Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Power Extraction”

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 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

The cosmological analysis of the SDSS/BOSS data from the Effective Field Theory of Large-Scale Structure

The Effective Field Theory of Large-Scale Structure is a formalism that allows us to predict the clustering of Cosmological Large-Scale Structure in the mildly non-linear regime in an accurate and reliable way. In this paper, after validating our technique against several sets of numerical simulations, we perform the analysis for the cosmological parameters of the DR12 BOSS data. We assume Λ CDM, a fixed value of the baryon/dark-matter ratio, Ω b /Ω c , and of the tilt of the primordial power spectrum, n s , and no significant input from numerical simulations. By using the one-loop power spectrum multipoles, we measure the primordial amplitude of the power spectrum, A s , the abundance of matter, Ω m , and the Hubble parameter, H 0 , {to about 13% , 3.2% and 3.2% respectively, obtaining ln (10 10 A s )=2.72± 0.13 , 0Ω m =0.309± 0.01 , H 0 =68.5± 2.2 km/(s Mpc) at 68% confidence level. If we then add a CMB prior on the sound horizon, the error bar on H 0 is reduced to 1.6% .} These results are a substantial qualitative and quantitative improvement with respect to former analyses, and suggest that the EFTofLSS is a powerful instrument to extract cosmological information from Large-Scale Structure.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

Image Deconvolution and Point-spread Function Reconstruction with STARRED: A Wavelet-based Two-channel Method Optimized for Light-curve Extraction

We present starred, a point-spread function (PSF) reconstruction, two-channel deconvolution, and light-curve extraction method designed for high-precision photometric measurements in imaging time series. An improved resolution of the data is targeted rather than an infinite one, thereby minimizing deconvolution artifacts. In addition, starred performs a joint deconvolution of all available data, accounting for epoch-to-epoch variations of the PSF and decomposing the resulting deconvolved image into a point source and an extended source channel. The output is a high-signal-to-noise-ratio, high-resolution frame combining all data and the photometry of all point sources in the field of view as a function of time. Of note, starred also provides exquisite PSF models for each data frame. We showcase three applications of starred in the context of the imminent LSST survey and of JWST imaging: (i) the extraction of supernovae light curves and the scene representation of their host galaxy; (ii) the extraction of lensed quasar light curves for time-delay cosmography; and (iii) the measurement of the spectral energy distribution of globular clusters in the "Sparkler," a galaxy at redshift z = 1.378 strongly lensed by the galaxy cluster SMACS J0723.3-7327. starred is implemented in jax, leveraging automatic differentiation and graphics processing unit acceleration. This enables the rapid processing of large time-domain data sets, positioning the method as a powerful tool for extracting light curves from the multitude of lensed or unlensed variable and transient objects in the Rubin-LSST data, even when blended with intervening objects.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

