Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “data representations”

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 811 records · Page 45

A Multiple Lines of Evidence Approach for Conceptual Site Models in Performance Assessments - 19070

Demonstration of the long-term performance of remediated radioactive waste sites relies on models that evaluate vadose zone and groundwater flow and contaminant transport for thousands of years. Model qualification, verification, and comparisons with data are essential elements to demonstrating the accuracy of long-term performance assessments (PAs). However, comparisons with data are generally limited due to incomplete characterization data and long-time scales. Since PAs support decision making to assure long-term protection of both human health and the environment, a conceptual site model (CSM) is needed to explain the hydrodynamic behavior and account for subsurface heterogeneities in sufficient detail to support confident decisions. In the case of the Waste Management Area (WMA) C PA, where the focus of the effort is on characterizing flow and transport through a thick vadose zone, site-specific data are sparse and larger-scale geologic descriptions are adopted with the risk of losing small scale features that may affect contaminant transport. Features such as horizontal bedding and sloping interfaces between contrasting material types, as well as vertically oriented features such as clastic dikes, may be difficult to delineate from sparse characterization data, but may affect the extent to which contaminants are transported. The PA conducted to identify long-term impacts associated with the closure of the single-shell tank (SST) farm at WMA C adopted an equivalent homogenous medium approach to represent the major stratigraphic units at the site. This approach explicitly represents major stratigraphic units but assigns hydraulic properties that implicitly account for the presence of small-scale heterogeneities and their impact on flow and contaminant transport to the groundwater. The objective of this study is to evaluate the available site-specific and analogue data that can be used to characterize heterogeneity and to assess its impact on fate and transport of contaminants that may lead to different conclusions when compared to the results of the equivalent homogeneous media approach. To this end, a multiple lines of evidence approach was used to construct alternative CSMs based on an evaluation of several types of data. These data include 1) general characteristics and features of the major stratigraphic units from historical descriptions; 2) borehole geologic logs; 3) particle size distribution measurements; 4) moisture content measurements; 5) spectral gamma data; and 6) concentrations of key constituents (i.e., Tc-99) in both the vadose zone and groundwater impacted by past releases. Based on an analysis of the available data, lines of evidence are evaluated for consistency and integrated in a consistent manner into scientifically defensible CSMs. Numerical models are then used to evaluate the impact that the explicit representation of heterogeneities has on contaminant transport. Together, the field data and the numerical modeling results indicate that heterogeneity caused by the small-scale features do not have a significant (i.e. greater than a factor of 2) impact on transport below WMA C relative to peak concentrations and arrival times for potential releases from waste tanks. The results of this study underscore the value of using multiple lines of evidence based on the quantity and quality of available data in developing alternative CSMs and evaluating their relative impact on key transport metrics such as arrival times and peak concentration. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Deep graph representations embed network information for robust disease marker identification

We report that the accurate disease diagnosis and prognosis based on omics data rely on the effective identification of robust prognostic and diagnostic markers that reflect the states of the biological processes underlying the disease pathogenesis and progression. In this article, we present GCNCC, a Graph Convolutional Network-based approach for Clustering and Classification, that can identify highly effective and robust network-based disease markers. Based on a geometric deep learning framework, GCNCC learns deep network representations by integrating gene expression data with protein interaction data to identify highly reproducible markers with consistently accurate prediction performance across independent datasets possibly from different platforms. GCNCC identifies these markers by clustering the nodes in the protein interaction network based on latent similarity measures learned by the deep architecture of a graph convolutional network, followed by a supervised feature selection procedure that extracts clusters that are highly predictive of the disease state. By benchmarking GCNCC based on independent datasets from different diseases (psychiatric disorder and cancer) and different platforms (microarray and RNA-seq), we show that GCNCC outperforms other state-of-the-art methods in terms of accuracy and reproducibility.

59 BASIC BIOLOGICAL SCIENCES↗

Learning from metastable symmetric-tilt grain boundaries using physics-based descriptors

Grain boundaries (GBs) govern critical properties of polycrystalline materials. Although significant advancements have been made in characterizing minimum energy and ordered GBs, real GBs are seldom found in such well-defined states. This diversity of atomic arrangements in metastable states makes it challenging to establish structure-property relationships with physical insights. Here, to address this challenge, we use data-driven methods to explore these relationships and examine the underlying physics. In this study, we utilize a large atomistic database (~5000) of minimum energy and metastable states of symmetric-tilt copper GBs, combined with physically motivated local atomic environment (LAE) descriptors [strain functional descriptors (SFDs)], to predict GB properties and gain physical insights. Our regression models exhibit robust predictive capabilities using only 19 descriptors, generalizing to atomic environments in nanocrystals. A significant highlight of our work is the integration of an unsupervised method with SFDs to elucidate LAEs at GBs and their role in determining properties. The model, trained on these minimum energy and metastable GBs using SFDs, predicts the properties of unseen nanocrystals with good accuracy. Our research underscores the role of a physics-based representation of LAEs and the efficacy of data-driven methods in establishing GB structure-property relationships.

