosion processes. Scans of photographic negatives were obtained for multiple photographs and several negatives were scanned with a calibrated photogrammetric scanner by Geomni (formerly Blue Skies Consulting) in Belen, New Mexico. Other negatives were provided by USDA or scanned on a high-resolution, large format media scanner in the United States National Archives Cartographic Research Room, College Park, Maryland (1939). An additional set of aerial photographs was obtained from the USGS EROS Data Center web site. For other years, photographic prints were available for aerial photography. Several prints were scanned with a large-format media scanner at 1200 dpi. Ground control points for selected digital images used in the stereoscopic analyses were identified in ArcMap. Ground control points were collected by matching features which could be identified in the aerial photography as well as the orthophotography or shaded relief imagery from the Lidar dataset. Such features included fence line intersections, road intersections, railroad bridges, and structures, depending on the age of the photography. Many old fence lines and abandoned roads remained visible in the shaded relief imagery while they were completely obscured by tree canopy in modern photography. Ground control elevations were sampled from the Lidar-based DEM or directly from point clouds. The image coordinates and matching three-dimensional projected coordinates of the ground control points were exported to IDL where parameters for a three-dimensional direct linear transformation (DLT) were obtained. Built-in singular value decomposition routines were used to solve an overdetermined set of equations for the eleven parameters of the DLT for a particular historical photograph. A solution to the DLT parameters was obtained for each historical aerial photograph in which features of interest were identified using the stereoscope. Ultimately, this process resulted in the identification of locations for features like gully heads using both the Lidar dataset and projection of the estimated location from the historical aerial photo under consideration back to the Lidar dataset. The distance between the estimate of the location from the historical image and that of the Lidar dataset was the estimated distance the feature has moved. This distance was then divided by the number of years between the Lidar dataset and the year of the historical aerial image of interest to get a rate of movement through time. This was done for several dozen points on each historical aerial image. There was inevitable uncertainty associated with the estimation of points from the historical aerial imagery. This includes estimation of changes in locations of features like gully heads through time. In this work a method to estimate the uncertainty associated with measurements of locations of features using the stereoscopic analysis is developed and applied. For features with locations in space that do not change (e.g., road intersections, etc.) the difference in measurements of locations from the Lidar dataset and that of the estimate from the historical aerial image provides an observation of the measurement error. These points used to estimate the measurement error are referred to as control points. For each of the historical aerial images, a different measurement error distribution is estimated using control points. These measurement errors are combined with the estimated distances from the stereoscopic analyses to produce distributions of gully retreat rates and hillslope erosion rates used along with output from Erosion Working Group (EWG) Landscape Evolution Models (LEMs) to provide statistical probability distributions for input into the PPA Model. Specifically, gully head retreat rate and gully widening rate were characterized using statistical probability distributions. The central limit theorem was then applied to develop rates that represent long-term averages that are used to inform a PPA Model built in GoldSim. The importance of these rates with respect to characterization of future risk can then assessed using sensitivity analyses. This provides an approach to determine if subsequent reduction of the uncertainty associated with the probability distributions of erosion rates will correspond to meaningful reduction in the estimation of future risk from the site. Ultimately this is a general method that utilizes historical aerial imagery to estimate rates of erosion with uncertainty. This information can be used to inform PPA models to project future risks from a given site. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Web-based Preprocessing and Visualization of 3D FIB Tomography Data for Nuclear Fuel Characterization

Three-dimensional (3D) focused ion beam (FIB) tomography enables reconstruction of internal nuclear fuel features that can't be fully evaluated through surface imaging alone. This capability supports characterization of fuel constituents and defects under thermal and irradiation conditions relevant to microreactor development. However, large tomography datasets can create data-handling, loading, and visualization challenges, especially when image-stack preparation and file conversion must be completed with separate tools. The Computational Ultraspatial Tomography Toolkit for High-Resolution Object Analysis Tools (CUTTRHOAT) is an open-source web application being developed to display FIB tomography datasets available through the Nuclear Research Data System (NRDS). The current alpha version requires prepared HDF5 datasets and has limited integrated data-preparation capabilities. This project improves CUTTHROAT by adding dataset-folder selection, automatic input detection, dataset scanning, missing-slice identification, blank-slice insertion, and image-stack-to-HDF5 conversion. Two applications will be compared: the baseline CUTTHROAT alpha workflow and the updated application containing the integrated data-handling and preprocessing functions. Evaluation will consider dataset detection accuracy, conversion success, loading time, rendering responsiveness, application stability, and user interaction. Preliminary results demonstrate successful loading of existing HDF5 files and converted image stacks, while testing also identified performance reductions caused by excessive blank-slice generation. The updated workflow reduces reliance on external preparation tools and supports more direct movement from image stacks to color-code 3D visualization. Future work includes refining missing-slice handling, integrating additional preprocessing functions, like a denoising feature, parsing TIFF metadata for automatic voxel scaling, and adding manual X, Y, and Z voxel-spacing inputs for PNG and JPEG.

