Search NASA⌕ Search

SEARCH · Search NASA

Results for “large scale network”

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 955 records · Page 53
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Using bursty announcements for detecting BGP routing anomalies

Despite the robust structure of the Internet, it is still susceptible to disruptive routing updates that prevent network traffic from reaching its destination. Our research shows that BGP announcements that are associated with disruptive updates tend to occur in groups of relatively high frequency, followed by periods of infrequent activity. We hypothesize that we may use these bursty characteristics to detect anomalous routing incidents. In this work, we use manually verified ground truth metadata and volume of announcements as a baseline measure, and propose a burstiness measure that detects prior anomalous incidents with high recall and better precision than the volume baseline. We quantify the burstiness of inter-arrival times around the date and times of four large-scale incidents: the Indosat hijacking event in April 2014, the Telecom Malaysia leak in June 2015, the Bharti Airtel Ltd. hijack in November 2015, and the MainOne leak in November 2018; and three smaller scale incidents that led to traffic interception: the Belarusian traffic direction in February 2013, the Icelandic traffic direction in July 2013, and the Russian telecom that hijacked financial services in April 2017. Our method leverages the burstiness of disruptive update messages to detect these incidents. We describe limitations, open challenges, and how this method can be used for routing anomaly detection.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Measurement of the Higgs boson mass in the H → ZZ*→ 4ℓ decay channel using 139 fb –1 of s = 13 TeV pp collisions recorded by the ATLAS detector at the LHC

The mass of the Higgs boson is measured in the H→ZZ * →4ℓ decay channel. The analysis uses proton–proton collision data from the Large Hadron Collider at a centre-of-mass energy of 13 TeV recorded by the ATLAS detector between 2015 and 2018, corresponding to an integrated luminosity of 139 fb –1 . The measured value of the Higgs boson mass is 124.99 ± 0.18(stat.) ± 0.04(syst.) GeV. In final states with muons, this measurement benefits from an improved momentum-scale calibration relative to that adopted in previous publications. The measurement also employs an analytic model that takes into account the invariant-mass resolution of the four-lepton system on a per-event basis and the output of a deep neural network discriminating signal from background events. This measurement is combined with the corresponding measurement using 7 and 8 TeV pp collision data, resulting in a Higgs boson mass of 124.94 ± 0.17(stat.) ± 0.03(syst.) GeV.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Room-Temperature Ferroelectric Epitaxial Nanowire Arrays with Photoluminescence

The development of large-scale, high-quality ferroelectric semiconductor nanowire arrays with interesting light-emitting properties can address limitations in traditional wide-bandgap ferroelectrics, thus serving as building blocks for innovative device architectures and next-generation high-density optoelectronics. Here, we investigate the optical properties of ferroelectric CsGeX 3 (X = Br, I) halide perovskite nanowires that are epitaxially grown on muscovite mica substrates by vapor phase deposition. Detailed structural characterizations reveal an incommensurate heteroepitaxial relationship with the mica substrate. Furthermore, photoluminescence that can be tuned from yellow-green to red emissions by varying the halide composition demonstrates that these nanowire networks can serve as platforms for future optoelectronic applications. In addition, the room-temperature ferroelectricity and ferroelectric domain structures of these nanowires are characterized using second harmonic generation (SHG) polarimetry. Finally, the combination of room-temperature ferroelectricity with photoluminescence in these nanowire arrays unlocks new avenues for the design of novel multifunctional materials.

77 NANOSCIENCE AND NANOTECHNOLOGY↗
DOE OSTI2026

Collapse of magnetized white dwarfs as site of heavy-element formation and kilonova signal

We present the first end-to-end calculation connecting the accretion-induced collapse (AIC) of a magnetized, rapidly rotating white dwarf to observable kilonova signatures, combining two-dimensional (2D) general-relativistic neutrino-magnetohydrodynamic simulations, followed by radiation hydrodynamics with in-situ nuclear network and 2D Monte Carlo radiative transfer with spatially resolved heating rates. Unlike all previous unmagnetized AIC models – which predicted proton-rich, $^{56}$Ni-dominated ejecta – strong magnetic fields eject ${\approx }\, 0.2\, \mathrm{ M}_\odot$ of neutron-rich material ($\langle Y_e \rangle \sim 0.24$) on dynamical time-scales, before neutrino irradiation can raise the electron fraction, enabling strong r-process nucleosynthesis up to and beyond the third peak. The resulting kilonova is lanthanide-rich ($X_{\rm lan} \approx 8~{{\ \rm per\ cent}}$) and dominated by near-infrared emission. We compute synthetic light curves in the Large Synoptic Survey Telescope and J ames Webb Space Telescope bands and find striking agreement, without parameter tuning, between the observations of AT 2023vfi/GRB 230307A and our broadband light curves for polar viewing angles. These results establish magnetized AIC as a viable channel for heavy r-process element production and a compelling progenitor candidate for long-duration gamma-ray bursts with kilonova signatures.

