Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “IDS”

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 487 records · Page 27

B56$δ$ long-disordered arms form a dynamic PP2A regulation interface coupled with global allostery and Jordan’s syndrome mutations

Intrinsically disordered regions (IDR) and short linear motifs (SLiMs) play pivotal roles in the intricate signaling networks governed by phosphatases and kinases. B56δ (encoded by PPP2R5D) is a regulatory subunit of protein phosphatase 2A (PP2A) with long IDRs that harbor a substrate-mimicking SLiM and multiple phosphorylation sites. De novo missense mutations in PPP2R5D cause intellectual disabilities (ID), macrocephaly, Parkinsonism, and a broad range of neurological symptoms. Our single-particle cryo-EM structures of the PP2A-B56δ holoenzyme reveal that the long, disordered arms at the B56δ termini fold against each other and the holoenzyme core. This architecture suppresses both the phosphatase active site and the substrate-binding protein groove, thereby stabilizing the enzyme in a closed latent form with dual autoinhibition. The resulting interface spans over 190 Å and harbors unfavorable contacts, activation phosphorylation sites, and nearly all residues with ID-associated mutations. Our studies suggest that this dynamic interface is coupled to an allosteric network responsive to phosphorylation and altered globally by mutations. Furthermore, we found that ID mutations increase the holoenzyme activity and perturb the phosphorylation rates, and the severe variants significantly increase the mitotic duration and error rates compared to the normal variant.

59 BASIC BIOLOGICAL SCIENCES↗

Ionization detail parameters and cluster dose: a mathematical model for selection of nanodosimetric quantities for use in treatment planning in charged particle radiotherapy

Abstract Objective . To propose a mathematical model for applying ionization detail (ID), the detailed spatial distribution of ionization along a particle track, to proton and ion beam radiotherapy treatment planning (RTP). Approach . Our model provides for selection of preferred ID parameters ( I p ) for RTP, that associate closest to biological effects. Cluster dose is proposed to bridge the large gap between nanoscopic I p and macroscopic RTP. Selection of I p is demonstrated using published cell survival measurements for protons through argon, comparing results for nineteen I p : N k , k = 2, 3, …, 10, the number of ionizations in clusters of k or more per particle, and F k , k = 1, 2, …, 10, the number of clusters of k or more per particle. We then describe application of the model to ID-based RTP and propose a path to clinical translation. Main results . The preferred I p were N 4 and F 5 for aerobic cells, N 5 and F 7 for hypoxic cells. Significant differences were found in cell survival for beams having the same LET or the preferred N k . Conversely, there was no significant difference for F 5 for aerobic cells and F 7 for hypoxic cells, regardless of ion beam atomic number or energy. Further, cells irradiated with the same cluster dose for these I p had the same cell survival. Based on these preliminary results and other compelling results in nanodosimetry, it is reasonable to assert that I p exist that are more closely associated with biological effects than current LET-based approaches and microdosimetric RBE-based models used in particle RTP. However, more biological variables such as cell line and cycle phase, as well as ion beam pulse structure and rate still need investigation. Significance . Our model provides a practical means to select preferred I p from radiobiological data, and to convert I p to the macroscopic cluster dose for particle RTP.

Engineering↗

A New Superconducting Undulator Cryostat for the APS Upgrade

The Advanced Photon Source (APS) is in the midst of a major facility upgrade including both a new electron storage ring (SR) and many new insertion devices ( IDs) providing x-ray photon beams to a new suite of experimental end stations. Included among the new IDs are four 4.8-meter superconducting undulator (SCU) cryostats, each containing two 1.8-meter planar undulator magnets operating at 4.2 K in either a phase shifted or canted configuration. We describe a new, compact cryocooler-based cryostat design which supports the magnets and associated subsystems and also fits the space constraints of the SR ID straight sections. The design is an evolution of earlier single-magnet 2-meter cryostats, retaining some subsystem commonality while incorporating lessons learned and several features unique to the challenge of supporting two independently operable undulator magnets in a single device.

Anliker, E.↗

NEW SUNS IN THE COSMOS?

