Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “3D segmentation”

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 433 records · Page 24
All sourcesNASA NTRSDOE OSTI
DOE OSTI2011

High resolution cone beam X-ray computed tomography of 3D-microstructures of cast Al-alloys

X-ray computed tomography (XCT) has become a very important method for non-destructive 3D-characterisation of materials. XCT systems with cone beam geometry, micro- or nano-focus tubes and matrix detectors are increasingly used in research and non-destructive testing. Spatial resolutions down to 1 {mu}m can be reached with such XCT-systems for heterogeneities in metals with high absorption contrast. High resolution cone beam XCT is applied to five different Al-alloys: AlMg5Si7, AlCu4Mg1, AlZn6Mg2Cu2, AlZn8Mg2Cu2 and AlSi12Ni1. Up to four different types of inhomogeneities are segmented in one alloy using voxel sizes between (0.4 {mu}m){sup 3} and (2.3 {mu}m){sup 3}. Target metallography and elemental analysis by energy dispersive X-ray analysis are used to identify the inhomogeneities. The possibilities and restrictions of XCT applied to Al-alloys are discussed. AlMg5Si7 XCT-data with a voxel size of (0.4 {mu}m){sup 3} show inhomogeneities with brighter grey-values than the Al-matrix identified as elongated Fe-aluminides, and those with lower grey-values identified as pores and Mg{sub 2}Si-particles with a 'Chinese script-like' structure. Higher-absorbing interdendritic Al-Al{sub 2}Cu-eutectic regions appear brighter than the Al-dendrites in the CT-data of AlCu4Mg1 with (1.1 {mu}m){sup 3}/voxel, whereas pores > 4 {mu}m appear darker than the Al-matrix. The size and the 3D-structure of the {alpha}-Al dendrite arms with a diameter of 50-100 {mu}m are determined in samples from chill cast billets of AlCu4Mg1 and AlZn6Mg2Cu2 alloys. The irregular interdendritic regions containing eutectic segregations with Cu- and Zn-rich phases are > 5 {mu}m wide. Equally absorbing primary equi-axed Al{sub 3}(Sc, Zr) particles > 5 {mu}m are distinguished in the centres of the dendrites by the level of sphericity values. The distribution of Ni- and Fe-aluminides in a squeeze cast AlSi12Ni1-alloy is imaged with (0.4 {mu}m){sup 3}/voxel, but the Si-phase cannot be segmented.

36 MATERIALS SCIENCE↗
DOE OSTI2016

Three-dimensional simulation of thermal harmonic lasing free electron laser with detuning of the fundamental

Detuning of the fundamental is a way to enhance harmonic generation. By this method, the wiggler is composed of two segments in such a way that the fundamental resonance of the second segment to coincide with the third harmonic of the first segment of the wiggler to generate extreme ultraviolet radiation and x-ray emission. A set of coupled, nonlinear, and first-order differential equations in three dimensions describing the evolution of the electron trajectories and the radiation field with warm beam is solved numerically by CYRUS 3D code in the steady-state for two models (1) seeded free electron laser (FEL) and (2) shot noise on the electron beam (self-amplified spontaneous emission FEL). Thermal effects in the form of longitudinal velocity spread are considered. Three-dimensional simulation describes self-consistently the longitudinal spatial dependence of radiation waists, curvatures, and amplitudes together with the evaluation of the electron beam. The evolutions of the transverse modes are investigated for the fundamental resonance and the third harmonic. Also, the effective modes of the third harmonic are studied. In this paper, we found that detuning of the fundamental with shot noise gives more optimistic result than the seeded FEL.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2025

