Search NASA⌕ Search

SEARCH · Search NASA

Results for “evaluation 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 937 records · Page 52

Low responsiveness of machine learning models to critical or deteriorating health conditions

Machine learning (ML) based mortality prediction models can be immensely useful in intensive care units. Such a model should generate warnings to alert physicians when a patient’s condition rapidly deteriorates, or their vitals are in highly abnormal ranges. Before clinical deployment, it is important to comprehensively assess a model’s ability to recognize critical patient conditions. We develop multiple medical ML testing approaches, including a gradient ascent method and neural activation map. We systematically assess these machine learning models’ ability to respond to serious medical conditions using additional test cases, some of which are time series. Guided by medical doctors, our evaluation involves multiple machine learning models, resampling techniques, and four datasets for two clinical prediction tasks. We identify serious deficiencies in the models’ responsiveness, with the models being unable to recognize severely impaired medical conditions or rapidly deteriorating health. For in-hospital mortality prediction, the models tested using our synthesized cases fail to recognize 66% of the injuries. In some instances, the models fail to generate adequate mortality risk scores for all test cases. Our study identifies similar kinds of deficiencies in the responsiveness of 5-year breast and lung cancer prediction models. Using generated test cases, we find that statistical machine-learning models trained solely from patient data are grossly insufficient and have many dangerous blind spots. Most of the ML models tested fail to respond adequately to critically ill patients. How to incorporate medical knowledge into clinical machine learning models is an important future research direction.

60 APPLIED LIFE SCIENCES↗

Exploring Autoencoder-based Error-bounded Compression for Scientific Data

Error-bounded lossy compression is becoming an indispensable technique for the success of today's scientific projects with vast volumes of data produced during the simulations or instrument data acquisitions. Not only can it significantly reduce data size, but it also can control the compression errors based on user-specified error bounds. Autoencoder (AE) models have been widely used in image compression, but few AE-based compression approaches support error-bounding features, which are highly required by scientific applications. To address this issue, we explore using convolutional autoencoders to improve error-bounded lossy compression for scientific data, with the following three key contributions. (1) We provide an in-depth investigation of the characteristics of various autoencoder models and develop an error-bounded autoencoder-based framework in terms of the SZ model. (2) We optimize the compression quality for main stages in our designed AE-based error-bounded compression framework, fine-tuning the block sizes and latent sizes and also optimizing the compression efficiency of latent vectors. (3) We evaluate our proposed solution using five real-world scientific datasets and comparing them with six other related works. Experiments show that our solution exhibits a very competitive compression quality from among all the compressors in our tests. In absolute terms, it can obtain a much better compression quality (100%similar to 800% improvement in compression ratio with the same data distortion) compared with SZ2.1 and ZFP in cases with a high compression ratio.

Liu, Jinyang↗

A Framework for Neural Network Inference on FPGA-Centric SmartNICs

FPGA-based SmartNICs offer great potential to significantly improve the performance of high-performance computing and warehouse data processing by tightly coupling support for reconfigurable data-intensive computation with cross-node communication, thereby mitigating the von Neumann bottleneck. Existing work, however, has been generally been limited in that it assumes an accelerator model where kernels are offloaded to SmartNICs, but most control tasks are left to the CPUs. This leads to frequent waiting, inferior performance, and scaling challenges. In this work, we propose a new distributive data-centric computing framework, named FCsN, for reconfigurable SmartNIC-based systems. Through a lightweight task circulation execution model and its implementation architecture, FCsN allows the complete detaching of kernel execution, control logic, system scheduling, and network communication to the SmarNICs. This boosts performance by: (i) avoiding the control dependency with CPUs and (ii) supporting streaming kernel execution and network communication at line rate and in a very fine-grained manner. We demonstrate the efficiency and flexibility of FCsN using various types of neural network applications including graph neural networks; as these last are both irregular and data intensive they offer an especially robust demonstration. Evaluations using commonly-used neural network models and graph datasets show that a system with the support of FCsN can achieve, on average, 144 speedups over the MPI-based standard CPU baselines.

Guo, Anqi↗

Efficient Delaunay Tessellation through K-D Tree Decomposition

Delaunay tessellations are fundamental data structures in computational geometry. They are important in data analysis, where they can represent the geometry of a point set or approximate its density. The algorithms for computing these tessellations at scale perform poorly when the input data is unbalanced. We investigate the use of k-d trees to evenly distribute points among processes and compare two strategies for picking split points between domain regions. Because resulting point distributions no longer satisfy the assumptions of existing parallel Delaunay algorithms, we develop a new parallel algorithm that adapts to its input and prove its correctness. We evaluate the new algorithm using two late-stage cosmology datasets. The new running times are up to 50 times faster using k-d tree compared with regular grid decomposition. Moreover, in the unbalanced data sets, decomposing the domain into a k-d tree is up to five times faster than decomposing it into a regular grid.

