Search NASA⌕ Search

SEARCH · Search NASA

Results for “map 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 289 records · Page 16

Computational 3D histological phenotyping of whole zebrafish by X-ray histotomography

Organismal phenotypes frequently involve multiple organ systems. Histology is a powerful way to detect cellular and tissue phenotypes, but is largely descriptive and subjective. To determine how synchrotron-based X-ray micro-tomography (micro-CT) can yield 3-dimensional whole-organism images suitable for quantitative histological phenotyping, we scanned whole zebrafish, a small vertebrate model with diverse tissues, at ~1 micron voxel resolutions. Micro-CT optimized for cellular characterization (histotomography) allows brain nuclei to be computationally segmented and assigned to brain regions, and cell shapes and volumes to be computed for motor neurons and red blood cells. Striking individual phenotypic variation was apparent from color maps of computed densities of brain nuclei. Unlike histology, the histotomography also allows the study of 3-dimensional structures of millimeter scale that cross multiple tissue planes. We expect the computational and visual insights into 3D cell and tissue architecture provided by histotomography to be useful for reference atlases, hypothesis generation, comprehensive organismal screens, and diagnostics.

59 BASIC BIOLOGICAL SCIENCES↗

SU-C-BRA-03: An Automated and Quick Contour Errordetection for Auto Segmentation in Online Adaptive Radiotherapy

Purpose: To develop a tool that can quickly and automatically assess contour quality generated from auto segmentation during online adaptive replanning. Methods: Due to the strict time requirement of online replanning and lack of ‘ground truth’ contours in daily images, our method starts with assessing image registration accuracy focusing on the surface of the organ in question. Several metrics tightly related to registration accuracy including Jacobian maps, contours shell deformation, and voxel-based root mean square (RMS) analysis were computed. To identify correct contours, additional metrics and an adaptive decision tree are introduced. To approve in principle, tests were performed with CT sets, planned and daily CTs acquired using a CT-on-rails during routine CT-guided RT delivery for 20 prostate cancer patients. The contours generated on daily CTs using an auto-segmentation tool (ADMIRE, Elekta, MIM) based on deformable image registration of the planning CT and daily CT were tested. Results: The deformed contours of 20 patients with total of 60 structures were manually checked as baselines. The incorrect rate of total contours is 49%. To evaluate the quality of local deformation, the Jacobian determinant (1.047±0.045) on contours has been analyzed. In an analysis of rectum contour shell deformed, the higher rate (0.41) of error contours detection was obtained compared to 0.32 with manual check. All automated detections took less than 5 seconds. Conclusion: The proposed method can effectively detect contour errors in micro and macro scope by evaluating multiple deformable registration metrics in a parallel computing process. Future work will focus on improving practicability and optimizing calculation algorithms and metric selection.

60 APPLIED LIFE SCIENCES↗

TH-CD-206-01: Expectation-Maximization Algorithm-Based Tissue Mixture Quantification for Perfusion MRI

Purpose: To investigate the feasibility of estimating the tissue mixture perfusions and quantifying cerebral blood flow change in arterial spin labeled (ASL) perfusion MR images. Methods: The proposed perfusion MR image analysis framework consists of 5 steps: (1) Inhomogeneity correction was performed on the T1- and T2-weighted images, which are available for each studied perfusion MR dataset. (2) We used the publicly available FSL toolbox to strip off the non-brain structures from the T1- and T2-weighted MR images. (3) We applied a multi-spectral tissue-mixture segmentation algorithm on both T1- and T2-structural MR images to roughly estimate the fraction of each tissue type - white matter, grey matter and cerebral spinal fluid inside each image voxel. (4) The distributions of the three tissue types or tissue mixture across the structural image array are down-sampled and mapped onto the ASL voxel array via a co-registration operation. (5) The presented 4-dimensional expectation-maximization (4D-EM) algorithm takes the down-sampled three tissue type distributions on perfusion image data to generate the perfusion mean, variance and percentage images for each tissue type of interest. Results: Experimental results on three volunteer datasets demonstrated that the multi-spectral tissue-mixture segmentation algorithm was effective to initialize tissue mixtures from T1- and T2-weighted MR images. Compared with the conventional ASL image processing toolbox, the proposed 4D-EM algorithm not only generated comparable perfusion mean images, but also produced perfusion variance and percentage images, which the ASL toolbox cannot obtain. It is observed that the perfusion contribution percentages may not be the same as the corresponding tissue mixture volume fractions estimated in the structural images. Conclusion: A specific application to brain ASL images showed that the presented perfusion image analysis method is promising for detecting subtle changes in tissue perfusions, which is valuable for the early diagnosis of certain brain diseases, e.g. multiple sclerosis.

