Search NASA⌕ Search

SEARCH · Search NASA

Results for “network architecture”

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 OSTI2026

ZENN: A thermodynamics-inspired computational framework for heterogeneous data–driven modeling

Traditional entropy-based methods—such as cross-entropy loss in classification problems—have long been essential tools for representing the information uncertainty and physical disorder in data and for developing artificial intelligence algorithms. However, the rapid growth of data across various domains has introduced new challenges, particularly the integration of heterogeneous datasets with intrinsic disparities. To address this, we introduce a zentropy-enhanced neural network (ZENN), extending zentropy theory into the data science domain via intrinsic entropy, enabling more effective learning from heterogeneous data sources. ZENN simultaneously learns both energy and intrinsic entropy components, capturing the underlying structure of multisource data. To support this, we redesign the neural network architecture to better reflect the intrinsic properties and variability inherent in diverse datasets. We demonstrate the effectiveness of ZENN on classification tasks and energy landscape reconstructions, showing its superior generalization capabilities and robustness-particularly in predicting high-order derivatives. In image and text classification tasks, ZENN demonstrates superior generalization by introducing a learnable temperature variable that models latent multisource heterogeneity, allowing it to surpass state-of-the-art models on CIFAR-10/100, BBC News, and AG News. As a practical application in materials science, we employ ZENN to reconstruct the Helmholtz energy landscape of Fe3Pt using data generated from density functional theory and capture key material behaviors, including negative thermal expansion and the critical point in the temperature–pressure space. Overall, this work presents a zentropy-grounded framework for data-driven machine learning, positioning ZENN as a versatile and robust approach for scientific problems involving complex, heterogeneous datasets.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Extracting the gamma-ray source-count distribution below the Fermi-LAT detection limit with deep learning

We reconstruct the extra-galactic gamma-ray source-count distribution, or dN/dS, of resolved and unresolved sources by adopting machine learning techniques. Specifically, we train a convolutional neural network on synthetic 2-dimensional sky-maps, which are built by varying parameters of underlying source-counts models and incorporate the Fermi-LAT instrumental response functions. The trained neural network is then applied to the Fermi-LAT data, from which we estimate the source count distribution down to flux levels a factor of 50 below the Fermi-LAT threshold. We perform our analysis using 14 years of data collected in the (1,10) GeV energy range. The results we obtain show a source count distribution which, in the resolved regime, is in excellent agreement with the one derived from cataloged sources, and then extends as dN/dS ~ S -2 in the unresolved regime, down to fluxes of 5 · 10 -12 cm -2 s -1 . The neural network architecture and the devised methodology have the flexibility to enable future analyses to study the energy dependence of the source-count distribution.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

Using graph neural networks to reconstruct charged pion showers in the CMS High Granularity Calorimeter

A novel method to reconstruct the energy of hadronic showersin the CMS High Granularity Calorimeter (HGCAL) is presented. TheHGCAL is a sampling calorimeter with very fine transverse andlongitudinal granularity. The active media are silicon sensors andscintillator tiles readout by SiPMs and the absorbers are acombination of lead and Cu/CuW in the electromagnetic section, andsteel in the hadronic section. The shower reconstruction method isbased on graph neural networks and it makes use of a dynamicreduction network architecture. It is shown that the algorithm isable to capture and mitigate the main effects that normally hinderthe reconstruction of hadronic showers using classicalreconstruction methods, by compensating for fluctuations in themultiplicity, energy, and spatial distributions of the shower'sconstituents. The performance of the algorithm is evaluated usingtest beam data collected in 2018 prototype of the CMS HGCALaccompanied by a section of the CALICE AHCAL prototype. Thecapability of the method to mitigate the impact of energy leakagefrom the calorimeter is also demonstrated.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2026

