SEARCH · Search NASA
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.
A digital twin for synchrotron-based tomography for generating synthetic datasets from ground-truth phantoms. The code outputs greyscale projection images / tomographic volumes with realistic artifacts such as noise and phase-contrast and emulates their dependence on the acquisition parameters defining the beam and detector configuration. Some ground-truth phantoms are included with the code.
The Radiological Anomaly Detection and Identification (RADAI) software package is a python library for implementing, training, and storing algorithms that detect and identify anomalies in gamma-ray spectra. The library defines a general framework for implementing detection (binary) and identification (classification) algorithms, objects to encapsulate the results of analyses, a variety of temporal filtering tools that can be used in constructing algorithms, and conceptual design that allows easy reading and writing of algorithms (and their time dependent state). In addition to this framework, the library includes implementations of a variety of algorithms from the scientific literature including: gross-counts k-sigma, SPRT, N-SCRAD, Region of Interest, and Censored Energy Window. The implementation of these algorithms within the RADAI package was done to facilitate user-initiated training and configuration to by applied to different gamma-ray detector types. Finally, benchmarked and synthetic datasets will be made available for standardized algorithm characterization with corresponding utilities in the RADAI package for data access and processing.
This is the official code for the ICML 2024 paper "Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies". This code extends that of Wang et al. (2023) to facilitate state-of-the-art CIFAR-10 adversarial robustness, via training of WideResNet models on various large synthetic datasets. The code also facilitates derivation of the various scaling laws put forth in our ICML paper, which we use to compute efficient training settings.
Abstract Droplet-level interactions in clouds are often parameterized by a modified gamma fitted to a “global” droplet size distribution. Do “local” droplet size distributions of relevance to microphysical processes look like these average distributions? This paper describes an algorithm to search and classify characteristic size distributions within a cloud. The approach combines hypothesis testing, specifically, the Kolmogorov–Smirnov (KS) test, and a widely used class of machine learning algorithms for identifying clusters of samples with similar properties: density-based spatial clustering of applications with noise (DBSCAN) is used as the specific example for illustration. The two-sample KS test does not presume any specific distribution, is parameter free, and avoids biases from binning. Importantly, the number of clusters is not an input parameter of the DBSCAN-type algorithms but is independently determined in an unsupervised fashion. As implemented, it works on an abstract space from the KS test results, and hence spatial correlation is not required for a cluster. The method is explored using data obtained from the Holographic Detector for Clouds (HOLODEC) deployed during the Aerosol and Cloud Experiments in the Eastern North Atlantic (ACE-ENA) field campaign. The algorithm identifies evidence of the existence of clusters of nearly identical local size distributions. It is found that cloud segments have as few as one and as many as seven characteristic size distributions. To validate the algorithm’s robustness, it is tested on a synthetic dataset and successfully identifies the predefined distributions at plausible noise levels. The algorithm is general and is expected to be useful in other applications, such as remote sensing of cloud and rain properties. Significance Statement A typical cloud can have billions of drops spread over tens or hundreds of kilometers in space. Keeping track of the sizes, positions, and interactions of all of these droplets is impractical, and, as such, information about the relative abundance of large and small drops is typically quantified with a “size distribution.” Droplets in a cloud interact locally, however, so this work is motivated by the question of whether the cloud droplet size distribution is different in different parts of a cloud. A new method, based on hypothesis testing and machine learning, determines how many different size distributions are contained in a given cloud. This is important because the size distribution describes processes such as cloud droplet growth and light transmission through clouds.
In this study, we design a statistical method to couple observations with a physics-based tropical cyclone (TC) rainfall model (TCR) and engineered-synthetic storms for assessing TC rainfall hazard. We first propose a bias-correction method to minimize the errors induced by TCR via matching the probability distribution of TCR-simulated historical TC rainfall with gauge observations. Then we assign occurrence probabilities to engineered-synthetic storms to reflect local climatology, through a resampling method that matches the probability distribution of a newly proposed storm parameter named rainfall potential (POT) in the synthetic dataset with that in the observation. POT is constructed to include several important storm parameters for TC rainfall such as TC intensity, duration, and distance and environmental humidity near landfall, and it is shown to be correlated with TCR-simulated rainfall. The proposed method has a satisfactory performance in reproducing the rainfall hazard curve in various locations in the continental United States; it is an improvement over the traditional joint probability method (JPM) for TC rainfall hazard assessment.