Improving ICARUS Track Reconstruction Algorithms

The ICARUS experiment is part of the Short-Baseline Neutrino (SBN) program at Fermilab. The main goal of the experiment is to investigate the possibility of sterile neutrinos in the O(1 eV) mass region and provide clarification of the anomaly detected from the Liquid Scintillator Neutrino Detector (LSND) and MiniBooNE experiments. The ICARUS-T600 detector is a Liquid Argon Time Projection Chamber (LAr-TPC), that can provide excellent 3D imaging and calorimetric reconstruction of any ionizing particles. This detection technique allows a detailed study of neutrino interactions, spanning a wide energy spectrum (from a few keV to several hundreds of GeV). The detector consists of two identical adjacent modules, filled with a total of 760 tons of ultra-pure liquid argon. Each module houses two LAr-TPCs separated by a common cathode with a maximum drift distance of 1.5 m, equivalent to about 1 ms drift time for the nominal $500$ V/m electric drift field. The anode is made of three parallel wire planes positioned 3 mm apart, where the stainless-steel wires are oriented on each plane at a different angle with respect to the horizontal direction ($+60^\degree$,$-60^\degree$,$0^\degree$). The first two planes (Induction 1 and Induction 2) provide a non-destructive charge measurement, whereas the ionization charge is fully collected by the last collection plane. In total, 53248 wires with a 3 mm pitch and length up to 9 m are installed in the detector. In the first stage of the reconstruction, segments of waveforms corresponding to physical signals (hits) are searched for in the deconvolved wire waveform with a threshold-based hit-finding algorithm. Each hit is then fitted with a Gaussian, whose area is proportional to the number of drift electrons generating the signal. In the second stage of the reconstruction, hits are passed as input to Pandora, a framework software composed of different pattern recognition algorithms, that performs a 3D reconstruction of the full image recorded in the collected event, including the identification of interaction vertices and tracks and showers inside the TPC. These are organized into a hierarchical structure (called slice) of particles generated starting from a primary interaction vertex. In some cases, related to the inefficiencies in the hit detection or excessive deflection of the particle trajectory, Pandora breaks the particle's track into two or more smaller pieces and considers each piece as an independent track. We studied this phenomenon focusing on primary muons from ν_μ CC interactions contained in a single module with a track at least 20 cm long, to exclude delta rays. The study determined that about $7-8\%$ of the muon tracks are broken. Approximately $80\%$ of the times, Pandora assigns all segments of the track to the same slice (intra-slice track split), while in the remaining $20\%$ of the cases, one of the segments is associated with another slice (extra-slice track split). To mitigate this phenomenon, we designed an algorithm that detects and stitches the tracks broken by Pandora for the intra-slice split. In Monte Carlo simulations, the algorithm showed an efficiency exceeding $80\%$ and a purity exceeding $93\%$.

Ricci, Alessandro Maria [Pisa U.; INFN, Pisa] (ORC↗
DOE OSTI2016

TH-AB-209-08: Next Generation Dedicated 3D Breast Imaging with XACT

Purpose: Exposure to radiation increases the risk of cancer. We have designed a new imaging paradigm, X-ray induced acoustic computed tomography (XACT). Applying this innovative technology to breast imaging, an X-ray exposure can generate a 3D acoustic image, which dramatically reduces the radiation dose to patients when compared to conventional breast CT. Methods: Theoretical calculations are done to determine the appropriate X-ray energy and ultrasound frequency in breast XACT imaging. A series of breast CT image along the coronal plane from a patient with calcifications in the breast tissue are used as the source image. HU value based segmentation is done to distinguish the skin, adipose tissue, glandular tissue, breast calcification, and chest bone from each CT image. X-ray dose deposition in each pixel is calculated based on the tissue type by using GEANT4 Monte Carlo toolkits. The initial pressure rise caused by X-ray energy deposition is calculated according to tissue properties. Then, the X-ray induced acoustic wave propagation is simulated by K-WAVE toolkit. Breast XACT images are reconstructed from the recorded time-dependent ultrasound waves. Results: For imaging a breast with large size (16cm in diameter at chest wall), the photon energy of X-ray source and the central frequency of ultrasound detector is determined as 20keV and 5.5MHz. Approximately 10 times contrast between a calcification and the breast tissue can be acquire from XACT image. The calcification can be clearly identified from the reconstructed XACT image. Conclusion: XACT technique takes the advantages of X-ray absorption contrast and high ultrasonic resolution. With the proposed innovative technology, one can potentially reduce radiation dose to patient in 3D breast imaging as compared with current x-ray modalities, while still maintaining high imaging contrast and spatial resolution.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2017

Dynamics of Shape-Persistent Giant Molecules: Zimm-like Melt, Elastic Plateau, and Cooperative Glass-like