Big Data For Operation and Maintenance Cost Reduction

The purpose of this research is to develop a first-of-a-kind framework for integrating Big Data capability into the daily activities of our current fleet of nuclear power plants. Big Data is traditionally defined as data sets with high volume, velocity, and heterogeneity, and the existing Big Data analytics capabilities are now widely popular in fields such as finance, weather, e-commerce, healthcare and sports. In the nuclear industry, while the volume and velocity of data may present computational challenges for existing analytics capabilities, data heterogeneity are seen to present the major challenge. This research project mainly focuses on incorporating the wide range of data heterogeneities in nuclear power plants into an integrated Big Data Analytics capability. The primary end-product of this project is a Big Data framework that is capable of dealing with the large volume and heterogeneity of the data found in nuclear power plants to extract timely and valuable information on equipment performance. The framework can generate system insights that are actionable relations between measurable impacts and the corresponding maintenance action plans and enable optimization of plant operation and maintenance based on the extracted information. The developed framework is capable of handling heterogeneous data including both image data and time-series sensor data. Specifically, this developed framework includes the following components. The first component is an overarching maintenance ontology which includes system insights required by maintenance optimization. The maintenance ontology interacts with other components in the developed framework. The second component handles Piping & Instrumentation Diagram (P&ID) data. It can be used to extract system components and their relations automatically from the P&IDs. This extracted information is stored in the first component, i.e., maintenance ontology, and is also used as input to the third component, i.e., a tool for generating the fault tree for the corresponding system. The generated fault tree in turn is stored in the ontology for assessing risk that is used as a criterion in maintenance policy optimization. The fourth component is a tool for inferring the parameters in the Markov degradation model for a nuclear system. It uses basic information from the ontology. The fifth component is a tool for assessing the degradation level using sensor measurement data, for example, pressure, flowrate. This tool can be used for determining corrective maintenance actions. The results obtained from components four and five are returned to the ontology. The sixth component of the framework is a tool for optimizing the maintenance policy for a nuclear system of interest. It takes certain basic information from the ontology, e.g., costs of maintenance actions and system failures, as input, and returns the optimal maintenance policy to the ontology. This tool can be used for determining predictive maintenance actions. A set of experiments have also been conducted to verify the algorithms developed in this project for nuclear system degradation monitoring. The experiments are based on four solenoid valves, similar to the ones used in nuclear power plants. The analyses based on the experimental data using two algorithms, i.e., the Randomized Window Decomposition (RWD) algorithm and the particle filtering algorithm, and the results are introduced in the report. The Big Data framework developed in this project can be used as a support tool in daily activities of plant operation and maintenance and will reduce current costs while maintaining or improving safety levels. Overall, the project will not only benefit existing reactors, however it will open new frontiers to realize the long overdue value of Big Data Analytics in the nuclear sphere.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2026

Dark Energy Survey Year 3 results: Simulation-based 𝑤CDM inference from weak lensing and galaxy clustering maps with deep learning: Analysis design

Data-driven approaches using deep learning are emerging as powerful techniques to extract non-Gaussian information from cosmological large-scale structure. Here, this work presents the first simulation-based inference (SBI) pipeline that combines weak lensing and galaxy clustering maps in a realistic Dark Energy Survey Year 3 (DES Y3) configuration and serves as preparation for a forthcoming analysis of the survey data. We develop a scalable forward model based on the CosmoGridV1 suite of N-body simulations to generate over one million self-consistent mock realizations of DES Y3 at the map level. Leveraging this large dataset, we train deep graph convolutional neural networks on the full survey footprint in spherical geometry to learn low-dimensional features that approximately maximize mutual information with target parameters. These learned compressions enable neural density estimation of the implicit likelihood via normalizing flows in a ten-dimensional parameter space spanning cosmological 𝑤CDM, intrinsic alignment, and linear galaxy bias parameters, while marginalizing over baryonic, photometric redshift, and shear bias nuisances. To ensure robustness, we extensively validate our inference pipeline using synthetic observations derived from both systematic contaminations in our forward model and independent Buzzard galaxy catalogs. Our forecasts yield significant improvements in cosmological parameter constraints, achieving 2−3× higher figures of merit in the 𝛺 𝑚 − 𝑆 8 plane relative to our implementation of baseline two-point statistics and effectively breaking parameter degeneracies through probe combination. These results demonstrate the potential of SBI analyses powered by deep learning for upcoming Stage-IV wide-field imaging surveys.