Morozov, Dmitriy↗

A Deep Learning Approach for In-Network Synchrophasor Missing Data Recovery Using Programmable Network Switches

Phasor measurement unit (PMU) networks deliver accurate and timely measurements, which is essential for managing today’s electric power systems. To ensure data quality and enhance the cyber-resilience of PMU networks against malicious attacks and data errors, this study presents an online PMU missing data recovery scheme by leveraging P4 programmable switches. The data plane incorporates a customized PMU protocol parser that abstracts the necessary payload data for recovery. Recovery processes are executed in the control plane using a pre-trained machine learning model. Both traditional and advanced ML models, such as transformer and TimeGPT, are explicitly employed for data prediction. This approach ensures rapid and precise data recovery. Performance evaluations focus on recovery speed and accuracy, using a real dataset from a campus microgrid. With 20% missing PMU data, the mean absolute percentage error for voltage magnitude is 0.0384%, and the phase angle error discrepancy is approximately 0.4064%.

Phasor Measurement Unit, Machine Learning, Program↗

Ecological Benchmark for Chemicals

The Ecological Benchmark Tool dataset serves as a comprehensive repository of benchmarks designed to assess ecological risks at contaminated sites. This tool facilitates the evaluation of various environmental media and contaminants, supporting regulatory compliance and ecological protection. Benchmarks are available for air, biota, sediment, soil, and surface water. The dataset also provides species-specific benchmarks for fish, plants, birds, mammals, and invertebrates. Users can select benchmark sources, media, individual chemicals, and retrieve results in tabular or spreadsheet formats for analysis. Benchmarks are derived from authoritative sources, including government agencies, scientific councils, and academic publications. The dataset supports ecological risk assessments, regulatory decision-making, and environmental planning, with tools for benchmarking against chemical thresholds, sensitive species protection, and habitat impact evaluations. This structured approach ensures a robust evaluation of ecological risks tailored to site-specific and regulatory needs.

Stewart, Debra [Oak Ridge National Laboratory (ORN↗

Evaluating multi-slice ptychography tomography for X-ray imaging

X-ray ptychography typically relies on single-slice reconstruction approaches that assume minimal beam propagation through the specimen. However, this approximation breaks down for thick samples or when using high numerical aperture optics, leading to reconstruction artifacts due to multiple scattering. Multi-slice ptychographic tomography (MSPT) addresses this limitation by explicitly modeling beam propagation through the specimen while reducing angular sampling requirements for tomography, but its performance depends critically on reconstruction parameters and experimental conditions. Here, we systematically evaluate MSPT using numerical simulations and experimental X-ray datasets to understand how factors such as object thickness, optical parameters, and initialization strategies affect reconstruction accuracy. We demonstrate that informed object initialization significantly improves depth resolution and enables accurate projection extension, reducing the angular sampling requirements for tomographic reconstruction. Experimental demonstration confirms that MSPT produces reconstructions with reduced artifacts, establishing it as a robust approach for nanoscale imaging at modern synchrotron facilities.

Luktuke, Amey [Argonne National Laboratory (ANL), ↗

Assimilation of Wave Imaging Radar Observations for Real-time Wave-by-Wave Forecasting

