Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “hierarchical models”

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 235 records · Page 13
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Exploring the energy landscape of RBMs: reciprocal space insights into bosons, hierarchical learning and symmetry breaking

Deep generative models have become ubiquitous due to their ability to learn and sample from complex distributions. Despite the proliferation of various frameworks, the relationships among these models remain largely unexplored, a gap that hinders the development of a unified theory of AI learning. In this work, we address two central challenges: clarifying the connections between different deep generative models and deepening our understanding of their learning mechanisms. We focus on Restricted Boltzmann Machines (RBMs), a class of generative models known for their universal approximation capabilities for discrete distributions. By introducing a reciprocal space formulation for RBMs, we reveal a connection between these models, diffusion processes, and systems of coupled bosons. Our analysis shows that at initialization, the RBM operates at a saddle point, where the local curvature is determined by the singular values of the weight matrix, whose distribution follows the Marc̆enko-Pastur law and exhibits rotational symmetry. During training, this rotational symmetry is broken due to hierarchical learning, where different degrees of freedom progressively capture features at multiple levels of abstraction. This leads to a symmetry breaking in the energy landscape, reminiscent of Landau’s theory. This symmetry breaking in the energy landscape is characterized by the singular values and the weight matrix eigenvector matrix. We derive the corresponding free energy in a mean-field approximation. We show that in the limit of infinite size RBM, the reciprocal variables are Gaussian distributed. Our findings indicate that in this regime, there will be some modes for which the diffusion process will not converge to the Boltzmann distribution. To illustrate our results, we trained replicas of RBMs with different hidden layer sizes using the MNIST dataset. Our findings not only bridge the gap between disparate generative frameworks but also shed light on the fundamental processes underpinning learning in deep generative models.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Including Physics-Informed Atomization Constraints in Neural Networks for Reactive Chemistry

Machine learning interatomic potentials (MLIPs) have emerged as powerful tools for investigating atomistic systems with high accuracy and a relatively low computational cost. However, a common and unaddressed challenge with many current neural network (NN) MLIP models is their limited ability to accurately predict the relative energies of systems containing isolated or nearly isolated atoms, which appear in various reactive processes. To address this limitation, we present a mathematical technique for modifying any existing atom-centered NN architecture to account for the energies of isolated atoms. The result produces a consistent prediction of the atomization energy (AE) of a system using minimal constraints on the model. Using this technique, we build a model architecture that we call hierarchically interacting particle neural network (HIP-NN)-AE, an AE-constrained version of the HIP-NN, as well as ANI-AE, the AE-constrained version of the accurate NN engine for molecular energies (ANI). Our results demonstrate AE consistency of AE-constrained models, which drastically improves the AE predictions for the models. We compare the AE-constrained approach to unconstrained models as well as models from the literature in other scenarios, such as bond dissociation energies, bond dissociation pathways, and extensibility tests. These results show that the constraints improve the model performance in some of these tasks and do not negatively affect the performance on any tasks. The AE constraint approach thus offers a robust solution to the challenges posed by isolated atoms in energy prediction tasks.

74 ATOMIC AND MOLECULAR PHYSICS↗
DOE OSTI2025

ThinCurr: An open-source 3D thin-wall eddy current modeling code for the analysis of large-scale systems of conducting structures

In this paper we present a new thin-wall eddy current modeling code, ThinCurr, for studying inductively-coupled currents in 3D conducting structures -- with primary application focused on the interaction between currents flowing in coils, plasma, and conducting structures of magnetically-confined plasma devices. The code utilizes a boundary finite element method on an unstructured, triangular grid to accurately capture device structures. The new code, part of the broader Open FUSION Toolkit, is open-source and designed for ease of use without sacrificing capability and speed through a combination of Python, Fortran, and C/C++ components. Scalability to large models is enabled through use of hierarchical off-diagonal low-rank compression of the inductance matrix, which is otherwise dense. Ease of handling large models of complicated geometry is further supported by automatic determination of supplemental elements through a greedy homology approach. Here, a detailed description of the numerical methods of the code and verification of the implementation of those methods using cross-code comparisons against the VALEN code and Ansys commercial analysis software is shown.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