Thomsen, A. [Zurich, ETH] (ORCID:0000000203099021)↗
DOE OSTI2024

Enhancing the cooling performance of thermocouples: a power-constrained topology optimization procedure

Abstract Heat pumping through thermoelectric devices has many advantages over traditional cooling. However, their current efficiency is a limiting factor in their implementation. In this paper, we approach the non-convex topology optimization of thermoelectrical elements for cooling applications through the method of moving asymptotes (MMA) to improve their cooling capabilities per watt usage. The optimization problem is defined for a given power budget, aiming for the minimum temperature with a known heat pumping need. The introduction of power as a constraint justifies the introduction of the voltage gradient across the thermocouple as a design variable to maintain the thermoelectrical device in its optimum power-to-heat extraction ratio. To better understand the convergence of this non-convex problem, we present a two-variable analytical thermoelectric optimization model. This example provides information on how to select the penalty parameters used to scale the three material coefficients involved in the problem to obtain lower objective values and better convergence using MMA. The analytical model shows the non-convexity of the problem and provides the recommendation to use penalization coefficients of the form $$p_k=p_{\sigma }>p_{\alpha }=1$$ p k = p σ > p α = 1 for the thermal conductivity, electrical conductivity, and Seebeck coefficients. We tested these penalization coefficients through optimizations of a model based on the 1MC10-031 commercial thermoelectric-cooler (TEC) using the finite element method (FEM). These penalization coefficients provided local minima without the need for volume constraints. With this procedure, we found designs that provided temperatures close to 10 degrees lower using 60% less semiconductor material volume compared to the initial design.

Gutiérrez, G. Reales↗
DOE OSTI2024

Efficient distributed continual learning for steering experiments in real-time

Deep learning has emerged as a powerful method for extracting valuable information from large volumes of data. However, when new training data arrives continuously (i.e., is not fully available from the beginning), incremental training suffers from catastrophic forgetting (i.e., new patterns are reinforced at the expense of previously acquired knowledge). Training from scratch each time new training data becomes available would result in extremely long training times and massive data accumulation. Rehearsal-based continual learning has shown promise for addressing the catastrophic forgetting challenge, but research to date has not addressed performance and scalability. To fill this gap, we propose an approach based on a distributed rehearsal buffer that efficiently complements data-parallel training on multiple GPUs to achieve high accuracy, short runtime, and scalability. It leverages a set of buffers (local to each GPU) and uses several asynchronous techniques for updating these local buffers in an embarrassingly parallel fashion, all while handling the communication overheads necessary to augment input minibatches using unbiased, global sampling. We further propose a generalization of rehearsal buffers to support both classification and generative learning tasks, as well as more advanced rehearsal strategies (notably Dark Experience Replay, leveraging knowledge distillation). We illustrate this approach with a real-life HPC streaming application from the domain of ptychographic image reconstruction. Furthermore, we run extensive experiments on up to 128 GPUs of the ThetaGPU supercomputer to compare our approach with baselines representative of training-from-scratch (the upper bound in terms of accuracy) and incremental training (the lower bound). Results show that rehearsal-based continual learning achieves a top-5 validation accuracy close to the upper bound, while simultaneously exhibiting a runtime close to the lower bound.

Asynchronous data management↗
DOE OSTI2021

Ab Initio Molecular Dynamics Simulations of Amorphous Calcium Carbonate: Interpretation of Pair Distribution Function and X-Ray Absorption Spectroscopy Data

The structure and transformation of hydrous amorphous calcium carbonate (ACC) are key to understanding biomineralization pathways and their relationship with the properties of the resulting material. Quantitative interpretation of scattering experiments aimed at elucidating the structure of ACC is challenging, due to the amorphous nature of this material, and, therefore, requires models for the structure and the scattering physics. Here, we generate physically realistic ensembles of hydrated ACC structures and their vibrational disorder from ab initio molecular dynamics (AIMD) simulations with an emphasis on enabling the consistent interpretation of the finer details of three complementary structural probes: neutron and x-ray pair distribution experiments and x-ray absorption spectroscopy (XAS). In each case, we simulate the signal directly in reciprocal space and then manipulate it into the real-space pair distribution function (PDF) or spectrum using the same procedures for the experimental and theoretical data. Good agreement with experiment was obtained across the three techniques with the simulations accounting well for all features in the spectra. Remaining small discrepancies pointed to differences between real samples and the idealized simulated systems such as deviations from the nominal CaCO3·nH2O stoichiometry. Additionally, the simulations offered a more accurate description of the local coordination environment of calcium than previous shell-by-shell fits to spectra of synthetic ACC and classical molecular dynamics simulations. This work demonstrates that AIMD is a powerful approach for extracting detailed structural information from neutron PDF, x-ray PDF, and XAS of amorphous carbonate phases.