The present work reports on the discovery of three stars that we have identified to be rotating Sun-like stars, based on rotational modulation signatures inferred from light curves from the CoRoT mission's Public Archives. In our analysis, we performed an initial selection based on the rotation period and position in the period-T{sub eff} diagram. This revealed that the stars CoRoT IDs 100746852, 102709980, and 105693572 provide potentially good matches to the Sun with a similar rotation period. To refine our analysis, we applied a novel procedure, taking into account the fluctuations of the features associated with photometric modulation at different time intervals and the fractality traces that are present in the light curves of the Sun and of these ''New Sun'' candidates alike. In this sense, we computed the so-called Hurst exponent for the referred stars, for a sample of 14 CoRoT stars with sub- and super-solar rotational periods, and for the Sun itself in its active and quiet phases. We found that the Hurst exponent can provide a strong discriminant of Sun-like behavior, going beyond what can be achieved with solely the rotation period itself. In particular, we find that CoRoT ID 105693572 is the star that most closely matches the solar rotation properties as far as the latter's imprints on light curve behavior are concerned. The stars CoRoT IDs 100746852 and 102709980 have significant smaller Hurst exponents than the Sun, notwithstanding their similarity in rotation periods.

79 ASTRONOMY AND ASTROPHYSICS↗

Neutrino factory optimization for nonstandard interactions

We study the optimization of a neutrino factory with respect to nonstandard neutral current neutrino interactions, and compare the results to those obtained without nonstandard interactions. We discuss the muon energy, baselines, and oscillation channels as degrees of freedom. Our conclusions are based on both analytical calculations and on a full numerical simulation of the neutrino factory setup proposed by the international design study (IDS-NF). We consider all possible nonstandard parameters, and include their complex phases. We identify the impact of the different parameters on the golden, silver, and disappearance channels. We come to the conclusion that, even in the presence of nonstandard interactions, the performance of the neutrino factory hardly profits from a silver channel detector, unless the muon energy is significantly increased compared to the IDS-NF setup. Apart from the dispensable silver channel detector, we demonstrate that the IDS-NF setup is close to optimal even if nonstandard interactions are considered. We find that one very long baseline is a key component in the search for nonstandard interactions, in particular, for |{epsilon}{sub {mu}}{sub {tau}}{sup m}| and |{epsilon}{sub {tau}}{sub {tau}}{sup m}|.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Focusing a round coherent beam by spatial filtering the horizontal source

This paper illustrates the use of spatial filtering with a horizontal slit near the source to enlarge the horizontal coherence in an experimental station and produce a diffraction-limited round focus at an insertion device beamline for X-ray photon correlation spectroscopy experiments. Simple expressions are provided to guide the optical layout, and wave propagation simulations confirm their applicability. The two-dimensional focusing performance of Be compound refractive lenses to produce a round diffraction-limited focus at 11 keV capable of generating a high-contrast speckle pattern of an aerogel sample is demonstrated. The coherent scattering patterns have comparable speckle sizes in both horizontal and vertical directions. The focal spot sizes are consistent with hybrid ray-tracing calculations. Producing a two-dimensional focus on the sample can be helpful to resolve speckle patterns with modern pixel array detectors with high visibility. This scheme has now been in use since 2019 for the 8-ID beamline at the Advanced Photon Source, sharing the undulator beam with two separate beamlines, 8-ID-E and 8-ID-I at 7.35 keV, with increased partially coherent flux, reduced horizontal spot sizes on samples, and good speckle contrast.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Intrusion Detection for Cybersecurity of Power Electronics Dominated Grids: Inverters PQ Set-Points Manipulation

This work provides cybersecurity analytics for a high photovoltaic (PV) penetrated distribution network, representing future power electronics dominated grid (PEDG). Firstly, the impact of active and reactive power (PQ) set-points manipulation on the network is studied. Then, an intrusion detection system (IDS) is developed for identifying the potentially compromised PV inverters in the network. The proposed IDS is based on defining the normal, safe, and abnormal operation regions of the PV inverters from point of view of the steady state voltage stability of the network. These three-operation regions are identified by utilizing active power, reactive power, and voltage (PQV) limits of each specific grid-following inverter in the network. Each grid-following inverter's PQV contour includes the information of network topology, inverter ratings, and inverter controller. The developed PQ limits are integrated into the centralized secondary control layer for realization of the proposed IDS. Furthermore, the proposed secondary control layer is capable of providing remedial actions during an anomaly event to enhance the grid resiliency. The theoretical analyses are verified by several attack scenarios for a network of grid-following inverters.

