BobGAT: Towards Inferring Software Bill of Behavior with Pre-Trained Graph Attention Networks
Explore the source record for details and available documents.
Mathematics and Computing, Computer science, Infor↗
SEARCH · Engineering Papers
Results for “network science”
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.
Developing a Machine-Learning-Based Processing Framework for Twitter and Other Crowdsourced Data
Crowdsourced data streams such as Twitter and other social media are important sources of real-time and historical global information for Earth science applications. At the NASA Goddard Earth Sciences Data and Information Services Center (GES DISC), we have been exploring the Twitter data stream for its potential in augmenting the validation program of NASA's Global Precipitation Measurement (GPM) mission. To realize this potential, we need to increase the information density and enhance the quality of filtered precipitation tweets. We have implemented various components of a machine learning (ML)-based processing infrastructure for crowdsourced data that outputs, in this instance, useful and usable information derived from precipitation tweets. We have test enriched the Twitter stream with higher quality active tweets from those knowingly contributing to our effort and from existing crowdsourced programs (e.g., mPING, CoCoRaHS). We have experimented with various algorithms for processing tweets, including Naà ve Bayes, Convolutional Neural Network (CNN), Hierarchical Attention Network (HAN), and semi-supervised learning (with tri-training). Our current work focuses on (1) automated review of Earth science-related publications to determine relationships between discipline research needs and ML algorithms; (2) investigating Sequential Generative Adversarial Network (SeqGAN) for processing precipitation tweets for anomaly detection; and (3) managing crowdsourced data in a way that is compatible with existing NASA satellite data archives and using the data for ML applications. Key results include (1) network visualization of NLP-processed publications in various Earth science disciplines; (2) difference between GPM-linked, generated tweets and collected actual tweets that is small for GPM-determined light to moderate rain cases and high for GPM-determined heavy rain cases; and (3) identification of MongoDB for storing raw tweets and Zarr format for gridded tweets (compatible with GPM data). Our results have taken us a step closer to an operational ML-based tweet processing infrastructure and have already demonstrated that tweet-derived precipitation information is potentially useful for validation of Earth science satellite data.
Teng, William↗
Machine learning moment closure models for the radiative transfer equation I: Directly learning a gradient based closure
In this paper, we take a data-driven approach and apply machine learning to the moment closure problem for the radiative transfer equation in slab geometry. Instead of learning the unclosed high order moment, we propose to directly learn the gradient of the high order moment using neural networks. This new approach is consistent with the exact closure we derive for the free streaming limit and also provides a natural output normalization. Finally, a variety of benchmark tests, including the variable scattering problem, the Gaussian source problem with both periodic and reflecting boundaries, and the two-material problem, show both good accuracy and generalizability of our machine learning closure model.
Computer science↗
Students Planting Research Of Use To Space (SPROUTS) Networking and Engagement of Interns at Kennedy Space Center
While Kennedy Space Center (KSC) has had summer interns in the life sciences for many years, beginning in 2016, the internship program was re-envisioned. Rather than having many interns in the summer with numerous innovative small projects created primarily for this purpose, the current model is to offer internship opportunities every semester (Spring, Summer, and Fall), so that research is continuous and sustained. Since 2016 we have had 64 internship opportunities for undergraduate and graduate students in the areas of space crop production and microgravity simulation support. Some students have participated in more than one opportunity, so 52 separate individuals have participated in this program. While interns primarily worked with individual mentors on a main project, most also worked on group projects with other interns or developed smaller secondary projects on their own initiative. In addition, all interns participated in a weekly Lunch, Learn, and Discuss seminar series where they were encouraged to present their research, learn from scientists at KSC, and engage with members of the space life sciences community. When the face-to-face spring internship of 2020 ended prematurely, we resumed the weekly seminar series as a virtual event, and this led to the concept of engaging former interns. Current and former interns were invited to participate in the on-going virtual series, and 46 asked to be included on the mailing list. Our current seminar series involves remote seminars or hosted discussions from contacts within and outside of the agency, and engages a large network of current scientists and former interns with an weekly participation averaging 40-50 people. Speakers include experts from industry, academia, and other space agencies working on topics of interest to KSC space life science researchers. In addition, this series has served as a brain trust and brainstorming mechanism for KSC scientists to invite and discuss new ideas and concepts. The advent of remote work and virtual platforms has allowed us to engage with interns in a new way that will continue as future interns are integrated into this network of individuals interested in space research. This work is funded by NASA’s Space Biology Program.