36 - MATERIALS SCIENCE↗

Towards robust surrogate models: Benchmarking machine learning approaches to expediting phase field simulations of brittle fracture

Data-driven approaches have the potential to make modeling complex, nonlinear physical phenomena significantly more computationally tractable. For example, computational modeling of fracture is a core challenge where machine learning techniques have the potential to provide a much needed speedup that would enable progress in areas such as multi-scale modeling and uncertainty quantification. Currently, phase field modeling (PFM) of fracture is one such approach that offers a convenient variational formulation to model crack nucleation, branching and propagation. To date, machine learning techniques have shown promise in approximating PFM simulations. While standard fracture benchmarks represent realistic scenarios frequently observed in practice, they typically do not provide sufficiently challenging tests for data-driven methods. Here, to address this gap, we introduce a challenging dataset based on PFM simulations designed to benchmark and advance ML methods for fracture modeling. This dataset includes three energy decomposition methods, two boundary conditions, and 1000 random initial crack configurations for a total of 6000 simulations. Each sample contains 100 time steps capturing the temporal evolution of the crack field. Alongside this dataset, we also implement and evaluate Physics Informed Neural Networks (PINN), Fourier Neural Operators (FNO), and UNet models as baselines, and explore the impact of ensembling strategies on prediction accuracy. With this combination of our dataset and baseline models drawn from the literature we aim to provide a standardized and challenging benchmark for evaluating machine learning approaches to solid mechanics. Our results highlight both the promise and limitations of popular current models, and demonstrate the utility of this dataset as a testbed for advancing machine learning in fracture mechanics research.

Benchmark dataset↗

Predicting Overall Survival After Stereotactic Ablative Radiation Therapy in Early-Stage Lung Cancer: Development and External Validation of the Amsterdam Prognostic Model

Purpose: A prognostic model for 5-year overall survival (OS), consisting of recursive partitioning analysis (RPA) and a nomogram, was developed for patients with early-stage non-small cell lung cancer (ES-NSCLC) treated with stereotactic ablative radiation therapy (SABR). Methods and Materials: A primary dataset of 703 ES-NSCLC SABR patients was randomly divided into a training (67%) and an internal validation (33%) dataset. In the former group, 21 unique parameters consisting of patient, treatment, and tumor factors were entered into an RPA model to predict OS. Univariate and multivariate models were constructed for RPA-selected factors to evaluate their relationship with OS. A nomogram for OS was constructed based on factors significant in multivariate modeling and validated with calibration plots. Both the RPA and the nomogram were externally validated in independent surgical (n=193) and SABR (n=543) datasets. Results: RPA identified 2 distinct risk classes based on tumor diameter, age, World Health Organization performance status (PS) and Charlson comorbidity index. This RPA had moderate discrimination in SABR datasets (c-index range: 0.52-0.60) but was of limited value in the surgical validation cohort. The nomogram predicting OS included smoking history in addition to RPA-identified factors. In contrast to RPA, validation of the nomogram performed well in internal validation (r{sup 2}=0.97) and external SABR (r{sup 2}=0.79) and surgical cohorts (r{sup 2}=0.91). Conclusions: The Amsterdam prognostic model is the first externally validated prognostication tool for OS in ES-NSCLC treated with SABR available to individualize patient decision making. The nomogram retained strong performance across surgical and SABR external validation datasets. RPA performance was poor in surgical patients, suggesting that 2 different distinct patient populations are being treated with these 2 effective modalities.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Data-driven probability concentration and sampling on manifold