This project addressed Topic 3: “Wave Measurement Instrumentation for Feed Forward Controls” under the FOA number DE-FOA-0000971. The overall goal of the program was to develop a phase-resolving wave forecasting technique for application to the active control of Wave Energy Conversion (WEC) devices. We have developed an approach that couples a wave imaging marine radar with a phase-resolving linear wave model for real-time wave field reconstruction and forward propagation of the wave field in space and time. The scope of the project was to develop and assess the performance of this novel forecasting system. Specific project goals were as follows: Develop and verify a fast, GPU-based (Graphical Processing Unit) wave propagation model suitable for phase-resolved computation of nearshore wave transformation over variable bathymetry; Compare the accuracy and speed of performance of the wave model against a deep water model in their ability to predict wave field transformation in the intermediate water depths (50 to 70 m) typical of planned WEC sites; Develop and implement a variational assimilation algorithm that can ingest wave imaging radar observations and estimate the time-varying wave conditions offshore of the domain of interest such that the observed wave field is best reconstructed throughout the domain and then use this to produce model forecasts for a given WEC location; Collect wave-resolving marine radar data, along with relevant in situ wave data, at a suitable wave energy test site, apply the algorithm to the field data, assess performance, and identify any necessary improvements; and Develop a production cost estimate that addresses the affordability of the wave forecasting technology and include in the Final Report. The developed forecasting algorithm (“Wavecast”) was evaluated for both speed and accuracy against a substantial synthetic dataset. Early in the project, performance tests definitively demonstrated that the system was capable of forecasting in real-time, as the GPU-based wave model backbone was very computationally efficient. The data assimilation algorithm was developed on a polar grid domain in order to match the sampling characteristics of the observation system (wave imaging marine radar). For verification purposes, a substantial set of synthetic wave data (i.e. forward runs of the wave model) were generated to be used as ground truth for comparison to the reconstructions and forecasts produced by Wavecast. For these synthetic cases, Wavecast demonstrated very good accuracy, for example, typical forecast correlation coefficients were between 0.84-0.95 when compared to the input data. Dependencies on shadowing, observational noise, and forecast horizon were also identified. During the second year of the project, a short field deployment was conducted in order to assess forecast accuracy under field conditions. For this, a radar was installed on a fishing vessel and observations were collected at the South Energy Test Site (SETS) off the coast of Newport, OR. At the SETS site, simultaneous in situ wave observations were also available owing to an ongoing field project funded separately. Unfortunately, the position and heading information that was available for the fishing vessel were not of sufficient accuracy in order to validate the forecast in a phase-resolving sense. Instead, a spectral comparison was made between the Wavecast forecast and the data from the in situ wave buoy. Although the wave and wind conditions during the field test were complex, the comparison showed a promising reconstruction of the wave spectral shape, where both peaks in the bimodal spectrum were represented. However, the total reconstructed spectral energy (across all directions and frequencies) was limited to 44% of the observed spectrum. Overall, wave-by-wave forecasting using a data assimilation approach based on wave imaging radar observations and a physics-based wave model shows promise for short-term phase-resolved predictions. Two recommendations for future work are as follows: first, we would recommend additional focused field campaigns for algorithm validation. The field campaign should be long enough to capture a range of wave conditions relevant to the target application and WEC site. In addition, it will be crucial to make sure the vessel of choice has high accuracy position and heading instrumentation (this instrumentation is commercially available but not standard on commercial fishing vessels). The second recommendation is to expand the model physics in the wave model backbone to include some nonlinear effects. Specifically, the third-order correction to the wave speed due to amplitude dispersion would be the next step in order to more accurately represent the phase speeds of large amplitude waves.

16 TIDAL AND WAVE POWER↗

Understanding spatial and temporal drivers of variation in tree hydraulic processes and their consequences for climate feedbacks (Final Technical Report)

This is the final technical report from the first phase of a project that changed institutions. The grant was titled “Understanding spatial and temporal drivers of variation in tree hydraulic processes and their consequences for climate feedbacks.” The overall objectives of this project were to (1) provide model‐compatible datasets of key plant hydraulic traits and status for model evaluation, parameterization and validation and (2) use these data to pinpoint ecosystem responses to a changing hydroclimate by addressing both long‐term climatic drying and episodic extreme droughts. We planned to address the objectives with three research activities to quantify plant responses to chronic water stress and episodic drought: (1) generate high frequency observations of soil and plant hydraulic data across different landscape positions at multiple sites, (2) quantify plant hydraulic trait plasticity in response to experimental soil moisture reduction in situ in two central hardwood forests, and (3) simulate the carbon consequences of incorporating plant hydrodynamics and plant acclimation to water stress in the DOE‐sponsored plant hydrodynamics model FATES‐HYDRO. As of the transfer of this project to another institution, we had made substantial progress on activities 1 and 2, and started activity 3.

54 ENVIRONMENTAL SCIENCES↗

TrojAI Alternate Analysis

In this portion of the TrojAI evaluation, we focus on the cyber-network-c2-mar2024 dataset. Recall that in this round ResNet18 and ResNet34 neural networks (NN) were trained on the USTC-TFC2016 dataset with the aim of distinguishing between benign versus botnet command and control (c2) packets. A range of bytes from each packet was reformatted into a 28x28 pixel image, and the collection of reformatted packets served as the training (and testing) data for the two ResNet models. For some of the data a trigger watermark was strategically placed to affect various inputs to the NNs. This watermarked, or poisoned, data in turn created a poisoned, or trojaned NN. The data were poisoned in different ways ultimately creating different trojaned NNs. This collection of trojaned NNs was combined with various versions of not trojaned NNs and served as the training and testing data for the performers. The performers’ task was to construct a classifier to distinguish between the trojaned and not trojaned models. It was previously noted that the performers struggled with the cyber-network-c2-mar2024 dataset, motivating this investigation of potential reasons the performers experienced challenges.

