SEARCH · Engineering Papers

Results for “Complex networks”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,189 records · Page 66

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Scaling Laws of Graph Neural Networks for Atomistic Materials Modeling

Atomistic materials modeling is a critical task with wide-ranging applications, from drug discovery to materials science, where accurate predictions of the target material property can lead to significant advancements in scientific discovery. Graph Neural Networks (GNNs) represent the state-of-the-art approach for modeling atomistic material data thanks to their capacity to capture complex relational structures. While machine learning performance has historically improved with larger models and datasets, GNNs for atomistic materials modeling remain relatively small compared to large language models (LLMs), which leverage billions of parameters and terabyte-scale datasets to achieve remarkable performance in their respective domains. To address this gap, we explore the scaling limits of GNNs for atomistic materials modeling by developing a foundational model with billions of parameters, trained on extensive datasets in terabytescale. Our approach incorporates techniques from LLM libraries to efficiently manage large-scale data and models, enabling both effective training and deployment of these large-scale GNN models. This work addresses three fundamental questions in scaling GNNs: the potential for scaling GNN model architectures, the effect of dataset size on model accuracy, and the applicability of LLM-inspired techniques to GNN architectures. Specifically, the outcomes of this study include (1) insights into the scaling laws for GNNs, highlighting the relationship between model size, dataset volume, and accuracy, (2) a foundational GNN model optimized for atomistic materials modeling, and (3) a GNN codebase enhanced with advanced LLM-based training techniques. Our findings lay the groundwork for large-scale GNNs with billions of parameters and terabyte-scale datasets, establishing a scalable pathway for future advancements in atomistic materials modeling.

Li, Chaojian [ORNL] (ORCID:0000000340309777)↗

DOE OSTI2024

Exploration of Novel Neuromorphic Methodologies for Materials Applications

Many of today's most interesting questions involve understanding and interpreting complex relationships within graph-based structures. For instance, in materials science, predicting material properties often relies on analyzing the intricate network of atomic interactions. Graph neural networks (GNNs) have emerged as a popular approach for these tasks; however, they suffer from limitations such as inefficient hardware utilization and over-smoothing. Recent advancements in neuromorphic computing offer promising solutions to these challenges. In this work, we evaluate two such neuromorphic strategies known as reservoir computing and hyperdimensional computing. We compare the performance of both approaches for bandgap classification and regression using a subset of the Materials Project dataset. Our results indicate recent advances in hyperdimensional computing can be applied effectively to better represent molecular graphs.

Gobin, Derek [George Mason University, Virginia]↗

DOE OSTI2025

Through the lens of bioenergy crops: advances, bottlenecks, and promises of plant engineering

Advances in engineering of bioenergy crops were driven over the past years by adapting technological breakthroughs and accelerating conventional applications but also exposed intriguing challenges. New tools revealed rich interconnectivity in the exponentially growing and dynamic 'big' omics data' of metabolomes, transcriptomes, and genomes at previously inaccessible magnitude (global, cross-species, meta-) and resolution (single cell). Insights enabled fresh hypotheses and stimulated disciplines such as functional genomics with discovery of broad regulatory networks and their determinants, that is, DNA parts, including promoters, regulatory elements, and transcription factors. Their rational design, assembly into increasingly complex blueprints, and installation into diverse chassis is an existing frontier that may benefit from emerging technologies to address bottlenecks. Interweaving nature-inspired to fully synthetic parts has already allowed building of fine-tuned regulatory circuits, or new-to-nature metabolic routes insulated from the biological context of the chassis species. Similarly, developments and the evolving need for unifying principles in plant transformation and species-agnostic technologies highlight future opportunities for engineering the next generation of bioenergy plants.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2022