MHD↗
DOE OSTI2022

Computer Science Research Needs for Parallel Discrete Event Simulation (PDES)

Historically, scientific computing efforts have demonstrated the clear need for, and effective use of, supercomputing with traditional time-stepped simulations. Nevertheless, there are several areas in the mission spaces of the U.S. Department of Energy and other agencies waiting to tap advanced computing research using a different, discrete event style of modeling, simulation, and analysis. These span a wide spectrum of applications including energy grid resilience, urban planning and policy, transportation science, building technologies, emergency response and planning, environmental impact analysis, computational epidemiology, Internet communications, cyber security, and cyber-physical systems, to name only a few. Even within traditional scientific applications, the role of discrete event modes of execution is increasing in the form of new event-based mathematical solvers such as quantized state integration methods and discrete-continuous hybrid system solvers. Co-design of advanced supercomputing hardware systems is another area that exploits discrete event simulation at its core for effective analyses. Complex systems, entity behaviors and interconnections play a significant role in all these applications, which are mapped to large-scale models with discrete event formulations. To make advancements in all the aforementioned scientific areas, many technical aspects need to be more thoroughly studied and deeply understood in parallel discrete event simulation (PDES). The unique dynamics inherent in a discrete event modeling approach, by their very nature, intersect and influence the entire stack of the computing system, including (a) the unique nature of the instruction sets exercised in PDES workloads without a predominance of high-precision floating point operations, (b) virtual time-constrained multi-threaded execution of many logical processes per processor, (c) extremely variable and difficult to predict network traffic characteristics, (d) interfaces and inter-dependencies with machine learning and artificial intelligence codes at higher software layers, and (e) highly challenging load balancing needs, especially in effectively accounting for accelerated/extremely heterogeneous computing in current and future high-performance computing systems. Efficient and accurate parallel execution of PDES workloads is also dominated by challenges in dealing with their asynchronous concurrency fundamentally present at the model level. Conservative synchronization, optimistic/speculative synchronization, and their hybrid schemes open new questions in fundamental computer science with respect to reversibility of computation and prediction (lookahead) of behaviors inherent within model codes. On the implementation front, there are relatively few scalable, general-purpose parallel discrete event simulators in the world, and even fewer have been studied on emerging hardware platforms. To enable scientific advances using PDES, the research needs in computer science must also be pursued and met in the intersection of the algorithmic and hardware-aware aspects of scalable PDES engines. This report is aimed at capturing a computer science-oriented view of this important area of research in PDES, presenting a sample of important applications with their inherent discrete event technology elements. Needs are outlined in core areas of parallel discrete event research as well as cross-cutting directions in computer science research that positively impact scientific advancements across several important application areas. A selection of priority research opportunities in advanced computing for PDES is identified to serve as reference for key research topics and their order of importance for scientific advancements.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

To What Extent Will Decarbonization Deepen the Conversation Between Industry and the Grid?

Decarbonization - the transition away from un-mitigated fossil fuel combustion throughout the economy - requires big changes from both power and process systems. On the power system side, those changes are expected to include large increases in variable generation, e.g., from wind and solar, which has near-zero marginal costs and at large shares can produce infrequent but consequential energy droughts. On the process systems side, industries are investigating their options for direct and indirect electrification, the latter exemplified by replacing fossil fuel inputs with zero-carbon, energy-carrying chemicals like hydrogen and ammonia produced via electrochemical processes. The economic features of these changes within the larger context of power and process systems suggest that their realization could be accompanied by a paradigm shift in how industrial facilities interact with the grid. For example, the dominant type of demand participation in power markets could change from today's focus on load reductions at peak times to a new focus on shifting electricity use, enabled in part by large-scale product storage, to take advantage of renewable energy that would otherwise be curtailed and to avoid consumption during high-price energy droughts. This talk will describe these and other possible design and operational approaches from grid and industrial economic perspectives, culminating in an enumeration of open problems that lie at the interface of today and tomorrow's power and process systems.