A new methodology is proposed for generating realizations of a random vector with values in a finite-dimensional Euclidean space that are statistically consistent with a dataset of observations of this vector. The probability distribution of this random vector, while a priori not known, is presumed to be concentrated on an unknown subset of the Euclidean space. A random matrix is introduced whose columns are independent copies of the random vector and for which the number of columns is the number of data points in the dataset. The approach is based on the use of (i) the multidimensional kernel-density estimation method for estimating the probability distribution of the random matrix, (ii) a MCMC method for generating realizations for the random matrix, (iii) the diffusion-maps approach for discovering and characterizing the geometry and the structure of the dataset, and (iv) a reduced-order representation of the random matrix, which is constructed using the diffusion-maps vectors associated with the first eigenvalues of the transition matrix relative to the given dataset. The convergence aspects of the proposed methodology are analyzed and a numerical validation is explored through three applications of increasing complexity. The proposed method is found to be robust to noise levels and data complexity as well as to the intrinsic dimension of data and the size of experimental datasets. Both the methodology and the underlying mathematical framework presented in this paper contribute new capabilities and perspectives at the interface of uncertainty quantification, statistical data analysis, stochastic modeling and associated statistical inverse problems.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Constraining the dynamical dark energy parameters: Planck-2013 vs WMAP9

We determine the best-fit values and confidence limits for dynamical dark energy parameters together with other cosmological parameters on the basis of different datasets which include WMAP9 or Planck-2013 results on CMB anisotropy, BAO distance ratios from recent galaxy surveys, magnitude-redshift relations for distant SNe Ia from SNLS3 and Union2.1 samples and the HST determination of the Hubble constant. We use a Markov Chain Monte Carlo routine to map out the likelihood in the multi-dimensional parameter space. We show that the most precise determination of cosmological parameters with the narrowest confidence limits is obtained for the Planck+HST+BAO+SNLS3 dataset. The best-fit values and 2σ confidence limits for cosmological parameters in this case are Ω{sub de} = 0.718±0.022, w{sub 0} = −1.15{sup +0.14}{sub −0.16}, c{sub a}{sup 2} = −1.15{sup +0.02}{sub −0.46}, Ω{sub b}h{sup 2} = 0.0220±0.0005, Ω{sub cdm}h{sup 2} = 0.121±0.004, h = 0.713±0.027, n{sub s} = 0.958{sup +0.014}{sub −0.010}, A{sub s} = (2.215{sup +0.093}{sub −0.101})⋅10{sup −9}, τ{sub rei} = 0.093{sup +0.022}{sub −0.028}. For this dataset, the ΛCDM model is just outside the 2σ confidence region, while for the dataset WMAP9+HST+BAO+SNLS3 the ΛCDM model is only 1σ away from the best fit. The tension in the determination of some cosmological parameters on the basis of two CMB datasets WMAP9 and Planck-2013 is highlighted.

79 ASTRONOMY AND ASTROPHYSICS↗

Neutrino constraints: what large-scale structure and CMB data are telling us?

We discuss the reliability of neutrino mass constraints, either active or sterile, from the combination of different low redshift Universe probes with measurements of CMB anisotropies. In our analyses we consider WMAP 9-year or Planck Cosmic Microwave Background (CMB) data in combination with Baryonic Acoustic Oscillations (BAO) measurements from BOSS DR11, galaxy shear measurements from CFHTLenS, SDSS Ly α forest constraints and galaxy cluster mass function from Chandra observations. At odds with recent similar studies, to avoid model dependence of the constraints we perform a full likelihood analysis for all the datasets employed. As for the cluster data analysis we rely on to the most recent calibration of massive neutrino effects in the halo mass function and we explore the impact of the uncertainty in the mass bias and re-calibration of the halo mass function due to baryonic feedback processes on cosmological parameters. We find that none of the low redshift probes alone provide evidence for massive neutrino in combination with CMB measurements, while a larger than 2σ detection of non zero neutrino mass, either active or sterile, is achieved combining cluster or shear data with CMB and BAO measurements. Yet, the significance of the detection exceeds 3σ if we combine all four datasets. For a three active neutrino scenario, from the joint analysis of CMB, BAO, shear and cluster data including the uncertainty in the mass bias we obtain ∑ m{sub ν} =0.29{sup +0.18}{sub -0.21} eV and ∑ m{sub ν} =0.22{sup +0.17}{sub -0.18} eV 95%CL) using WMAP9 or Planck as CMB dataset, respectively. The preference for massive neutrino is even larger in the sterile neutrino scenario, for which we get m{sub s}{sup eff}=0.44{sup +0.28}{sub -0.26} eV and Δ N{sub eff}=0.78{sup +0.60}{sub -0.59} 95%CL) from the joint analysis of Planck, BAO, shear and cluster datasets. For this data combination the vanilla ΛCDM model is rejected at more than 3σ and a sterile neutrino mass as motivated by accelerator anomaly is within the 2σ errors. Conversely, the Ly α data favour vanishing neutrino masses and from the data combination Planck+BAO+Ly α we get the tight upper limits ∑ m{sub ν} <0.14 eV and m{sub s}{sup eff}<0.22 eV—Δ N{sub eff}<1.11 95%CL) for the active and sterile neutrino model, respectively. Finally, results from the full data combination reflect the tension between the σ{sub 8} constraints obtained from cluster and shear data and that inferred from Ly α forest measurements; in the active neutrino scenario for both CMB datasets employed, the full data combination yields only an upper limits on ∑ m{sub ν}, while assuming an extra sterile neutrino we still get preference for non-vanishing mass, m{sub s}{sup eff}=0.26{sup +0.22}{sub -0.24} eV, and dark contribution to the radiation content, Δ N{sub eff}=0.82±0.55.