Improving Single-Stage Object Detectors for Nighttime Pedestrian Detection

We report Improving the reliability of nighttime pedestrian detection is a crucial challenge towards the design of robust autonomous systems. Not surprisingly, most pedestrian fatalities occur in low-illumination settings, thus emphasizing the need for new algorithmic advances. This work presents a novel pedestrian detection approach that makes a number of crucial modifications to the state-of-the-art YOLOV5-PANet architecture, in order to improve the reliability of features extracted from nighttime images. More specifically, the proposed architecture systematically incorporates powerful shuffle attention mechanisms and a transformer module to improve the feature learning pipeline. Instead of advocating the use of other sensing modalities that are better suited for nighttime detection, our approach relies only on conventional RGB cameras and is hence broadly applicable. Our empirical studies with nighttime pedestrian detection benchmarks show that with only minimal increase in model complexity, our approach provides significant improvements in detection efficacy over existing solutions. Finally, we explore the impact of post-hoc network pruning on the speed-accuracy trade-off of our approach and demonstrate that it is well suited for reduced memory/compute requirements.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Nonlinear behavior of urban flood peaks in the U.S. Mid-Atlantic region

Urbanization, i.e., increasing urban development areas in a watershed, is well known as a major cause of increasing flood magnitudes. This study analyzes the observed flood peaks at 262 watersheds in the U.S. Mid-Atlantic region with varying levels of urban development and free from reservoir impacts. Our analysis reveals an interesting, V-shaped nonlinear behavior: flood peaks first decrease and then increase with increasing percentage of urban development area at the watershed scale (PDAW), with the shift occurring at a PDAW threshold of around 10%. Regression analyses suggest that the V-shaped pattern primarily results from complex interactions among climate conditions (e.g., storm-event rainfall) and landscape properties (e.g., elevation, distance to the coast). A neural network model was then developed to capture such interactions, satisfactorily reproducing the V-shaped pattern with an R-squared value of 0.58, RMSE of 6.72 mm/day, and NSE of 0.55. These findings highlight the need to account for nonlinear dynamics in flood prediction and management in the coastal environment.

flood peaks↗

DOE OSTI2025

Modernizing to an AI-Ready Control System

The Accelerator Controls Operations Research Network (ACORN) project will modernize the accelerator control system and upgrade power supplies to enable future operations of the Fermilab Accelerator Complex with megawatt proton beams. By focusing on MLOps, ACORN enables full integration of AI into the control system to allow safe and reliable improvements to accelerator beam operations.

43 PARTICLE ACCELERATORS↗

DOE OSTI2024

A Comparison between Invariant and Equivariant Classical and Quantum Graph Neural Networks

Machine learning algorithms are heavily relied on to understand the vast amounts of data from high-energy particle collisions at the CERN Large Hadron Collider (LHC). The data from such collision events can naturally be represented with graph structures. Therefore, deep geometric methods, such as graph neural networks (GNNs), have been leveraged for various data analysis tasks in high-energy physics. One typical task is jet tagging, where jets are viewed as point clouds with distinct features and edge connections between their constituent particles. The increasing size and complexity of the LHC particle datasets, as well as the computational models used for their analysis, have greatly motivated the development of alternative fast and efficient computational paradigms such as quantum computation. In addition, to enhance the validity and robustness of deep networks, we can leverage the fundamental symmetries present in the data through the use of invariant inputs and equivariant layers. In this paper, we provide a fair and comprehensive comparison of classical graph neural networks (GNNs) and equivariant graph neural networks (EGNNs) and their quantum counterparts: quantum graph neural networks (QGNNs) and equivariant quantum graph neural networks (EQGNN). The four architectures were benchmarked on a binary classification task to classify the parton-level particle initiating the jet. Based on their area under the curve (AUC) scores, the quantum networks were found to outperform the classical networks. However, seeing the computational advantage of quantum networks in practice may have to wait for the further development of quantum technology and its associated application programming interfaces (APIs).