Internships↗
Optimal Traffic Signal Control Using Priority Metric Based on Real-Time Measured Traffic Information
Optimizing traffic control systems at traffic intersections can reduce network-wide fuel consumption as well as improve traffic flow. While traffic signals have conventionally been controlled based on predetermined schedules, various adaptive control systems have been developed recently using advanced sensors such as cameras, radars, and LiDARs. By utilizing rich traffic information enabled by the advanced sensors, more efficient or optimal traffic signal control is possible in response to varying traffic conditions. This paper proposes an optimal traffic signal control method to minimize network-wide fuel consumption utilizing real-time traffic information provided by advanced sensors. This new method employs a priority metric calculated by a weighted sum of various factors, including the total number of vehicles, total vehicle speed, vehicle waiting time, and road preference. Genetic Algorithm (GA) is used as a global optimization method to determine the optimal weights in the priority metric. In order to evaluate the effectiveness of the proposed method, a traffic simulation model is developed in a high-fidelity traffic simulation environment called SUMO, based on a real-world traffic network. The traffic flow within this model is simulated using actual measured traffic data from the traffic network, enabling a comprehensive assessment of the novel optimal traffic signal control method in realistic conditions. The simulation results show that the proposed priority metric-based real-time traffic signal control algorithm can significantly reduce network-wide fuel consumption compared to the conventional fixed-time control and coordinated actuated control methods that are currently used in the modeled network. Additionally, incorporating truck priority in the priority metric leads to further improvements in fuel consumption reduction.
47 OTHER INSTRUMENTATION↗
Red Wine Fermentation Alters Grape Seed Morphology and Internal Porosity
During wine fermentation, grape berry components, including seeds, undergo extensive physical and chemical changes that result in the release of flavonoids, such as tannins, from seeds into wine. Understanding changes in seed morphology during fermentation is crucial for aiding the development of accurate prediction models for flavonoid extraction during winemaking, which enhances fermentation management and ensures consistency in wines from year to year. High-resolution x-ray microcomputed tomography (x-ray μCT) was used to investigate the effect of red wine fermentation on changes in grape seed morphology. Using a PyTorch-based implementation of a fully convolutional network with a Resnet-101 backbone for semantic segmentation of x-ray μCT images, we quantified extensive alteration to grape seed structure during fermentation. Image analyses revealed the development of a pore network breaking apart the seed endosperm by the end of fermentation, leading to an increase in surface area. Fermentation significantly altered grape seed morphology. Such alterations could enable transport of seed flavonoids from inside the endosperm and integument to outside the seed. Further research on the physical processes occurring in seeds during wine fermentation is necessary to build better physiochemical models.
59 BASIC BIOLOGICAL SCIENCES↗
Hybrid Machine Learning for Scanning Near-Field Optical Spectroscopy
The underlying physics behind an experimental observation often lacks a simple analytical description. This is especially the case for scanning probe microscopy techniques, where the interaction between the probe and the sample is nontrivial. Realistic modeling to include the details of the probe is always exponentially more difficult than its "spherical cow" counterparts. On the other hand, a well-trained artificial neural network based on real data can grasp the hidden correlation between the signal and sample properties. In this work, we show that, via a combination of model calculation and experimental data acquisition, a physics-infused hybrid neural network can predict the tip-sample interaction in the widely used scattering-type scanning near-field optical microscope. This hybrid network provides a long-sought solution for accurate extraction of material properties from tip-specific raw data. The methodology can be extended to other scanning probe microscopy techniques as well as other data-oriented physical problems in general.