Giant molecules are a new class of soft matter having threedimensional (3D) shapes and composed of chemically linked rigid molecular nanoparticles. Structurally, a 3D cluster of molecular nanoparticles can be one giant molecule or a few giant molecules associated together via specific interactions. The dynamics of clusters that are smaller than a critical diameter (~5 nm) presents a power law relaxation exponent of 0.7 at the high frequency region corresponding to segmental dynamics. Such scaling is similar to the result of the Zimm model although those clusters are neither chain-like nor in solution. Clusters that are larger than this critical diameter and formed by the association of giant molecules exhibit an elastic plateau due to caging of individual giant molecules. Herein, we hypothesize that clusters of such a large size cannot move as a whole, even above the glass transition temperature of the sample. They thus are “cooperative glass-like”. A structural cluster of giant molecules could be abstracted as a dynamical cluster consisting of unlinked but cooperatively mobile beads. As derived in the random first-order transition theory, the cluster loses its mobility and reaches the glassy state when the diameter of the cluster is 6 times larger than the bead diameter. In our cases, we estimate that the critical diameter for these clusters is also approximately 6 times the bead diameter based on the glassy shear modulus of giant molecules. Thus, shape-persistent giant molecules may serve as a bridge between polymers and colloids and a platform to mimic cooperative rearrangements.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2012

High resolution detection and excitation of resonant magnetic perturbations in a wall-stabilized tokamak

We report high-resolution detection of the 3D plasma magnetic response of wall-stabilized tokamak discharges in the High Beta Tokamak-Extended Pulse [T. H. Ivers et al., Phys. Plasmas 3, 1926 (1996)] device. A new adjustable conducting wall has been installed on HBT-EP made up of 20 independent, movable, wall segments instrumented with three distinct sets of 40 modular coils that can be independently driven to generate a wide variety of magnetic perturbations. High-resolution detection of the plasma response is made with 216 poloidal and radial magnetic sensors that have been located and calibrated with high-accuracy. Static and dynamic plasma responses to resonant and non-resonant magnetic perturbations are observed through measurement of the step-response following a rapid change in the toroidal phase of the applied perturbations. Biorthogonal decomposition of the full set of magnetic sensors clearly defines the structures of naturally occurring external kinks as being composed of independent m/n = 3/1 and 6/2 modes. Resonant magnetic perturbations were applied to discharges with pre-existing, saturated m/n = 3/1 external kink mode activity. This m/n = 3/1 kink mode was observed to lock to the applied perturbation field. During this kink mode locked period, the plasma resonant response is characterized by a linear, a saturated, and a disruptive plasma regime dependent on the magnitude of the applied field and value of the edge safety factor and plasma rotation.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2023

Low-Cost X-Ray CT System for Imaging of Roots

The goal of this project was to develop and demonstrate an innovative, low cost, field deployable, stationary 3D x-ray computed tomography (CT) system that will image total root phenotypes with a micron size resolution at a throughput of hundreds of plants per cycle. This system is based on UHV’s unique low cost linear x-ray tube technology and sophisticated reconstruction & image segmentation algorithms developed at University of Massachusetts, Lowel and University of Nottingham; and was tested for several types of soils at University of Wisconsin and Texas A&M University. Currently, no technologies exist that have been designed to image roots in complex media such as agricultural field conditions. Due to its small size, high resolution & fast imaging of fine roots, low power consumption, large penetration depth (i.e. ability to see through several feet of soil) and ease of field deployability, this CT system will increase the speed and efficacy of discovery, field translation, and deployment of improved crops and systems that improve soil carbon accumulation and storage, decrease N2O emissions, and improve water efficiency leading towards advancements that could mitigate 10% of the total US Greenhouse gases. This degree of imaging in the field has never been available and would be invaluable to scientists in understanding how environmental conditions and phenotypic variations contribute to carbon deposition through root development.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2015

