SEARCH · Engineering Papers

Results for “pixel”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,333 records · Page 74

All sources NASA NTRS DOE OSTI

DOE OSTI2023

Low-energy Electron-track Imaging for a Liquid Argon Time-projection-chamber Telescope Concept Using Probabilistic Deep Learning

The GammaTPC is an MeV-scale single-phase liquid argon time-projection-chamber gamma-ray telescope concept with a novel dual-scale pixel-based charge-readout system. It promises to enable a significant improvement in sensitivity to MeV-scale gamma rays over previous telescopes. The novel pixel-based charge readout allows for imaging of the tracks of electrons scattered by Compton interactions of incident gamma rays. The two primary contributors to the accuracy of a Compton telescope in reconstructing an incident gamma-ray’s original direction are its energy and position resolution. In this work, we focus on using deep learning to optimize the reconstruction of the initial position and direction of electrons scattered in Compton interactions, including using probabilistic models to estimate predictive uncertainty. We show that the deep-learning models are able to predict locations of Compton scatters of MeV-scale gamma rays from simulated 500 μm pixel-based data to better than 1 mm rms error and are sensitive to the initial direction of the scattered electron. We compare and contrast different deep-learning uncertainty estimation algorithms for reconstruction applications. Additionally, we show that event-by-event estimates of the uncertainty of the locations of the Compton scatters can be used to select those events that were reconstructed most accurately, leading to improvement in locating the origin of gamma-ray sources on the sky.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2024

Physically Motivated Deep Learning to Superresolve and Cross Calibrate Solar Magnetograms

Abstract Superresolution (SR) aims to increase the resolution of images by recovering detail. Compared to standard interpolation, deep learning-based approaches learn features and their relationships to leverage prior knowledge of what low-resolution patterns look like in higher resolution. Deep neural networks can also perform image cross-calibration by learning the systematic properties of the target images. While SR for natural images aims to create perceptually convincing results, SR of scientific data requires careful quantitative evaluation. In this work, we demonstrate that deep learning can increase the resolution and calibrate solar imagers belonging to different instrumental generations. We convert solar magnetic field images taken by the Michelson Doppler Imager (resolution ∼2″ pixel −1 ; space based) and the Global Oscillation Network Group (resolution ∼2.″5 pixel −1 ; ground based) to the characteristics of the Helioseismic and Magnetic Imager (resolution ∼0.″5 pixel −1 ; space based). We also establish a set of performance measurements to benchmark deep-learning-based SR and calibration for scientific applications.

Muñoz-Jaramillo, Andrés (ORCID:0000000247160840)↗

DOE OSTI2022

PRMI: A Dataset of Minirhizotron Images for Diverse Plant Root Study

Understanding a plant's root system architecture (RSA) is crucial for a variety of plant science problem domains including sustainability and climate adaptation. Minirhizotron (MR) technology is a widely-used approach for phenotyping RSA non-destructively by capturing root imagery over time. Precisely segmenting roots from the soil in MR imagery is a critical step in studying RSA features. In this paper, we introduce a large-scale dataset of plant root images captured by MR technology. In total, there are over 72K RGB root images across six different species including cotton, papaya, peanut, sesame, sunflower, and switchgrass in the dataset. The images span a variety of conditions including varied root age, root structures, soil types, and depths under the soil surface. All of the images have been annotated with weak image-level labels indicating whether each image contains roots or not. The image-level labels can be used to support weakly supervised learning in plant root segmentation tasks. In addition, 63K images have been manually annotated to generate pixel-level binary masks indicating whether each pixel corresponds to root or not. These pixel-level binary masks can be used as ground truth for supervised learning in semantic segmentation tasks. By introducing this dataset, we aim to facilitate the automatic segmentation of roots and the research of RSA with deep learning and other image analysis algorithms.