36 MATERIALS SCIENCE↗

Surrogate models for plasma displacement and current in 3D perturbed magnetohydrodynamic equilibria in tokamaks

Abstract A numerical database of over one thousand perturbed three-dimensional (3D) equilibria has been generated, constructed based on the MARS-F (Liu et al 2000 Phys. Plasmas 7 3681) computed plasma response to the externally applied 3D field sources in multiple tokamak devices. Perturbed 3D equilibria with the n = 1–4 ( n is the toroidal mode number) toroidal periodicity are computed. Surrogate models are created for the computed perturbed 3D equilibrium utilizing model order reduction (MOR) techniques. In particular, retaining the first few eigenstates from the singular value decomposition (SVD) of the data is found to produce reasonably accurate MOR-representations for the key perturbed quantities, such as the perturbed parallel plasma current density and the plasma radial displacement. SVD also helps to reveal the core versus edge plasma response to the applied 3D field. For the database covering the conventional aspect ratio devices, about 95% of data can be represented by the truncated SVD-series with inclusion of only the first five eigenstates, achieving a relative error (RE) below 20%. The MOR-data is further utilized to train neural networks (NNs) to enable fast reconstruction of perturbed 3D equilibria, based on the two-dimensional equilibrium input and the 3D source field. The best NN-training is achieved for the MOR-data obtained with a global SVD approach, where the full set of samples used for NN training and testing are stretched and form a large matrix which is then subject to SVD. The fully connected multi-layer perceptron, with one or two hidden layers, can be trained to predict the MOR-data with less than 10% RE. As a key insight, a better strategy is to train separate NNs for the plasma response fields with different toroidal mode numbers. It is also better to apply MOR and to subsequently train NNs separately for conventional and low aspect ratio devices, due to enhanced toroidal coupling of Fourier spectra in the plasma response in the latter case.

3D equilibrium↗

Lineage-based functional types: characterising functional diversity to enhance the representation of ecological behaviour in Land Surface Models

Process-based vegetation models attempt to represent the wide range of trait variation in biomes by grouping ecologically similar species into plant functional types (PFTs). This approach has been successful in representing many aspects of plant physiology and biophysics but struggles to capture biogeographic history and ecological dynamics that determine biome boundaries and plant distributions. Grass-dominated ecosystems are broadly distributed across all vegetated continents and harbour large functional diversity, yet most Land Surface Models (LSMs) summarise grasses into two generic PFTs based primarily on differences between temperate C 3 grasses and (sub)tropical C 4 grasses. Incorporation of species-level trait variation is an active area of research to enhance the ecological realism of PFTs, which form the basis for vegetation processes and dynamics in LSMs. Using reported measurements, we developed grass functional trait values (physiological, structural, biochemical, anatomical, phenological, and disturbance-related) of dominant lineages to improve LSM representations. In this work, our method is fundamentally different from previous efforts, as it uses phylogenetic relatedness to create lineage-based functional types (LFTs), situated between species-level trait data and PFT-level abstractions, thus providing a realistic representation of functional diversity and opening the door to the development of new vegetation models.

54 ENVIRONMENTAL SCIENCES↗

Validation and parameterization of a novel physics-constrained neural dynamics model applied to turbulent fluid flow

We report, in fluid physics, data-driven models to enhance or accelerate time to solution are becoming increasingly popular for many application domains, such as alternatives to turbulence closures, system surrogates, or for new physics discovery. In the context of reduced order models of high-dimensional time-dependent fluid systems, machine learning methods grant the benefit of automated learning from data, but the burden of a model lies on its reduced-order representation of both the fluid state and physical dynamics. In this work, we build a physics-constrained, data-driven reduced order model for Navier–Stokes equations to approximate spatiotemporal fluid dynamics in the canonical case of isotropic turbulence in a triply periodic box. The model design choices mimic numerical and physical constraints by, for example, implicitly enforcing the incompressibility constraint and utilizing continuous neural ordinary differential equations for tracking the evolution of the governing differential equation. We demonstrate this technique on a three-dimensional, moderate Reynolds number turbulent fluid flow. In assessing the statistical quality and characteristics of the machine-learned model through rigorous diagnostic tests, we find that our model is capable of reconstructing the dynamics of the flow over large integral timescales, favoring accuracy at the larger length scales. More significantly, comprehensive diagnostics suggest that physically interpretable model parameters, corresponding to the representations of the fluid state and dynamics, have attributable and quantifiable impact on the quality of the model predictions and computational complexity.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