97 MATHEMATICS AND COMPUTING↗

Model Card for WaveDenoiser

This study used STEAD to train and evaluate this model because STEAD is among the best benchmark datasets available for local to regional data. STEAD is a global dataset with over 1 million 60 s long seismic waveforms that originated from approximately 450,000 earthquakes and background noise captured by more than 2,500 seismic stations. Each waveform in STEAD was attached with metadata such as earthquake locations, station locations, and signal arrival times when available

58 GEOSCIENCES↗

New Mexico cloud super cooled liquid water survey final report 2009.

Los Alamos and Sandia National Laboratories are partners in an effort to survey the super-cooled liquid water in clouds over the state of New Mexico in a project sponsored by the New Mexico Small Business Assistance Program. This report summarizes the scientific work performed at Sandia National Laboratories during the 2009. In this second year of the project a practical methodology for estimating cloud super-cooled liquid water was created. This was accomplished through the analysis of certain MODIS sensor satellite derived cloud products and vetted parameterizations techniques. A software code was developed to analyze multiple cases automatically. The eighty-one storm events identified in the previous year effort from 2006-2007 were again the focus. Six derived MODIS products were obtained first through careful MODIS image evaluation. Both cloud and clear-sky properties from this dataset were determined over New Mexico. Sensitivity studies were performed that identified the parameters which most influenced the estimation of cloud super-cooled liquid water. Limited validation was undertaken to ensure the soundness of the cloud super-cooled estimates. Finally, a path forward was formulized to insure the successful completion of the initial scientific goals which include analyzing different of annual datasets, validation of the developed algorithm, and the creation of a user-friendly and interactive tool for estimating cloud super-cooled liquid water.

54 ENVIRONMENTAL SCIENCES↗

Efficient Distributed Sequence Parallelism for Transformer-Based Image Segmentation

We introduce an efficient distributed sequence parallel approach for training transformer-based deep learning image segmentation models. The neural network models are comprised of a combination of a Vision Transformer encoder with a convolutional decoder to provide image segmentation mappings. The utility of the distributed sequence parallel approach is especially useful in cases where the tokenized embedding representation of image data are too large to fit into standard computing hardware memory. To demonstrate the performance and characteristics of our models trained in sequence parallel fashion compared to standard models, we evaluate our approach using a 3D MRI brain tumor segmentation dataset. We show that training with a sequence parallel approach can match standard sequential model training in terms of convergence. Furthermore, we show that our sequence parallel approach has the capability to support training of models that would not be possible on standard computing resources.

Lyngaas, Isaac↗

Data Validation Experiments with a Computer-Generated Imagery Dataset for International Nuclear Safeguards

Computer vision models have great potential as tools for international nuclear safeguards verification activities, but off-the-shelf models require fine-tuning through transfer learning to detect relevant objects. Because open-source examples of safeguards-relevant objects are rare, and to evaluate the potential of synthetic training data for computer vision, we present the Limbo dataset. Limbo includes both real and computer-generated images of uranium hexafluoride containers for training computer vision models. Here, we generated these images iteratively based on results from data validation experiments that are detailed here. The findings from these experiments are applicable both for the safeguards community and the broader community of computer vision research using synthetic data.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗

Cloud Area Distributions of Shallow Cumuli: A New Method for Ground-Based Images

We develop a new approach that resolves cloud area distributions of single-layer shallow cumuli from ground-based observations. Our simple and computationally inexpensive approach uses images obtained from a Total Sky Imager (TSI) and complementary information on cloud base height provided by lidar measurements to estimate cloud equivalent diameter (CED) over a wide range of cloud sizes (about 0.01–3.5 km) with high temporal resolution (30 s). We illustrate the feasibility of our approach by comparing the estimated CEDs with those derived from collocated and coincident high-resolution (0.03 km) Landsat cloud masks with different spatial and temporal patterns of cloud cover collected over the Atmospheric Radiation Measurement (ARM) Southern Great Plains (SGP) site. We demonstrate that (1) good (~7%) agreement between TSI and Landsat characteristic cloud size can be obtained for clouds that fall within the region of the sky observable by the TSI and (2) large clouds that extend beyond this region are responsible for noticeable (~16%) underestimation of the TSI characteristic cloud size. Our approach provides a previously unavailable dataset for process studies in the convective boundary layer and evaluation of shallow cumuli in cloud-resolving models.