A deep learning approach to identify missing is-a relations in SNOMED CT

Abstract Objective SNOMED CT is the largest clinical terminology worldwide. Quality assurance of SNOMED CT is of utmost importance to ensure that it provides accurate domain knowledge to various SNOMED CT-based applications. In this work, we introduce a deep learning-based approach to uncover missing is-a relations in SNOMED CT. Materials and Methods Our focus is to identify missing is-a relations between concept-pairs exhibiting a containment pattern (ie, the set of words of one concept being a proper subset of that of the other concept). We use hierarchically related containment concept-pairs as positive instances and hierarchically unrelated containment concept-pairs as negative instances to train a model predicting whether an is-a relation exists between 2 concepts with containment pattern. The model is a binary classifier leveraging concept name features, hierarchical features, enriched lexical attribute features, and logical definition features. We introduce a cross-validation inspired approach to identify missing is-a relations among all hierarchically unrelated containment concept-pairs. Results We trained and applied our model on the Clinical finding subhierarchy of SNOMED CT (September 2019 US edition). Our model (based on the validation sets) achieved a precision of 0.8164, recall of 0.8397, and F1 score of 0.8279. Applying the model to predict actual missing is-a relations, we obtained a total of 1661 potential candidates. Domain experts performed evaluation on randomly selected 230 samples and verified that 192 (83.48%) are valid. Conclusions The results showed that our deep learning approach is effective in uncovering missing is-a relations between containment concept-pairs in SNOMED CT.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

ERF: Energy Research and Forecasting

The Energy Research and Forecasting (ERF) code is a new model that simulates the mesoscale and microscale dynamics of the atmosphere using the latest high-performance computing architectures. It employs hierarchical parallelism using an MPI+X model, where X may be OpenMP on multicore CPU-only systems, or CUDA, HIP, or SYCL on GPU-accelerated systems. ERF is built on AMReX (Zhang et al., 2019, 2021), a block-structured adaptive mesh refinement (AMR) software framework that provides the underlying performance-portable software infrastructure for block-structured mesh operations. The "energy" aspect of ERF indicates that the software has been developed with renewable energy applications in mind. In addition to being a numerical weather prediction model, ERF is designed to provide a flexible computational framework for the exploration and investigation of different physics parameterizations and numerical strategies, and to characterize the flow field that impacts the ability of wind turbines to extract wind energy. The ERF development is part of a broader effort led by the US Department of Energy's Wind Energy Technologies Office.

17 WIND ENERGY↗
DOE OSTI2020

Bottom-Up Meets Top-Down: The Crossroads of Multiscale Chromatin Modeling

Chromatin can be viewed as a hierarchically structured fiber that regulates gene expression. It consists of a complex network of DNA and proteins whose characteristic dynamical modes facilitate compaction and rearrangement in the cell nucleus. These modes stem from chromatin's fundamental unit, the nucleosome, and their effects are propagated across length scales. Understanding the effects of nucleosome dynamics on the chromatin fiber, primarily through post-translational modifications that occur on the histones, is of central importance to epigenetics. Within the last decade, imaging and chromosome conformation capture techniques have revealed a number of structural and statistical features of the packaged chromatin fiber at a hitherto unavailable level of resolution. Such experiments have led to increased efforts to develop polymer models that aim to reproduce, explain, and predict the contact probability scaling and density heterogeneity. At nanometer scales, available models have focused on the role of the nucleosome and epigenetic marks on local chromatin structure. At micrometer scales, existing models have sought to explain scaling laws and density heterogeneity. Less work, however, has been done to reconcile these two approaches: bottom-up and top-down models of chromatin. Here, we highlight the multiscale simulation models that are driving toward an understanding of chromatin structure and function, from the nanometer to the micron scale, and we highlight areas of opportunity and some of the prospects for new frameworks that bridge these two scales. Taken together, experimental and modeling advances over the last few years have established a robust platform for the study of chromatin fiber structure and dynamics, which will be of considerable use to the chromatin community in developing an understanding of the interplay between epigenomic regulation and molecular structure.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