41 EE - Solar Energy Technologies Office (EE-4S)↗

Identity Document to Selfie Face Matching Across Adolescence

Matching live images (“selfies”) to images from ID documents is a problem that can arise in various applications. A challenging instance of the problem arises when the face image on the ID document is from early adolescence and the live image is from later adolescence. We explore this problem using a private dataset called Chilean Young Adult (CHIYA) dataset, where we match live face images taken at age 18-19 to face images on scanned ID documents created at ages 9 to 18. State-of-the-art deep learning face matchers (e.g., ArcFace) have relatively poor accuracy for document-to-selfie face matching. To achieve higher accuracy, we fine-tune the best available open-source model with triplet loss for a few-shot learning. Experiments show that our approach achieves higher accuracy than the DocFace+ model recently developed for this problem. Our fine-tuned model was able to improve the true acceptance rate for the most difficult (largest age span) subset from 62.92% to 96.67% at a false acceptance rate of 0.01%. Our fine-tuned model is available for use by other researchers.

Albiero, Vítor↗

Hierarchical Clustering and Visualization of Aggregate Cyber Data

Most commercial intrusion detections systems (IDS) can produce a very high volume of alerts, and are typically plagued by a high false positive rate. The approach described here uses Splunk to aggregate IDS alerts. The aggregated IDS alerts are retrieved from Splunk programmatically and are then clustered using text analysis and visualized using a sunburst diagram to provide an additional understanding of the data. The equivalent of what the cluster analysis and visualization provides would require numerous detailed queries using Splunk and considerable manual effort.

Patton, Robert M↗

Testbed-based Evaluation of SIEM Tool for Cyber Kill Chain Model in Power Grid SCADA System

Development of a smarter electric grid necessitates addressing the associated cyber security challenges. Since the interdependence between the legacy grid infrastructure and advanced information technology is growing rapidly, there are numerous ways advanced, motivated, and persistent attackers can affect the SCADA based critical infrastructure. Hence, developing a security information and event management (SIEM) is crucial for securing the SCADA power system. This paper presents the application of Security Onion (SecOn) to develop the network security monitoring (NSM) and intrusion detection system (IDS) in the context of SCADA cyber physical security. Initially, we have applied a cyber kill-chain model to demonstrate the different stages of attacks and associated mechanisms. Later, the rule- based IDS (RIDS) is developed using Snort IDS, and tested in the cyber-physical SCADA environment. Furthermore, we have evaluated its performance in terms of accuracy and detection latency. Our experimental results reveal that the SecOn tool is efficient in monitoring and detecting attacks within an acceptable time frame with a high accuracy rate.

24 POWER TRANSMISSION AND DISTRIBUTION↗

SU-F-T-224: Importance of Timely Review of Daily Cone-Beam CTs: Dosimetric Evaluation of Rejected CBCTs for Head and Neck Patients

Purpose: To dosimetrically evaluate the importance of timely reviewing daily CBCTs for patients with head and neck cancer. Methods: After each fraction daily cone-beam CT (CBCT) for head and neck patients are reviewed by physicians prior to next treatment. Physician rejected image registrations of CBCT were identified and analyzed for 17 patients. These CBCT images were rigidly fused with planning CT images and the contours from the planning CT were transferred to CBCTs. Because of limited extension in the superior-inferior dimension contours with partial volumes in CBCTs were discarded. The treatment isocenter was placed by applying the clinically recorded shifts to the volume isocenter of the CBCT. Dose was recalculated at the shifted isocenter using a homogeneous dose calculation algorithm. Dosimetrically relevant changes defined as greater than 5% deviation from the clinically accepted plans but with homogeneous dose calculation were evaluated for the high dose (HD), intermediate dose (ID), and low dose (LD) CTVs, spinal cord, larynx, oropharynx, parotids, and submandibular glands. Results: Among seventeen rejected CBCTS, HD-CTVs, ID-CTVs, and LD-CTVs were completely included in the CBCTs for 17, 1, and 15 patients, respectively. The prescription doses to the HD-CTV, ID-CTV, and LD-CTV were received by < 95% of the CTV volumes in 5/17, 1/1, and 5/15 patients respectively. For the spinal cord, the maximum doses (D0.03cc) were increased > 5% in 13 of 17 patients. For the oropharynx, larynx, parotid, and submandibular glands, the mean dose of these organs at risk was increased > 5% in 7/17, 8/12, 11/16 and 6/16 patients, respectively. Conclusion: Timely review daily CBCTs for head and neck patients under daily CBCT guidance is important, and uncorrected setup errors can translate to dosimetrically relevant dose increases in organsat- risk and dose decreases in the clinical target volumes.