This paper introduces a new parallel clustering algorithm, named Feel-the-Way clustering algorithm, that provides better or equivalent convergence rate than the traditional clustering methods by optimizing the synchronization and communication costs. Our algorithm design centers on how to optimize three factors simultaneously: reduced synchronizations, improved convergence rate, and retained same or comparable optimization cost. To compare the optimization cost, we use the Sum of Square Error (SSE) cost as the metric, which is the sum of the square distance between each data point and its assigned clusters. Compared with the traditional MPI k-means algorithm, the new Feel-the-Way algorithm requires less communications among participating processes. As for the convergence rate, the new algorithm requires fewer number of iterations to converge. As for the optimization cost, it obtains the SSE costs that are close to the k-means algorithm. In the paper, we first design the full-step Feel-the-Way k-means clustering algorithm that can significantly reduce the number of iterations that are required by the original k-means clustering method. Next, we improve the performance of the full-step algorithm by adopting an optimized sampling-based approach, named reassignment-history-aware sampling. Our experimental results show that the optimized sampling-based Feel-the-Way method is significantly faster than the widely used k-means clustering method, and can provide comparable optimization costs. More extensive experiments with several synthetic datasets and real-world datasets (e.g., MNIST, CIFAR-10, ENRON, and PLACES-2) show that the new parallel algorithm can outperform the open source MPI k-means library by up to 110% on a high-performance computing system using 4,096 CPU cores. In addition, the new algorithm can take up to 51% fewer iterations to converge than the k-means clustering algorithm.
At nuclear power plants (NPPs), anomaly detection and identification (i.e., determining the causes of anomalies) are important tasks for ensuring the safe and efficient operation of NPPs. These tasks are currently labor-intensive and costly, and are made more difficult by the size and complexity of NPP systems. An alternative approach to conducting these tasks is to automate them, such as via the reconstruction-based contribution method, which is a well-researched unsupervised machine learning method that uses a data-driven model of anomaly-free behavior to detect events and then identify each variable’s contributions to those events. The present effort developed a novel contribution approach that utilized a leave-one-variable-out (LOVO) model, with which each variable is predicted using all the other variables. The novelty lay in transforming this model into a reconstruction model and modifying the identification algorithm to work with the new reconstruction model. To evaluate this method in a controlled environment, a synthetic dataset based on spring-mass-damper (SMD) systems (commonly found in mechanical engineering references) was used, with known anomalies introduced into the system. The proposed method successfully detected the anomalies and afforded insights into their causes, thus enabling the appropriate identifications to be made.
This study focuses on the comparative study of deep learning (DL) models for pore space and discrete fracture networks (DFNs) segmentation in synthetic fractured digital rocks, specifically targeting low-permeability rock formations, such as shale and tight sandstones. Accurate characterization of pore space and DFNs is critical for subsequent property analysis and fluid flow modeling. Four DL models, SegNet, U-Net, U-Net-wide, and nested U-Net (i.e., U-Net++), were trained, validated, and tested using synthetic datasets, including input and label image pairs with varying properties. The model performance was assessed regarding pixel-wise metrics, including the F1 score and pixel-wise difference maps. In addition, the physics-based metrics were considered for further analysis, including sample porosity and absolute permeability. Particularly, We first simulated the permeability of porous media containing only pore space and then simulated the permeability of porous media with DFNs added. The difference between these two values is used to quantify the connectivity of segmented DFNs, which is an important parameter for low-permeability rocks. The pixel-wise metrics showed that the nested U-Net model outperformed the rest of the DL models in pore space and DFNs segmentation, with the SegNet model exhibiting the second-best performance. Particularly, nested U-Net enhanced segmentation accuracy for challenging boundary pixels affected by partial volume effects. The U-Net-wide model achieved improved accuracy compared to the U-Net model, which indicated the influence of parameter numbers. Similarly, nested U-Net has the closest match to the ground truth of physics-based metrics, including the porosity of pore space and DFNs, and the permeability difference quantifying the connectivity of DFNs. The findings highlight the effectiveness of DL models, especially the U-Net++ model with nested architecture and redesigned skip connections, in accurately segmenting pore spaces and DFNs, which are crucial for pore-scale fluid flow and transport simulation in low-permeability rocks.