Computer aided detection of surgical retained foreign object for prevention

Purpose: Surgical retained foreign objects (RFOs) have significant morbidity and mortality. They are associated with approximately $1.5 × 10{sup 9} annually in preventable medical costs. The detection accuracy of radiographs for RFOs is a mediocre 59%. The authors address the RFO problem with two complementary technologies: a three-dimensional (3D) gossypiboma micro tag, the μTag that improves the visibility of RFOs on radiographs, and a computer aided detection (CAD) system that detects the μTag. It is desirable for the CAD system to operate in a high specificity mode in the operating room (OR) and function as a first reader for the surgeon. This allows for fast point of care results and seamless workflow integration. The CAD system can also operate in a high sensitivity mode as a second reader for the radiologist to ensure the highest possible detection accuracy. Methods: The 3D geometry of the μTag produces a similar two dimensional (2D) depiction on radiographs regardless of its orientation in the human body and ensures accurate detection by a radiologist and the CAD. The authors created a data set of 1800 cadaver images with the 3D μTag and other common man-made surgical objects positioned randomly. A total of 1061 cadaver images contained a single μTag and the remaining 739 were without μTag. A radiologist marked the location of the μTag using an in-house developed graphical user interface. The data set was partitioned into three independent subsets: a training set, a validation set, and a test set, consisting of 540, 560, and 700 images, respectively. A CAD system with modules that included preprocessing μTag enhancement, labeling, segmentation, feature analysis, classification, and detection was developed. The CAD system was developed using the training and the validation sets. Results: On the training set, the CAD achieved 81.5% sensitivity with 0.014 false positives (FPs) per image in a high specificity mode for the surgeons in the OR and 96.1% sensitivity with 0.81 FPs per image in a high sensitivity mode for the radiologists. On the independent test set, the CAD achieved 79.5% sensitivity with 0.003 FPs per image in a high specificity mode for the surgeons and 90.2% sensitivity with 0.23 FPs per image in a high sensitivity mode for the radiologists. Conclusions: To the best of the authors’ knowledge, this is the first time a 3D μTag is used to produce a recognizable, substantially similar 2D projection on radiographs regardless of orientation in space. It is the first time a CAD system is used to search for man-made objects over anatomic background. The CAD system for the μTags achieved reasonable performance in both the high specificity and the high sensitivity modes.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2019

Formation and stability of long basal-prismatic facets in Mg

Long BP facets bounding {101¯2} 1¯011 twins in Mg ( ≥ 4nm) have been observed experimentally. However, the formation of these long BP facets has not been studied and their contribution/role to the twin growth remains unclear. We observed a long straight BP facet (27 nm) using high-resolution transmission electron microscopy (HRTEM) and investigated its formation, stability, and mobility by atomistic simulations. Experimentally, a serrated twin interface containing short CTBs and short BP facets near a (101¯2) twin tip is observed to transform under the effects of the electron beam into a long straight semi-coherent BP facet that contains disclination dipoles. Molecular dynamics (MD) simulations of the relaxation of a 3D twin domain reveals another process whereby a long partially-relaxed BP interface forms and contains an I 2 stacking fault. A comparison between the energy of these configurations as obtained by atomistic simulations suggests that these transformations occur in two steps: (1) serrated interfaces composed of coherent BP segments with lengths less than 2 nm combine and form a long and straight coherent BP facets and (2) these long coherent BP facets quickly transform into relaxed ones with misfit defects. Importantly, it is found that long BP facets are relatively immobile, and upon reloading, decay into more mobile serrated interfaces prior to migrating. Here, the work presented suggests that the atomistic configurations of BP facets during twin growth processes differ significantly from relaxed BP interfaces that would be observed by TEM.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Chain trajectories, domain shapes, and terminal boundaries in block copolymers

The packing geometry of macromolecules in complex mesophases is of key importance to self-organization in synthetic and biological soft materials. While approximate or heuristic models rely on often-untested assumptions about how flexible molecules “fit in” to distinct locations of complex assemblies, physical assemblies derive from ensembles of fluctuating conformations, obscuring the connection between mesophase geometry and the underlying arrangements. Here, we present an approach to extract and analyze features of molecular packing in diblock block copolymer (BCP) melts, a prototypical soft matter system, based on the statistical description of chain conformations in self-consistent field (SCF) theory. We show how average BCP chain trajectories in ordered morphologies can be analyzed from the SCF-derived orientational order parameter of chain segments. We use these extracted trajectories to analyze the features of local packing geometry, including chain bending and tilt, as well as the terminal boundaries that delineate distinct domains in ordered BCP morphologies. In conclusion, we illustrate this analysis by focusing on measurable features of packing frustration in 2D (columnar) and 3D (spherical and bicontinuous) morphologies, notably establishing an explicit link between chain conformations in complex morphologies and their medial geometry.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
NASA NTRS2020