Neural posterior unfolding

Differential cross section measurements are the currency of scientific exchange in particle and nuclear physics. A key challenge for these analyses is the correction for detector distortions, known as deconvolution or unfolding. Binned unfolding of cross section measurements traditionally rely on the regularized inversion of the response matrix that represents the detector response, mapping pre-detector (`particle level') observables to post-detector (`detector level') observables. In this paper we introduce Neural Posterior Unfolding, a modern, Bayesian approach that leverages normalizing flows for unfolding. By using normalizing flows for neural posterior estimation, NPU offers several key advantages including implicit regularization through the neural network architecture, fast amortized inference that eliminates the need for repeated retraining, and direct access to the full uncertainty in the unfolded result. In addition to introducing NPU, we implement a classical Bayesian unfolding method called Fully Bayesian Unfolding (FBU) in modern Python so it can also be studied. These tools are validated on simple Gaussian examples and then tested on simulated jet substructure examples from the Large Hadron Collider (LHC). We find that the Bayesian methods are effective and worth additional development to be analysis ready for cross section measurements at the LHC and beyond.

Analysis and statistical methods↗
DOE OSTI2022

Real-time semantic segmentation on FPGAs for autonomous vehicles with hls4ml

In this paper, we investigate how field programmable gate arrays can serve as hardware accelerators for real-time semantic segmentation tasks relevant for autonomous driving. Considering compressed versions of the ENet convolutional neural network architecture, we demonstrate a fully-on-chip deployment with a latency of 4.9 ms per image, using less than 30% of the available resources on a Xilinx ZCU102 evaluation board. The latency is reduced to 3 ms per image when increasing the batch size to ten, corresponding to the use case where the autonomous vehicle receives inputs from multiple cameras simultaneously. We show, through aggressive filter reduction and heterogeneous quantization-aware training, and an optimized implementation of convolutional layers, that the power consumption and resource utilization can be significantly reduced while maintaining accuracy on the Cityscapes dataset.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

Simultaneous energy and mass calibration of large-radius jets with the ATLAS detector using a deep neural network

The energy and mass measurements of jets are crucial tasks for the Large Hadron Collider experiments. This paper presents a new calibration method to simultaneously calibrate these quantities for large-radius jets measured with the ATLAS detector using a deep neural network (DNN). To address the specificities of the calibration problem, special loss functions and training procedures are employed, and a complex network architecture, which includes feature annotation and residual connection layers, is used. The DNN-based calibration is compared to the standard numerical approach in an extensive series of tests. The DNN approach is found to perform significantly better in almost all of the tests and over most of the relevant kinematic phase space. In particular, it consistently improves the energy and mass resolutions, with a 30% better energy resolution obtained for transverse momenta $p$ T > $500$ GeV.

47 OTHER INSTRUMENTATION↗
DOE OSTI2024

Forecasting high-dimensional spatio-temporal systems from sparse measurements

This paper introduces a new neural network architecture designed to forecast high-dimensional spatio-temporal data using only sparse measurements. The architecture uses a two-stage end-to-end framework that combines neural ordinary differential equations (NODEs) with vision transformers. Initially, our approach models the underlying dynamics of complex systems within a low-dimensional space; and then it reconstructs the corresponding high-dimensional spatial fields. Many traditional methods involve decoding high-dimensional spatial fields before modeling the dynamics, while some other methods use an encoder to transition from high-dimensional observations to a latent space for dynamic modeling. In contrast, our approach directly uses sparse measurements to model the dynamics, bypassing the need for an encoder. This direct approach simplifies the modeling process, reduces computational complexity, and enhances the efficiency and scalability of the method for large datasets. We demonstrate the effectiveness of our framework through applications to various spatio-temporal systems, including fluid flows and global weather patterns. Although sparse measurements have limitations, our experiments reveal that they are sufficient to forecast system dynamics accurately over long time horizons. Our results also indicate that the performance of our proposed method remains robust across different sensor placement strategies, with further improvements as the number of sensors increases. This robustness underscores the flexibility of our architecture, particularly in real-world scenarios where sensor data is often sparse and unevenly distributed.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Energy metric prediction for double insertion mutants via the RoseNet deep learning framework

