Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “complex network”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

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

At least 1,207 records · Page 67
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Implementing a neural network interatomic model with performance portability for emerging exascale architectures

The two main thrusts of computational science are increasingly accurate predictions and faster calculations; to this end, the zeitgeist in molecular dynamics (MD) simulations is pursuing machine learned and data driven interatomic models, e.g. neural network potentials, and novel hardware architectures, e.g. GPUs. Current implementations of neural network potentials are orders of magnitude slower than traditional interatomic models and while looming exascale computing offers the ability to run large, accurate simulations with these models, achieving portable performance for MD with new and varied exascale hardware requires rethinking traditional algorithms, using novel data structures, and library solutions. We re-implement a neural network interatomic model in CabanaMD, an MD proxy application, built on libraries developed for performance portability. Our implementation shows significantly improved thread scaling in this complex kernel as compared to a current LAMMPS implementation, across both strong and weak scaling. Our single-source solution enables simulations up to 20 million atoms on a single CPU node and 4 million atoms with improved performance on a single GPU. Furthermore, we also explore parallelism and data layout choices (using flexible data structures called AoSoAs) and their effect on performance, seeing up to ~50% and ~5% improvements in performance on a GPU by choosing the right level of parallelism and data layout respectively.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Complexity of many-body interactions in transition metals via machine-learned force fields from the TM23 data set

Abstract This work examines challenges associated with the accuracy of machine-learned force fields (MLFFs) for bulk solid and liquid phases ofd-block elements. In exhaustive detail, we contrast the performance of force, energy, and stress predictions across the transition metals for two leading MLFF models: a kernel-based atomic cluster expansion method implemented using sparse Gaussian processes (FLARE), and an equivariant message-passing neural network (NequIP). Early transition metals present higher relative errors and are more difficult to learn relative to late platinum- and coinage-group elements, and this trend persists across model architectures. Trends in complexity of interatomic interactions for different metals are revealed via comparison of the performance of representations with different many-body order and angular resolution. Using arguments based on perturbation theory on the occupied and unoccupieddstates near the Fermi level, we determine that the large, sharpddensity of states both above and below the Fermi level in early transition metals leads to a more complex, harder-to-learn potential energy surface for these metals. Increasing the fictitious electronic temperature (smearing) modifies the angular sensitivity of forces and makes the early transition metal forces easier to learn. This work illustrates challenges in capturing intricate properties of metallic bonding with current leading MLFFs and provides a reference data set for transition metals, aimed at benchmarking the accuracy and improving the development of emerging machine-learned approximations.

Chemistry↗
DOE OSTI2024

Data-scarce surrogate modeling of shock-induced pore collapse process

Understanding the mechanisms of shock-induced pore collapse is of great interest in various disciplines in sciences and engineering, including materials science, biological sciences, and geophysics. However, numerical modeling of the complex pore collapse processes can be costly. To this end, a strong need exists to develop surrogate models for generating economic predictions of pore collapse processes. Here, in this work, we study the use of a data-driven reduced-order model, namely dynamic mode decomposition, and a deep generative model, namely conditional generative adversarial networks, to resemble the numerical simulations of the pore collapse process at representative training shock pressures. Since the simulations are expensive, the training data are scarce, which makes training an accurate surrogate model challenging. To overcome the difficulties posed by the complex physics phenomena, we make several crucial treatments to the plain original form of the methods to increase the capability of approximating and predicting the dynamics. In particular, physics information is used as indicators or conditional inputs to guide the prediction. In realizing these methods, the training of each dynamic mode composition model takes only around 30 s on CPU. In contrast, training a generative adversarial network model takes 8 h on GPU. Moreover, using dynamic mode decomposition, the final-time relative error is around 0.3% in the reproductive cases. We also demonstrate the predictive power of the methods at unseen testing shock pressures, where the error ranges from 1.3 to 5% in the interpolatory cases and 8 to 9% in extrapolatory cases.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Deep reinforcement learning control of hydraulic fracturing