79 ASTRONOMY AND ASTROPHYSICS↗

SpaceNet 9—Cross-Sensor Alignment of Optical and SAR Imagery

Precise registration of high-resolution synthetic aperture radar (SAR) and optical imagery is necessary for realizing the full potential and benefits of multimodal image analysis. However, two significant challenges presently exist. First, there is a lack of annotated datasets and benchmarks available for high-resolution SAR–optical image registration. Second, an assessment of efficient and reliable image registration methods that can precisely align these modalities is lacking. Here, we present a holistic description of the SpaceNet 9 Challenge and its results. We present a description of the dataset and baseline algorithm along with the results of the challenge, including a description of the winning algorithms. We release the SpaceNet 9 dataset along with open-sourcing the winning algorithms and baseline. The objective of SpaceNet 9 was to compute a dense displacement map that indicates the shift needed to align pixels in an optical image to the pixels in a SAR image. The challenge launched in April 2025 and was active for approximately two months. The top five solutions reduced image alignment error from approximately 34 m to under 13 m for public and private test data, with the best results obtaining a registration error of only 8.5 and 6.7 m on the public testing and private testing dataset, respectively. Usage of pretrained image matching models, robust outlier rejection with RANSAC, and estimating local displacement were common among the top solutions. The results of this challenge provide insight into high-resolution SAR–optical image registration and offer opportunities for future benchmarking in this domain. The baseline algorithm, winning solutions, and datasets are available at https://spacenet.ai/sn9-challenge/.

benchmark datasets↗

Investigation of a breathing surrogate prediction algorithm for prospective pulmonary gating

Purpose: A major challenge of four dimensional computed tomography (4DCT) in treatment planning and delivery has been the lack of respiration amplitude and phase reproducibility during image acquisition. The implementation of a prospective gating algorithm would ensure that images would be acquired only during user-specified breathing phases. This study describes the development and testing of an autoregressive moving average (ARMA) model for human respiratory phase prediction under quiet respiration conditions. Methods: A total of 47 4DCT patient datasets and synchronized respiration records was utilized in this study. Three datasets were used in model development and were removed from further evaluation of the ARMA model. The remaining 44 patient datasets were evaluated with the ARMA model for prediction time steps from 50 to 1000 ms in increments of 50 and 100 ms. Thirty-five of these datasets were further used to provide a comparison between the proposed ARMA model and a commercial algorithm with a prediction time step of 240 ms. Results: The optimal number of parameters for the ARMA model was based on three datasets reserved for model development. Prediction error was found to increase as the prediction time step increased. The minimum prediction time step required for prospective gating was selected to be half of the gantry rotation period. The maximum prediction time step with a conservative 95% confidence criterion was found to be 0.3 s. The ARMA model predicted peak inhalation and peak exhalation phases significantly better than the commercial algorithm. Furthermore, the commercial algorithm had numerous instances of missed breath cycles and falsely predicted breath cycles, while the proposed model did not have these errors. Conclusions: An ARMA model has been successfully applied to predict human respiratory phase occurrence. For a typical CT scanner gantry rotation period of 0.4 s (0.2 s prediction time step), the absolute error was relatively small, 0.06{+-}0.02 s at peak inhalation and 0.05{+-}0.04 s at peak exhalation. The application of the ARMA model for prospective pulmonary gating has been demonstrated.

62 RADIOLOGY AND NUCLEAR MEDICINE↗