Studying the structural and functional implications of protein mutations is an important task in computational biology and bioinformatics. We leverage our previously proposed RoseNet neural network architecture to predict energy metrics of proteins with double amino acid insertions or deletions (InDels). We train models on previously generated benchmark datasets containing the exhaustive double InDel mutations for three proteins, as well as an additional three proteins for which ∼145k random mutants, each with two InDels, have been generated. We expand on our previous work by evaluating three additional proteins and analyzing domain features that impact the prediction capabilities of RoseNet. These features include InDels into secondary structures and the solvent accessible surface area (SASA) scores of the residues. We uncover further evidence to support that RoseNet has a higher proficiency of generalizing to unseen residue combinations than unseen insertion positions. We also observe that RoseNet produces higher-quality predictions when inserting into a β-sheet over an α-helix. Additionally, when the insertions fall in an area of high SASA, RoseNet often displays better performance than inserting into areas of low SASA.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2026

Knowledge-guided learning with curated prior genetic biomarkers for robust model interpretation

Abstract Motivation Knowledge-guided learning offers effective and robust model training strategies in data-scarce settings by incorporating established domain knowledge, thereby enhancing generalization, robustness, and interpretability. By contrast, conventional deep learning approaches rely purely on data-driven learning, which can limit robust model interpretability, particularly in high-dimensional settings with limited size samples. In computational biology, knowledge-guided learning has primarily leveraged network- and structural-based knowledge, leading to biologically interpretable representations and enhanced predictive performance compared to conventional approaches. However, curated biomarkers, one of the most accessible forms of biological knowledge, remain largely unexplored within knowledge-guided paradigms. Results In this study, we propose a model-agnostic training paradigm, Biomarker-driven Explainable Prior-guided Learning (BioExPL), that can be applied to any neural networks that incorporates curated prior knowledge. BioExPL enforces neural networks to reflect curated biomarker priors in their latent representations through a novel knowledge-alignment loss. BioExPL consistently demonstrated significantly improved predictive performance and enhanced model interpretability with minimized computational overhead in simulation studies and intensive experiments on multiple cancer datasets. BioExPL not only integrates prior curated knowledge into the model but also accurately identifies unknown associated signals additionally. BioExPL is model-agnostic and domain-independent, enabling its integration into diverse neural network architectures. Availability and implementation The open-source is publicly available at: https://github.com/datax-lab/BioExPL.

Baek, Beomsu [Department of Computer Science, Univ↗
DOE OSTI2023

Fungal drops: a novel approach for macro- and microscopic analyses of fungal mycelial growth

Abstract This study presents an inexpensive approach for the macro- and microscopic observation of fungal mycelial growth. The ‘fungal drops’ method allows to investigate the development of a mycelial network in filamentous microorganisms at the colony and hyphal scales. A heterogeneous environment is created by depositing 15–20 µl drops on a hydrophobic surface at a fixed distance. This system is akin to a two-dimensional (2D) soil-like structure in which aqueous-pockets are intermixed with air-filled pores. The fungus (spores or mycelia) is inoculated into one of the drops, from which hyphal growth and exploration take place. Hyphal structures are assessed at different scales using stereoscopic and microscopic imaging. The former allows to evaluate the local response of regions within the colony (modular behaviour), while the latter can be used for fractal dimension analyses to describe the hyphal network architecture. The method was tested with several species to underpin the transferability to multiple species. In addition, two sets of experiments were carried out to demonstrate its use in fungal biology. First, mycelial reorganization of Fusarium oxysporum was assessed as a response to patches containing different nutrient concentrations. Second, the effect of interactions with the soil bacterium Pseudomonas putida on habitat colonization by the same fungus was assessed. This method appeared as fast and accessible, allowed for a high level of replication, and complements more complex experimental platforms. Coupled with image analysis, the fungal drops method provides new insights into the study of fungal modularity both macroscopically and at a single-hypha level.