60 APPLIED LIFE SCIENCES↗

SU-E-J-103: Propagation of Rectum and Bladder Contours for Tandem and Ring (T&R) HDR Treatment Using Deformable Image Registration

Purpose: To investigate the feasibility of using DIR to propagate the manually contoured rectum and bladder from the 1st insertion to the new CT images on subsequent insertions and evaluate the segmentation performance. Methods: Ten cervical cancer patients, who were treated by T&R brachytherapy in 3–4 insertions, were retrospectively collected. In each insertion, rectum and bladder were manually delineated on the planning CT by a physicist and verified by a radiation oncologist. Using VelocityAI (Velocity Medical Solutions, Atlanta, GA), a rigid registration was firstly employed to match the bony structures between the first insertion and each of the following insertions, then a multi-pass B-spine DIR was carried out to further map the sub volume that encompasses rectum and bladder. The resultant deformation fields propagated contours, and dice similarity coefficient (DSC) was used to quantitatively evaluate the agreement between the propagated contours and the manually-delineated organs. For the 3rd insertion, we also evaluated if the segmentation performance could be improved by propagating the contours from the most recent insertion, i.e., the 2nd insertion. Results: On average, the contour propagation took about 1 minute. The average and standard deviation of DSC over all insertions and patients was 0.67±0.10 (range: 0.44–0.81) for rectum, and 0.78±0.07 (range: 0.63–0.87) for bladder. For the 3rd insertion, propagating contours from the 2nd insertion could improve the segmentation performance in terms of DSC from 0.63±0.10 to 0.72±0.08 for rectum, and from 0.77±0.07 to 0.79±0.06 for bladder. A Wilcoxon signed rank test indicated that the improvement was statistically significant for rectum (p = 0.004). Conclusion: The preliminary results demonstrate that deformable image registration could efficiently and accurately propagate rectum and bladder contours between CT images in different T&R brachytherapy fractions. We are incorporating the propagated contours into our learning-based method to further segment these organs.

60 APPLIED LIFE SCIENCES↗

An Atlas-Based Electron Density Mapping Method for Magnetic Resonance Imaging (MRI)-Alone Treatment Planning and Adaptive MRI-Based Prostate Radiation Therapy

Purpose: Prostate radiation therapy dose planning directly on magnetic resonance imaging (MRI) scans would reduce costs and uncertainties due to multimodality image registration. Adaptive planning using a combined MRI-linear accelerator approach will also require dose calculations to be performed using MRI data. The aim of this work was to develop an atlas-based method to map realistic electron densities to MRI scans for dose calculations and digitally reconstructed radiograph (DRR) generation. Methods and Materials: Whole-pelvis MRI and CT scan data were collected from 39 prostate patients. Scans from 2 patients showed significantly different anatomy from that of the remaining patient population, and these patients were excluded. A whole-pelvis MRI atlas was generated based on the manually delineated MRI scans. In addition, a conjugate electron-density atlas was generated from the coregistered computed tomography (CT)-MRI scans. Pseudo-CT scans for each patient were automatically generated by global and nonrigid registration of the MRI atlas to the patient MRI scan, followed by application of the same transformations to the electron-density atlas. Comparisons were made between organ segmentations by using the Dice similarity coefficient (DSC) and point dose calculations for 26 patients on planning CT and pseudo-CT scans. Results: The agreement between pseudo-CT and planning CT was quantified by differences in the point dose at isocenter and distance to agreement in corresponding voxels. Dose differences were found to be less than 2%. Chi-squared values indicated that the planning CT and pseudo-CT dose distributions were equivalent. No significant differences (p > 0.9) were found between CT and pseudo-CT Hounsfield units for organs of interest. Mean {+-} standard deviation DSC scores for the atlas-based segmentation of the pelvic bones were 0.79 {+-} 0.12, 0.70 {+-} 0.14 for the prostate, 0.64 {+-} 0.16 for the bladder, and 0.63 {+-} 0.16 for the rectum. Conclusions: The electron-density atlas method provides the ability to automatically define organs and map realistic electron densities to MRI scans for radiotherapy dose planning and DRR generation. This method provides the necessary tools for MRI-alone treatment planning and adaptive MRI-based prostate radiation therapy.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