The Generic Aquifer Model calculates the concentrations of dissolved salt and dissolved CO 2 surrounding a leaking legacy well. The Generic Aquifer model can also estimate the size of an “impact plume” where concentration changes exceed user-specified thresholds. The model is a component of NRAP-Open-IAM, an open-source Integrated Assessment Model (IAM) developed by the National Risk Assessment Partnership (NRAP) to perform risk assessment for geologic CO 2 storage. The input parameters were selected to cover a wide range of groundwater aquifers and leakage rates. The generic aquifer model was developed using a generative adversarial deep learning network, trained using a large synthetic dataset of STOMP multiphase flow simulations. The deep learning model predictions of dissolved salt and dissolved CO 2 in the aquifer compare well to the original STOMP simulation results. The extent of aquifer impacted by leaking CO 2 or brine is calculated using a user-defined mass fraction threshold. The aquifer impact volumes calculated based on STOMP simulation results compare well to those calculated based on the deep learning model. In a provided python script, gridded observation results from the generic aquifer component of NRAP-Open-IAM are converted to HDF5 format files for monitoring design with the DREAM code.
In this project, we have established a nondestructive, generalized methodology that (1) fuses rich field data with advanced ML for proactive reliability forecasting, (2) dramatically reduces experimental iterations via synthetic dataset generation, and (3) achieves unprecedented regression precision in both anomaly detection and component-level degradation assessment—paving the way for truly predictive maintenance of grid-tied PV inverters under diverse outdoor conditions.
When embarking on a retrofit of a building envelope, it is critical to understand the composition of its assembly. This practice is currently done by destructive and invasive material testing or demolition, which is sometimes not possible when in historic or protected buildings. To address this problem, in-situ thermal testing can be utilized along with machine learning classification algorithms to infer the composition of an assembly. In this paper, a proof-of-concept K-nearest neighbors classification model is developed to classify assembly composition from effective thermal resistance, effective thermal mass, and assembly cladding. This model was trained and tested utilizing a synthetic dataset producing an F1-score of 94.6%. This model was also validated with experimental data from a 100-year old wall assembly, confirming the model’s real-world validity. The paper presents a framework for inferring as-built envelope assemblies, all without having to damage or disturb the building and its occupants.
Design under uncertainty has significantly grown in research developments during the past decade. Additionally, machine learning (ML) and explainable ML (XML) have offered various opportunities to provide reliable predictable models. The current article investigates the use of finite element modeling (FEM), ML and XML predictions, and uncertain-based design of carbon-carbon (C-C) composites for use in ultra-high temperatures. A C-C composite concentrating solar power (CSP) as a microvascular receiver is considered as a case study. These C-C composites are fiber composites with directly integrated carbonized microchannels to form a lightweight, high-absorptivity material that includes an embedded microvascular network of channels. The topology of these microchannels is engineered to optimize heat transfer to a supercritical carbon dioxide (sCO2) heat transfer fluid. The mechanical characterization of C-C composites is highly challenging. Thus, designing every component made of C-C composites for ultra-high temperature applications needs an uncertainty-based analysis. As a part of a comprehensive project on the development of a novel carbonized microvascular C-C composite, this paper explores C-C composite sensitivity analysis, FEM, ML prediction, and XML analysis. The resulting composite can then be carbonized and coated with an oxidation-resistant coating to form a thermally efficient and mechanically robust C-C composite. An ANSYS 3-D-FE model was used to analyze the CSP’s stress/strain. To consider the variability in the mechanical and thermal properties of C-C composites, various mechanical properties are considered as the ANSYS FEM’s input. A synthetic dataset from 730 ANSYS runs was produced to feed into the ML and XML algorithms for uncertainty analysis and prediction. The ML and XML algorithms could accurately predict the CSP stresses/strains.