Buffi, Matteo↗
DOE OSTI2021

El-CID: a filter for gravitational-wave electromagnetic counterpart identification

ABSTRACT As gravitational-wave (GW) interferometers become more sensitive and probe ever more distant reaches, the number of detected binary neutron star mergers will increase. However, detecting more events farther away with GWs does not guarantee corresponding increase in the number of electromagnetic counterparts of these events. Current and upcoming wide-field surveys that participate in GW follow-up operations will have to contend with distinguishing the kilonova (KN) from the ever increasing number of transients they detect, many of which will be consistent with the GW sky-localization. We have developed a novel tool based on a temporal convolutional neural network architecture, trained on sparse early-time photometry and contextual information for Electromagnetic Counterpart Identification (El-CID). The overarching goal for El-CID is to slice through list of new transient candidates that are consistent with the GW sky localization, and determine which sources are consistent with KNe, allowing limited target-of-opportunity resources to be used judiciously. In addition to verifying the performance of our algorithm on an extensive testing sample, we validate it on AT2017gfo – the only EM counterpart of a binary neutron star merger discovered to date – and AT2019npv – a supernova that was initially suspected as a counterpart of the GW event, GW190814, but was later ruled out after further analysis.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

Photometric identification of compact galaxies, stars, and quasars using multiple neural networks

We present MargNet, a deep learning-based classifier for identifying stars, quasars, and compact galaxies using photometric parameters and images from the Sloan Digital Sky Survey Data Release 16 catalogue. MargNet consists of a combination of convolutional neural network and artificial neural network architectures. Using a carefully curated data set consisting of 240 000 compact objects and an additional 150 000 faint objects, the machine learns classification directly from the data, minimizing the need for human intervention. MargNet is the first classifier focusing exclusively on compact galaxies and performs better than other methods to classify compact galaxies from stars and quasars, even at fainter magnitudes. This model and feature engineering in such deep learning architectures will provide greater success in identifying objects in the ongoing and upcoming surveys, such as Dark Energy Survey and images from the Vera C. Rubin Observatory.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Deep learning Hamiltonians from disordered image data in quantum materials

The capabilities of image probe experiments are rapidly expanding, providing new information about quantum materials on unprecedented length- and timescales. Many such materials feature inhomogeneous electronic properties with intricate pattern formation on the observable surface. This rich spatial structure contains information about interactions, dimensionality, and disorder—a spatial encoding of the Hamiltonian driving the pattern formation. Image recognition techniques from machine learning are an excellent tool for interpreting information encoded in the spatial relationships in such images. Here, we develop a deep learning framework for using the rich information available in these spatial correlations in order to discover the underlying Hamiltonian driving the patterns. We first vet the method on a known case, scanning near-field optical microscopy on a thin film of V⁢O 2 . We then apply our trained convolutional neural network architecture to new optical microscope images of a different V⁢O 2 film as it goes through the metal-insulator transition. We find that a two-dimensional Hamiltonian with both interactions and random field disorder is required to explain the intricate, fractal intertwining of metal and insulator domains during the transition. This detailed knowledge about the underlying Hamiltonian paves the way for using the model to control the pattern formation via, e.g., tailored hysteresis protocols. Finally, we also introduce a distribution-based confidence measure on the results of a multilabel classifier, which does not rely on adversarial training. In addition, we propose a machine-learning-based criterion for diagnosing a physical system's proximity to criticality.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2024

Probabilistic neural networks for improved analyses with phenomenological R -matrix

Here we present a method for measurement analyses based on probabilistic deep neural networks that provide several advantages over conventional analyses with phenomenological models. These include predicting physical quantities directly from data, the rapid generation of statistically robust uncertainties, and the ability to bypass some parameters that may induce ambiguities and complications in data analysis. As deep learning methods make predictions through “black boxes,” the uncertainty quantification is typically challenging. We use a probabilistic framework that provides thorough uncertainty quantification and is straightforward to follow in practice. With the network architecture based on the Transformer, we demonstrate the current method for predicting nuclear resonance parameters from scattering data using the phenomenological R-matrix model.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2024