X-ray microscopy enables multiscale high-resolution 3D imaging of plant cells, tissues, and organs

Capturing complete internal anatomies of plant organs and tissues within their relevant morphological context remains a key challenge in plant science. While plant growth and development are inherently multiscale, conventional light, fluorescence, and electron microscopy platforms are typically limited to imaging of plant microstructure from small flat samples that lack a direct spatial context to, and represent only a small portion of, the relevant plant macrostructures. We demonstrate technical advances with a lab-based X-ray microscope (XRM) that bridge the imaging gap by providing multiscale high-resolution three-dimensional (3D) volumes of intact plant samples from the cell to the whole plant level. Serial imaging of a single sample is shown to provide sub-micron 3D volumes co-registered with lower magnification scans for explicit contextual reference. High-quality 3D volume data from our enhanced methods facilitate sophisticated and effective computational segmentation. Advances in sample preparation make multimodal correlative imaging workflows possible, where a single resin-embedded plant sample is scanned via XRM to generate a 3D cell-level map, and then used to identify and zoom in on sub-cellular regions of interest for high-resolution scanning electron microscopy. In total, we present the methodologies for use of XRM in the multiscale and multimodal analysis of 3D plant features using numerous economically and scientifically important plant systems.

59 BASIC BIOLOGICAL SCIENCES↗

TH-A-18C-01: Design Optimization of Segmented Scintillators for Megavoltage Cone- Beam CT

Purpose: Active matrix flat-panel imagers incorporating thick, segmented scintillators for megavoltage cone-beam CT (MV CBCT) imaging have demonstrated strong potential for facilitating soft-tissue visualization at low, clinically practical doses. In order to identify scintillator design parameters that optimize performance for this purpose, a modeling technique which includes both radiation and optical effects and which lends itself to computationally practical implementation has been developed and explored. Methods: A hybrid modeling technique, based on Monte Carlo event-by-event simulation of radiation transport and separate determination of optical effects, was devised as an alternative to computationally prohibitive event-by- event simulations of both radiation and optical transport. The technique was validated against empirical results from a previously reported 1.13 cm thick, 1.016 mm element-to-element pitch BGO scintillator prototype. Using this technique, the contrast-to-noise ratio (CNR) and spatial resolution performance of numerous scintillator designs, with thicknesses ranging from 0.5 to 6 cm and pitches ranging from 0.508 to 1.524 mm, were examined. Results: CNR and spatial resolution performance for the various scintillator designs demonstrate complex behavior as scintillator thickness and pitch are varied - exhibiting a clear trade-off between these two imaging metrics up to a thickness of ~3 cm. Based on these results, an optimization map highlighting those regions of design that provide a balance between these metrics was created. The map indicates that, for a given set of optical parameters, scintillator thickness and pitch can be judiciously chosen to maximize performance without resorting to thicker, more costly scintillators. Conclusion: Modeling radiation and optical effects in thick, segmented scintillators through use of a hybrid modeling technique provides a practical way to gain insight as to how to optimize the performance of such devices for radiotherapy imaging. Assisted by such modeling, the development of practical designs should greatly facilitate low-dose, soft tissue visualization through MV CBCT imaging. This project was supported in part by NIH grant R01 CA051397.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

LABQ3: Bayesian method for quantification of mineral compositions and nano-scale elemental mapping of 3D synchrotron XCT data