Prange, Micah P.↗
DOE OSTI2020

Indicator Patterns of Forced Change Learned by an Artificial Neural Network

Abstract Many problems in climate science require the identification of signals obscured by both the “noise” of internal climate variability and differences across models. Following previous work, we train an artificial neural network (ANN) to predict the year of a given map of annual‐mean temperature (or precipitation) from forced climate model simulations. This prediction task requires the ANN to learn forced patterns of change amidst a background of climate noise and model differences. We then apply a neural network visualization technique (layerwise relevance propagation) to visualize the spatial patterns that lead the ANN to successfully predict the year. These spatial patterns thus serve as “reliable indicators” of the forced change. The architecture of the ANN is chosen such that these indicators vary in time, thus capturing the evolving nature of regional signals of change. Results are compared to those of more standard approaches like signal‐to‐noise ratios and multilinear regression in order to gain intuition about the reliable indicators identified by the ANN. We then apply an additional visualization tool (backward optimization) to highlight where disagreements in simulated and observed patterns of change are most important for the prediction of the year. This work demonstrates that ANNs and their visualization tools make a powerful pair for extracting climate patterns of forced change.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

First constraints from marked angular power spectra with Subaru Hyper Suprime-Cam Survey First-Year Data

We present the first application of marked power spectra to weak lensing data, using maps from the Subaru Hyper Suprime-Cam Year 1 (HSC-Y1) survey. Marked convergence fields, constructed by weighting the convergence field with non-linear functions of its smoothed version, are designed to encode higher-order information while remaining computationally tractable. Using simulations tailored to the HSC-Y1 data, we test three mark functions that up- or down-weight different density environments. Our results show that combining multiple types of marked auto and cross-spectra improves constraints on the clustering amplitude parameter S8≡σ8Ωm/0.3 by ≈43 per cent compared to standard two-point power spectra. When applied to the HSC-Y1 data, this translates into a constraint on S8=0.807±0.024⁠. We assess the sensitivity of the marked power spectra to systematics, including baryonic effects, intrinsic alignment, photometric redshifts, and multiplicative shear bias. We note that some of the additional information introduced by the marked field originates from scales smaller than the scale cut, and is partly Gaussian in nature. This does not invalidate our systematic tests. These results demonstrate the promise of marked statistics as a practical and powerful tool for extracting non-Gaussian information from weak lensing surveys.

Cowell, Jessica A. [Oxford U.; Tokyo U., IPMU] (OR↗
DOE OSTI2024

Deep learning insights into cosmological structure formation

The evolution of linear initial conditions present in the early Universe into extended halos of dark matter at late times can be computed using cosmological simulations. However, a theoretical understanding of this complex process remains elusive; in particular, the role of anisotropic information in the initial conditions in establishing the final mass of dark matter halos remains a long-standing puzzle. Here, we build a deep learning framework to investigate this question. We train a three-dimensional convolutional neural network to predict the mass of dark matter halos from the initial conditions, and quantify in full generality the amounts of information in the isotropic and anisotropic aspects of the initial density field about final halo masses. We find that anisotropies add a small, albeit statistically significant amount of information over that contained within spherical averages of the density field about final halo mass. However, the overall scatter in the final mass predictions does not change qualitatively with this additional information, only decreasing from 0.9 dex to 0.7 dex. Given such a small improvement, our results demonstrate that isotropic aspects of the initial density field essentially saturate the relevant information about final halo mass. Therefore, instead of searching for information directly encoded in initial conditions anisotropies, a more promising route to accurate, fast halo mass predictions is to add approximate dynamical information based e.g. on perturbation theory. More broadly, our results indicate that deep learning frameworks can provide a powerful tool for extracting physical insight into cosmological structure formation. Published by the American Physical Society 2024