14 SOLAR ENERGY↗

The Variable Infiltration Capacity model version 5 (VIC-5): infrastructure improvements for new applications and reproducibility

The Variable Infiltration Capacity (VIC) model is a macroscale semi-distributed hydrologic model. VIC development began in the early 1990s and the model has since been used extensively for basin- to global-scale applications that include hydrologic dataset construction, trend analysis of hydrologic fluxes and states, data evaluation and assimilation, forecasting, coupled climate modeling, and climate change impact assessment. Ongoing operational applications of the VIC model include the University of Washington's drought monitoring and forecasting systems and NASA's Land Data Assimilation System. This paper documents the development of VIC version 5 (VIC-5), which includes a major reconfiguration of the legacy VIC source code to support a wider range of modern hydrologic modeling applications. The VIC source code has been moved to a public GitHub repository to encourage participation by the broader user and developer communities. The reconfiguration has separated the core physics of the model from the driver source code, whereby the latter is responsible for memory allocation, preprocessing and post-processing, and input–output (I–O). VIC-5 includes four drivers that use the same core physics modules, but which allow for different methods for accessing this core to enable different model applications. Finally, VIC-5 is distributed with robust test infrastructure, components of which routinely run during development using cloud-hosted continuous integration. The work described here provides an example to the model development community for extending the life of a legacy model that is being used extensively. The development and release of VIC-5 represents a significant step forward for the VIC user community in terms of support for existing and new model applications, reproducibility, and scientific robustness.

42 ENGINEERING↗

Evaluation of obstacle modelling approaches for resource assessment and small wind turbine siting: case study in the northern Netherlands

Abstract. Growth in adoption of distributed wind turbines for energy generation is significantly impacted by challenges associated with siting and accurate estimation of the wind resource. Small turbines, at hub heights of 40 m or less, are greatly impacted by terrestrial obstacles such as built structures and vegetation that can cause complex wake effects. While some progress in high-fidelity complex fluid dynamics (CFD) models has increased the potential accuracy for modelling the impacts of obstacles on turbulent wind flow, these models are too computationally expensive for practical siting and resource assessment applications. To understand the efficacy of available models in situ, this study evaluates classic and commonly used methods alongside new state-of-the-art lower-order models derived from CFD simulations and machine learning approaches. This evaluation is conducted using a subset of an extensive original dataset of measurements from more than 300 operational wind turbines in the northern Netherlands. The results show that data-driven methods (e.g. machine learning and statistical modelling) are most effective at predicting production at real sites with an average error in annual energy production of 2.5 %. When sufficient data may not be available de novo to support these data-driven approaches, models derived from high-fidelity simulations show promise and reliably outperform classic methods. On average these models have 6.3 %–11.5 % error compared with 26 % for classic methods and 27 % baseline error for reanalysis data without obstacle correction. While more performant on average, these methods are also sensitive to the quality of obstacle descriptions and reanalysis inputs.

17 WIND ENERGY↗

The Importance of User Feedback in Sustaining Trusted Repositories

The NASA Earth Observation System Data and Information System (EOSDIS) has been operating since 1994 and is serving a global user community with well-managed Earth science data in a variety of scientific disciplines. EOSDIS processes, archives and distributes data and information products resulting from spaceborne and airborne instruments as well as in situ measurements from field campaigns. The Earth Science Data and Information System (ESDIS) Project at the NASA Goddard Space Flight Center manages EOSDIS with its 12 Distributed Active Archive Centers (DAACs) located across the United States. During the entire life of EOSDIS, the ESDIS Project and the DAACs have deployed many different mechanisms for user feedback, which have proven extremely valuable to their evolution and performance in their service to user communities. Some of the inputs from our user groups have resulted in fundamental changes in the architecture, design and operations of EOSDIS, while others have provided novel ideas for incremental changes. The EOSDIS DAACs have User Working Groups (UWGs) that represent broad user communities in the Earth science disciplines served by the DAACs. The UWGs meet periodically to assess and provide feedback on dataset and service priorities. As regular users of the data and services of the DAAC and experts in the scientific disciplines, the UWG members provide valuable inputs for planning and prioritizing the services, as well as addition of new datasets, for the benefit of the community. The EOSDIS is evaluated annually through an independently administered survey of its users resulting in the American Customer Satisfaction Index (ACSI). The survey provides an ACSI score as well as free-text suggestions from users, which are also helpful in making specific system improvements. In addition, each of the DAACs has a user services group that address on-going requests for help and other comments from users. The ESDIS Project has established a mechanism through the "earthdata" website (http://earthdata.nasa.gov) for users to provide feedback of any kind and these questions/comments are routed to the appropriate individuals in the Project or the DAACs. These various forms of receiving user feedback and responding to them continue to be extremely valuable in evolving and sustaining our Earth Science repository.

Behnke, Jeanne↗