Hydraulic fracturing is a technique to extract oil and gas from shale formations, and obtaining a uniform proppant concentration along the fracture is key to its productivity. Recently, various model predictive control schemes have been proposed to achieve this objective. But such controllers require an accurate and computationally efficient model which is difficult to obtain given the complexity of the process and uncertainties in the rock formation properties. In this article, we design a model-free data-based reinforcement learning controller which learns an optimal control policy through interactions with the process. Deep reinforcement learning (DRL) controller is based on the Deep Deterministic Policy Gradient algorithm that combines Deep-Q-network with actor-critic framework. In addition, we utilize dimensionality reduction and transfer learning to quicken the learning process. We show that the controller learns an optimal policy to obtain uniform proppant concentration despite the complex nature of the process while satisfying various input constraints.

42 ENGINEERING↗
DOE OSTI2024

CO 2 storage site characterization using ensemble-based approaches with deep generative models

Estimating spatially distributed properties such as permeability from available sparse measurements is a great challenge in efficient subsurface CO 2 storage operations. In this paper, a deep generative model that can accurately capture complex subsurface structure is tested with an ensemble-based inversion method for accurate and accelerated characterization of CO 2 storage sites. We chose Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) for its realistic reservoir property representation and Ensemble Smoother with Multiple Data Assimilation (ES-MDA) for its robust data fitting and uncertainty quantification capability. WGAN-GP are trained to generate high-dimensional permeability fields from a low-dimensional latent space and ES-MDA then updates the latent variables by assimilating available measurements. Several subsurface site characterization examples including Gaussian, channelized, and fractured reservoirs are used to evaluate the accuracy and computational efficiency of the proposed method and the main features of the unknown permeability fields are characterized accurately with reliable uncertainty quantification. Furthermore, the estimation performance is compared with a widely-used variational, i.e., optimization-based, inversion approach, and the proposed approach outperforms the variational inversion method in several benchmark cases. We explain such superior performance by visualizing the objective function in the latent space: because of nonlinear and aggressive dimension reduction via generative modeling, the objective function surface becomes extremely complex while the ensemble approximation can smooth out the multi-modal surface during the minimization. This suggests that the ensemble-based approach works well over the variational approach when combined with deep generative models at the cost of forward model runs unless convergence-ensuring modifications are implemented in the variational inversion.

42 ENGINEERING↗
DOE OSTI2025

Polypropylene Composites Reinforced With Recycled Waste Cellulosic Fiber/Fine Mixture: The Impact of Cellulose Sieving on Performance

This study explores how a sieving step of waste cellulosic fiber and fine (WCFF) mixture affects the performance of WCFF‐loaded polypropylene (PP) composites and whether the separation of fines from fibers offers an added benefit. The WCFF samples were downsized, and four different filler size ranges were sieved using a series of mesh sizes from 4 to 0.85 mm. The WCFF/PP composites were then compounded at 20 wt.% loading of WCFF using a twin‐screw extruder. Incorporating WCFF increased the tensile strength to 41.28 MPa and the modulus to 3207 MPa, accounting for 28% and 38% enhancements, respectively. Interestingly, the greatest improvements were associated with the nonsieved WCFF case, and the sieved WCFF fibers provided only marginal enhancements over virgin PP. The outperformance of nonsieved WCFF was attributed to the synergistic reinforcement of hybrid fibers and fines as well as the maintenance of longer fibers in the system. However, the strain at break and impact strength of PP decreased after introducing WCFF. Moreover, the complex viscosity and storage modulus increased with an increase in the filler size, due to the formation of a more effective percolative network. The PP's crystallinity exhibited a relatively strong dependency on the sieving, where WCFF samples with short‐aspect‐ratio fillers promoted the crystallinity significantly. It was also found that the WCFF degradation onset temperature increased once it was incorporated into PP. This study suggests that waste cellulosic feedstocks can be utilized as a reinforcement without additional sieving to manufacture high‐performance and cost‐effective composites.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Demystify radiation-enhanced hydrogen isotope diffusion in Fe-Ni-Cr austenitic stainless steels