Forestano, Roy T. (ORCID:0000000203552076)↗

DOE OSTI2024

Assembly and Repair of Photosystem II in Chlamydomonas reinhardtii

Oxygenic photosynthetic organisms use Photosystem II (PSII) to oxidize water and reduce plastoquinone. Here, we review the mechanisms by which PSII is assembled and turned over in the model green alga Chlamydomonas reinhardtii. This species has been used to make key discoveries in PSII research due to its metabolic flexibility and amenability to genetic approaches. PSII subunits originate from both nuclear and chloroplastic gene products in Chlamydomonas. Nuclear-encoded PSII subunits are transported into the chloroplast and chloroplast-encoded PSII subunits are translated by a coordinated mechanism. Active PSII dimers are built from discrete reaction center complexes in a process facilitated by assembly factors. The phosphorylation of core subunits affects supercomplex formation and localization within the thylakoid network. Proteolysis primarily targets the D1 subunit, which when replaced, allows PSII to be reactivated and completes a repair cycle. While PSII has been extensively studied using Chlamydomonas as a model species, important questions remain about its assembly and repair which are presented here.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2023

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

Plant phenotyping is typically a time-consuming and expensive endeavor, requiring large groups of researchers to meticulously measure biologically relevant plant traits, and is the main bottleneck in understanding plant adaptation and the genetic architecture underlying complex traits at population scale. In this work, we address these challenges by leveraging few-shot learning with convolutional neural networks to segment the leaf body and visible venation of 2,906 Populus trichocarpa leaf images obtained in the field. In contrast to previous methods, our approach (a) does not require experimental or image preprocessing, (b) uses the raw RGB images at full resolution, and (c) requires very few samples for training (e.g., just 8 images for vein segmentation). Traits relating to leaf morphology and vein topology are extracted from the resulting segmentations using traditional open-source image-processing tools, validated using real-world physical measurements, and used to conduct a genome-wide association study to identify genes controlling the traits. In this way, the current work is designed to provide the plant phenotyping community with (a) methods for fast and accurate image-based feature extraction that require minimal training data and (b) a new population-scale dataset, including 68 different leaf phenotypes, for domain scientists and machine learning researchers. All of the few-shot learning code, data, and results are made publicly available.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2021

Topological Machine Learning Methods for Power System Responses to Contingencies: Preprint

While deep learning tools, coupled with the emerging machinery of topological data analysis, are proven to deliver various performance gains in a broad range of applications, from image classification to biosurveillance to blockchain fraud detection, their utility in areas of high societal importance such as power system modeling and, particularly, resilience quantification in the energy sector yet remain untapped. To provide fast acting synthetic regulation and contingency reserve services to the grid while having minimal disruptions on customer quality of service, we propose a new topologybased system that depends on neural network architecture for impact metrics classification and prediction in power systems. This novel topology-based system allows one to evaluate the impact of three power system contingency types, namely, in conjunction with transmission lines, transformers, and transmission lines combined with transformers. We show that the proposed new neural network architecture equipped with local topological measures facilitates both more accurate classification of unserved load as well as the amount of unserved load. In addition, we are able to learn complex relationships between electrical properties and local topological measurements on the simulated response to contingencies for NREL-SIIP power system.

graph theory↗

DOE OSTI2024

Characterizing climate pathways using feature importance on echo state networks

The 2022 National Defense Strategy of the United States listed climate change as a serious threat to national security. Climate intervention methods, such as stratospheric aerosol injection, have been proposed as mitigation strategies, but the downstream effects of such actions on a complex climate system are not well understood. The development of algorithmic techniques for quantifying relationships between source and impact variables related to a climate event (i.e., a climate pathway) would help inform policy decisions. Data-driven deep learning models have become powerful tools for modeling highly nonlinear relationships and may provide a route to characterize climate variable relationships. In this paper, we explore the use of an echo state network (ESN) for characterizing climate pathways. ESNs are a computationally efficient neural network variation designed for temporal data, and recent work proposes ESNs as a useful tool for forecasting spatiotemporal climate data. However, ESNs are noninterpretable black-box models along with other neural networks. The lack of model transparency poses a hurdle for understanding variable relationships. We address this issue by developing feature importance methods for ESNs in the context of spatiotemporal data to quantify variable relationships captured by the model. We conduct a simulation study to assess and compare the feature importance techniques, and we demonstrate the approach on reanalysis climate data. In the climate application, we consider a time period that includes the 1991 volcanic eruption of Mount Pinatubo. This event was a significant stratospheric aerosol injection, which acts as a proxy for an anthropogenic stratospheric aerosol injection. Furthermore, we are able to use the proposed approach to characterize relationships between pathway variables associated with this event that agree with relationships previously identified by climate scientists.

