Search NASA⌕ Search

SEARCH · Search NASA

Results for “network optimization”

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 1,585 records · Page 88
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Reducing Communication in Graph Neural Network Training

Graph Neural Networks (GNNs) are powerful and flexible neural networks that use the naturally sparse connectivity information of the data. GNNs represent this connectivity as sparse matrices, which have lower arithmetic intensity and thus higher communication costs compared to dense matrices, making GNNs harder to scale to high concurrencies than convolutional or fully-connected neural networks. Here, we introduce a family of parallel algorithms for training GNNs and show that they can asymptotically reduce communication compared to previous parallel GNN training methods. We implement these algorithms, which are based on 1D, 1. 5D, 2D, and 3D sparse-dense matrix multiplication, using torch.distributed on GPU-equipped clusters. Our algorithms optimize communication across the full GNN training pipeline. We train GNNs on over a hundred GPUs on multiple datasets, including a protein network with over a billion edges.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Spatial Graph Attention and Curiosity-driven Policy for Antiviral Drug Discovery

We developed Distilled Graph Attention Policy Networks (DGAPNs), a curiosity-driven reinforcement learning model to generate novel graph-structured chemical representations that optimize user-defined objectives by efficiently navigating a physically constrained domain. The framework is examined on the task of generating molecules that are designed to bind, noncovalently, to functional sites of SARS-CoV-2 proteins. We present a spatial Graph Attention Network (sGAT) that leverages self-attention over both node and edge attributes as well as encoding spatial structure -- this capability is of considerable interest in areas such as molecular and synthetic biology and drug discovery. An attentional policy network is then introduced to learn decision rules for a dynamic, fragment-based chemical environment, and state-of-the-art policy gradient techniques are employed to train the network with enhanced stability. Exploration is efficiently encouraged by incorporating innovation reward bonuses learned and proposed by random network distillation. In experiments, our framework achieved outstanding results compared to state-of-the-art algorithms, while increasing the diversity of proposed molecules and reducing the complexity of paths to chemical synthesis.

Wu, Yulun↗
DOE OSTI2024

A deep learning approach to fast analysis of collective Thomson scattering spectra

Fast analysis of collective Thomson scattering ion acoustic wave features using a deep convolutional neural network model is presented. The network was trained from spectra to predict the plasma parameters, including ion velocities, population fractions, and ion and electron temperatures. A fully kinetic particle-in-cell simulation was used to model a laboratory astrophysics experiment and simulate a diagnostic image of the ion acoustic wave feature. Network predictions were compared with Bayesian inference of the plasma model parameters for both the simulated and experimentally measured images. Both approaches were fairly accurate predicting the simulated image and the network predictions matched a good portion of the Bayesian results for the experimentally measured image. The Bayesian approach is more robust to noise and motivates future work to train deep learning models with realistic noise. The advantage of the deep learning model is making thousands of predictions in a few hundred milliseconds, compared to a few seconds to minutes per prediction for the optimization and Bayesian approaches presented here. The results demonstrate promising capabilities of deep learning models to analyze Thomson data orders of magnitude faster than conventional methods when using the neural network for standalone analysis. If more rigorous analysis is needed, neural network predictions can be used to quickly initialize other optimization methods and increase chances of success. This is especially useful when the dataset becomes very large or highly dimensional and manually refining initial conditions for the entire dataset are no longer tractable.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

Designing Ti-6Al-4V microstructure for strain delocalization using neural networks

Abstract The deformation behavior of Ti-6Al-4V titanium alloy is significantly influenced by slip localized within crystallographic slip bands. Experimental observations reveal that intense slip bands in Ti-6Al-4V form at strains well below the macroscopic yield strain and may serially propagate across grain boundaries, resulting in long-range localization that percolates through the microstructure. These connected, localized slip bands serve as potential sites for crack initiation. Although slip localization in Ti-6Al-4V is known to be influenced by various factors, an investigation of optimal microstructures that limit localization remains lacking. In this work, we develop a novel strategy that integrates an explicit slip band crystal plasticity technique, graph networks, and neural network models to identify Ti-6Al-4V microstructures that reduce the propensity for strain localization. Simulations are conducted on a dataset of 3D polycrystals, each represented as a graph to account for grain neighborhood and connectivity. The results are then used to train neural network surrogate models that accurately predict localization-based properties of a polycrystal, given its microstructure. These properties include the ratio of slip accumulated in the band to that in the matrix, fraction of total applied strain accommodated by slip bands, and spatial connectivity of slip bands throughout the microstructure. The initial dataset is enriched by synthetic data generated by the surrogate models, and a grid search optimization is subsequently performed to find optimal microstructures. Describing a 3D polycrystal with only a few features and a combination of graph and neural network models offer robustness compared to the alternative approaches without compromising accuracy. We show that while each material property is optimized through a unique microstructure solution, elongated grain shape emerges as a recurring feature among all optimal microstructures. This finding suggests that designing microstructures with elongated grains could potentially mitigate strain localization without compromising strength.