A Causal Approach to Integrate Component Health Data into System Reliability Models

Two of the challenges of current plant reliability approaches are the ability to integrate plant health data, and to support decision making. Condition based data and diagnostic/prognostic information are in fact not considered into plant reliability models to inform system engineers on the most critical components. Currently, the propagation of quantitative health data from the component to the system level is a challenge given the diverse nature/structure of the data. On the other hand, plant reliability methods (which are typically based on fault-trees or reliability block diagrams) can effectively propagate data from the component to the system level, but values of failure rates or failure probabilities are an approximated integral representation of the past industry-wide operational experience, and it neglects the present component health status (e.g., diagnostic and condition-based data) and health projection (when available from prognostic data). Our first claim is that system reliability models should propagate health information from the component to the system/plant level in order to provide a quantitative snapshot of system/plant health and identify the most critical components. Our second claim is that component health should be informed solely by that specific component current and historical performance data and should not be an approximated integral representation of the past industry-wide operational experience. This paper is directly supporting these two claims by proposing a different approach to perform reliability modeling which relies on available component diagnostic, prognostic and condition-based data to measure component health, and it propagates this information through fault tree models. The propagation of health data from the component to the system level is performed not in terms of probability, but in terms of margins where margin is defined as the “distance” between the present actual status and an undesired event (e.g., failure or unacceptable performance). Through a cause-effect lens, while classical reliability models target the effect associated to a component performance, a margin-based approach focuses on the cause of an undesired component performance (i.e., component health). Hence, thinking of reliability in terms of margins implies decision making based on causal reasoning. We will show how fault tree models can be solved using a margin language and how this process can effectively assist system engineers to identify the most critical components.

97 MATHEMATICS AND COMPUTING↗

A Variational Autoencoder Model Toward Molecular Structure Representation Learning of Fuels

Here, in this work, a Variational Autoencoder (VAE)-based data-driven modeling framework is developed with the overarching goal of enabling fuel design. The VAE model is trained on a large dataset with several chemical species to learn a compressed latent space molecular representation. Chemical structure in the form of Simplified Molecular Input Line Entry System (SMILES) string is fed as input, encoded into the VAE latent space, and decoded back to the SMILES string using Long Short-Term Memory (LSTM) networks. Complexities of the VAE training loss function are thoroughly examined by varying the weightage (beta (𝜷) parameter) of the latent space regularization term, thereby assessing the balance between reconstruction accuracy and validity, and focusing on both accurate molecular structure reconstruction and latent space consistency. Two different strategies for 𝜷 variation are evaluated: linear annealing and cyclic annealing. In addition, the impact of total correlation adjustment and hierarchical priors is also studied with regard to the balance between reconstruction fidelity and latent space regularization, and potential issues such as posterior collapse, over-regularization, and poor disentanglement of latent variables. Overall, the best performance of the model is achieved with hierarchical priors and incrementally increasing 𝜷 from 0 to a threshold value of 0.25 over 75 epochs. The generative VAE model can be readily coupled with Quantitative Structure–Property Relationship (QSPR) analysis to develop an integrated end-to-end framework for fuel-property prediction and molecular design of novel promising fuels.

fuel design↗

Navigating Uncertainty: Challenges in Visualizing Ensemble Data and Surrogate Models for Decision Systems

Uncertainty visualization plays a critical role in transforming ensemble simulation data into actionable insights by effectively communicating various dimensions of uncertainty within a system. The emergence of artificial intelligence-driven surrogate models trained on multirun ensemble data offers a transformative opportunity to replace computationally intensive simulations with fast estimates, enabling users to explore data spaces with unprecedented depth and interactivity. However, integrating ensemble data and surrogate models into decision-making workflows and tools introduces novel challenges for uncertainty visualization. These include reconciling and clearly communicating the unique uncertainties associated with ensembles and their surrogate model estimates, and leveraging these approximations to inform actionable decisions. This work explores these challenges in the context of high-dimensional data visualization, bridging discrete datasets with their continuous representations and addressing the complexities of systems that support iterative navigation between input and output spaces. We evaluate the role of uncertainty visualization in fostering intuitive, actionable interactions and identify critical hurdles in advancing this frontier of computational simulation.