How to Obtain the Redshift Distribution from Probabilistic Redshift Estimates

Abstract A reliable estimate of the redshift distribution n ( z ) is crucial for using weak gravitational lensing and large-scale structures of galaxy catalogs to study cosmology. Spectroscopic redshifts for the dim and numerous galaxies of next-generation weak-lensing surveys are expected to be unavailable, making photometric redshift (photo- z ) probability density functions (PDFs) the next best alternative for comprehensively encapsulating the nontrivial systematics affecting photo- z point estimation. The established stacked estimator of n ( z ) avoids reducing photo- z PDFs to point estimates but yields a systematically biased estimate of n ( z ) that worsens with a decreasing signal-to-noise ratio, the very regime where photo- z PDFs are most necessary. We introduce Cosmological Hierarchical Inference with Probabilistic Photometric Redshifts ( CHIPPR ), a statistically rigorous probabilistic graphical model of redshift-dependent photometry that correctly propagates the redshift uncertainty information beyond the best-fit estimator of n ( z ) produced by traditional procedures and is provably the only self-consistent way to recover n ( z ) from photo- z PDFs. We present the chippr prototype code, noting that the mathematically justifiable approach incurs computational cost. The CHIPPR approach is applicable to any one-point statistic of any random variable, provided the prior probability density used to produce the posteriors is explicitly known; if the prior is implicit, as may be the case for popular photo- z techniques, then the resulting posterior PDFs cannot be used for scientific inference. We therefore recommend that the photo- z community focus on developing methodologies that enable the recovery of photo- z likelihoods with support over all redshifts, either directly or via a known prior probability density.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

A Network-Aware Distributed Energy Resource Aggregation Framework for Flexible, Cost-Optimal, and Resilient Operation

To efficiently use the ubiquitous behind-the-meter distributed energy resources (DERs) in distribution systems for providing grid services, this paper presents a hierarchical control framework for DER optimal aggregation and control. We first develop a convex optimization model to evaluate the DER flexibility, and then use a convex model-predictive-control based approach to dispatch those DERs. The hierarchical control framework consists of a utility controller, community aggregators and multiple home energy management systems. The flexibility of the DERs is evaluated by each controller in the hierarchy such that the resultant flexibility is feasible given its operational domain. Based on the determined flexibility, the hierarchical controllers then compute optimal setpoints for the DERs to help the distribution system regulate node voltages and provide other distribution grid services. Numerical simulations performed on a model of a real distribution feeder in Colorado, using actual DER data in a residential community demonstrate that the proposed approach can effectively alleviate voltage issues and support resilient operation.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2022

Preparing for the next pandemic via transfer learning from existing diseases with hierarchical multi-modal BERT: a study on COVID-19 outcome prediction

Abstract Developing prediction models for emerging infectious diseases from relatively small numbers of cases is a critical need for improving pandemic preparedness. Using COVID-19 as an exemplar, we propose a transfer learning methodology for developing predictive models from multi-modal electronic healthcare records by leveraging information from more prevalent diseases with shared clinical characteristics. Our novel hierarchical, multi-modal model ( $${\textsc {TransMED}}$$ T R A N S MED ) integrates baseline risk factors from the natural language processing of clinical notes at admission, time-series measurements of biomarkers obtained from laboratory tests, and discrete diagnostic, procedure and drug codes. We demonstrate the alignment of $${\textsc {TransMED}}$$ T R A N S MED ’s predictions with well-established clinical knowledge about COVID-19 through univariate and multivariate risk factor driven sub-cohort analysis. $${\textsc {TransMED}}$$ T R A N S MED ’s superior performance over state-of-the-art methods shows that leveraging patient data across modalities and transferring prior knowledge from similar disorders is critical for accurate prediction of patient outcomes, and this approach may serve as an important tool in the early response to future pandemics.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Accelerating eigenvalue computation for nuclear structure calculations via perturbative corrections

Subspace projection methods utilizing perturbative corrections have been proposed for computing the lowest few eigenvalues and corresponding eigenvectors of large Hamiltonian matrices. In this paper, we build upon these methods and introduce the term Subspace Projection with Perturbative Corrections (SPPC) method to refer to this approach. We tailor the SPPC for nuclear many-body Hamiltonians represented in a truncated configuration interaction subspace, i.e., the no-core shell model (NCSM). We use the hierarchical structure of the NCSM Hamiltonian to partition the Hamiltonian as the sum of two matrices. The first matrix corresponds to the Hamiltonian represented in a small configuration space, whereas the second is viewed as the perturbation to the first matrix. Eigenvalues and eigenvectors of the first matrix can be computed efficiently. Because of the split, perturbative corrections to the eigenvectors of the first matrix can be obtained efficiently from the solutions of a sequence of linear systems of equations defined in the small configuration space. These correction vectors can be combined with the approximate eigenvectors of the first matrix to construct a subspace from which more accurate approximations of the desired eigenpairs can be obtained. We show by numerical examples that the SPPC method can be more efficient than conventional iterative methods for solving large-scale eigenvalue problems such as the Lanczos, block Lanczos and the locally optimal block preconditioned conjugate gradient (LOBPCG) method. The method can also be combined with other methods to avoid convergence stagnation.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2026