black-box models↗

DOE OSTI2020

NSFnets (Navier-Stokes flow nets): Physics-informed neural networks for the incompressible Navier-Stokes equations

In the last 50 years there has been a tremendous progress in solving numerically the Navier-Stokes equations using finite differences, finite elements, spectral, and even meshless methods. Yet, in many real cases, we still cannot incorporate seamlessly (multi-fidelity) data into existing algorithms, and for industrial-complexity applications the mesh generation is time consuming and still an art. Moreover, solving ill-posed problems (e.g., lacking boundary conditions) or inverse problems is often prohibitively expensive and requires different formulations and new computer codes. Here, we employ physics-informed neural networks (PINNs), encoding the governing equations directly into the deep neural network via automatic differentiation, to overcome some of the aforementioned limitations for simulating incompressible laminar and turbulent flows. We develop the Navier-Stokes flow nets (NSFnets) by considering two different mathematical formulations of the Navier-Stokes equations: the velocity-pressure (VP) formulation and the vorticity-velocity (VV) formulation. Since this is a new approach, we first select some standard benchmark problems to assess the accuracy, convergence rate, computational cost and flexibility of NSFnets; analytical solutions and direct numerical simulation (DNS) databases provide proper initial and boundary conditions for the NSFnet simulations. The spatial and temporal coordinates are the inputs of the NSFnets, while the instantaneous velocity and pressure fields are the outputs for the VP-NSFnet, and the instantaneous velocity and vorticity fields are the outputs for the VV-NSFnet. This is unsupervised learning and, hence, no labeled data are required beyond boundary and initial conditions and the fluid properties. The residuals of the VP or VV governing equations, together with the initial and boundary conditions, are embedded into the loss function of the NSFnets. No data is provided for the pressure to the VP-NSFnet, which is a hidden state and is obtained via the incompressibility constraint without extra computational cost. Unlike the traditional numerical methods, NSFnets inherit the properties of neural networks (NNs), hence the total error is composed of the approximation, the optimization, and the generalization errors. Here, we empirically attempt to quantify these errors by varying the sampling (“residual”) points, the iterative solvers, and the size of the NN architecture. For the laminar flow solutions, we show that both the VP and the VV formulations are comparable in accuracy but their best performance corresponds to different NN architectures. The initial convergence rate is fast but the error eventually saturates to a plateau due to the dominance of the optimization error. For the turbulent channel flow, we show that NSFnets can sustain turbulence at , but due to expensive training we only consider part of the channel domain and enforce velocity boundary conditions on the subdomain boundaries provided by the DNS data base. We also perform a systematic study on the weights used in the loss function for balancing the data and physics components, and investigate a new way of computing the weights dynamically to accelerate training and enhance accuracy. In the last part, we demonstrate how NSFnets should be used in practice, namely for ill-posed problems with incomplete or noisy boundary conditions as well as for inverse problems. We obtain reasonably accurate solutions for such cases as well without the need to change the NSFnets and at the same computational cost as in the forward well-posed problems. As a result, we also present a simple example of transfer learning that will aid in accelerating the training of NSFnets for different parameter settings.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

Laboratory investigation of hydraulic fracturing in granitic rocks using active and passive seismic monitoring