This paper presents a new Bayesian algorithm for retrieving surface rain rate from Tropical Rainfall Measurements Mission (TRMM) Microwave Imager (TMI) over the ocean, along with validations against estimates from the TRMM Precipitation Radar (PR). The Bayesian approach offers a rigorous basis for optimally combining multichannel observations with prior knowledge. While other rain rate algorithms have been published that are based at least partly on Bayesian reasoning, this is believed to be the first self-contained algorithm that fully exploits Bayes Theorem to yield not just a single rain rate, but rather a continuous posterior probability distribution of rain rate. To advance our understanding of theoretical benefits of the Bayesian approach, we have conducted sensitivity analyses based on two synthetic datasets for which the true conditional and prior distribution are known. Results demonstrate that even when the prior and conditional likelihoods are specified perfectly, biased retrievals may occur at high rain rates. This bias is not the result of a defect of the Bayesian formalism but rather represents the expected outcome when the physical constraint imposed by the radiometric observations is weak, due to saturation effects. It is also suggested that the choice of the estimators and the prior information are both crucial to the retrieval. In addition, the performance of our Bayesian algorithm is found to be comparable to that of other benchmark algorithms in real-world applications, while having the additional advantage of providing a complete continuous posterior probability distribution of surface rain rate.
The success of MODIS (the Moderate Resolution Imaging Spectrometer) in creating unprecedented, timely, high-quality data for vegetation and other studies has created great anticipation for data from VIIRS (the Visible/Infrared Imager Radiometer Suite). VIIRS will be carried onboard the joint NASA/Department of Defense/National Oceanic and Atmospheric Administration NPP (NPOESS (National Polar-orbiting Operational Environmental Satellite System) Preparatory Project). Because the VIIRS instruments will have lower spatial resolution than the current MODIS instruments 400 m versus 250 m at nadir for the channels used to generate Normalized Difference Vegetation Index data, scientists need the answer to this question: how will the change in resolution affect vegetation studies? By using simulated VIIRS measurements, this question may be answered before the VIIRS instruments are deployed in space. Using simulated VIIRS products, the U.S. Department of Agriculture and other operational agencies can then modify their decision support systems appropriately in preparation for receipt of actual VIIRS data. VIIRS simulations and validations will be based on the ART (Application Research Toolbox), an integrated set of algorithms and models developed in MATLAB(Registerd TradeMark) that enables users to perform a suite of simulations and statistical trade studies on remote sensing systems. Specifically, the ART provides the capability to generate simulated multispectral image products, at various scales, from high spatial hyperspectral and/or multispectral image products. The ART uses acquired ( real ) or synthetic datasets, along with sensor specifications, to create simulated datasets. For existing multispectral sensor systems, the simulated data products are used for comparison, verification, and validation of the simulated system s actual products. VIIRS simulations will be performed using Hyperion and MODIS datasets. The hyperspectral and hyperspatial properties of Hyperion data will be used to produce simulated MODIS and VIIRS products. Hyperion-derived MODIS data will be compared with near-coincident MODIS collects to validate both spectral and spatial synthesis, which will ascertain the accuracy of converting from MODIS to VIIRS. MODIS-derived VIIRS data is needed for global coverage and for the generation of time series for regional and global investigations. These types of simulations will have errors associated with aliasing for some scene types. This study will help quantify these errors and will identify cases where high-quality, MODIS-derived VIIRS data will be available.
The Ice, Cloud, and land Elevation Satellite-2 (ICESat-2) and its sole scientific instrument, the Advanced Topographic Laser Altimeter System (ATLAS), was launched on 15 September 2018 with a primary goal of measuring changes in the surface of the Earth's land ice (glaciers and ice sheets). ATLAS is a photon-counting laser altimeter, which records the transit time of individual photons in order to reconstruct surface height along track. The ground-track pattern repeats every 91 days such that changes in ice sheet surface height can be estimated through time. In this paper, we describe the set of algorithms that have been developed for ICESat-2 to retrieve ice sheet surface height from the geolocated photons for the Land Ice Along-Track Height Product (ATL06), and demonstrate their output and performance using a synthetic dataset over various land-ice surfaces and under different cloud conditions. We show that the ATL06 algorithm is expected to perform at the level required to meet the ICESat-2 science objectives for land ice.