Xu, Weihuang↗

DOE OSTI2021

Inpainting radar missing data regions with deep learning

Abstract. Missing and low-quality data regions are a frequent problem for weather radars. They stem from a variety of sources: beam blockage, instrument failure, near-ground blind zones, and many others. Filling in missing data regions is often useful for estimating local atmospheric properties and the application of high-level data processing schemes without the need for preprocessing and error-handling steps – feature detection and tracking, for instance. Interpolation schemes are typically used for this task, though they tend to produce unrealistically spatially smoothed results that are not representative of the atmospheric turbulence and variability that are usually resolved by weather radars. Recently, generative adversarial networks (GANs) have achieved impressive results in the area of photo inpainting. Here, they are demonstrated as a tool for infilling radar missing data regions. These neural networks are capable of extending large-scale cloud and precipitation features that border missing data regions into the regions while hallucinating plausible small-scale variability. In other words, they can inpaint missing data with accurate large-scale features and plausible local small-scale features. This method is demonstrated on a scanning C-band and vertically pointing Ka-band radar that were deployed as part of the Cloud Aerosol and Complex Terrain Interactions (CACTI) field campaign. Three missing data scenarios are explored: infilling low-level blind zones and short outage periods for the Ka-band radar and infilling beam blockage areas for the C-band radar. Two deep-learning-based approaches are tested, a convolutional neural network (CNN) and a GAN that optimize pixel-level error or combined pixel-level error and adversarial loss respectively. Both deep-learning approaches significantly outperform traditional inpainting schemes under several pixel-level and perceptual quality metrics.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2016

Coupling sky images with radiative transfer models: a new method to estimate cloud optical depth

A method for retrieving cloud optical depth ( τ c ) using a UCSD developed ground-based sky imager (USI) is presented. The radiance red–blue ratio (RRBR) method is motivated from the analysis of simulated images of various τ c produced by a radiative transfer model (RTM). From these images the basic parameters affecting the radiance and red–blue ratio (RBR) of a pixel are identified as the solar zenith angle ( θ 0 ), τ c , solar pixel angle/scattering angle ( θ s ), and pixel zenith angle/view angle ( θ z ). The effects of these parameters are described and the functions for radiance, I λ τ c , θ 0 , θ s , θ z , and RBR τ c , θ 0 , θ s , θ z are retrieved from the RTM results. RBR, which is commonly used for cloud detection in sky images, provides non-unique solutions for τ c , where RBR increases with τ c up to about τ c = 1 (depending on other parameters) and then decreases. Therefore, the RRBR algorithm uses the measured I λ meas θ s , θ z , in addition to RBR meas θ s , θ z , to obtain a unique solution for τ c . The RRBR method is applied to images of liquid water clouds taken by a USI at the Oklahoma Atmospheric Radiation Measurement (ARM) program site over the course of 220 days and compared against measurements from a microwave radiometer (MWR) and output from the Min et al. (2003) method for overcast skies. τ c values ranged from 0 to 80 with values over 80, being capped and registered as 80. A τ c RMSE of 2.5 between the Min et al. (2003) method and the USI are observed. The MWR and USI have an RMSE of 2.2, which is well within the uncertainty of the MWR. In conclusion, the procedure developed here provides a foundation to test and develop other cloud detection algorithms.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2021

ClimateNet: an expert-labeled open dataset and deep learning architecture for enabling high-precision analyses of extreme weather

Abstract. Identifying, detecting, and localizing extreme weather events is a crucial first step in understanding how they may vary under different climate change scenarios. Pattern recognition tasks such as classification, object detection, and segmentation (i.e., pixel-level classification) have remained challenging problems in the weather and climate sciences. While there exist many empirical heuristics for detecting extreme events, the disparities between the output of these different methods even for a single event are large and often difficult to reconcile. Given the success of deep learning (DL) in tackling similar problems in computer vision, we advocate a DL-based approach. DL, however, works best in the context of supervised learning – when labeled datasets are readily available. Reliable labeled training data for extreme weather and climate events is scarce. We create “ClimateNet” – an open, community-sourced human-expert-labeled curated dataset that captures tropical cyclones (TCs) and atmospheric rivers (ARs) in high-resolution climate model output from a simulation of a recent historical period. We use the curated ClimateNet dataset to train a state-of-the-art DL model for pixel-level identification – i.e., segmentation – of TCs and ARs. We then apply the trained DL model to historical and climate change scenarios simulated by the Community Atmospheric Model (CAM5.1) and show that the DL model accurately segments the data into TCs, ARs, or “the background” at a pixel level. Further, we show how the segmentation results can be used to conduct spatially and temporally precise analytics by quantifying distributions of extreme precipitation conditioned on event types (TC or AR) at regional scales. The key contribution of this work is that it paves the way for DL-based automated, high-fidelity, and highly precise analytics of climate data using a curated expert-labeled dataset – ClimateNet. ClimateNet and the DL-based segmentation method provide several unique capabilities: (i) they can be used to calculate a variety of TC and AR statistics at a fine-grained level; (ii) they can be applied to different climate scenarios and different datasets without tuning as they do not rely on threshold conditions; and (iii) the proposed DL method is suitable for rapidly analyzing large amounts of climate model output. While our study has been conducted for two important extreme weather patterns (TCs and ARs) in simulation datasets, we believe that this methodology can be applied to a much broader class of patterns and applied to observational and reanalysis data products via transfer learning.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2017