Understanding and containing hydrogen isotope diffusion is crucial for many nuclear applications. In situ experiments have consistently shown that radiation significantly enhances isotope diffusion in austenitic stainless steels. Despite extensive research, the mechanism behind this phenomenon remains elusive, as most radiation-induced defects (e.g., vacancies, dislocations, and grain boundaries) typically trap hydrogen, thereby slowing diffusion. While grain boundaries may increase in-plane diffusivity and interstitials may enhance diffusion due to material swelling, these effects are relatively minor. Utilizing an Fe-Ni-Cr-H interatomic potential for stainless steels, we conducted extensive molecular dynamics simulations to investigate the origins of radiation-enhanced diffusion. Here, our findings reveal that when a system is resolidified, mimicking defects created by radiation displacements, the resulting structure contains a mixture of phases, boundaries, and dislocation networks. This defective structure significantly increases hydrogen diffusivity, enhancing it by approximately 1.7 times at 900 K. These results suggest that the complex defect structures formed during radiation displacements are the primary drivers of the observed diffusion enhancement, providing valuable insights into the mechanisms underlying radiation-enhanced diffusion in nuclear materials.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Surface-Functionalized Cellulose Nanocrystals as Nanofillers for Crosslinking Processes: Implications for Thermosetting Resins

Understanding the response of fillers in the epoxy resin crosslinking process and characterizing polymer–filler dynamics are the key features that guide the engineering of new thermosetting resin composites. Here, in this work, X-ray photon correlation spectroscopy (XPCS) is used as a thermal analysis tool to track the microscopic changes occurring during the cure of a functionalized cellulose nanocrystal (mCNC)–epoxy composite. In contrast, traditional methods such as differential scanning calorimetry (DSC) and curing rheology are used to understand the kinetics and properties on macroscopic length scales. Of interest is the influence of the mCNC on the curing kinetics and properties of the thermosetting resin. Two levels of modification (increasing hydrophobicity) were chosen to observe the effect of functionalization. Before cure, the highly functionalized CNC (mCNC3) shows a 44% increase in complex viscosity (η*), while the less functionalized CNC (mCNC2) shows a η* value similar to that of the neat resin. As the cure cycle progresses, results from DSC, rheology, and XPCS further show the enhancement in dispersion for mCNC3. The results show a clear difference in the maximum drift velocity, maximum heat flow, and complex viscosity during the ramp to the isothermal cure temperature (T cure ). Such results suggest that mCNC3 contains a well-dispersed network of particles due to the higher level of functionalization. During T cure , a transition in elastic modulus (G') occurs only for the highly functionalized CNC particle system. We believe that heat-induced aggregation occurs, and the crosslinked resin ultimately dominates the macroscopic properties of the final cured system for all samples. The results from the three techniques are in good agreement and showcase XPCS as a beneficial experimental tool for characterizing the microscopic dynamics of particulate-filled thermosetting resins. Hence, we envision this to be a fundamental curing study for the design of thermosetting resin composites.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Prediction of vacancy defect diffusion paths in high entropy alloys via machine learning on molecular dynamics data