co-design↗
DOE OSTI2020

Chapter 14: Machine Learning of Combustion LES Models from Reacting Direct Numerical Simulation

In this chapter we demonstrate how supervised deep learning techniques can be used to construct models for the filtered progress variable source term necessary for large eddy simulation (LES). The source data for the model is a direct numerical simulation (DNS) of a reacting flow in a low swirl burner configuration. Filtered quantities taken from the DNS data are used to train a deep neural network (DNN)-based model. An efficient data sampling strategy was devised to ensure that a uniform representation of all the states observed in the filtered DNS data are equally present in the training dataset. A-priori testing of the DNN-based model highlights the representative power of DNN to accurately reproduce the filtered reaction progress variable source term over a range of scales and various flame regimes as seen in an industrial burner.

combustion LES models↗
DOE OSTI2023

Bi-fidelity modeling of uncertain and partially unknown systems using DeepONets

Recent advances in modeling large-scale, complex physical systems have shifted research focuses towards data-driven techniques. However, generating datasets by simulating complex systems can require significant computational resources. Similarly, acquiring experimental datasets can prove difficult. For these systems, often computationally inexpensive, but in general inaccurate models, known as the low-fidelity models, are available. Here in this paper, we propose a bi-fidelity modeling approach for complex physical systems, where we model the discrepancy between the true system's response and a low-fidelity response in the presence of a small training dataset from the true system's response using a deep operator network, a neural network architecture suitable for approximating nonlinear operators. We apply the approach to systems that have parametric uncertainty and are partially unknown. Three numerical examples are used to show the efficacy of the proposed approach to model uncertain and partially unknown physical systems.

MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Maximum strength and dislocation patterning in multi–principal element alloys

Multi–principal element alloys (MPEAs) containing three or more components in high concentrations render a tunable chemical short-range order (SRO). Leveraging large-scale atomistic simulations, we probe the limit of Hall-Petch strengthening and deformation mechanisms in a model CrCoNi alloy and unravel chemical ordering effects. The presence of SRO appreciably increases the maximum strength and lowers the propensity for faulting and structure transformation, accompanied by intensification of planar slip and strain localization. Deformation grains exhibit notably different microstructures and dislocation patterns that prominently depend on their crystallographic orientation and the number of active slip planes. Grain of single-planar slip attains the highest volume fraction of deformation-induced structure transformation, and grain with double-slip planes develops the densest dislocation network. These results advancing the fundamental understanding of deformation mechanisms and dislocation patterning in MPEAs suggest a mechanistic strategy for tuning mechanical behavior through simultaneously tailoring grain texture and local chemical order.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Distributed Resources for the Earth System Grid Federation (ESGF) Advanced Management (DREAM). Final Report

Distributed Resources for the Earth System Grid Federation (ESGF) Advanced Management (DREAM) is a proposed system that will enable data from an infinite number of diverse sources to be organized and accessed from anywhere using any handheld or other computer device. The approach offers a powerful roadmap for the creation and integration of a unified knowledge base of an entire ecosystem, including its many geophysical, geographical, social, political, agricultural, energy, transportation, and cyber aspects. The resulting aggregation of data has the potential to generate an informational universe of unprecedented size that has never before been possible due to the prohibitive costs, managerial complexity, and technical barriers associated with ever-changing exponential-growth data flows. We envision that DREAM will accelerate discovery by enabling climate researchers, among other types of researchers, to manage, analyze, and visualize data from earth-scale measurements and simulations. DREAM’s success will be built on proven components that leverage existing services and resources. A key building block for DREAM will be the ESGF, chaired by Dean N. Williams. Expanding on the existing ESGF, the project will ensure that the access, storage, movement, and analysis of the large quantities of data that are processed and produced by diverse science projects can be dynamically distributed with proper resource management. Much of the Office of Science data is currently generated by multiple stand-alone facilities. DREAM can collect data accumulated from these facilities and incorporate it into a fully integrated network accessible from anywhere in the world. The result is a completely new paradigm shift for data management, analysis, and visualization enabling researchers to: Manage their calculations, data, tools, and research results; Ensure that all data are sharable, reproducible and (re)usable—accompanied by appropriate metadata describing its provenance, syntax, and semantics at creation; Advance application performance by selectively adapting APIs and services in response to scientific requirements and architectural complexities; and Provide scalable interactive resource management—navigate data and metadata at multiple levels, provide architecture-aware data integration, analysis and visualization tools. We will engage closely with DOE, NASA, and NOAA science groups working at the leading edge of computing. These engagements—in domains such as biology, climate, and hydrology—will allow us to advance disciplinary science goals and inform our development of technologies that can accelerate discovery across DOE more broadly. We will advertise and promote our technologies via dedicated workshops, tutorials, and sessions at conferences, stand-alone events with broad inter-disciplinary invitation, and engagements with leadership facilities.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Insights of Molecular Mechanism of Xylem Development in Five Black Poplar Cultivars