Hyperspectral Image Classification Using Graph Clustering Methods

Hyperspectral imagery is a challenging modality due to the dimension of the pixels which can range from hundreds to over a thousand frequencies depending on the sensor. Most methods in the literature reduce the dimension of the data using a method such as principal component analysis, however this procedure can lose information. More recently methods have been developed to address classification of large datasets in high dimensions. This paper presents two classes of graph-based classification methods for hyperspectral imagery. Using the full dimensionality of the data, we consider a similarity graph based on pairwise comparisons of pixels. The graph is segmented using a pseudospectral algorithm for graph clustering that requires information about the eigenfunctions of the graph Laplacian but does not require computation of the full graph. We develop a parallel version of the Nyström extension method to randomly sample the graph to construct a low rank approximation of the graph Laplacian. With at most a few hundred eigenfunctions, we can implement the clustering method designed to solve a variational problem for a graph-cut-based semi-supervised or unsupervised classification problem. We implement OpenMP directive-based parallelism in our algorithms and show performance improvement and strong, almost ideal, scaling behavior. The method can handle very large datasets including a video sequence with over a million pixels, and the problem of segmenting a data set into a pre-determined number of classes.

47 OTHER INSTRUMENTATION↗

DOE OSTI2025

IM3 Phase 2 Official Simulations: GCAM-Demeter-SELECT Annualized Land Use and Land Cover, Wood Harvest and Fertilization Data with Dynamic Urbanization Harmonized to CLM Land Definitions at 0.125 Degrees

Annualized land use land cover data, including wood harvest and fertilizer use data from the Global Change Analysis Model (GCAM) downscaled to 0.125 degrees for couping with the Community Land Model (CLM). GCAM here refers to GCAM-USA v5.3.im3 which has an enhanced electricity sector and an updated data system needed to represent regional to local scale dynamics. Data is also harmonized with future urbanization projections from the Spatially-Explicit, Long-term, Empirical City developmenT (SELECT) model. Projections/Data are generated using the demeter land use and land cover downscaling model. Original projections were generated at 0.05 degrees before being aggregared to 0.125 degrees. Projections are available for 8 alternative scenarios. Two versions of final data are included- one with managed forests or harvested forest area per pixel broken out and one with the same aggregated into total forests. Following folders are included: demeter_78_PFT_output:This is the final output of dynamic land use land cover change for 78 PFTs as required by CLM raw_outputs_incl_managed_forest: This is the final output but with managed forests broken out as a different PFT. Essentially a 79th PFT is added. wood_harvest_outputs: Wood harvest output per pixel in gC/m2 fertilization_outputs: Fertilizer use per pixel in gN/m2 Each NetCDF file in each folder represents a projection for a separate year, scenario. Land use outputs are organized as PFT level data saved as subdata. Link to GCAM version used- https://data.msdlive.org/records/yb23g-44274 Link to SELECT documentation -https://www.sciencedirect.com/science/article/pii/S1364815219301707 Link to CLM documentation- - https://www.cesm.ucar.edu/models/clm In case of questions contact- kanishka.narayan@pnnl.gov

GCAM-USA↗

DOE OSTI2018

An automated, high-throughput method for standardizing image color profiles to improve image-based plant phenotyping

High-throughput phenotyping has emerged as a powerful method for studying plant biology. Large image-based datasets are generated and analyzed with automated image analysis pipelines. A major challenge associated with these analyses is variation in image quality that can inadvertently bias results. Images are made up of tuples of data called pixels, which consist of R, G, and B values, arranged in a grid. Many factors, for example image brightness, can influence the quality of the image that is captured. These factors alter the values of the pixels within images and consequently can bias the data and downstream analyses. Here, we provide an automated method to adjust an image-based dataset so that brightness, contrast, and color profile is standardized. The correction method is a collection of linear models that adjusts pixel tuples based on a reference panel of colors. We apply this technique to a set of images taken in a high-throughput imaging facility and successfully detect variance within the image dataset. In this case, variation resulted from temperature-dependent light intensity throughout the experiment. Using this correction method, we were able to standardize images throughout the dataset, and we show that this correction enhanced our ability to accurately quantify morphological measurements within each image. We implement this technique in a high-throughput pipeline available with this paper, and it is also implemented in PlantCV.