97 MATHEMATICS AND COMPUTING↗

A representation-independent electronic charge density database for crystalline materials

In addition to being the core quantity in density functional theory, the charge density can be used in many tertiary analyses in materials sciences from bonding to assigning charge to specific atoms. The charge density is data-rich since it contains information about all the electrons in the system. With increasing utilization of machine-learning tools in materials sciences, a data-rich object like the charge density can be utilized in a wide range of applications. The database presented here provides a modern and user-friendly interface for a large and continuously updated collection of charge densities as part of the Materials Project. In addition to the charge density data, we provide the theory and code for changing the representation of the charge density which should enable more advanced machine-learning studies for the broader community.

36 MATERIALS SCIENCE↗

Mixture Model Framework for Traumatic Brain Injury Prognosis Using Heterogeneous Clinical and Outcome Data

Prognoses of Traumatic Brain Injury (TBI) outcomes are neither easily nor accurately determined from clinical indicators. This is due in part to the heterogeneity of damage inflicted to the brain, ultimately resulting in diverse and complex outcomes. Using a data-driven approach on many distinct data elements may be necessary to describe this large set of outcomes and thereby robustly depict the nuanced differences among TBI patients’ recovery. In this work, we develop a method for modeling large heterogeneous data types relevant to TBI. Our approach is geared toward the probabilistic representation of mixed continuous and discrete variables with missing values. The model is trained on a dataset encompassing a variety of data types, including demographics, blood-based biomarkers, and imaging findings. In addition, it includes a set of clinical outcome assessments at 3, 6, and 12 months post-injury. The model is used to stratify patients into distinct groups in an unsupervised learning setting. We use the model to infer outcomes using input data, and show that the collection of input data reduces uncertainty of outcomes over a baseline approach. In addition, we quantify the performance of a likelihood scoring technique that can be used to self-evaluate the extrapolation risk of prognosis on unseen patients.

97 MATHEMATICS AND COMPUTING↗

The structure of liquid water up to 360 MPa from x-ray diffraction measurements using a high Q-range and from molecular simulation

X-ray diffraction measurements of liquid water are reported at pressures up to 360 MPa corresponding to a density of 0.0373 molecules per Å{sup 3}. The measurements were conducted at a spatial resolution corresponding to Q{sub max} = 16 Å{sup −1}. The method of data analysis and measurement in this study follows the earlier benchmark results reported for water under ambient conditions having a density of 0.0333 molecules per Å{sup 3} and Q{sub max} = 20 Å{sup −1} [J. Chem. Phys. 138, 074506 (2013)] and at 70 °C having a density of 0.0327 molecules per Å{sup 3} and Q{sub max} = 20 Å{sup −1} [J. Chem. Phys. 141, 214507 (2014)]. The structure of water is very different at these three different T and P state points and thus they provide the basis for evaluating the fidelity of molecular simulation. Measurements show that at 360 MPa, the 4 waters residing in the region between 2.3 and 3 Å are nearly unchanged: the peak position, shape, and coordination number are nearly identical to their values under ambient conditions. However, in the region above 3 Å, large structural changes occur with the collapse of the well-defined 2nd shell and shifting of higher shells to shorter distances. The measured structure is compared to simulated structure using intermolecular potentials described by both first-principles methods (revPBE-D3) and classical potentials (TIP4P/2005, MB-pol, and mW). The DFT-based, revPBE-D3, method and the many-body empirical potential model, MB-pol, provide the best overall representation of the ambient, high-temperature, and high-pressure data. The revPBE-D3, MB-pol, and the TIP4P/2005 models capture the densification mechanism, whereby the non-bonded 5th nearest neighbor molecule, which partially encroaches the 1st shell at ambient pressure, is pushed further into the local tetrahedral arrangement at higher pressures by the more distant molecules filling the void space in the network between the 1st and 2nd shells.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

NeRVI: Compressive neural representation of visualization images for communicating volume visualization results

We present NeRVI, a new deep-learning approach that compresses a large collection of visualization images generated from time-varying data for communicating volume visualization results. Based on an image-based implicit neural representation, our approach represents tens of thousands of high-resolution rendering images parametrized by different parameters via a hybrid model of multilayer perceptrons and convolutional neural networks. Here, our model predicts images and corresponding masks, and the masks are utilized for loss computation and network training to capture fine structural details and small components. In conjunction with model quantization and weight encoding, NeRVI yields highly compact compressive neural representations while preserving the image fidelity well. We demonstrate the effectiveness of NeRVI with isosurface rendering and direct volume rendering images generated from multiple data sets and compare NeRVI with other state-of-the-art deep learning-based (InSituNet, SIREN, NeRF, and NeRV) methods. Quantitative and qualitative results show that NeRVI provides an alternative solution that augments domain scientists' ability to manage, represent, and communicate scientific visualization output.