Quantitative analysis of mineral compositions is essential in understanding geochemical, mineralogical and environmental processes. Fine-resolution 3D imaging is widely done using synchrotron X-ray computed tomography (XCT), but existing analyses are limited to visualization and segmentation. This paper presents a new method, Linear Attenuation Bayesian Quantitative 3D-mapper (LABQ3), based on the linearity of X-ray attenuation with respect to elemental concentrations. To address the random variability in attenuation measurements, LABQ3 employs Bayesian decision theory to minimize classification error, using reference attenuation distributions from scans of pure mineral standards. To demonstrate LABQ3 and test its performance, we studied precipitated carbonate samples. XCT scans were done at multiple energies using the transmission X-ray microscope (TXM) at beamline 32-ID-C of the Advanced Photon Source at Argonne National Laboratory. The reconstructed 3D images have a voxel size of 20 nm. Analyses revealed rich nano-scale compositional heterogeneity within individual particles. A mixture of calcium and cadmium produced an overall stoichiometric composition of (Ca 0.78 ,Cd 0.22 )CO 3 , with some voxels containing nearly pure CdCO 3 . The addition of zinc led to an overall stoichiometric composition of 33% Ca, 28% Cd, 39% Zn, with a nearly pure CaCO 3 core and compositional zonation through the rim. These compositional gradients are related to temporal sequences of carbonate mineral formation where Cd precipitated at the beginning in (Ca,Cd)CO 3 , while Cd and Zn precipitated at the end in (Ca, Cd,Zn)CO 3 . Results differ from bulk analyses using Inductively Coupled Plasma-Mass Spectrometry (ICP-MS), showing that LABQ3 provides particle-specific insights. LABQ3 distinguishes itself by quantifying chemical compositions along a continuum, making it different from XCT analyses based on segmentation. LABQ3 allows simultaneous acquisition of morphology and chemical composition in 3D, facilitating the interpretation of chemical gradients of trace elements, quantification of solid solution compositions, inferences about temporal sequences of mineral precipitation, and addressing other concerns about solid-phase chemistry.

58 GEOSCIENCES↗

Precursory signatures of protein folding/unfolding: From time series correlation analysis to atomistic mechanisms

Folded conformations of proteins in thermodynamically stable states have long lifetimes. Before it folds into a stable conformation, or after unfolding from a stable conformation, the protein will generally stray from one random conformation to another leading thus to rapid fluctuations. Brief structural changes therefore occur before folding and unfolding events. These short-lived movements are easily overlooked in studies of folding/unfolding for they represent momentary excursions of the protein to explore conformations in the neighborhood of the stable conformation. The present study looks for precursory signatures of protein folding/unfolding within these rapid fluctuations through a combination of three techniques: (1) ultrafast shape recognition, (2) time series segmentation, and (3) time series correlation analysis. The first procedure measures the differences between statistical distance distributions of atoms in different conformations by calculating shape similarity indices from molecular dynamics simulation trajectories. The second procedure is used to discover the times at which the protein makes transitions from one conformation to another. Finally, we employ the third technique to exploit spatial fingerprints of the stable conformations; this procedure is to map out the sequences of changes preceding the actual folding and unfolding events, since strongly correlated atoms in different conformations are different due to bond and steric constraints. The aforementioned high-frequency fluctuations are therefore characterized by distinct correlational and structural changes that are associated with rate-limiting precursors that translate into brief segments. Guided by these technical procedures, we choose a model system, a fragment of the protein transthyretin, for identifying in this system not only the precursory signatures of transitions associated with α helix and β hairpin, but also the important role played by weaker correlations in such protein folding dynamics.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Toward Magnetic Resonance–Only Simulation: Segmentation of Bone in MR for Radiation Therapy Verification of the Head

Purpose: To develop a practical method to localize bones in magnetic resonance (MR) images, to create “computed tomography–like” MR images (ctMRI) that could be used for radiation therapy verification, and to generate MR-based digitally reconstructed radiographs (DRR). Methods and Materials: Using T1-weighted MR images, an air mask was derived from the manual contouring of all airways within the head and neck region using axial images at 6 anatomic levels. Compact bone, spongy bone, and soft tissue masks were then automatically generated using the statistical data derived from MR intensities and the air mask. ctMRI were then generated by mapping the MR intensities of the voxels within these masks into the CT number ranges of corresponding tissues. MR-based DRRs created from ctMRI were quantitatively evaluated using the co-registered MR and CT head images of 20 stereotactic radiosurgery patients. Ten anatomical points, positioned on the skull segmented using a threshold of 300 HU, in CT and ctMRI, were used to determine the differences in distance between MR-based DRRs and CT-based DRRs, and to evaluate the geometric accuracy of ctMRI and MR-based DRRs. Results: The bony structures were identified on ctMRI and were visible in the MR-based DRRs. From the 20 patient cases, the mean geometric difference and standard deviation between the 10 anatomical points on MR-based and CT-based DRRs was −0.05 ± 0.85 mm, respectively. This included uncertainty in image fusion. The maximum distance difference was 1.88 mm. Conclusions: A practical method was developed to segment bone from MR images. The ctMRI created can be used for radiation treatment verification when MR-only simulation is performed. MR-based DRRs can be used in place of CT-based DRRs.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Processing of X-ray snapshots from crystals in random orientations