SUMMARY Knowledge of the fracturing processes can be important for the optimization of pressurized fluid injection operations in the deep underground rock mass. Active and passive seismic monitoring techniques have been used in the field for tracking or mapping the propagating hydraulic fracture. Although both these monitoring techniques provide valuable information about the generated fracture network, it is difficult for either technique to comprehensibly identify the different processes associated with hydraulic fracturing. The combined active and passive monitoring has the potential for better characterization of the complex hydraulic fracturing phenomena. In this study, laboratory hydraulic fracturing experiments with combined active and passive seismic monitoring were conducted on true triaxially loaded Barre granite cubes with different fluid injection rates. The seismic inelastic fracturing was detected by 16 passive acoustic emission sensors, where 3678 and 2370 seismic source events were detected for the high and low injection rate experiments, respectively. For active monitoring, strong variations in the attributes of signals were observed which were transmitted through four source–receiver pairs, placed both perpendicular and parallel to the generated hydraulic fracture. Positive velocity changes were observed for active sensor pairs with ray paths passing through the generated hydraulic fracture indicating fluid permeation, whereas isolated dry deformation was characterized by a slight but permanent velocity decrease. Compared to velocity, the energy of the active signals was 1–2 orders of magnitude more sensitive to different hydraulic fracturing processes. However, the sensitivity and signatures of the active signal attributes were found to be dependent on the frequency range and direction of ray path with respect to the location of the generated fracture network. Using the coupled evaluation of the active and passive signals we were able to systematically identify various hydraulic fracturing processes including: (1) aseismic deformation, (2) fracture initiation and fluid permeation, (3) pressure build-up, (4) fracture propagation and (5) pressure release and leak-off. The results of this study showed that combining the respective advantages of active and passive seismic techniques and using both of them to monitor the failure processes can facilitate a more comprehensive understanding and better control of the hydraulic stimulations in subsurface operations.

Geochemistry & Geophysics↗

DOE OSTI2022

Conjugated polyelectrolyte-based ternary exciton funnels via liposome scaffolds

There is great interest in developing inexpensive, molecular light-harvesting systems capable of efficiently converting photon energy to chemical potential energy. It is highly desirable to do so using self-assembly and in a manner that supports environmentally benign processing. A critical consideration in any such assembly is the ability to absorb a substantial fraction of the solar emission spectrum and to be able to efficiently move excited states through the space to a functional interface. We have previously shown that aqueous inter-conjugated polyelectrolyte (CPE) complexes can act as ultrafast and efficient energy-transfer antennae. Here we demonstrate formation of a hierarchically assembled, aqueous system based on an inter-CPE exciton donor/acceptor network and a lipid vesicle scaffold. Using a model small-molecule organic semiconductor embedded in the vesicle membrane, we form a ternary exciton funnel that is oriented towards the membrane interior. We show that, although energy transfer is efficient, the assembly morphology depends sensitively on preparation conditions and relative ionic stoichiometry. We propose several approaches towards stabilizing such aqueous assemblies. Furthermore, this work highlights a path to formation of an aqueous, panchromatic light-harvesting system, whose functional complexity can be systematically increased with modularity.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2023

CoolPINNs: A physics-informed neural network modeling of active cooling in vascular systems

Emerging technologies like hypersonic aircraft, space exploration vehicles, and batteries avail fluid circulation in embedded microvasculatures for efficient thermal regulation. Modeling is vital during the design and operational phases of these engineered systems. However, many challenges exist in developing a modeling framework. What is lacking is an accurate framework that (i) captures sharp jumps in the thermal flux across complex vasculature layouts, (ii) deals with oblique derivatives (involving tangential and normal components), (iii) handles nonlinearity because of radiative heat transfer, (iv) provides a high-speed forecast for real-time monitoring, and (v) facilitates robust inverse modeling. Here, this paper addresses these challenges by availing the power of physics-informed neural networks (PINNs). We develop a fast, reliable, and accurate Scientific Machine Learning (SciML) framework for vascular-based thermal regulation—called CoolPINNs: a PINNs-based modeling framework for active cooling. The proposed mesh-less framework elegantly overcomes all the mentioned challenges. The significance of the reported research is multi-fold. First, the framework is valuable for real-time monitoring of thermal regulatory systems because of rapid forecasting. Second, researchers can address complex thermoregulation designs since the approach is meshless. Finally, the framework facilitates systematic parameter identification and inverse modeling studies, perhaps the most significant utility of the current framework.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2021