Direct Numerical Simulations of Acoustic Disturbances in Various Rectangular Nozzle Configurations

We perform Direct Numerical Simulations (DNS) to study the acoustic freestream disturbances radiating from the turbulent boundary layers along the contoured nozzle walls of a hypersonic wind tunnel with a rectangular test section. To begin with, the effects of the spanwise end walls are suppressed by confining the spanwise computational domain to a finite segment of the overall nozzle cross section and by imposing periodic boundary conditions across that spanwise domain. Besides providing a building-block configuration to reveal par- tial effects of the enclosed acoustic environment within the wind tunnel, these computations serve as a stepping stone toward the goal of fully-3D computations including the nozzle end walls. Building upon the earlier simulations of Deegan et al. (2018), we show that the computed acoustic characteristics in the spanwise periodic simulations are insensitive to changes in the grid resolution parameters (e.g., x+ and z+). This is relative to the previous simulations that involved a coarser resolution in the streamwise and wall-normal directions, especially up- stream of the test section. Furthermore, we outline a comparison of the pressure fluctuations induced by the turbulent boundary layers over the contoured nozzle walls and several other calculations involving boundary layers over a single flat plate at nearly the same value of the edge Mach number. We also show the impact of having only one turbulent boundary layer instead of two within the computational setup. Various flow statistics, including the first and second moments of the unsteady flow field, are computed for the different flow configurations. Good comparisons of the statistics of the nozzle-wall boundary-layer turbulence and of the freestream acoustic disturbances between the simulations of coarser and finer grids confirms DNS procedure, but also the insensitivity of noise characteristics t section to the inflow turbulence generation technique.

Hildebrand, Nathaniel↗
DOE OSTI2019

Hydraulic-Fracture-Height Growth Under the Combined Influence of Stress Barriers and Natural Fractures

A fully coupled finite-element/finite-volume code is used here to model 3D hydraulically driven fractures under the influence of strong vertical variations in closure stress interacting with natural fractures. Previously unknown 3D interaction mechanisms on fracture-height growth are revealed. Slipping of a natural fracture, triggered by elevated fluid pressure from an intersecting hydraulic fracture, can induce both increases and decreases of normal stress in the minimum-horizontal-stress direction, toward the center and tip of the natural fracture, respectively. Consequently, natural fractures are expected to be able to both encourage and inhibit the progress of hydraulic fractures propagating through stress barriers, depending on the relative locations between the intersecting fractures. Once the hydraulic fracture propagates above the stress barrier through the weakened segment near a favorably located natural fracture, a configuration consisting of two opposing fractures cuts the stress barrier from above and below. The fluid pressure required to break the stress barrier under such opposing-fracture configurations is substantially lower than that required by a fracture penetrating the same barrier from one side. Sensitivity studies of geologic conditions and operational parameters have also been performed to explore the feasibility of controlled fracture height. The interactions between hydraulic fractures, natural fractures, and geologic factors such as stress barriers in three dimensions are shown to be much more complex than in two dimensions. Although it is impossible to exhaust all the possible configurations, the ability of a 3D, fully coupled numerical model to naturally capture these processes is well-demonstrated.

42 ENGINEERING↗
DOE OSTI2016

WE-AB-BRA-09: Registration of Preoperative MRI to Intraoperative Radiographs for Automatic Vertebral Target Localization