A new method for the treatment of partial reflections from X-ray snapshots is implemented in the program package nXDS, which yields intensity data of almost the same quality as those obtained by the classical rotation method. A functional expression is introduced that relates scattered X-ray intensities from a still or a rotation snapshot to the corresponding structure-factor amplitudes. The new approach was implemented in the program nXDS for processing monochromatic diffraction images recorded by a multi-segment detector where each exposure could come from a different crystal. For images containing indexable spots, the intensities of the expected reflections and their variances are obtained by profile fitting after mapping the contributing pixel contents to the Ewald sphere. The varying intensity decline owing to the angular distance of the reflection from the surface of the Ewald sphere is estimated using a Gaussian rocking curve. This decline is dubbed ‘Ewald offset correction’, which is well defined even for still images. Together with an image-scaling factor and other corrections, an explicit expression is defined that predicts each recorded intensity from its corresponding structure-factor amplitude. All diffraction parameters, scaling and correction factors are improved by post-refinement. The ambiguous case of a lower point group than the lattice symmetry is resolved by a method reminiscent of the technique of ‘selective breeding’. It selects the indexing alternative for each image that yields, on average, the highest correlation with intensities from all other images. Processing a test set of rotation images by XDS and treating the same images by nXDS as snapshots of crystals in random orientations yields data of comparable quality, clearly indicating an anomalous signal from Se atoms.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Structural insights into the human RyR2 N-terminal region involved in cardiac arrhythmias

X-ray and solution structures of the human RyR2 N-terminal region were obtained under near-physiological conditions. The structure exhibits a unique network of interactions between its three domains, revealing an important stabilizing role of the central helix. Human ryanodine receptor 2 (hRyR2) mediates calcium release from the sarcoplasmic reticulum, enabling cardiomyocyte contraction. The N-terminal region of hRyR2 (amino acids 1–606) is the target of >30 arrhythmogenic mutations and contains a binding site for phosphoprotein phosphatase 1. Here, the solution and crystal structures determined under near-physiological conditions, as well as a homology model of the hRyR2 N-terminal region, are presented. The N-terminus is held together by a unique network of interactions among its three domains, A, B and C, in which the central helix (amino acids 410–437) plays a prominent stabilizing role. Importantly, the anion-binding site reported for the mouse RyR2 N-terminal region is notably absent from the human RyR2. The structure concurs with the differential stability of arrhythmogenic mutations in the central helix (R420W, I419F and I419F/R420W) which are owing to disparities in the propensity of mutated residues to form energetically favourable or unfavourable contacts. In solution, the N-terminus adopts a globular shape with a prominent tail that is likely to involve residues 545–606, which are unresolved in the crystal structure. Docking the N-terminal domains into cryo-electron microscopy maps of the closed and open RyR1 conformations reveals C{sup α} atom movements of up to 8 Å upon channel gating, and predicts the location of the leucine–isoleucine zipper segment and the interaction site for spinophilin and phosphoprotein phosphatase 1 on the RyR surface.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Oregon Cascades Play Fairway Analysis: Raster Datasets and Models

This submission includes maps of the spatial distribution of basaltic, and felsic rocks in the Oregon Cascades. It also includes a final Play Fairway Analysis (PFA) model, with the heat and permeability composite risk segments (CRS) supplied separately. Metadata for each raster dataset can be found within the zip files, in the TIF images

15 GEOTHERMAL ENERGY↗

Pan-arctic river bank erosion and accretion, and planform metrics measured over intervals ranging from 1973 to 2016