Black poplar (Populus deltoides, P. nigra, and their hybrids) is the main poplar cultivars in China. It offers interesting options of large-scale biomass production for bioenergy due to its rapid growth and high yield. Poplar wood properties were associated with chemical components and physical structures during wood formation. In this study, five poplar cultivars, P. euramericana ‘Zhonglin46’ (Pe1), P. euramericana ‘Guariento’ (Pe2), P. nigra ‘N179’ (Pn1), P. deltoides ‘Danhong’ (Pd1), and P. deltoides ‘Nanyang’ (Pd2), were used to explore the molecular mechanism of xylem development. We analyzed the structural differences of developing xylem in the five cultivars and profiled the transcriptome-wide gene expression patterns through RNA sequencing. The cross sections of the developing xylem showed that the cell wall thickness of developed fiber in Pd1 was thickest and the number of xylem vessels of Pn1 was the least. A total of 10,331 differentially expressed genes were identified among 10 pairwise comparisons of the five cultivars, most of them were related to programmed cell death and secondary cell wall thickening. K-means cluster analysis and Gene Ontology enrichment analysis showed that the genes highly expressed in Pd1 were related to nucleotide decomposition, metabolic process, transferase, and microtubule cytoskeleton; whereas the genes highly expressed in Pn1 were involved in cell wall macromolecule decomposition and polysaccharide binding processes. Based on a weighted gene co-expression network analysis, a large number of candidate regulators for xylem development were identified. And their potential regulatory roles to cell wall biosynthesis genes were validated by a transient overexpression system. This study provides a set of promising candidate regulators for genetic engineering to improve feedstock and enhance biofuel conversion in the bioenergy crop Populus.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Downscaling atmospheric chemistry simulations with physically consistent deep learning

Abstract. Recent advances in deep convolutional neural network (CNN)-based super resolution can be used to downscale atmospheric chemistry simulations with substantially higher accuracy than conventional downscaling methods. This work both demonstrates the downscaling capabilities of modern CNN-based single image super resolution and video super-resolution schemes and develops modifications to these schemes to ensure they are appropriate for use with physical science data. The CNN-based video super-resolution schemes in particular incur only 39 % to 54 % of the grid-cell-level error of interpolation schemes and generate outputs with extremely realistic small-scale variability based on multiple perceptual quality metrics while performing a large (8×10) increase in resolution in the spatial dimensions. Methods are introduced to strictly enforce physical conservation laws within CNNs, perform large and asymmetric resolution changes between common model grid resolutions, account for non-uniform grid-cell areas, super-resolve lognormally distributed datasets, and leverage additional inputs such as high-resolution climatologies and model state variables. High-resolution chemistry simulations are critical for modeling regional air quality and for understanding future climate, and CNN-based downscaling has the potential to generate these high-resolution simulations and ensembles at a fraction of the computational cost.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Productive Programming of Distributed Systems with the SHAD C++ Library

High-performance computing (HPC) is often perceived as a matter of making large-scale systems (e.g., clusters) run as fast as possible, regardless the required programming effort. However, the idea of "bringing HPC to the masses" has recently emerged. Inspired by this vision, we have designed SHAD, the Scalable High-performance Algorithms and Data-structures library. SHAD is open source software, written in C++, for C++ developers. Unlike other HPC libraries for distributed systems, which rely on SPMD models, SHAD adopts a shared-memory programming abstraction, to make C++ programmers feel at home. Underneath, SHAD manages tasking and data-movements, moving the computation where data resides and taking advantage of asynchrony to tolerate network latency. At the bottom of his stack, SHAD can interface with multiple runtime systems: this not only improves developer’s productivity, by hiding the complexity of such software and of the underlying hardware, but also greatly enhance code portability. Thanks to its abstraction layers, SHAD can indeed target different systems, ranging from laptops to HPC clusters, without any need for modifying the user-level code. We have prototyped and open-sourced the implementation of (a subset of) the C++ standard library (STL) targeting multi-node HPC clusters. Our work allows plain STL-based C++ code to scale on HPC systems, with no need for rewriting the code to exploit the complex hardware. SHAD is available under Apache v2 License at https://github.com/pnnl/SHAD. In this paper we overview the design of the SHAD library, depicting its main components: runtime systems abstractions for tasking; parallel and distributed data-structures; STL-compliant interfaces and algorithms.