Identifying the diffusion path of point defects is a critical step in understanding their evolution and the mechanisms of related phenomena. Defect diffusion occurs at small length and time scales, with impacts on material properties that may continue to evolve over ns to μs, ms, and the continuum scale (s, min, etc., and cm, m, etc.). The time scale accessible to molecular dynamics (MD) simulations is limited by small step sizes, typically in the fs range. Thus, surrogate models of MD simulations through machine learning (ML)-based algorithms are of great interest, especially for complex systems such as high entropy alloys (HEAs). In this work, dynamics governing vacancy migration in HEA were approximated with graph convolutional network (GCN) models as ansatzes for kinetic Monte Carlo (KMC) rate catalogs. Network design considered that diffusion in crystalline solids generally depends on interactions between defects and their immediate neighbor atoms. Graphs represented the vacancy surroundings, MD-generated trajectories provided training and comparison datasets, and unsupervised GCN models approximated interatomic dynamics governing vacancy migration in HEAs as ansatzes for KMC. A proof-of-concept model trained on MD data for the Fe, Ni, Cr, Co, and Cu HEA environment was used with two different neighbor interactions to assess the feasibility of training a GCN to predict vacancy defect transition rates in the HEA environment. The resulting setup rapidly generated MD-formatted synthetic trajectories based on dynamics learned from the MD training set, with a time acceleration of roughly two orders of magnitude and a similar diffusion coefficient to MD observations. Additionally, Nudged Elastic Band (NEB) calculations were performed on randomly generated FeNiCrCoCu HEA structures to determine vacancy migration barriers across nearest-neighbor sites. Transition probabilities for each jump, categorized by atomic type, were extracted from these calculations. NEB-based and GCN-based approaches led to similar outcomes.

Reimer, C↗
DOE OSTI2026

Conformalized-KANs: Uncertainty Quantification with Coverage Guarantees for Kolmogorov-Arnold Networks (KANs) in Scientific Machine Learning

This paper explores uncertainty quantification (UQ) methods in the context of Kolmogorov–Arnold Networks (KANs). We apply an ensemble approach to KANs to obtain a heuristic measure of UQ, enhancing interpretability and robustness in modeling complex functions. Building on this, we introduce Conformalized-KANs, which integrate conformal prediction, a distribution-free UQ technique, with KAN ensembles to generate calibrated prediction intervals with guaranteed coverage.} Extensive numerical experiments are conducted to evaluate the effectiveness of these methods, focusing particularly on the robustness and accuracy of the prediction intervals under various hyperparameter settings. We show that the conformal KAN predictions can be applied to recent extensions of KANs, including Finite Basis KANs (FBKANs) and multifideilty KANs (MFKANs). The results demonstrate the potential of our approaches to significantly improve the reliability and applicability of KANs in scientific machine learning.

• Artificial intelligence (AI) / machine learning ↗
DOE OSTI2022

Building an extensible cell wall

Abstract This article recounts, from my perspective of four decades in this field, evolving paradigms of primary cell wall structure and the mechanism of surface enlargement of growing cell walls. Updates of the structures, physical interactions, and roles of cellulose, xyloglucan, and pectins are presented. This leads to an example of how a conceptual depiction of wall structure can be translated into an explicit quantitative model based on molecular dynamics methods. Comparison of the model’s mechanical behavior with experimental results provides insights into the molecular basis of complex mechanical behaviors of primary cell wall and uncovers the dominant role of cellulose–cellulose interactions in forming a strong yet extensible network.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Dynamic Boundary Microgrids Under Privatization Considerations

Microgrids have physical, electrical, and logical (data, network, and ownership) boundaries. To power unserved customer loads during an outage, microgrids can extend the traditional operational boundaries. This can become complex when considering microgrid-to-microgrid (M2M) interactions where sensitive information such as competitive microgrid operational data is not shared. This work proposes an optimization method coordinated between microgrid controllers and distribution management systems that limits data sharing. The method involves a competitive bidding strategy that maximizes unserved load coverage while minimizing resource utilization and sensitive operational data sharing among entities. The work is validated on a two-microgrid system with photovoltaic and energy storage systems and curves of load derived from real world residential buildings datasets. Results show that the proposed method, when applied for three distinct use cases of energy storage sufficiency to cover the predefined boundary and/or the expanded boundary, can successfully select and bid the available load coverage.