60 APPLIED LIFE SCIENCES↗

Classification of Complete Proteomes of Different Organisms and Protein Sets Based on Their Protein Distributions in Terms of Some Key Attributes of Proteins

The existence of complete genome sequences makes it important to develop different approaches for classification of large-scale data sets and to make extraction of biological insights easier. Here, we propose an approach for classification of complete proteomes/protein sets based on protein distributions on some basic attributes. We demonstrate the usefulness of this approach by determining protein distributions in terms of two attributes: protein lengths and protein intrinsic disorder contents (ID). The protein distributions based on L and ID are surveyed for representative proteome organisms and protein sets from the three domains of life. The two-dimensional maps (designated as fingerprints here) from the protein distribution densities in the LD space defined by ln( L ) and ID are then constructed. The fingerprints for different organisms and protein sets are found to be distinct with each other, and they can therefore be used for comparative studies. As a test case, phylogenetic trees have been constructed based on the protein distribution densities in the fingerprints of proteomes of organisms without performing any protein sequence comparison and alignments. The phylogenetic trees generated are biologically meaningful, demonstrating that the protein distributions in the LD space may serve as unique phylogenetic signals of the organisms at the proteome level.

59 BASIC BIOLOGICAL SCIENCES↗

Fox Trails

1. This software utilizes python pandas to pull data from P6 databases or XER files. The software transforms the datasets into multiple main tables by joining, filtering, iteratively flattening hierarchical structured data, and pivoting datasets to give simple flat output tables. The activity table includes all of the information related to an activity including activity codes, global, EPS, and project codes, UDFs, and WBS information as separate columns. This includes the code id, code value and sequence number for all levels in hierarchical codes. The resource table is similar to the activity table and includes all of the information related to resources on activities including UPFs and resource codes. The resource time phased table takes the resource information and time phases it for the budget, forecast, late, and actual dates/units/costs that closely matches P6's user interface's values as it implements the resource curve and calendars. The wbs table contains the WBS structure broken out by levels and includes UDFs, codes, and notebook topics. The final P6 data table is the relationships table which simply contains the relationships. 2. When a user updates the tool with data (via giving it P6 project names with database username/password information or XER files) the system creates the data in #1, then creates a networkx graph with the activity data imbedded in the node data and the relationships added as edges. Each edge also has it's float calculated (working time distance between the predecessor and successor) and attached to the edge. Activities are also tagged as a potential start of a path based on their constraints, constraint dates, remaining start date, and activity status. When a user enters an activity ID into the UI, it runs a shortest path calculation on the network graph between each node tagged as potential start to the entered activity id based on the float tagged on the edge. Each path returned by the algorithm contains all of the nodes on the path in order, as well as the total float of the edges that make the path. This data is then collected and returned to the user in the form of a gantt chart with groupings for each path that includes the total float for each group. 3. Similar to 2, if the user passes through a reference dataset each activity set in the path is checked to see if it had a path in the reference dataset, if that path was the primary path between the start and end activities, and what has changed regarding logic and durations. These changes are color coded and summarized before sent to the user to be displayed by the UI for simple discovery. 4. Utilizing the data from #1, the user can submit desired grouping code(s) and filters to the system. The system will then pull the activities, resources, and relationships and create a gantt chart based on the groupings sent and filtered based on the filters sent. 5. The system will produce a gantt chart in a similar method to #4, but allows interactivity with the data. As the user interacts with the gantt chart, the software captures the changes and stores it with the user making the change so that project controls and implement those changes in P6.