36 MATERIALS SCIENCE↗
Miniature, Low-Power, Waveguide Based Infrared Fourier Transform Spectrometer for Spacecraft Remote Sensing
Fourier transform spectrometers have a venerable heritage as flight instruments. However, obtaining an accurate spectrum exacts a penalty in instrument mass and power requirements. Recent advances in a broad class of non-scanning Fourier transform spectrometer (FTS) devices, generally called spatial heterodyne spectrometers, offer distinct advantages as flight optimized systems. We are developing a miniaturized system that employs photonics lightwave circuit principles and functions as an FTS operating in the 7-14 micrometer spectral region. The inteferogram is constructed from an ensemble of Mach-Zehnder interferometers with path length differences calibrated to mimic scan mirror sample positions of a classic Michelson type FTS. One potential long-term application of this technology in low cost planetary missions is the concept of a self-contained sensor system. We are developing a systems architecture concept for wide area in situ and remote monitoring of characteristic properties that are of scientific interest. The system will be based on wavelength- and resolution-independent spectroscopic sensors for studying atmospheric and surface chemistry, physics, and mineralogy. The self-contained sensor network is based on our concept of an Addressable Photonics Cube (APC) which has real-time flexibility and broad science applications. It is envisaged that a spatially distributed autonomous sensor web concept that integrates multiple APCs will be reactive and dynamically driven. The network is designed to respond in an event- or model-driven manner or reconfigured as needed.
Hewagama, TIlak↗
Assessing the Application of a Genomic Network Analysis in Population Ecology: Inferring Patterns of Dispersal and Geographic Structure in the Emerging Pathogen, Coccidioides
A challenge in population ecology studies is identifying how to best group individuals into populations, especially when individual origin is unknown. Machine learning has improved upon traditional methods of identifying population structure and is more efficient at handling large, complex datasets. We demonstrate the applicability of a machine learning method to identify hierarchical population structure in an emerging pathogen, Coccidioides spp., the causative agent of Valley fever. We compared the network clusters to structure identified by traditional tools as a validation of the network performance. We used publicly available whole-genome data for 48 C. immitis and 102 C. posadasii, resulting in 168,211 genome-wide SNPs among the two species. The network analysis grouped samples into populations comparable to the literature for these species but also identified fine-scale geographic structure and travel-associated cases not reported thus far. Exploring different resolutions in the network made it easy to identify unique genotypes specific to California and possibly Nevada, as well as Phoenix- and Tucson-acquired infections in non-endemic areas, regardless of reported travel history. The present study provides a promising example of how a ML-based network analysis can improve our ability to understand pathogen ecology, group cases into populations and infer travel-associated infections.
59 BASIC BIOLOGICAL SCIENCES↗
Global Network Analysis of Neisseria gonorrhoeae Identifies Coordination between Pathways, Processes, and Regulators Expressed during Human Infection
Neisseria gonorrhoeae is a Gram-negative diplococcus that is responsible for the sexually transmitted infection gonorrhea, a high-morbidity disease in the United States and worldwide. Over the past several years, N. gonorrhoeae strains resistant to antibiotics used to treat this infection have begun to emerge across the globe. Thus, new treatment strategies are needed to combat this organism. Here, we utilized N. gonorrhoeae transcriptomic data sets, including those obtained from natural infection of the human genital tract, to infer the first global gene coexpression network of this pathogen. Interrogation of this network revealed genes central to the network that are likely critical for gonococcal growth, metabolism, and virulence, including genes encoding hypothetical proteins expressed during mucosal infection. In addition, network analysis revealed overlap in the response of N. gonorrhoeae to incubation with neutrophils and exposure to hydrogen peroxide stress in vitro. Network analysis also identified new targets of the gonococcal global regulatory protein Fur, while examination of the network neighborhood of genes allowed us to assign additional putative categories to several proteins. Collectively, the characterization of the first gene coexpression network for N. gonorrhoeae described here has revealed new regulatory pathways and new categories for proteins and has shown how processes important to gonococcal infection in both men and women are linked. This information fills a critical gap in our understanding of virulence strategies of this obligate human pathogen and will aid in the development of new treatment strategies for gonorrhea.