Purpose: Accurate localization of target vertebrae is essential to safe, effective spine surgery, but wrong-level surgery occurs with surprisingly high frequency. Recent research yielded the “LevelCheck” method for 3D-2D registration of preoperative CT to intraoperative radiographs, providing decision support for level localization. We report a new method (MR-LevelCheck) to perform 3D-2D registration based on preoperative MRI, presenting a solution for the increasingly common scenario in which MRI (not CT) is used for preoperative planning. Methods: Direct extension of LevelCheck is confounded by large mismatch in image intensity between MRI and radiographs. The proposed method overcomes such challenges with a simple vertebrae segmentation. Using seed points at centroids, vertebrae are segmented using continuous max-flow method and dilated by 1.8 mm to include surrounding cortical bone (inconspicuous in T2w-MRI). MRI projections are computed (analogous to DRR) using segmentation and registered to intraoperative radiographs. The method was tested in a retrospective IRB-approved study involving 11 patients undergoing cervical, thoracic, or lumbar spine surgery following preoperative MRI. Registration accuracy was evaluated in terms of projection-distance-error (PDE) between the true and estimated location of vertebrae in each radiograph. Results: The method successfully registered each preoperative MRI to intraoperative radiographs and maintained desirable properties of robustness against image content mismatch, and large capture range. Segmentation achieved Dice coefficient = 89.2 ± 2.3 and mean-absolute-distance (MAD) = 1.5 ± 0.3 mm. Registration demonstrated robust performance under realistic patient variations, with PDE = 4.0 ± 1.9 mm (median ± iqr) and converged with run-time = 23.3 ± 1.7 s. Conclusion: The MR-LevelCheck algorithm provides an important extension to a previously validated decision support tool in spine surgery by extending its utility to preoperative MRI. With initial studies demonstrating PDE <5 mm and 0% failure rate, the method is now in translation to larger scale prospective clinical studies. S. Vogt and G. Kleinszig are employees of Siemens Healthcare.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2017

Point Cloud Based Approach to Stem Width Extraction of Sorghum

A revolution in the field of genomics has produced vast amounts of data and furthered our understanding of the genotypephenotype map, but is currently constrained by manually intensive or limited phenotype data collection. We propose an algorithm to estimate stem width, a key characteristic used for biomass potential evaluation, from 3D point cloud data collected by a robot equipped with a depth sensor in a single pass in a standard field. The algorithm applies a two step alignment to register point clouds in different frames, a Frangi filter to identify stemlike objects in the point cloud and an orientation based filter to segment out and refine individual stems for width estimation. Individually, detected stems which are split due to occlusions are merged and then registered with previously found stems in previous camera frames in order to track temporally. We then refine the estimates to produce an accurate histogram of width estimates per plot. Since the plants in each plot are genetically identical, distributions of the stem width per plot can be useful in identifying genetically superior sorghum for biofuels.

09 BIOMASS FUELS↗
NASA NTRS2018

NeMO-Net & Fluid Lensing: The Neural Multi-Modal Observation & Training Network for Global Coral Reef Assessment Using Fluid Lensing Augmentation of NASA EOS Data

We present preliminary results from NASA NeMO-Net, the first neural multi-modal observation and training network for global coral reef assessment. NeMO-Net is an open-source deep convolutional neural network (CNN) and interactive active learning training software in development which will assess the present and past dynamics of coral reef ecosystems. NeMO-Net exploits active learning and data fusion of mm-scale remotely sensed 3D images of coral reefs captured using fluid lensing with the NASA FluidCam instrument, presently the highest-resolution remote sensing benthic imaging technology capable of removing ocean wave distortion, as well as hyperspectral airborne remote sensing data from the ongoing NASA CORAL mission and lower-resolution satellite data to determine coral reef ecosystem makeup globally at unprecedented spatial and temporal scales. Aquatic ecosystems, particularly coral reefs, remain quantitatively misrepresented by low-resolution remote sensing as a result of refractive distortion from ocean waves, optical attenuation, and remoteness. Machine learning classification of coral reefs using FluidCam mm-scale 3D data show that present satellite and airborne remote sensing techniques poorly characterize coral reef percent living cover, morphology type, and species breakdown at the mm, cm, and meter scales. Indeed, current global assessments of coral reef cover and morphology classification based on km-scale satellite data alone can suffer from segmentation errors greater than 40%, capable of change detection only on yearly temporal scales and decameter spatial scales, significantly hindering our understanding of patterns and processes in marine biodiversity at a time when these ecosystems are experiencing unprecedented anthropogenic pressures, ocean acidification, and sea surface temperature rise. NeMO-Net leverages our augmented machine learning algorithm that demonstrates data fusion of regional FluidCam (mm, cm-scale) airborne remote sensing with global low-resolution (m, km-scale) airborne and spaceborne imagery to reduce classification errors up to 80% over regional scales. Such technologies can substantially enhance our ability to assess coral reef ecosystems dynamics.