Castellana, Vito G.↗
DOE OSTI2020

Development of neural network force fields for corrosion studies

To fully understand the chemistry and physics of corrosion, novel methods of simulation must be developed. One approach is designing machine learning (ML) algorithms integrated with density functional theory to develop adaptive force fields to gain insight into corrosion behavior namely at the surface of metal oxides. Current methods of modeling corrosion are slow due to the computational cost of resolving both reaction mechanics and mass transport processes. Machine learning methods can be implemented to obtain structure-activity relationships at both the molecular and bulk scale while still retaining the accuracy of density functional theory (DFT) and significantly decreasing the time needed for simulations of complex chemical processes in the various environments of corrosion. Multiscale models are needed for corrosion studies to fully understand its processes not only at the atomic length scale (chemical bonding, energies, and forces), but also at the nano and meso length scales (solid-state physics and material science processes). Current methods of study include DFT, molecular dynamics, and Monte Carlo. The limitation of DFT is that only a small number of atoms or molecules can be simulated at that level of theory. Density functional theory is used to study the electronic structure of atoms and molecules, and calculate the force component of each atom. However, these calculations are limited to about 1000 atoms. Custom periodic boundary conditions (PBC) can be used to describe the various environments and defects that affect the atomic forces to produce a large data set from which a training set can be derived. Machine learning can be utilized to overcome the barrier of modeling macroscopic and multi-scale processes from ab initio calculations through the development of adaptive force fields. Local environments determine the atomic forces of a given system, therefore adaptive force fields must be created to produce reliable quantum mechanical calculations. This can be achieved by developing a learning algorithm that uses the mapped atomic forces or fingerprint as an input to produce energies and magnetic moments as output. A systematic approach was used to begin to build a data set in order to accurately describe the atomic forces in various environments. In Figure 4 below, a simple PBC cell of Fe{sub 2}O{sub 3} was first optimized. A surface optimization was performed next, followed by a hydroxylated surface optimization. Once this calculation has converged, the adsorption of halide species to the hydroxylated surface will be investigated. TensorFlow is an open source platform for machine learning developed by Google. Using a high level application program interface (API) such as Keras allows for building and training ML models easily in a number of different environments and languages. For this project, a neural network was developed within Anaconda in Python. Future Work: Further development of reference data set; Refining neural network and learning algorithm; Fingerprinting atomic environment to enable mapping of atomic force components; Choosing appropriate training set from reference data; Learning from training set and enabling non-linear mapping of training set fingerprints and the atomic forces; Estimation of uncertainty to identify ranges of outside applicability; Testing and analysis of molecular dynamic simulations.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Microseismic Monitoring of Laboratory Hydraulic Fracturing Experiments in Granitic Rocks for Different Fracture Propagation Regimes

While hydraulic fracturing (HF) is a widely employed process, the underlying fracturing processes are still heavily contested. The attributes of the HF generated fracture network can exhibit substantial variation when dealing with specific HF propagation regimes encountered in the field. In this study, HF experiments were performed on true-triaxially loaded Barre granite cubes, with microseismic monitoring, to identify and characterize the fracturing mechanisms associated with different viscosity injection fluids. Utilizing fluids with high (oil/1450 cP) and low (water/1 cP) viscosity represented two key HF propagation regimes: viscosity- and toughness-dominated. The experiments conducted with oil involved higher breakdown pressures, larger fluid volumes, and slower fracture propagation speeds. Furthermore, the frequency–magnitude distribution (b value) for all experiments (1.9–2.3) was similar to those encountered for large-scale operations. Slightly larger b values were encountered during the initiation phase (2.4–2.7) relative to the fracture propagation and post-fracturing phases (1.9–2.2). Techniques such as polarity and moment-tensor inversion were utilized to characterize the source mechanisms. For the HF experiments with oil, tensile fractures were most dominant (92%) in the initiation phase compared to fracture propagation and post-fracturing phases (70–75%). Similar tensile fracturing dominancy was not observed with water, attributable to fluid permeation and leak-off. Regardless of the injection fluid or classification criteria employed, tensile fractures were the dominant type consistently, with fewer occurring in water experiments but the specific ratio of crack types varied with different source mechanism criteria employed.