Fox, Ben↗

Ocpp 2.0.1. Interim Kpi Calculator

The project is split into four pieces. The first is a raw OCPP log parser. The second is a file splitter. The third is a message parser. The final piece is the Interim KPI calculator. The OCPP log parser was created from two different formats of raw OCPP 2.0.1 data. Its intended purpose is to extract device IDs and OCPP event messages from nontabular text logs. The parser looks for specific substrings in the logs to identify which of the two "standards" it should select from. The KPI generator does not perform any of its calculations in parallel. Instead, we opt for a naive batching approach. The splitter takes the file generated from the parser and creates many smaller files for each of the device IDs in the dataset. This allows the pandas queries in the log formatter to be iterate over a significantly smaller slice of data, increasing performance significantly. The message parser step takes messages from each of the files (containing distinct device IDs) and breaks the message out into pieces. The final result is a file with different columns specifying different attributes of the JSON message. The file is an aggregation of all different devices. This is the most complex portion of the code. The KPI calculator takes the parsed messages, as a single file, and calculates the KPI from that data. An excel file is produced with four sheets. These contain the metrics for Session Success, Charge Start Success, Charge End Success, and Charge Start Time. It includes the metrics for the different equations in the Interim KPI Implementation Guide as well as a weighted sum of the different equations for each KPI (excluding Charge End Success and Charge Start Time).

Quinn, Casey↗

Cross-kingdom patterns of alternative splicing and splice recognition

Variations in transcript splicing can reveal how eukaryotes recognize intronic splice sites. Retained introns (RIs) commonly appear when the intron definition (ID) mechanism of splice site recognition inconsistently identifies intron-exon boundaries, and cassette exons (CEs) are often caused by variable recognition of splice junctions by the exon definition (ED) mechanism. We have performed a comprehensive survey of alternative splicing across 42 eukaryotes to gain insight into how spliceosomal introns are recognized. All eukaryotes we studied exhibit RIs, which appear more frequently than previously thought. CEs are also present in all kingdoms and most of the organisms in our analysis. We observe that the ratio of CEs to RIs varies substantially among kingdoms, while the ratio of competing 3' acceptor and competing 5' donor sites remains nearly constant. In addition, we find the ratio of CEs to RIs in each organism correlates with the length of its introns. In all 14 fungi we examined, as well as in most of the 9 protists, RIs far outnumber CEs. This differs from the trend seen in 13 multicellular animals, where CEs occur much more frequently than RIs. The six plants we analyzed exhibit intermediate proportions of CEs and RIs. Our results suggest that most extant eukaryotes are capable of recognizing splice sites via both ID and ED, although ED is most common in multicellular animals and ID predominates in fungi and most protists.

59 BASIC BIOLOGICAL SCIENCES↗

HydraGNN_Predictive_GFM_2024 - Ensemble of predictive graph foundation models for ground state atomistic materials modeling