satellite data↗
NASA NTRS2018

NASA NeMO-Net

We present preliminary results from NASA NeMO-Net, the first neural multi-modal observation and training network for global coral reef assessment. NeMO-Net is an open-source deep convolutional neural network (CNN) and interactive active learning training software in development which will assess the present and past dynamics of coral reef ecosystems. NeMO-Net exploits active learning and data fusion of mm-scale remotely sensed 3D images of coral reefs captured using fluid lensing with the NASA FluidCam instrument, presently the highest-resolution remote sensing benthic imaging technology capable of removing ocean wave distortion, as well as hyperspectral airborne remote sensing data from the ongoing NASA CORAL mission and lower-resolution satellite data to determine coral reef ecosystem makeup globally at unprecedented spatial and temporal scales. Aquatic ecosystems, particularly coral reefs, remain quantitatively misrepresented by low- resolution remote sensing as a result of refractive distortion from ocean waves, optical attenuation, and remoteness. Machine learning classification of coral reefs using FluidCam mm-scale 3D data show that present satellite and airborne remote sensing techniques poorly characterize coral reef percent living cover, morphology type, and species breakdown at the mm, cm, and meter scales. Indeed, current global assessments of coral reef cover and morphology classification based on km-scale satellite data alone can suffer from segmentation errors greater than 40%, capable of change detection only on yearly temporal scales and decameter spatial scales, significantly hindering our understanding of patterns and processes in marine biodiversity at a time when these ecosystems are experiencing unprecedented anthropogenic pressures, ocean acidification, and sea surface temperature rise. NeMO-Net leverages our augmented machine learning algorithm that demonstrates data fusion of regional FluidCam (mm, cm-scale) airborne remote sensing with global low-resolution (m, km-scale) airborne and spaceborne imagery to reduce classification errors up to 80% over regional scales. Such technologies can substantially enhance our ability to assess coral reef ecosystems dynamics.

NASA↗
DOE OSTI2024

Reinforcement learning for block decomposition of planar CAD models

Abstract The problem of hexahedral mesh generation of general CAD models has vexed researchers for over 3 decades and analysts often spend more than 50% of the design-analysis cycle time decomposing complex models into simpler blocks meshable by existing techniques. The decomposed blocks are required for generating good quality meshes (tilings of quadrilaterals or hexahedra) suitable for numerical simulations of physical systems governed by conservation laws. We present a novel AI-assisted method for decomposing (segmenting) planar CAD (computer-aided design) models into well shaped rectangular blocks. Even though the simple examples presented here can also be meshed using many conventional methods, we believe this work is proof-of-principle of a AI-based decomposition method that can eventually be generalized to complex 2D and 3D CAD models. Our method uses reinforcement learning to train an agent to perform a series of optimal cuts on the CAD model that result in a good quality block decomposition. We show that the agent quickly learns an effective strategy for picking the location and direction of the cuts and maximizing its rewards. This paper is the first successful demonstration of an agent autonomously learning how to perform this block decomposition task effectively, thereby holding the promise of a viable method to automate this challenging process for more complex cases.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Design of a robot-automated flat plate/reflection geometry x-ray diffraction setup for accelerated materials discovery and structural screening

Here, we report the design, construction, and automation of a flat plate sample loading, alignment, and data acquisition system for X-ray diffraction measurements in reflection geometry implemented at the Stanford Synchrotron Radiation Lightsource. The system is built onto a single platform, enabling facile transferability, and is compartmentalized into sample storage, sample transfer, and sample position/alignment segments. The core feature of this system is a six-axis robotic arm that offers a large range of highly reproducible and programable movements. The degrees of freedom of the robot arm enable adaptability in which movements can be modified to fit various beamline environments and sample configurations. Samples are housed on 3D printed sample mounts, which are arranged onto a 6 × 2 array of sample cassettes capable of holding 7 samples. Using sample mounts designed for solid oxide electrolysis button cells (SOECs), the maximum tray capacity is 84 samples, which can be aligned and run in ~ 24 hours with long exposure scans. The sample array is additionally capable of accommodating a range of sample sizes and geometries due to the rapid 3D printed fabrication. The components of the setup will be described in detail and performance will be demonstrated with a set of representative SOEC and XRD standard samples. Opportunities for future developments and integration with the automated setup are summarized.

08 HYDROGEN↗