58 GEOSCIENCES↗
DOE OSTI2023

Hierarchical Self-Assembly of Carbon Dots into High-Aspect-Ratio Nanowires

Here, we report a spontaneous and hierarchical self-assembly mechanism of carbon dots prepared from citric acid and urea into nanowire structures with large aspect ratios (>50). Scattering-type scanning near-field optical microscopy (s-SNOM) with broadly tunable mid-IR excitation was used to interrogate details of the self-assembly process by generating nanoscopic chemical maps of local wire morphology and composition. s-SNOM images capture the evolution of wire formation and the complex interplay between different chemical constituents directing assembly over the nano- to microscopic length scales. We propose that residual citrate promotes tautomerization of melamine surface functionalities to produce supramolecular shape synthons comprised of melamine-cyanurate adducts capable of forming long-range and highly directional hydrogen-bonding networks. This intrinsic, heterogeneity-driven self-assembly mechanism reflects synergistic combinations of high chemical specificity and long-range cooperativity that may be harnessed to reproducibly fabricate functional structures on arbitrary surfaces.

77 NANOSCIENCE AND NANOTECHNOLOGY↗
DOE OSTI2020

Global analysis of SBP gene family in Brachypodium distachyon reveals its association with spike development

SQUAMOSA-promoter binding like proteins (SBPs/SPLs) are plant specific transcription factors targeted by miR156 and involved in various biological pathways, playing multi-faceted developmental roles. This gene family is not well characterized in Brachypodium. We identified a total of 18 SBP genes in B. distachyon genome. Phylogenetic analysis revealed that SBP gene family in Brachypodium expanded through large scale duplication. A total of 10 BdSBP genes were identified as targets of miR156. Transcript cleavage analysis of selected BdSBPs by miR156 confirmed their antagonistic connection. Alternative splicing was observed playing an important role in BdSBPs and miR156 interaction. Characterization of T-DNA Bdsbp9 mutant showed reduced plant growth and spike length, reflecting its involvement in the spike development. Expression of a majority of BdSBPs elevated during spikelet initiation. Specifically, BdSBP1 and BdSBP3 differentially expressed in response to vernalization. Differential transcript abundance of BdSBP1, BdSBP3, BdSBP8, BdSBP9, BdSBP14, BdSBP18 and BdSBP23 genes was observed during the spike development under high temperature. Co-expression network, protein–protein interaction and biological pathway analysis indicate that BdSBP genes mainly regulate transcription, hormone, RNA and transport pathways. Our work reveals the multi-layered control of SBP genes and demonstrates their association with spike development and temperature sensitivity in Brachypodium.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2020

Overcoming small minirhizotron datasets using transfer learning

Minirhizotron technology is widely used to study root growth and development. Yet, standard approaches for tracing roots in minirhiztron imagery is extremely tedious and time consuming. Machine learning approaches can help to automate this task. However, lack of enough annotated training data is a major limitation for the application of machine learning methods. Transfer learning is a useful technique to help with training when available datasets are limited. In this paper, we investigated the effect of pre-trained features from the massives-cale, irrelevant ImageNet dataset and a relatively moderate-scale, but relevant peanut root dataset on switchgrass root imagery segmentation applications. We compiled two minirhizotron image datasets to accomplish this study: one with 17,550 peanut root images and another with 28 switchgrass root images. Both datasets were paired with manually labeled ground truth masks. Deep neural networks based on the U-net architecture were used with different pre-trained features as initialization for automated, precise pixel-wise root segmentation in minirhizotron imagery. We observed that features pre-trained on a closely related but relatively moderate size dataset like our peanut dataset were more effective than features pre-trained on the large but unrelated ImageNet dataset. Here, we achieved high quality segmentation on peanut root dataset with 99.04% accuracy at the pixel-level and overcame errors in human-labeled ground truth masks. By applying transfer learning technique on limited switchgrass dataset with features pre-trained on peanut dataset, we obtained 99% segmentation accuracy in switchgrass imagery using only 21 images for training (fine tuning). Furthermore, the peanut pre-trained features can help the model converge faster and have much more stable performance.

59 BASIC BIOLOGICAL SCIENCES↗