We provide the ensemble of fifteen pre-trained graph foundation models (GFMs) for atomistic materials modeling applications. Each one of the fifteen GFMs has been trained on five open-source datasets that (once aggregated) amount to over 154 million atomistic structures, which cover over two-thirds of the natural elements of the periodic table and that comprises a broad set of organic and inorganic compounds. This vast set of atomistic structures comprises ground state configurations that are dynamically stable (i.e., equilibrated structures with atomic forces approximately close to zero values) as well as dynamically unstable structures (i.e., non-equilibrium structures with non-negligible non-zero values of atomic forces). The ensemble of datasets aggregated does NOT include excited states. The datasets have been curated to remove atomistic structures with spectral norm of the force tensor above 100 eV/angstrom. Moreover, a linear term of the energy was computed for each dataset using a linear regression model that uses the chemical concentration of each natural element as regressor. The linear term predicted by the linear regression model has been subtracted from each original energy value to perform a re-alignment of the energy values across different electronic structures approximation theories performed to generate the diverse multi-source, multi-fidelity datasets. The folder "ADIOS_files" contains the set of pre-processed datasets in Adaptable I/O System (ADIOS) format (https://www.exascaleproject.org/research-project/adios/) that have been used for the development and training of GFMs in this work. The "ADIOS_files" directory contains 6 sub-directories named as follows: - ANI1x-v3.bp - MPTrj-v3.bp - OC2020-20M-v3.bp - OC2020-v3.bp - OC2022-v3.bp - qm7x-v3.bp Each sub-directory contains the pre-processed datasets converted in Adaptable I/O System (ADIOS) format (https://www.exascaleproject.org/research-project/adios/) that have been used to the development, training, and performance testing of the ensemble go predictive graph foundation models. Each GFM was developed using HydraGNN (https://github.com/ORNL/HydraGNN) as underlying graph neural network (GNN) architecture. The multi-task learning (MTL) capability of HydraGNN was used to simultaneously train the GFMs on labeled values for direct predictions of energy (a total system property of an atomistic structure that measures the chemical stability) and atomic forces (an atomic level property of an atomistic structure that measures the dynamical stability). The hyper parameters of the GFM have been tuned using scalable hyperparameter optimization (HPO) algorithms implemented in the software DeepHyper (https://github.com/deephyper/deephyper). The pre-training of each HPO trial was performed using distributed data parallelism (DDP) to scale the training across 128 compute nodes of the exascale OLCF supercomputer Frontier. Each HPO trial was trained only for 10 epochs and an early stopping was performed to avoid wasting significant computational resources on GNN architectures that were clearly underperforming. For each HPO trial, the 'omnistat' tool developed by (AMD Research - Advanced Micro Device) was used to measure the total energy consumption in kWh. The ensemble of GFMs was obtained by selecting the fifteen best performing HPO trials. Four models have been selected for their clear advantage in accuracy, and these are the GFMs with IDs 229, 156, 147, 260. Additional eleven models have been selected based on judicious balance between accuracy and energy consumption needed for training, and these are the GFMs with IDs 165, 78, 137, 1, 175, 171, 181, 67, 179, 167, 351. Each selected GFM of the ensemble was continued to cumulate a total of at most 30 epochs. In some cases, the total number of epochs actually performed was les than 30 due to two combined factors: (1) the size of the GFM (i.e., the number of model parameters to train) and (2) the total wall-clock time for which the computational resources could be allocated on OLCF-Frontier. The "Ensemble_of_models" directory contains 15 sub-directories named as follows: - gfm_0.229 - gfm_0.156 - gfm_0.147 - gfm_0.260 - gfm_0.165 - gfm_0.78 - gfm_0.137 - gfm_0.1 - gfm_0.175 - gfm_0.171 - gfm_0.181 - gfm_0.67 - gfm_0.179 - gfm_0.167 - gfm_0.351 Each one of these sub-directories refers to one of the fifteen HPO trials that have been selected to continue the pre-training with at most 30 epochs. With each sub-directory associated with a specific HPO trial, the following files can be found: - config.json: file for argument parsing to develop and train an HydraGNN architecture - gfm_0.ID_epoch_N.pk: file with model parameters for HPO ID trial after N epochs of training The ensemble of fifteen GFM architectures was used for (1) ensemble averaging to stabilize the predictions of energy and atomic forces after pre-training for post-processing analysis and (2) ensemble uncertainty quantification (UQ). The code used to develop, pre-train, and load the pre-trained models for post-processing analysis is available on the ORNL-GitHub at the following link: https://github.com/ORNL/HydraGNN/tree/Predictive_GFM_2024

36 MATERIALS SCIENCE↗

Profile Images and Annotations for Vehicle Re-identification Algorithms (PRIMAVERA)