47 OTHER INSTRUMENTATION↗

NASA NTRS1973

A technique for interpretation of multispectral remote sensor data

The author has identified the following significant results. The U.S. Army Engineer Waterways Experiment Station is engaged in a study to detect from ERTS-1 satellite data alterations to the absorption and scattering properties caused by movement of suspended particles and solutes in selected areas of the Chesapeake Bay and to correlate the data to determine the feasibility of delineating flow patterns, flushing action of the estuary, and sediment and pollutant dispersion. As a part of this study, ADP techniques have been developed that permit automatic interpretation of data from any multispectral remote sensor with computer systems which have limited memory capacity and computing speed. The multispectral remote sensor is considered as a reflectance spectrophotometer. The data which define the spectral reflectance characteristics of a scene are scanned pixel by pixel. Each pixel whose spectral reflectance matches a reference spectrum is identified, and the results are shown in a map that identifies the locations where spectrum matches were detected and spectrum that was matched. The interpretation technique is described and an example of interpreted data from ERTS-1 is presented.

Williamson, A. N.↗

NASA NTRS1973

Correlation of ERTS MSS data and earth coordinate systems

The author has identified the following significant results. Experience has revealed a problem in the analysis and interpretation of ERTS-1 multispectral scanner (MSS) data. The problem is one of accurately correlating ERTS-1 MSS pixels with analysis areas specified on aerial photographs or topographic maps for training recognition computers and/or evaluating recognition results. It is difficult for an analyst to accurately identify which ERTS-1 pixels on a digital image display belong to specific areas and test plots, especially when they are small. A computer-aided procedure to correlate coordinates from topographic maps and/or aerial photographs with ERTS-1 data coordinates has been developed. In the procedure, a map transformation from earth coordinates to ERTS-1 scan line and point numbers is calculated using selected ground control points nad the method of least squares. The map transformation is then applied to the earth coordinates of selected areas to obtain the corresponding ERTS-1 point and line numbers. An optional provision allows moving the boundaries of the plots inward by variable distances so the selected pixels will not overlap adjacent features.

Malila, W. A.↗

NASA NTRS1975

Estimating proportions of objects from multispectral scanner data

Progress is reported in developing and testing methods of estimating, from multispectral scanner data, proportions of target classes in a scene when there are a significiant number of boundary pixels. Procedures were developed to exploit: (1) prior information concerning the number of object classes normally occurring in a pixel, and (2) spectral information extracted from signals of adjoining pixels. Two algorithms, LIMMIX and nine-point mixtures, are described along with supporting processing techniques. An important by-product of the procedures, in contrast to the previous method, is that they are often appropriate when the number of spectral bands is small. Preliminary tests on LANDSAT data sets, where target classes were (1) lakes and ponds, and (2) agricultural crops were encouraging.

Horwitz, H. M.↗

NASA NTRS1975

Second generation digital techniques for processing LANDSAT MSS data

Results are reported for precision corrected LANDSAT MSS full scene registration of better than 0.5 picture element (rms), utilizing all digital methods. Examples of such registered full scene images are presented and evaluated by two methods: (1) change detection imagery which represents pixel by pixel the difference of corresponding pixel values in the registered data; and (2) direct measurement of registration errors throughout the imagery by means of a highly accurate cross correlation algorithm. Subscene image details illustrate the impact on registration accuracy of two interpolation algorithms.