Ahmadikia, Behnam↗
DOE OSTI2023

Structure of a HIV-1 IN-Allosteric inhibitor complex at 2.93 Å resolution: Routes to inhibitor optimization

HIV integrase (IN) inserts viral DNA into the host genome and is the target of the strand transfer inhibitors (STIs), a class of small molecules currently in clinical use. Another potent class of antivirals is the allosteric inhibitors of integrase, or ALLINIs. ALLINIs promote IN aggregation by stabilizing an interaction between the catalytic core domain (CCD) and carboxy-terminal domain (CTD) that undermines viral particle formation in late replication. Ongoing challenges with inhibitor potency, toxicity, and viral resistance motivate research to understand their mechanism. Here, we report a 2.93 Å X-ray crystal structure of the minimal ternary complex between CCD , CTD , and the ALLINI BI-224436. This structure reveals an asymmetric ternary complex with a prominent network of π-mediated interactions that suggest specific avenues for future ALLINI development and optimization.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

Average Incremental Cost Pricing for the AC Unit Commitment Problem [Rev. 1]

Unit Commitment (UC) problems that consider the Alternating Current (AC) model of the transmission network have long been considered intractable to solve at scale by the power system community. Recently, the Grid-Optimization (GO) Competition held by the Advanced Research Project Agency-Energy (ARPA-E) has facilitated the development of the first algorithms to solve large-scale ACUC problems. This new capability opens a path towards the explicit consideration of the AC transmission network model in UC problems used to clear day-ahead electricity markets. This calls for the analysis of electricity market structures that accommodate both the continuous non-linearity of the AC transmission network and the discrete non-linearity of the UC problem simultaneously. This paper serves as an initial effort to do so by proposing an Average Incremental Cost (AIC) pricing structure that is designed around the ACUC problem. In particular, an AIC one-pass pricing problem is proposed that represents a continuously constrained variant of the ACUC problem and allows for the computation of Locational Incremental Prices (LIPs) for both real and reactive power as the local optimal Lagrange multipliers of the power balance constraints. To avoid degeneracy, the pricing problem includes a small parameter ϵ > 0. Under certain assumptions market participants are shown to realize profit that converges to a non-negative value as ϵ approaches zero, practically ensuring profitability for small values of ϵ. We additionally provide many simple and important examples that provide intuition and insights into the proposed prices. Examples illustrate the basic concept of AIC pricing, the derived profitability results, the existence of multiple LIPs, the importance of including reactive power in the dispatch and pricing problems, the need for reactive power prices, and the improved incentives exhibited by LIPs as compared to traditional Locational Marginal Prices (LMPs). We additionally indicate many directions for future work including analysis of larger test cases.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2018

Gas Reliability Analysis Integrated Library (GRAIL)

The Gas Reliability Analysis Integrated Library (GRAIL) is a prototype computational tool for solving a class of intra-day model-predictive control problems for a simplified network model of midstream natural gas pipeline systems. The model accurately resolves dynamic gas flows through long pipes using a non-ideal gas equation of state. It can be used to provide optimal intra-day flow schedules as well as spatiotemporal economic values of natural gas while ensuring that pipeline hydraulic limitations, compressor station constraints, operational factors, and pre-existing shipping contracts are satisfied. The inputs to the code are a model of the pipeline system as well as time-series data that specify boundary conditions on the network and time-dependent constraints on the optimal control problem. The outputs are time-series data that provide an approximately optimal solution of flows, pressures, compressor settings, and sensitivities to the objective function.

Zlotnik, Anatoly↗
DOE OSTI2021

Spatial Graph Attention and Curiosity-driven Policy for Antiviral Drug Discovery

We developed Distilled Graph Attention Policy Networks (DGAPNs), a curiosity-driven reinforcement learning model to generate novel graph-structured chemical representations that optimize user-defined objectives by efficiently navigating a physically constrained domain. Here, the framework is examined on the task of generating molecules that are designed to bind, noncovalently, to functional sites of SARS-CoV-2 proteins. We present a spatial Graph Attention Network (sGAT) that leverages self-attention over both node and edge attributes as well as encoding spatial structure -- this capability is of considerable interest in areas such as molecular and synthetic biology and drug discovery. An attentional policy network is then introduced to learn decision rules for a dynamic, fragment-based chemical environment, and state-of-the-art policy gradient techniques are employed to train the network with enhanced stability. Exploration is efficiently encouraged by incorporating innovation reward bonuses learned and proposed by random network distillation. In experiments, our framework achieved outstanding results compared to state-of-the-art algorithms, while increasing the diversity of proposed molecules and reducing the complexity of paths to chemical synthesis.