Multi-resolution enhancement for full-spectrum neural representations

Scientific data acquisition continues to outpace storage and analysis capabilities, making voxel-basedrepresentations increasingly intractable. Implicit neural representations (INRs) offer a promising solutionby encoding signals through coordinate-based neural networks, serving as surrogates of data, withcomputational and storage requirements scaling with network complexity rather than data dimensionality.However, smaller INRs struggle to faithfully represent multiscale structures, high-frequency informationand fine textures that constitute a large proportion of scientific measurements. We propose WIEN-INR, atheoretically guided hierarchical INR framework that distributes modelling across resolution scales andenables improved representation capacity through a novel enhancement network to recover subtle details.This multiscale architecture allows smaller networks to retain the full spatial-frequency content of thesignal as well as preserve training efficiency and lower storage cost. Evaluated on distinct raw experimentalmeasurements across scales and complexities, WIEN-INR represents a practical step towards a broaderadoption of neural representations in scientific workflows, delivering compact, robust and high-fidelityrepresentations.

Ni, Yuan [SLAC National Accelerator Laboratory (SL↗
DOE OSTI2022

pnnl/TransMED

Transfer Learning From Existing Diseases Via Hierarchical Multi-Modal BERT Models

Ham, Colby↗
DOE OSTI2024

PROVABGS: The Probabilistic Stellar Mass Function of the BGS One-percent Survey

We present the probabilistic stellar mass function (pSMF) of galaxies in the DESI Bright Galaxy Survey (BGS), observed during the One-percent Survey. The One-percent Survey was one of DESI's survey validation programs conducted from 2021 April to May, before the start of the main survey. It used the same target selection and similar observing strategy as the main survey and successfully observed the spectra and redshifts of 143,017 galaxies in the r < 19.5 magnitude-limited BGS Bright sample and 95,499 galaxies in the fainter surface-brightness- and color-selected BGS Faint sample over z < 0.6. We derive pSMFs from posteriors of stellar mass, M*, inferred from DESI photometry and spectroscopy using the Hahn et al. PRObabilistic Value-Added BGS (PROVABGS) Bayesian spectral energy distribution modeling framework. We use a hierarchical population inference framework that statistically and rigorously propagates the M* uncertainties. Furthermore, we include correction weights that account for the selection effects and incompleteness of the BGS observations. We present the redshift evolution of the pSMF in BGS, as well as the pSMFs of star-forming and quiescent galaxies classified using average specific star formation rates from PROVABGS. Overall, the pSMFs show good agreement with previous stellar mass function measurements in the literature. Our pSMFs showcase the potential and statistical power of BGS, which in its main survey will observe >100 × more galaxies. Moreover, we present the statistical framework for subsequent population statistics measurements using BGS, which will characterize the global galaxy population and scaling relations at low redshifts with unprecedented precision.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2026

Coupling Noah-Multiparameterization land-surface Model with Energy Research and Forecasting Model

The Energy Research and Forecasting (ERF) model is a high-performance atmospheric model built on the AMReX adaptive mesh refinement (AMR) framework, enabling efficient simulations on heterogeneous computing platforms that combine multicore processors with hardware accelerators. To support land–atmosphere interactions within ERF’s AMR-based environment, a land-surface model must be capable of operating directly on hierarchically refined meshes. In this work, we present a methodology for coupling the Fortran-based Noah-Multiparameterization (Noah-MP) land-surface model with ERF’s C++ codebase. Rather than rewriting Noah-MP, we construct a Fortran–C interoperability layer using CodeScribe, a tool that leverages large language models (LLMs) to automate the generation of interface code. CodeScribe applies structured prompting techniques to generate bindings that support efficient data exchange and function calls between ERF and Noah-MP. The coupling framework also incorporates AMR-aware data handling strategies, allowing NoahMP to operate seamlessly within ERF’s hierarchical mesh structure. This work provides a structured approach for integrating legacy Fortran models into modern C++-based modeling systems using LLM-assisted code generation.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