97 MATHEMATICS AND COMPUTING↗

Improving the phenomenology of K{sub l3} form factors with analyticity and unitarity

The shape of the vector and scalar K{sub l3} form factors is investigated by exploiting analyticity and unitarity in a model-independent formalism. The method uses as input dispersion relations for certain correlators computed in perturbative QCD in the deep Euclidean region, soft-meson theorems, and experimental information on the phase and modulus of the form factors along the elastic part of the unitarity cut. We derive constraints on the coefficients of the parameterizations valid in the semileptonic range and on the truncation error. The method also predicts low-energy domains in the complex t plane where zeros of the form factors are excluded. The results are useful for K{sub l3} data analyses and provide theoretical underpinning for recent phenomenological dispersive representations for the form factors.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Toward FAIR Representations of Microbial Interactions

Despite an ever-growing number of data sets that catalog and characterize interactions between microbes in different environments and conditions, many of these data are neither easily accessible nor intercompatible. These limitations present a major challenge to microbiome research by hindering the streamlined drawing of inferences across studies.

59 BASIC BIOLOGICAL SCIENCES↗

Message-passing neural networks for high-throughput polymer screening

Machine learning methods have shown promise in predicting molecular properties, and given sufficient training data, machine learning approaches can enable rapid high-throughput virtual screening of large libraries of compounds. Graph-based neural network architectures have emerged in recent years as the most successful approach for predictions based on molecular structure and have consistently achieved the best performance on benchmark quantum chemical datasets. However, these models have typically required optimized 3D structural information for the molecule to achieve the highest accuracy. These 3D geometries are costly to compute for high levels of theory, limiting the applicability and practicality of machine learning methods in high-throughput screening applications. In this study, we present a new database of candidate molecules for organic photovoltaic applications, comprising approximately 91,000 unique chemical structures. Compared to existing datasets, this dataset contains substantially larger molecules (up to 200 atoms) as well as extrapolated properties for long polymer chains. We show that message-passing neural networks trained with and without 3D structural information for these molecules achieve similar accuracy, comparable to state-of-the-art methods on existing benchmark datasets. Furthermore, these results therefore emphasize that for larger molecules with practical applications, near-optimal prediction results can be obtained without using optimized 3D geometry as an input. We further show that learned molecular representations can be leveraged to reduce the training data required to transfer predictions to a new density functional theory functional.

14 SOLAR ENERGY↗

A representation-independent electronic charge density database for crystalline materials

Abstract In addition to being the core quantity in density-functional theory, the charge density can be used in many tertiary analyses in materials sciences from bonding to assigning charge to specific atoms. The charge density is data-rich since it contains information about all the electrons in the system. With the increasing prevalence of machine-learning tools in materials sciences, a data-rich object like the charge density can be utilized in a wide range of applications. The database presented here provides a modern and user-friendly interface for a large and continuously updated collection of charge densities as part of the Materials Project. In addition to the charge density data, we provide the theory and code for changing the representation of the charge density which should enable more advanced machine-learning studies for the broader community.

36 MATERIALS SCIENCE↗

Converting tabular data into images for deep learning with convolutional neural networks

Abstract Convolutional neural networks (CNNs) have been successfully used in many applications where important information about data is embedded in the order of features, such as speech and imaging. However, most tabular data do not assume a spatial relationship between features, and thus are unsuitable for modeling using CNNs. To meet this challenge, we develop a novel algorithm, image generator for tabular data (IGTD), to transform tabular data into images by assigning features to pixel positions so that similar features are close to each other in the image. The algorithm searches for an optimized assignment by minimizing the difference between the ranking of distances between features and the ranking of distances between their assigned pixels in the image. We apply IGTD to transform gene expression profiles of cancer cell lines (CCLs) and molecular descriptors of drugs into their respective image representations. Compared with existing transformation methods, IGTD generates compact image representations with better preservation of feature neighborhood structure. Evaluated on benchmark drug screening datasets, CNNs trained on IGTD image representations of CCLs and drugs exhibit a better performance of predicting anti-cancer drug response than both CNNs trained on alternative image representations and prediction models trained on the original tabular data.

59 BASIC BIOLOGICAL SCIENCES↗