This dataset contains 636,246 profile images of vehicles representing 13,963 unique vehicles. The data was collected by a set of roadside sensors over the course of three years. Each time a vehicle passed by one of the sensors, a series of images was collected. The images were processed to detect and localize each vehicle, and a license plate reader collocated with the sensor was used to provide a unique ID for the vehicle. Actual license plate numbers have been obfuscated by replacing with an arbitrary numerical ID for each vehicle. After localizing the vehicle in each image, the original RGB image was rotated, scaled, and shifted to produce a new RGB image of size 234x234 pixels such that the outermost two wheels are located at predetermined pixel locations in the image. In this way, all vehicle images are aligned to one another. This registration process occasionally results in a portion of certain vehicles being cutoff at the edges of the image. The dataset has been partitioned into two sets called training and validation. The two partitions no common vehicles, i.e., a vehicle present in one partition is guaranteed not to be present in the other. In this way, an algorithm can be validated against a set of new vehicles that were not seen during the training process. The training set contains 543,926 images from 64,440 vehicle passes representing 11,918 unique vehicles, while the validation set contains 92,320 images from 10,991 vehicle passes representing 2,045 unique vehicles. Vehicle images are organized by directories corresponding to unique vehicles. The file naming scheme is as follows: veh_{vehID}_tr_{passID}_{frameID}_{elevation}_{timeofday}.jpg where {vehID} is the vehicle ID (unique across the entire dataset), {passID} is an identifier for each tracked vehicle pass (unique across the entire dataset), {frameID} is the index of the frame within the given vehicle pass starting at 0, {elevation} is a two-letter string indicating whether the sensor was elevated (el) or at ground-level (gl), and {timeofday} is a two-letter string indicating whether the image was captured during daytime (dt) or nighttime (nt).

image↗

Supporting information for Few-Shot Learning Enables Population-Scale Analysis of Leaf Traits in Populus trichocarpa

In this work, we use few-shot learning to segment the body and vein architecture of P. trichocarpa leaves from high-resolution scans obtained in the UC Davis common garden. Leaf and vein segmentation are formulated as separate tasks, in which convolutional neural networks (CNNs) are used to iteratively expand partial segmentations until reaching stopping criteria. Our leaf and vein segmentation approaches use just 50 and 8 manually traced images for training, respectively, and are applied to a set of 2,634 top and bottom leaf scans. We show that both methods achieve high segmentation accuracy, in some cases exceeding even human-level segmentation. The leaf and vein segmentations are subsequently used to extract 68 morphological traits using traditional open-source image processing tools, which are validated using real-world physical measurements. For a biological perspective, we perform a genome-wide association study using the vein density trait to discover novel genetic architectures associated with multiple physiological processes relating to leaf development and function. In addition to sharing all of the few-shot learning code (see https://github.com/jlager/few-shot-leaf-segmentation), we are releasing all images, manual segmentations, model predictions, 68 extracted leaf phenotypes, and a new set of SNPs called against the v4 P. trichocarpa genome for 1,419 genotypes. The data folder includes all images, ground truth segmentations, predicted segmentations, and extracted leaf traits. All images encode the sample ID in the file name by indicating the treatment, block, row, position, and leaf side, respectively. For example, the file, C_1_1_2_bot.jpeg, indicates the control treatment, block 1, row 1, position 2, and the bottom side of the leaf. Tabulated results include position IDs as well as the corresponding genotype IDs. The images folder includes the 2,906 high-resolution leaf scans taken in the field. The leaf_masks folder includes 50 ground truth segmentations used for training the leaf tracing algorithm. The leaf_preds folder includes the 2,906 predicted segmentations from the leaf tracing algorithm. The vein_masks folder includes 8 ground truth segmentations used for training the vein growing algorithm. The vein_preds folder includes the 1,453 predicted segmentations from the vein growing algorithm. The vein_probs folder includes the 1,453 predicted probability maps from the vein growing algorithm before thresholding. The genomes folder includes the set of SNPs called against the v4 P. trichocarpa genome for 1,419 genotypes with a README file detailing the steps taken. The results folder includes: (i) raw values of the 68 predicted leaf traits in digital_traits.tsv, (ii) manually measured values of petiole length and width in manual_traits.tsv, (iii) thin plate spline (TPS) adjusted values of the vein density trait in vein_density_tps_adj.tsv, (iv) best linear unbiased prediction (BLUP) adjusted values of the vein density trait in vein_density_blups.tsv, and (v) GWAS results for the vein density trait, including chromosome positions and corresponding P values, in gwas_results.csv.

09 BIOMASS FUELS↗