59 BASIC BIOLOGICAL SCIENCES↗
Identification of Novel Genomic Associations and Gene Candidates for Grain Starch Content in Sorghum
Starch accumulated in the endosperm of cereal grains as reserve energy for germination serves as a staple in human and animal nutrition. Unraveling genetic control for starch metabolism is important for breeding grains with high starch content. In this study, we used a sorghum association panel with 389 individuals and 141,557 single nucleotide polymorphisms (SNPs) to fit linear mixed models (LMM) for identifying genomic regions and potential candidate genes associated with starch content. Three associated genomic regions, one in chromosome (chr) 1 and two novel associations in chr-8, were identified using combination of LMM and Bayesian sparse LMM. All significant SNPs were located within protein coding genes, with SNPs ∼ 52 Mb of chr-8 encoding a Casperian strip membrane protein (CASP)-like protein (Sobic.008G111500) and a heat shock protein (HSP) 90 (Sobic.008G111600) that were highly expressed in reproductive tissues including within the embryo and endosperm. The HSP90 is a potential hub gene with gene network of 75 high-confidence first interactors that is enriched for five biochemical pathways including protein processing. The first interactors of HSP90 also showed high transcript abundance in reproductive tissues. The candidates of this study are likely involved in intricate metabolic pathways and represent candidate gene targets for source-sink activities and drought and heat stress tolerance during grain filling.
genomics↗
Automated Detection of Instability-Inducing Channel Geometry Transitions in Saint-Venant Simulation of Large-Scale River Networks
A new sweep-search algorithm (SSA) is developed and tested to identify the channel geometry transitions responsible for numerical convergence failure in a Saint-Venant equation (SVE) simulation of a large-scale open-channel network. Numerical instabilities are known to occur at “sharp” transitions in discrete geometry, but the identification of problem locations has been a matter of modeler’s art and a roadblock to implementing large-scale SVE simulations. The new method implements techniques from graph theory applied to a steady-state 1D shallow-water equation solver to recursively examine the numerical stability of each flowpath through the channel network. The SSA is validated with a short river reach and tested by the simulation of ten complete river systems of the Texas–Gulf Coast region by using the extreme hydrological conditions recorded during hurricane Harvey. The SSA successfully identified the problematic channel sections in all tested river systems. Subsequent modification of the problem sections allowed stable solution by an unsteady SVE numerical solver. The new SSA approach permits automated and consistent identification of problem channel geometry in large open-channel network data sets, which is necessary to effectively apply the fully dynamic Saint-Venant equations to large-scale river networks or for city-wide stormwater networks.
54 ENVIRONMENTAL SCIENCES↗
Self-supervised learning and prediction of microstructure evolution with convolutional recurrent neural networks
Not Available
36 MATERIALS SCIENCE↗
Providing biological context for GWAS results using eQTL regulatory and co‐expression networks in Populus
Summary Our study utilized genome‐wide association studies (GWAS) to link nucleotide variants to traits in Populus trichocarpa , a species with rapid linkage disequilibrium decay. The aim was to overcome the challenge of interpreting statistical associations at individual loci without sufficient biological context, which often leads to reliance solely on gene annotations from unrelated model organisms. We employed an integrative approach that included GWAS targeting multiple traits using three individual techniques for lignocellulose phenotyping, expression quantitative trait loci (eQTL) analysis to construct transcriptional regulatory networks around each candidate locus and co‐expression analysis to provide biological context for these networks, using lignocellulose biosynthesis in Populus trichocarpa as a case study. The research identified three candidate genes potentially involved in lignocellulose formation, including one previously recognized gene (Potri.005G116800/VND1, a critical regulator of secondary cell wall formation) and two genes (Potri.012G130000/AtSAP9 and Potri.004G202900/BIC1) with newly identified putative roles in lignocellulose biosynthesis. Our integrative approach offers a framework for providing biological context to loci associated with trait variation, facilitating the discovery of new genes and regulatory networks.