Using Neural Network Force Fields to Ascertain the Quality of Ab Initio Simulations of Liquid Water

Accurately simulating the properties of bulk water, despite the apparent simplicity of the molecule, is still a challenge. In order to fully understand and reproduce its complex phase diagram, it is necessary to perform simulations at the ab initio level, including quantum mechanical effects both for electrons and nuclei. This comes at a high computational cost, given that the structural and dynamical properties tend to require long timescales and large simulation cells. In this work, we evaluate the errors that density functional theory (DFT)-based simulations routinely incur into due time- and size-scale limitations. These errors are evaluated using neural-network-trained force fields that are accurate at the level of DFT methods. We compare different exchange and correlation potentials for properties of bulk water that require large timescales. Here we show that structural properties are less dependent on the system size and that dynamical properties such as the diffusion coefficient have a strong dependence on the simulation size and timescale. Our results facilitate comparisons of DFT-based simulation results with experiments and offer a path to discriminate between model and convergence errors in these simulations.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2024

Data Imbalance, Uncertainty Quantification, and Transfer Learning in Data‐Driven Parameterizations: Lessons From the Emulation of Gravity Wave Momentum Transport in WACCM

Abstract Neural networks (NNs) are increasingly used for data‐driven subgrid‐scale parameterizations in weather and climate models. While NNs are powerful tools for learning complex non‐linear relationships from data, there are several challenges in using them for parameterizations. Three of these challenges are (a) data imbalance related to learning rare, often large‐amplitude, samples; (b) uncertainty quantification (UQ) of the predictions to provide an accuracy indicator; and (c) generalization to other climates, for example, those with different radiative forcings. Here, we examine the performance of methods for addressing these challenges using NN‐based emulators of the Whole Atmosphere Community Climate Model (WACCM) physics‐based gravity wave (GW) parameterizations as a test case. WACCM has complex, state‐of‐the‐art parameterizations for orography‐, convection‐, and front‐driven GWs. Convection‐ and orography‐driven GWs have significant data imbalance due to the absence of convection or orography in most grid points. We address data imbalance using resampling and/or weighted loss functions, enabling the successful emulation of parameterizations for all three sources. We demonstrate that three UQ methods (Bayesian NNs, variational auto‐encoders, and dropouts) provide ensemble spreads that correspond to accuracy during testing, offering criteria for identifying when an NN gives inaccurate predictions. Finally, we show that the accuracy of these NNs decreases for a warmer climate (4 × CO 2 ). However, their performance is significantly improved by applying transfer learning, for example, re‐training only one layer using ∼1% new data from the warmer climate. The findings of this study offer insights for developing reliable and generalizable data‐driven parameterizations for various processes, including (but not limited to) GWs.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2022

Network analysis uncovers the communication structure of SARS-CoV-2 spike protein identifying sites for immunogen design

The COVID-19 pandemic, caused by the SARS-CoV-2 virus, has triggered myriad efforts to understand the structure and dynamics of this complex pathogen. The spike glycoprotein of SARS-CoV-2 is a significant target for immunogens as it is the means by which the virus enters human cells, while simultaneously sporting mutations responsible for immune escape. These functional and escape processes are regulated by complex molecular-level interactions. Our study presents quantitative insights on domain and residue contributions to allosteric communication, immune evasion, and local- and global-level control of functions through the derivation of a weighted graph representation from all-atom MD simulations. Focusing on the ancestral form and the D614G-variant, we provide evidence of the utility of our approach by guiding the selection of a mutation that alters the spike’s stability. Taken together, the network approach serves as a valuable tool to evaluate communication “hot-spots” in proteins to guide design of stable immunogens.

60 APPLIED LIFE SCIENCES↗