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2020

Indicator-directed Dynamic Power Management for Iterative Workloads on GPU-Accelerated Systems

Modern high-performance and warehouse computing centers show strong interest in minimizing system power consumption while satisfying customers’ quality of service (QoS). Dynamic voltage and frequency scaling (DVFS) is effective for achieving this goal. Nevertheless, automating the process online and making it transparent to users must address three major challenges: (1) Complexity — today’s hardware components (e.g., CPUs, GPUs, memory, network, etc.) can be configured in several or dozens of frequency/voltage states for satisfying divergent system demands. Given their combination and the emergence of heterogeneity, searching the optimal configuration in the design space online can be timing consuming. (2) QoS guarantee — user-defined objectives such as power constraint and performance target must be monitored, predicted and ensured at the best effort. (3) Adaptability — various known and unknown workloads run on systems. Workloads characteristics should be quickly determined and configurations dynamically adjusted in accord with workloads and QoS. In this work, we focus on applications exhibiting an interesting feature – iterative or periodic, which is common among conventional HPC and emerging machine learning workloads. We propose an online dynamic power-performance (ODPP) management framework to dynamically adjust GPU DVFS configurations to meet performance and power objectives and constraints, without any code annotation or intrusion. Particularly, ODPP extracts the performance and power indicators for applications from their resources utilization profiles in a short episode. It further automatically constructs an accurate model that infers from the indicators how the application's performance and power vary with GPU core and memory frequencies. Aided with the model, for both seen and unseen applications, ODPP can quickly determine the most appropriate DVFS configuration for their execution. We evaluate ODPP on an NVIDIA GPU using multiple exascale computing (ECP) and deep learning applications.

Zou, Pengfei↗
DOE OSTI2020

DeepFreeze: Towards Scalable Asynchronous Checkpointing of Deep Learning Models

In the age of big data, deep learning has emerged as a powerful tool to extract insight and exploit its value, both in industry and scientific applications. One common pattern emerging in such applications is frequent checkpointing of the state of the learning model during training, needed in a variety of scenarios: analysis of intermediate states to explain features and correlations with training data, exploration strategies involving alternative models that share a common ancestor, knowledge transfer, resilience, etc. However, with increasing size of the learning models and popularity of distributed data-parallel training approaches, simple checkpointing techniques used so far face several limitations: low serialization performance, blocking I/O, stragglers due to the fact that only a single process is involved in checkpointing. This paper proposes a checkpointing technique specifically designed to address the aforementioned limitations, introducing efficient asynchronous techniques to hide the overhead of serialization and I/O, and distribute the load over all participating processes. Experiments with two deep learning applications (CANDLE and ResNet) on a pre-Exascale HPC platform (Theta) shows significant improvement over state-of-art, both in terms of checkpointing duration and runtime overhead.