This dataset provides the tabular summary of analysis of 17 reaches of 15 Arctic rivers for river bank erosion and accretion rates, as well as, river channel properties such as channel width, bank curvature, and the aspect/orientation of the river banks. These rivers include the: Chandalar River, Alaska, Colville River, Alaska; Indigirka River, Russia; Kolyma River, Russia; Koyukuk River, Alaska; Lena River, Alaska; Noatak River, Alaska; Ob River, Russia; Pechora River, Russia; Tanana River, Alaska, Selawik River, Alaska; Taz River, Russia; Yana River, Russia; Yenisei River, Russia; and the Yukon River, Alaska. The dataset was generated from a total of 129 images including: Landsat, higher resolution satellite imagery, and aerial photography over time periods ranging from the 1970s and 2016. A full list of the image dates, row and path (for Landsat), and pixel resolutions is provided in the dataset. Masks for the Chandalar River, Tanana River, and Yukon at Holy Cross were obtained from Brown et al. (2020). The masks were analyzed using the Spatially Continuous Riverbank Erosion and Accretion Measurements (SCREAM) software detailed in Rowland et al. 2016. The masks used in this analysis can be found an accompanying dataset (doi:10.15485/1571527).In files with “summary” in the name, the data is provided at a pixel level, where each mapped bank pixel has an associated erosion or accretion value, a channel width, a curvature value, and an aspect each river and time period will have an individual file. Files with “Segments” in name provide data that is averaged along segments of the rivers. These data are consolidated into a single file each for the erosion and accretion measurements. These segments are approximately 10 channel widths in length. In addition to erosion and accretion rates, the segment-based results include area measurements of erosion and accretion, islands, and channels. Revisions 2023:-Data added for the Koyukuk River for time periods of 1978-2012, 1978-2018, and 2012-2018. ---Data added from the Chandalar River, Tanana River, and Yukon River at Holy Cross based on masks obtained from Brown et al. (2020).-Updated the values for Drainage area and river slope, see methods below-Added values for meant topographic slope for upstream contributing area, long term averaged annual maximum monthly flow, average annual maximum monthly flow for the time period of erosion record, and added the river slope extracted from the Lin et al. (2020) data product.-Add field for River Planform Multi threaded (M) or Single threaded-Added ‘ConsolidatedErosionSegments.csv’ which provides the same data as AllRiversErosionSegments.csv rebinned with averages along river segments based on upstream drainage area instead of channel segments based on lengths set to approximately 10 channel widths.

54 ENVIRONMENTAL SCIENCES↗

River bank erosion and accretion rates, and planform metrics of the East River, downstream of Gothic Colorado over intervals between 1955 and 2015

This dataset provides the tabular summary of analysis of an alluvial floodplain reach of the East River, downstream of Gothic, CO near Crested Butte. The measurements include bank erosion and accretion rates, channel width, bank curvature, and the aspect/orientation of the river banks. The measurements were derived from binary masks of the location of the river channel from aerial and satellite imagery collected on seven dates over a sixty-year timespan: 1955, 1973, 1983, 1990, 2001, 2011, and 2015. The masks were analyzed using the Spatially Continuous Riverbank Erosion and Accretion Measurements (SCREAM) software detailed in Rowland et al. 2016. The masks used in this analysis can be found an accompanying dataset (DOI: ). Rates of change along the East River were measured over a total of 8-time intervals: 1955-1973; 1955-2015; 1973-1983; 1983-1990; 1990-2001; 2001-2011; 2001-2015; and 2011-2015.In files with “summary” in the name, the data is provided at a pixel level, where each mapped bank pixel has an associated erosion or accretion value, a channel width, a curvature value, and an aspect each river and time period will have an individual file. Files with “Segments” in name provide data that is averaged along segments of the rivers. These segments are approximately 10 channel widths in length. In addition to erosion and accretion rates, the segment-based results include area measurements of erosion and accretion, islands, and channels. The number of islands is also included.

54 ENVIRONMENTAL SCIENCES↗

Automatic Rural Road Centerline Detection and Extraction from Aerial Images for a Forest Fire Decision Support System

To effectively manage the terrestrial firefighting fleet in a forest fire scenario, namely, to optimize its displacement in the field, it is crucial to have a well-structured and accurate mapping of rural roads. The landscape’s complexity, mainly due to severe shadows cast by the wild vegetation and trees, makes it challenging to extract rural roads based on processing aerial or satellite images, leading to heterogeneous results. This article proposes a method to improve the automatic detection of rural roads and the extraction of their centerlines from aerial images. This method has two main stages: (i) the use of a deep learning model (DeepLabV3+) for predicting rural road segments; (ii) an optimization strategy to improve the connections between predicted rural road segments, followed by a morphological approach to extract the rural road centerlines using thinning algorithms, such as those proposed by Zhang–Suen and Guo–Hall. After completing these two stages, the proposed method automatically detected and extracted rural road centerlines from complex rural environments. This is useful for developing real-time mapping applications.