Starke, Michael [ORNL] (ORCID:0000000221211195)↗
DOE OSTI2020

Robust Online Sequential RVFLNs for Data Modeling of Dynamic Time-Varying Systems with Application of an Ironmaking Blast Furnace

In a world where the increasing complexity of modern industrial processes brings difficulties for accurate mathematical modeling, taking advantage of data has become an efficient solution to complex dynamic process modeling issue. In this paper, we develop a novel robust online sequential version of random vector functional-link networks (RVFLNs) for data-driven modeling of dynamic time-varying system and applied it in a blast furnace (BF) ironmaking process. First, to overcome the time-varying dynamics of process and to enable the RVFLNs to learn online with avoiding data saturation, an improved online sequential version of RVFLNs (OS-RFVLNs) is first presented by online sequential learning with forgetting factor. This improved OS-RVFLNs algorithm is not only suitable for the real-time and large data transfer situation, but also can adjust the sensitivity of the algorithm to different samples with the help of the introduced forgetting factor. Second, since the output weights of the improved OS-RVFLNs as well as other RVFLNs algorithms are obtained by the least squares approach, a robustness problem may occur when the training dataset is contaminated with various outliers. To solve this problem, a Cauchy distribution weighted M-estimator is introduced to improve the robustness of the improved OS- RVFLNs. For this proposed robust OS-RVFLNs (R-OS- RVFLNs), since the weights of different outlier data are properly determined by the Cauchy distribution function, their corresponding contribution on modeling can be properly distinguished. Thus robust and better modeling results can be achieved. Experiments using actual industrial data of BF ironmaking process and comparative studies have demonstrated that the proposed method produces a better estimation accuracy and stronger robustness than other methods.

Blast furnace (BF), Modelling, Dynamic systems↗
DOE OSTI2023

Small-Molecule Catalysis by Transition-Metal Isocyanide Monomers, Clusters and Materials

DOE Catalysis Science Award DE-SC0018243 focused on the development and mechanistic understanding of small-molecule-activation and catalysis by monomeric and multinuclear transition-metal complexes supported by encumbering m-terphenyl isocyanide ligands. An additional goal of this award was the development of solid-state network materials featuring low-valent metal centers and ditopic m-terphenyl isocyanide ligands into functional platforms for catalytic chemical transformations. The emphasis on m-terphenyl isocyanides stems from a sustained effort by our research team that has shown these ancillary ligands to be particularly adept at stabilizing electronically or coordinately unsaturated metal centers. These metal centers in turn have been shown to effect catalytic and/or stoichiometric chemical transformations of substrates relevant to high-priority energy science goals. In addition, the stabilizing environment provided by these encumbering ligands has in several instances aided the detailed mechanistic elucidation of substrate activation process and/or have enabled important electronic structure insights to be uncovered.

36 MATERIALS SCIENCE↗
DOE OSTI2024

NoRA: A Tensor Network Ansatz for Volume-Law Entangled Equilibrium States of Highly Connected Hamiltonians

Motivated by the ground state structure of quantum models with all-to-all interactions such as mean-field quantum spin glass models and the Sachdev-Ye-Kitaev (SYK) model, we propose a tensor network architecture which can accomodate volume law entanglement and a large ground state degeneracy. We call this architecture the non-local renormalization ansatz (NoRA) because it can be viewed as a generalization of MERA, DMERA, and branching MERA networks with the constraints of spatial locality removed. We argue that the architecture is potentially expressive enough to capture the entanglement and complexity of the ground space of the SYK model, thus making it a suitable variational ansatz, but we leave a detailed study of SYK to future work. We further explore the architecture in the special case in which the tensors are random Clifford gates. Here the architecture can be viewed as the encoding map of a random stabilizer code. We introduce a family of codes inspired by the SYK model which can be chosen to have constant rate and linear distance at the cost of some high weight stabilizers. We also comment on potential similarities between this code family and the approximate code formed from the SYK ground space.