checkpointing↗
DOE OSTI2023

Clean Energy Technology Applications on US Mine Land: Technical Analysis

As the United States transitions toward a clean energy economy, an opportunity exists for redeveloping the more than 17,000 mine land sites located across the nation with clean energy technologies, which have a combined potential for generating more than 85 GW of clean electricity. This report provides an overview of the potential of demonstrating and deploying clean energy projects on current and former mine land. Clean energy project refers to a project that demonstrates one or more of the following technologies: solar; microgrids; geothermal; direct air capture; fossil-fueled electricity generation with carbon capture, utilization, and sequestration; energy storage, including pumped storage hydropower and compressed air energy storage; and advanced nuclear technologies. The report discusses the following technologies and their potential for creating jobs and generating tax revenue that would result in direct and indirect benefits to the local economy: Solar photovoltaics (PV) is being developed on current and former mine land in various parts of the world, including the United States. This approach is attractive because it requires limited infrastructure investment and would utilize the bare surfaces of mines and tailing ponds. Solar resource availability may be greater in the southern regions, including the Interior and Appalachian Basins and the southwestern United States. However, since some mine land sites include areas of significant change in elevation, the deployment of PV on mine land may require sophisticated planning to account for shading and irradiance, or may require regrading of the areas. PV does not create significant environmental risks and generally does not face public resistance; Geothermal systems are often spatially and genetically associated with ore deposits, and in some cases, they have been discovered while in search for epithermal mineral resources. Numerous diverse geothermal applications have been employed at mine land around the world, including power generation, mineral extraction from geothermal brines, process heating, direct use for other mining operations, and direct use for non-mining operations and subsurface energy storage, including geothermal heat pumps. Case studies highlighting these applications provide key lessons relating to identifying drivers and barriers to geothermal resource deployment and can be used to create screening tools for identifying the types and locations of mine land most amenable to utilizing geothermal resources; Carbon capture, utilization, and sequestration technologies include direct air capture (DAC) and enhanced weathering. DAC technologies include air contactors, regeneration systems, and CO 2 compression systems. Captured CO 2 can be converted to valuable feedstocks or possibly injected into abandoned subsurface mines where it would be absorbed by alkaline rock waste and mine tailings or by the porous minerals along the walls of the mine. DAC systems can be coupled with energy sources such as wind, solar, grid, or geothermal. Many DAC systems require a source of water or steam; however, some are expected to be net producers of water. Local impacts of DAC systems are expected to be low, and are related to land footprint, material disposal, and upstream impacts of energy and material production; Compressed air energy storage is an established energy storage technology in salt caverns. It has the potential for implementation in underground mines by pressurizing and storing a large amount of air using electrical compressors when excess electricity is available. When a need for discharge emerges, the air is used to spin turbines and produce the necessary volume of electricity. Abandoned or unused mine openings, including shafts, adits, access tunnels, and mined workings of any orientation, offer potential for vast amounts of compressed air energy storage if the site characteristics meet operational requirements; Pumped hydropower storage can be implemented in surface and subsurface mines. In surface mine applications, both reservoirs may be located in a mine pit or artificial reservoirs made of excavated materials. In subsurface mines, the lower reservoir may be implemented by waterproofing and flooding mine shafts and tunnels. The water is then pumped from the lower reservoir to the upper reservoir during periods of low load and high production, and it is discharged through the turbines during periods of peak demand. The potential environmental damages associated with acidity of mine water or the presence of toxic chemicals incentivizes the development of closed-loop technologies, in which water circulates inside the pumped hydropower facility without being discharged into the external water basins; Advanced nuclear energy technologies include small modular reactors, which can be deployed locally to produce electricity and heat. Such units require seismic stability and a supply of cooling water, but population constraints may exist in some areas. Therefore, remote mine land could represent an optimal location for siting advanced nuclear energy technologies.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2023

Domain Adaptive Graph Neural Networks for Constraining Cosmological Parameters Across Multiple Data Sets

Deep learning models have been shown to outperform methods that rely on summary statistics, like the power spectrum, in extracting information from complex cosmological data sets. However, due to differences in the subgrid physics implementation and numerical approximations across different simulation suites, models trained on data from one cosmological simulation show a drop in performance when tested on another. Similarly, models trained on any of the simulations would also likely experience a drop in performance when applied to observational data. Training on data from two different suites of the CAMELS hydrodynamic cosmological simulations, we examine the generalization capabilities of Domain Adaptive Graph Neural Networks (DA-GNNs). By utilizing GNNs, we capitalize on their capacity to capture structured scale-free cosmological information from galaxy distributions. Moreover, by including unsupervised domain adaptation via Maximum Mean Discrepancy (MMD), we enable our models to extract domain-invariant features. We demonstrate that DA-GNN achieves higher accuracy and robustness on cross-dataset tasks. Using data visualizations, we show the effects of domain adaptation on proper latent space data alignment. This shows that DA-GNNs are a promising method for extracting domain-independent cosmological information, a vital step toward robust deep learning for real cosmic survey data.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Bridging the Gap between Cosmological Simulations with Graph Neural Networks and Domain Adaptation