59 BASIC BIOLOGICAL SCIENCES↗
Detail Enhancement of AIRS/AMSU Temperature and Moisture Profiles Using a 3D Deep Neural Network
In recent decades, spaceborne microwave and hyperspectral infrared sounding instruments have significantly benefited weather forecasting and climate science. However, existing retrievals of lower troposphere temperature and humidity profiles have limitations in vertical resolution, and often cannot accurately represent key features such as the mixed layer thermodynamic structure and the inversion at the planetary boundary layer (PBL) top. Because of the existing limitations in PBL remote sensing from space, there is a compelling need to improve routine, global observations of the PBL and enable advances in scientific understanding and weather and climate prediction. To address this, we have developed a new 3D deep neural network (DNN) which enhances detail and reduces noise in Level 2 granules of temperature and humidity profiles from the Atmospheric Infrared Sounder (AIRS)/Advanced Microwave Sounding Unit (AMSU) sounder instruments aboard NASA’s Aqua spacecraft. We show that the enhancement improves accuracy and detail including key features such as capping inversions at the top of the PBL over land, resulting in improved accuracy in estimations of PBL height.
Adam B Milstein↗
Speeding up and reducing memory usage for scientific machine learning via mixed precision
Scientific machine learning (SciML) has emerged as a versatile approach to address complex computational science and engineering problems. Within this field, physics-informed neural networks (PINNs) and deep operator networks (DeepONets) stand out as the leading techniques for solving partial differential equations by incorporating both physical equations and experimental data. However, training PINNs and DeepONets require significant computational resources, including long computational times and large amounts of memory. In search of computational efficiency, training neural networks using half precision (float16) rather than the conventional single (float32) or double (float64) precision has gained substantial interest, given the inherent benefits of reduced computational time and memory consumed. However, we find that float16 cannot be applied to SciML methods, because of gradient divergence at the start of training, weight updates going to zero, and the inability to converge to a local minima. To overcome these limitations, we explore mixed precision, which is an approach that combines the float16 and float32 numerical formats to reduce memory usage and increase computational speed. Our experiments showcase that mixed precision training not only substantially decreases training times and memory demands but also maintains model accuracy. Here, we also reinforce our empirical observations with a theoretical analysis. The research has broad implications for SciML in various computational applications.
97 MATHEMATICS AND COMPUTING↗
Online MCMC Thinning with Kernelized Stein Discrepancy
A fundamental challenge in Bayesian inference is efficient representation of a target distribution. Many nonparametric approaches do so by sampling a large number of points using variants of Markov chain Monte Carlo (MCMC). Here, we propose an MCMC variant that retains only those posterior samples which exceed a kernelized Stein discrepancy (KSD) threshold, which we call KSD thinning. We establish the convergence and complexity trade-offs for several settings of KSD thinning as a function of the KSD threshold parameter, sample size, and other problem parameters. We provide experimental comparisons against other online nonparametric Bayesian methods that generate low-complexity posterior representations. We observe superior consistency/complexity trade-offs across a range of settings including MCMC sampling on two Bayesian inference problems from the biological sciences, and 10 × inference speedup and storage reduction for Bayesian neural networks with no loss of accuracy and no increase in training time. Our code is available at https://github.com/colehawkins/KSD-Thinning.
Bayesian inference↗
Scalable Data Center Capacity for DOE's AI Prototype: A Rapidly Available Gigawatt Data Center for DOE
The multilaboratory Gigawatt Data Center working group was commissioned to identify approaches to rapidly establish federal data centers with scalable capacities up to 1,000 MW. These state-of-the-art facilities will serve as hubs for interdisciplinary collaboration, industry partnerships, and transformative applications of artificial intelligence. The proposed strategic shift includes facilitating multilaboratory collaboration, prioritizing operational efficiency, expanding public–private partnerships, optimizing investments, ensuring long-term contractual flexibility, supporting open science and secure data enclaves, and exploiting high-speed national networks. Owing to their extensive experience and best practices, the US Department of Energy national laboratories are uniquely positioned to lead this initiative. We recommend conducting a feasibility analysis to rapidly identify the optimal sites for this initiative, and the effort will likely involve private industry for design, construction, financing, and operational integration. We also propose establishing multiple geographically diverse sites to ensure energy resilience, high operational reliability, and a diverse user base, thereby effectively addressing the nation’s critical needs.
42 ENGINEERING↗