Physics↗
DOE OSTI2024

Streamlining Ocean Dynamics Modeling with Fourier Neural Operators: A Multiobjective Hyperparameter and Architecture Optimization Approach

Training an effective deep learning model to learn ocean processes involves careful choices of various hyperparameters. We leverage DeepHyper’s advanced search algorithms for multiobjective optimization, streamlining the development of neural networks tailored for ocean modeling. The focus is on optimizing Fourier neural operators (FNOs), a data-driven model capable of simulating complex ocean behaviors. Selecting the correct model and tuning the hyperparameters are challenging tasks, requiring much effort to ensure model accuracy. DeepHyper allows efficient exploration of hyperparameters associated with data preprocessing, FNO architecture-related hyperparameters, and various model training strategies. We aim to obtain an optimal set of hyperparameters leading to the most performant model. Moreover, on top of the commonly used mean squared error for model training, we propose adopting the negative anomaly correlation coefficient as the additional loss term to improve model performance and investigate the potential trade-off between the two terms. The numerical experiments show that the optimal set of hyperparameters enhanced model performance in single timestepping forecasting and greatly exceeded the baseline configuration in the autoregressive rollout for long-horizon forecasting up to 30 days. Utilizing DeepHyper, we demonstrate an approach to enhance the use of FNO in ocean dynamics forecasting, offering a scalable solution with improved precision.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

A network approach for multiscale catchment classification using traits

Abstract. The classification of river catchments into groups with similar biophysical characteristics is useful to understand and predict their hydrological behavior. The increasing availability of remote sensing and other large-scale geospatial datasets has enabled the use of advanced data-driven approaches to classify catchments using traits such as topography, geology, climate, land cover, land use, and human influence. Unsupervised clustering algorithms based on the Euclidean distance are commonly used for trait-based classification but are not suitable for highly dimensional data. In this study we present a new network-based method for multi-scale catchment classification, which can be applied to large datasets and used to determine the traits associated with different catchment groups. In this framework, two networks are analyzed in parallel: the first being where the nodes are traits and the second being where the nodes are catchments. In both cases, edges represent pairwise similarity, and a network cluster detection algorithm is used for the classification. The trait network is used to investigate redundancy in the trait data and to condense this information into a small number of interpretable categories. The catchments network is used to classify the catchments into clusters and to identify representative catchments for the different groups using the degree centrality metric. We apply this method to classify 9067 river catchments across the contiguous United States at both regional and continental scales using 274 non-categorical traits. At the continental scale, we identify 25 interpretable trait categories and 34 catchment clusters of sizes greater than 50. We find that catchments with similar trait categories are typically located in the same region, with different spatial patterns emerging among clusters dominated by natural and anthropogenic traits. We also find that the catchment clusters exhibit distinct hydrological behavior based on an analysis of streamflow indices. This network approach provides several advantages over traditional means of classification, including better separation of clusters, the use of alternate similarity metrics that are more suitable for highly dimensional data, and reducing redundancy in the trait information. The paired catchment–trait networks enable analysis of hydrological behavior using the dominant trait categories for each catchment cluster. The approach can be used at multiple spatial scales since the network topologies adjust automatically to reflect the trait patterns at the scale of investigation. Finally, the representative catchments identified as hub nodes in the network can be used to guide transferable observational and modeling strategies. The method is broadly applicable beyond hydrology for classification of other complex systems that utilize different types of trait datasets.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Simple biochemical features underlie transcriptional activation domain diversity and dynamic, fuzzy binding to Mediator

Gene activator proteins comprise distinct DNA-binding and transcriptional activation domains (ADs). Because few ADs have been described, we tested domains tiling all yeast transcription factors for activation in vivo and identified 150 ADs. By mRNA display, we showed that 73% of ADs bound the Med15 subunit of Mediator, and that binding strength was correlated with activation. AD-Mediator interaction in vitro was unaffected by a large excess of free activator protein, pointing to a dynamic mechanism of interaction. Structural modeling showed that ADs interact with Med15 without shape complementarity (‘fuzzy’ binding). ADs shared no sequence motifs, but mutagenesis revealed biochemical and structural constraints. Finally, a neural network trained on AD sequences accurately predicted ADs in human proteins and in other yeast proteins, including chromosomal proteins and chromatin remodeling complexes. These findings solve the longstanding enigma of AD structure and function and provide a rationale for their role in biology.

60 APPLIED LIFE SCIENCES↗