Deep learning models have been shown to outperform methods that rely on summary statistics, like the power spectrum, in extracting information from complex cosmological data sets. However, due to differences in the subgrid physics implementation and numerical approximations across different simulation suites, models trained on data from one cosmological simulation show a drop in performance when tested on another. Similarly, models trained on any of the simulations would also likely experience a drop in performance when applied to observational data. Training on data from two different suites of the CAMELS hydrodynamic cosmological simulations, we examine the generalization capabilities of Domain Adaptive Graph Neural Networks (DA-GNNs). By utilizing GNNs, we capitalize on their capacity to capture structured scale-free cosmological information from galaxy distributions. Moreover, by including unsupervised domain adaptation via Maximum Mean Discrepancy (MMD), we enable our models to extract domain-invariant features. We demonstrate that DA-GNN achieves higher accuracy and robustness on cross dataset tasks (up to 28% better relative error and up to almost an order of magnitude better χ 2 ). Using data visualizations, we show the effects of domain adaptation on proper latent space data alignment. This shows that DA-GNNs are a promising method for extracting domain-independent cosmological information, a vital step toward robust deep learning for real cosmic survey data.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

KBase Silver Case Study: Determining Media Formulation Requirements for Isolation of Microbiome Constituents

KBase has powerful tools for extracting microbial genomes from metagenomes and performing phylogenomic analysis and metabolic modeling. These tools can be used to predict key media ingredients for isolating uncultured members of microbiomes. Essential to this process are high-quality genomes extracted from metagenomic assemblies, and Kbase has a tool for assessing the quality of genomes too. Below we identify growth factors for a myxobacteria ("slime bacteria") yet to be isolated from the rhizosphere of Miscanthus xgiganteus (hybrid of "Silvergrass"), cultivated at the Kellogg Biological Station in Michigan. Data was transferred with Globus from JGI-IMG. This narrative and the "KBase Gold Case Study: Can you find Delftia?" make up the Silver and Gold Narrative Set for teaching metagenomics concepts to students in the BIT 477/577 course at North Carolina State University. This tutorial will guide the user through the process of extracting and annotating high-quality genomes from a metagenomic data, performing phylogenomic analysis, building a metabolic model, and using these to predict nutrient requirments for growth and isolation of corresponding microbes.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Domain Adaptive Graph Neural Networks for Constraining Cosmological Parameters Across Multiple Data Sets

Deep learning models have been shown to outperform methods that rely on summary statistics, like the power spectrum, in extracting information from complex cosmological data sets. However, due to differences in the subgrid physics implementation and numerical approximations across different simulation suites, models trained on data from one cosmological simulation show a drop in performance when tested on another. Similarly, models trained on any of the simulations would also likely experience a drop in performance when applied to observational data. Training on data from two different suites of the CAMELS hydrodynamic cosmological simulations, we examine the generalization capabilities of Domain Adaptive Graph Neural Networks (DA-GNNs). By utilizing GNNs, we capitalize on their capacity to capture structured scale-free cosmological information from galaxy distributions. Moreover, by including unsupervised domain adaptation via Maximum Mean Discrepancy (MMD), we enable our models to extract domain-invariant features. We demonstrate that DA-GNN achieves higher accuracy and robustness on cross-dataset tasks (up to $28\%$ better relative error and up to almost an order of magnitude better $\chi^2$). Using data visualizations, we show the effects of domain adaptation on proper latent space data alignment. This shows that DA-GNNs are a promising method for extracting domain-independent cosmological information, a vital step toward robust deep learning for real cosmic survey data.

79 ASTRONOMY AND ASTROPHYSICS↗