Lourenço, Miguel (ORCID:0000000157673394)↗

High-dimensional Data-driven Energy optimization for Multi-Modal Transit Agencies (HD-EMMA) (Final Technical Report)

Public bus transit services in the U.S. are responsible for at least 19.7 million metric tons of CO 2 emission annually. Electric vehicles (EVs) can have a much lower environmental impact than comparable internal combustion engine vehicles (ICEVs), especially in urban areas. Unfortunately, EVs are also much more expensive than ICEVs. As a result, many public transit agencies can afford only mixed fleets of transit vehicles, consisting of EVs, hybrids (HEVs), and ICEVs. Transit agencies that operate such mixed fleets of vehicles face a challenging optimization problem: these agencies need to decide which vehicles are assigned to serving which transit trips. Since the advantage of EVs over ICEVs varies depending on the route and time of day (e.g., the benefit of EVs is higher in slower traffic with frequent stops and lower on highways), the assignment can have a significant effect on energy use and, hence, environmental impact. Through this project, we have developed reference data about energy collections and constructed a set of machine learning models that can accurately predict the energy consumption for the whole fleet at the level of each trip. We have used these models to develop a scheduling and assignment strategy that can rotate the different vehicle types across the transit agencies’ routes. The optimization algorithm ensures that the vehicles are matched to trips considering weather patterns, expected congestion, and road gradients to minimize the overall energy usage. We list the key observations from our project for other practitioners below. Details are available in the report, and the list of source code and our publications are included in the appendix. 1. We have demonstrated the feasibility of collecting, merging and analyzing large volumes of high-resolution real-world telemetry data from a mixed vehicle fleet. To mitigate the inherent noise of the recorded GPS points, the team developed an algorithm that filters data and maps the points onto a street. The algorithm considers previous and subsequent location measurements and different characteristics of nearby streets to determine how likely the vehicle travels on them. Then, the team segmented the time series into disjoint contiguous samples based on adjacent road segments and repeated the outlier detection and removal. For each data point, the team added features corresponding to elevation changes within the samples, weather features, such as temperature, and traffic data, such as speed ratio between actual speed and free-flow speed. 2. We have developed two forms of machine learning models that be used to understand and analyze the energy operations of a mixed vehicle transit fleet. The micro prediction model provides estimates of instantaneous energy prediction for all types of buses (diesel, hybrid, and electric). Such a model is important in evaluating the energy impacts of real-time bus operation strategies, but it is challenging due to diversified driving cycles of transit buses. The model can help the drivers understand the impact of their driving behaviors and short-term congestions. The macro prediction models estimate average energy consumption across the whole trip considering the features: distance traveled, various road-type features, elevation change, day of the week, time of day, various weather features (temperature, humidity, etc.), and traffic features (speed ratio and jam factor). 3. We have demonstrated that it is possible to transfer the machine learning models we have developed in this project to other teams and cities by using inductive transfer learning. We also showed that the performance of the macro energy prediction models can be improved using a multi-task learning approach where the learning parameters are shared between the models being developed for different vehicle types. The advantage of this approach is improved learning performance as the models can exploit common spatio-temporal and environmental characteristics. 4. Finally, we have developed trip and vehicle assignment and scheduling algorithms that use the energy prediction models and develop a trip to vehicle type (diesel, electric, hybrid) assignment for the whole operation to reduce overall emissions and cost. We have shown through simulations that the proposed algorithms can save $\$$ 48,910 in energy costs and 175 metric tons of CO 2 emission annually for CARTA.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

We Know Where We Don't Know: 3D Bayesian CNNs for Credible Geometric Uncertainty

Deep learning has been successfully applied to the segmentation of 3D Computed Tomography (CT) scans. Establishing the credibility of these segmentations requires uncertainty quantification (UQ) to identify untrustworthy predictions. Recent UQ architectures include Monte Carlo dropout networks (MCDNs), which approximate deep Gaussian processes, and Bayesian neural networks (BNNs), which learn the distribution of the weight space. BNNs are advantageous over MCDNs for UQ but are thought to be computationally infeasible in high dimension, and neither architecture has produced interpretable geometric uncertainty maps. We propose a novel 3D Bayesian convolutional neural network (BCNN), the first deep learning method which generates statistically credible geometric uncertainty maps and scales for application to 3D data. We present experimental results on CT scans of graphite electrodes and laser-welded metals and show that our BCNN outperforms an MCDN in recent uncertainty metrics. The geometric uncertainty maps generated by our BCNN capture distributions of sigmoid values that are interpretable as confidence intervals, critical for applications that rely on deep learning for high-consequence decisions.

97 MATHEMATICS AND COMPUTING↗