Total suspended solids (TSS) concentration is an important biogeochemical parameter for water quality management and sediment-transport studies. In this study, we propose a novel semi-analytical method for estimating TSS in clear to extremely turbid waters from remote-sensing reflectance (Rrs). The proposed method includes three sub-algorithms used sequentially. First, the remotely sensed waters are classified into clear (Type I), moderately turbid (Type II), highly turbid (Type III), and extremely turbid (Type IV) water types by comparing the values of Rrs at 490, 560, 620, and 754 nm. Second, semi-analytical models specific to each water type are used to determine the particulate backscattering coefficients (bbp) at a corresponding single wavelength (i.e., 560 nm for Type I, 665 nm for Type II, 754 nm for Type III, and 865 nm for Type IV). Third, a specific relationship between TSS and bbp at the corresponding wavelength is used in each water type. Unlike other existing approaches, this method is strictly semi-analytical and its sub-algorithms were developed using synthetic datasets only. The performance of the proposed method was compared to that of three other state-of-the-art methods using simulated (N = 1000, TSS ranging from 0.01 to 1100 g/m3) and in situ measured (N = 3421, TSS ranging from 0.09 to 2627 g/m3) pairs of Rrs and TSS. Results showed a significant improvement with a Median Absolute Percentage Error (MAPE) of 16.0% versus 30.2–90.3% for simulated data and 39.7% versus 45.9–58.1% for in situ data, respectively. The new method was subsequently applied to 175 MEdium Resolution Imaging Spectrometer (MERIS) and 498 Ocean and Land Colour Instrument (OLCI) images acquired in the 2003–2020 timeframe to produce long-term TSS time-series for Lake Suwa and Lake Kasumigaura, Japan. Performance assessments using MERIS and OLCI matchups showed good agreements with in situ TSS measurements.
Instantaneous photosynthetically available radiation (IPAR) at the ocean surface and its vertical profile below the surface play a critical role in models to calculate net primary productivity of marine phytoplankton. In this work, we report two IPAR prediction models based on neural network (NN) approach, one for open ocean and the other for coastal waters. These models are trained, validated, and tested using a large volume of synthetic datasets for open ocean and coastal waters simulated by a radiative transfer model. Our NN models are designed to predict IPAR under a large range of atmospheric and oceanic conditions. The NN models can compute subsurface IPAR profile very accurately up to euphotic zone depth. The root mean square errors associated with the diffuse attenuation coefficient of IPAR are less than 0.011 𝑚−1 and 0.036 𝑚−1 for open ocean and coastal waters respectively. The performance of the NN models is better than presently available semi analytical models, with significant superiority in coastal waters.
Achieving robust vision-based robotic tasks requires large amounts of data, which are often difficult to obtain in real-world scenarios. Simulators and synthetic data offer a cost-effective alternative, but the visual gap between simulation and reality hinders the performance of models when deployed in real-world environments. In this paper, we present a data augmentation pipeline that integrates a foundation model (Segment Anything Model) with an unsupervised image-to-image translation model (CycleGAN) for instance-level domain transfer from simulation to reality. This pipeline enables the generation of realistic labeled data from synthetic images for training supervised machine learning models in vision-based navigation tasks. We evaluate our approach on real-world data for ego-vehicle pose estimation, a critical autonomous navigation task involving the prediction of cross-track position and heading angle relative to road center line markings. The results of our tests show that our GAN-based data augmentation pipeline significantly outperforms models trained solely on simulation data or on data processed with standard image augmentation methods for sim-to-real transfer, enhancing model robustness and generalizability in real-world scenarios. Our method provides a scalable and flexible data augmentation tool for leveraging large synthetic datasets to enhance vision-based robotic navigation tasks.