Wu, Yulun↗
DOE OSTI2023

Galaxy Morphology Classification Using Bayesian Neural Networks for LSST

Within the decade, many new ground and space-based observatories will become operational, generating massive amounts of data on short timescales. New surveys like Rubin Observatory's Legacy Survey of Space and Time (LSST) will be capable of observing objects with greater resolution than ever before, but processing and analyzing these datasets optimally will pose a significant challenge. In an effort to prepare for this, we explore how incorporating Deep Neural Networks can better support future data-intensive Astrophysics tasks such as galaxy morphology classification.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2019

Surrogate Model Selection for Design Space Approximation And Surrogatebased Optimization

Surrogate models are used to map input data to output data when the actual relationship between the two is unknown or computationally expensive to evaluate for sensitivity analysis, uncertainty propagation and surrogate based optimization. This work evaluates the performance of eight surrogate modeling techniques for design space approximation and surrogate based optimization applications over a set of generated datasets with known characteristics. With this work, we aim to provide general rules for selecting an appropriate surrogate model form solely based on the characteristics of the data being modeled. Furthermore, the computational experiments revealed that, in general, multivariate adaptive regression spline models (MARS) and single hidden layer feed forward neural networks (ANN) yielded the most accurate predictions over the design space while Random Forest (RF) models most reliably identified the locations of the optimums when used for surrogate-based optimization.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Active Site Engineering via Optimizing the Heterogeneous Support Structure for Single-Atom Catalysis

Supported single-atom catalysts show a large range of activities and selectivities that depend on the local environment of the catalytic sites. Here a theory-based optimization strategy is presented that is based on a density functional theory determination of the transition states and intermediates for a low-dimensional coordinate representation of the heterogeneity of the active sites. The approach is applied to a vanadium catalyst on an amorphous SiO 2 support that involves a large kinetic network described using a full chemistry model. Without assuming a priori scaling relations or mechanism reduction, the optimal state of heterogeneity is found to lie at atomic configurations where the activation energies for two distinct key chemical processes are equal. It is found a posteriori that the behavior of the system is consistent with linear free energy scaling relations in the randomness parameters. The energetic span theory proves quite useful in reducing the full chemistry model to a small number of key reactions. The use of a nonlinear optimization algorithm in combination with energetic span theory provides significant simplification in treating disordered systems.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Automated and efficient local adaptive regression for principal component-based reduced-order modeling of turbulent reacting flows

Principal Component Analysis can be used to reduce the cost of Computational Fluid Dynamics simulations of turbulent reacting flows by reducing the dimensionality of the transported variables through projection of the thermochemical state onto a lower-dimensional manifold. However, because of the nonlinearity of the principal component source terms, nonlinear regression techniques must be utilized for the source terms in terms of the principal components. Unfortunately, widely available and utilized nonlinear regression techniques can have prohibitive computational requirements and/or accuracy that is highly dependent on user experience in ad hoc tuning of model architecture and hyperparameters. Here, in this work, a new nonlinear regression approach is proposed that is both computationally efficient and automated so does not require any user input. The approach is evaluated through a priori prediction of principal component source terms using data from a Direct Numerical Simulation of a turbulent nonpremixed n-heptane/air jet flame. In particular, the proposed framework consists of local regressions whose complexity is adapted according to the local nonlinearity of the data: local linear regression when accurate enough and local Artificial Neural Networks when nonlinear regression is required. The number of local clusters for local regression is determined automatically using the Davies-Bouldin index. In addition, Bayesian optimization is utilized for model training (i.e., to select the best architectures and hyperparameters of the nonlinear regressions in an unsupervised fashion), eliminating ad hoc hand-tuning and/or expensive grid searches. Overall, compared to a single, global neural network, the new local adaptive regression approach is shown to have comparable accuracy but 69% less training time due to the utilization of local linear regression and faster training of local neural networks.

42 ENGINEERING↗
DOE OSTI2020

Direction-optimizing Label Propagation and its Application for Community Detection

Label Propagation is a machine learning algorithm typically used for classification. It has also been found to be an effective method for detecting communities in networks. It has two attractive features as a community detection method: it has nearly linear runtime and it requires no \textit{a priori} community information. We propose a new Direction Optimizing Label Propagation Algorithm (DOLPA) that relies on the use of {\em frontiers} and alternates between label {\em push} and label {\em pull} operations to enhance the performance of LPA. Specifically, DOLPA has parameters for tuning the processing order of vertices in a graph. This reduces the number of edges visited and improves the quality of solution. We apply DOLPA to community detection and present the design and implementation of the algorithm as well as its shared-memory parallelization using OpenMP. Empirically, we evaluate our algorithm using synthetic graphs as well as real-world networks. Compared with the state-of-art \textit{Parallel Label Propagation} algorithm, we achieve at least two times the F-Score while reducing the runtime by 50\% for synthetic graphs with overlapping communities. We also compare DOLPA against the state-of-art parallel implementation of the Louvain method using the same graphs and show that DOLPA achieves about three times the F-Score at 10\% the runtime. On real-world graphs, we get a speedup of up to $10\times$ using 64 threads.