Rifman, S. S.↗

NASA NTRS1976

Application of Skylab EREP data for land use management

The author has identified the following significant results. The 1.09-1.19 micron band proved to be very valuable for discriminating a variety of land use categories, including agriculture, forest, and urban classes. The 1.55-1.75 micron band proved very useful in combination with the 1.09-1.19 micron band. Misregistration between spectral bands, even by as little as 1/2 pixel, may degrade classification accuracy. Identification accuracy of boundary or border pixels was as much as 13% lower than the accuracy for identifying internal field pixels. The principal conclusion with respect to the S190B camera system is that the higher resolution of the S190B system in comparison to previous space photography (Gemini, Apollo), to the S190A system (Skylab), and to LANDSAT imagery significantly increases the range of additional discrimination achievable.

Simonett, D. S.↗

NASA NTRS1977

Development of remote sensing technology in New Zealand, part 1. Seismotectonic, structural, volcanologic and geomorphic study of New Zealand, part 2. Indigenous forest assessment, part 3. Mapping land use and environmental studies in New Zealand, part 4. New Zealand forest service LANDSAT projects, part 5. Vegetation map and landform map of Aupouri Peninsula, Northland, part 6. Geographical applications of LANDSAT mapping, part 7

The author has identified the following significant results. Inspection of pixels obtained from LANDSAT of New Zealand revealed that not only can ships and their wakes be detected, but that information on the size, state of motion, and direction of movement was inferred by calculating the total number of pixels occupied by the vessel and wake, the orientation of these pixels, and the sum of their radiance values above the background level. Computer enhanced images showing the Waimihia State Forest and much of Kaingaroa State Forest on 22 December 1975 were examined. Most major forest categories were distinguished on LANDSAT imagery. However, the LANDSAT imagery seemed to be most useful for updating and checking existing forest maps, rather than making new maps with many forest categories. Snow studies were performed using two basins: Six Mile Creek and Mt. Robert. The differences in radiance levels indicated that a greater areal snow cover in Six Mile Creek Basin with the effect of lower radiance values from vegetation/snow regions. A comparison of the two visible bands (MSS 4 and 5) demonstrate this difference for the two basins.

Probine, M. C.↗

NASA NTRS1976

Experimental study of digital image processing techniques for LANDSAT data

The author has identified the following significant results. Results are reported for: (1) subscene registration, (2) full scene rectification and registration, (3) resampling techniques, (4) and ground control point (GCP) extraction. Subscenes (354 pixels x 234 lines) were registered to approximately 1/4 pixel accuracy and evaluated by change detection imagery for three cases: (1) bulk data registration, (2) precision correction of a reference subscene using GCP data, and (3) independently precision processed subscenes. Full scene rectification and registration results were evaluated by using a correlation technique to measure registration errors of 0.3 pixel rms thoughout the full scene. Resampling evaluations of nearest neighbor and TRW cubic convolution processed data included change detection imagery and feature classification. Resampled data were also evaluated for an MSS scene containing specular solar reflections.

Rifman, S. S.↗

NASA NTRS1977

Ground truth management system to support multispectral scanner /MSS/ digital analysis

A computerized geographic information system for management of ground truth has been designed and implemented to relate MSS classification results to in situ observations. The ground truth system transforms, generalizes and rectifies ground observations to conform to the pixel size and shape of high resolution MSS aircraft data. These observations can then be aggregated for comparison to lower resolution sensor data. Construction of a digital ground truth array allows direct pixel by pixel comparison between classification results of MSS data and ground truth. By making comparisons, analysts can identify spatial distribution of error within the MSS data as well as usual figures of merit for the classifications. Use of the ground truth system permits investigators to compare a variety of environmental or anthropogenic data, such as soil color or tillage patterns, with classification results and allows direct inclusion of such data into classification operations. To illustrate the system, examples from classification of simulated Thematic Mapper data for agricultural test sites in North Dakota and Kansas are provided.

Coiner, J. C.↗

NASA NTRS1977

The vector classifier

A linear classifier is developed. The classifier algorithm derives, from the picture element (pixel) response values, the response values for a point (called footpoint) consisting of determined proportions of distinct and operator defined land surfaces. The algorithm decides whether the pixel contains the content of the defined surfaces by testing the footpoint to pixelpoint distance against an operator specified threshold value. The test can be either of statistical or geometric form. Those pixels which give a positive result to the test are subclassified according to the proportions of the distinct land surfaces. The practical characteristics of the classifier are discussed and the classification results achieved, in a number of test areas, are described. The artificial nature of the classifier assumptions relate to certain land surface conditions. Testing the suitability of the classifier for other conditions is discussed.

Mccloy, K. R.↗