The effects of well damage and completion designs on geoelectrical responses in mature wellbore environments

Well integrity is one of the major concerns in long-term geologic storage sites due to the potential risk of well leakage and groundwater contamination. Evaluating changes in electrical responses due to energized steel-cased wells has the potential to quantify and predict possible wellbore failures because any kind of breakage or corrosion along highly conductive well casings will have an impact on the distribution of the subsurface electrical potential. However, realistic wellbore-geoelectrical models that can fully capture fine-scale details of well completion design and the state of well damage at the field scale require extensive computational effort, or they can even be intractable to simulate. To overcome this computational burden while still keeping the model realistic, we have used the hierarchical finite-element method that represents electrical conductivity at each dimensional component (1D edges, 2D planes, and 3D cells) of a tetrahedral mesh. This allows well completion designs with real-life geometric scales and well systems with realistic, detailed, progressive corrosion and damage in our models. We have developed a comparison of possible discretization approaches of a multicasing completion design in the finite-element model. The effects of the surface casing and the coupling between concentric well casings as well as the effects of the degree and the location of well damage on the electrical responses are also examined. As a result, we analyze real surface electric field data to detect wellbore integrity failure associated with damage.

58 GEOSCIENCES↗
DOE OSTI2023

Surface and subsurface oceanographic features drive forage fish distributions and aggregations: Implications for prey availability to top predators in the US Northeast Shelf ecosystem

Abstract Forage fishes are a critical food web link in marine ecosystems, aggregating in a hierarchical patch structure over multiple spatial and temporal scales. Surface‐level forage fish aggregations (FFAs) represent a concentrated source of prey available to surface‐ and shallow‐foraging marine predators. Existing survey and analysis methods are often imperfect for studying forage fishes at scales appropriate to foraging predators, making it difficult to quantify predator–prey interactions. In many cases, general distributions of forage fish species are known; however, these may not represent surface‐level prey availability to predators. Likewise, we lack an understanding of the oceanographic drivers of spatial patterns of prey aggregation and availability or forage fish community patterns. Specifically, we applied Bayesian joint species distribution models to bottom trawl survey data to assess species‐ and community‐level forage fish distribution patterns across the US Northeast Continental Shelf (NES) ecosystem. Aerial digital surveys gathered data on surface FFAs at two project sites within the NES, which we used in a spatially explicit hierarchical Bayesian model to estimate the abundance and size of surface FFAs. We used these models to examine the oceanographic drivers of forage fish distributions and aggregations. Our results suggest that, in the NES, regions of high community species richness are spatially consistent with regions of high surface FFA abundance. Bathymetric depth drove both patterns, while subsurface features, such as mixed layer depth, primarily influenced aggregation behavior and surface features, such as sea surface temperature, sub‐mesoscale eddies, and fronts influenced forage fish diversity. In combination, these models help quantify the availability of forage fishes to marine predators and represent a novel application of spatial models to aerial digital survey data.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Structure‐Aware Representation Learning for Effective Performance Prediction

ABSTRACT Application performance is a function of several unknowns stemming from the interactions between the application, runtime, OS, and underlying hardware, making it challenging to model performance using deep learning techniques, especially without a large labeled dataset. Collecting such labeled longitudinal datasets can take weeks. Intuitively, developers could save analysis time during code development by taking a comparative approach between multiple applications. However, the unknown dynamic interactions between applications and execution environments make it difficult for deep learning‐based models to predict the performance of new applications. In this paper, we address these problems by presenting a labeled dataset for the community and taking a comparative analysis approach to explore the source code differences between different correct implementations of the same problem. This paper assesses the feasibility of using purely static information, for example, Abstract Syntax Tree (AST), of applications to predict performance change based on code structure. We evaluate several deep learning‐based representation learning techniques for source code and propose an architecture for the tree‐based Long Short‐Term Memory (LSTM) models to discover latent representations for a source code's hierarchical structure. We demonstrate that our proposed architecture enables feed‐forward predictive models to predict change in performance using source code with up to 84% accuracy.

Ramadan, Tarek [Department of Computer Science Tex↗