Liu, X↗
DOE OSTI2026

High yield production of 3-hydroxypropionic acid using Issatchenkia orientalis

Biomanufacturing provides a more sustainable alternative to fossil-based chemical manufacturing. 3-Hydroxypropionic acid (3HP) is a top Department of Energy value-added chemical and precursor to bioplastics, yet cost-effective microbial production remains elusive. Here, we establish the acid-tolerant yeast Issatchenkia orientalis as a robust host for low-pH 3HP biosynthesis. Genome-scale modeling identifies the β-alanine pathway as optimal, offering the highest theoretical yield and lowest oxygen requirement. Thermodynamic analysis confirms its favorability under acidic conditions. Using sequence similarity network analysis, we discover highly active aspartate 1-decarboxylase (PAND), β-alanine-pyruvate aminotransferase (BAPAT), and 3HP dehydrogenase (YDFG), which significantly improve the pathway efficiency. Next, to further elevate the production, pathway optimization through multi-copy PAND integration, byproduct elimination (knockouts of pyruvate decarboxylase and glycerol-3-phosphate dehydrogenase), and reinforcement of aspartate flux by overexpression of pyruvate carboxylase and aspartate amino transferase improves the titer to 29 g/L in shake flasks. Fed-batch fermentation at pH 4 with low-cost corn steep liquor medium further increases the production to 92 g/L with 0.7 g/g yield and 0.55 g/L/h productivity. Techno-economic analysis indicates that such performance could potentially enable a financially viable process for sustainable acrylic acid production. This work establishes I. orientalis as a next-generation platform for cost-effective 3HP production and paves the way toward industrial commercialization.

Biotechnology↗
DOE OSTI2020

Calorimetry with deep learning: particle simulation and reconstruction for collider physics

Using detailed simulations of calorimeter showers as training data, we investigate the use of deep learning algorithms for the simulation and reconstruction of single isolated particles produced in high-energy physics collisions. We train neural networks on single-particle shower data at the calorimeter-cell level, and show significant improvements for simulation and reconstruction when using these networks compared to methods which rely on currently-used state-of-the-art algorithms. We define two models: an end-to-end reconstruction network which performs simultaneous particle identification and energy regression of particles when given calorimeter shower data, and a generative network which can provide reasonable modeling of calorimeter showers for different particle types at specified angles and energies. We investigate the optimization of our models with hyperparameter scans. Furthermore, we demonstrate the applicability of the reconstruction model to shower inputs from other detector geometries, specifically ATLAS-like and CMS-like geometries. These networks can serve as fast and computationally light methods for particle shower simulation and reconstruction for current and future experiments at particle colliders.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

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↗
DOE OSTI2016

Evolution of microstructure and grain boundary character distribution of a tin bronze annealed at different temperatures

Specimens cut from a rolled tin bronze sheet were annealed at 400–800 °C for 1 h and evolution of their microstructures was then characterized in details by electron channeling contrast imaging and electron backscatter diffraction techniques. Particularly, statistics on special boundaries (SBs) with Σ ≤ 29 and network connectivity of random high angle boundaries (HABs) in the annealed specimens were examined to probe optimization potentials of grain boundary character distribution (GBCD) for this material. Results show that the deformed microstructure in the as-received material begins to be recrystallized when the annealing temperature increase to 500 °C and average grain sizes surge with further increasing temperatures. As a result of the recrystallization, a large number of annealing twins (with Σ3 misorientation) are produced, leading to remarkably increased fractions of SBs (f{sub SBs}). Thanks to preexisting dense low angle boundaries, the majority of SBs in the 500 °C specimen with only partial recrystallization are Σ3{sub ic} (incoherent) boundaries, which effectively disrupt connectivity of random HABs network. Although the f{sub SBs} can be further increased (up to 72.5%) in specimens with full recrystallization (at higher temperatures), the Σ3{sub ic} boundaries would be replaced to some extent by Σ3{sub c} (coherent) boundaries which do not contribute directly to optimizing the GBCD. This work should be able to provide clear suggestions on applying the concept of grain boundary engineering to tin bronze alloys. - Highlights: • The rolled tin bronze begins to be recrystallized as temperature increases to 500 °C. • A lot of SBs are produced after recrystallization and the highest f{sub SBs} is 72.5%. • Partially recrystallized specimen has the optimum GBCD due to more Σ3{sub ic} boundaries. • The Σ3{sub ic} boundaries are replaced by Σ3{sub c} boundaries after full recrystallization.

36 MATERIALS SCIENCE↗