Exploring the synergy of kinematics and dynamics for collider physics

In collider experiments, an event is characterized by two distinct yet mutually complementary features: the “global features” and the “local features.” Kinematic information such as the event topology of a hard process, masses, and spins of particles comprises global features spanning the entire phase space. This global feature can be inferred from reconstructed objects. In contrast, representations of particles in gauge groups, such as quantum chromodynamics (QCD), offer localized features revealing the dynamics of an underlying theory. These local features, particularly observed in the patterns of radiation as raw data in various detector components, complement the global kinematic features. We propose a simple but effective neural network architecture that seamlessly integrates information from both kinematics and QCD to enhance the signal sensitivity at colliders. Published by the American Physical Society 2024

Ban, Kayoung (ORCID:000000019691877X)↗
DOE OSTI2023

Point-particle drag, lift, and torque closure models using machine learning: Hierarchical approach and interpretability

Developing deterministic neighborhood-informed point-particle closure models using machine learning has garnered interest recently from the dispersed multiphase flow community. The robustness of neural models for this complex multibody problem is hindered by the availability of particle-resolved data. Here, the present work addresses this unavoidable limitation of data paucity by implementing two strategies: (1) by using a rotation and reflection equivariant neural network and (2) by pursuing a physics-based hierarchical machine learning approach. The resulting machine-learned models are observed to achieve a maximum accuracy of 85% and 96% in the prediction of neighbor-induced force and torque fluctuations, respectively, for a wide range of Reynolds number and volume fraction conditions considered. Furthermore, we pursue force and torque network architectures that provide universal prediction spanning a wide range of Reynolds number (0.25 ≤ Re ≤250) and particle volume fraction (0 ≤ φ ≤0.4). The hierarchical nature of the approach enables improved prediction of quantities such as streamwise torque, by going beyond binary interactions to include trinary interactions.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2025

Autoregressive neural quantum states of Fermi Hubbard models

Neural quantum states (NQSs) have emerged as a powerful ansatz for variational quantum Monte Carlo studies of strongly correlated systems. Here, we apply recurrent neural networks (RNNs) and autoregressive transformer neural networks to the Fermi-Hubbard and the (non-Hermitian) Hatano-Nelson-Hubbard models in one and two dimensions. In both cases, we observe that the convergence of the RNN ansatz is challenged when increasing the interaction strength. We present a physically motivated and easy-to-implement strategy for improving the optimization, namely, by ramping of the model parameters. Furthermore, we investigate the advantages and disadvantages of the autoregressive sampling property of both network architectures. For the Hatano-Nelson-Hubbard model, we identify convergence issues that stem from the autoregressive sampling scheme in combination with the non-Hermitian nature of the model. Our findings provide insights into the challenges of the NQS approach and make the first step towards exploring strongly correlated electrons using this ansatz. Published by the American Physical Society 2025

Ibarra-García-Padilla, Eduardo (ORCID:000000019165↗
DOE OSTI2025

A Parallel Alternative for Energy-Efficient Neural Network Training and Inferencing

Energy efficiency of training and inferencing with large neural network models is a critical challenge facing the future of sustainable large-scale machine learning workloads. This paper introduces an alternative strategy, called phantom parallelism, to minimize the net energy consumption of traditional tensor (model) parallelism, the most energy-inefficient component of large neural network training. The approach is presented in the context of feed-forward network architectures as a preliminary, but comprehensive, proof-of-principle study of the proposed methodology. We derive new forward and backward propagation operators for phantom parallelism, implement them as custom autograd operations within an end-to-end phantom parallel training pipeline and compare its parallel performance and energy-efficiency against those of conventional tensor parallel training pipelines. Formal analyses that predict lower bandwidth and FLOP counts are presented with supporting empirical results on up to 256 GPUs that corroborate these gains. Experiments are shown to deliver ∼50% reduction in the energy consumed to train FFNs using the proposed phantom parallel approach when compared with conventional tensor parallel methods. Additionally, the proposed approach is shown to train smaller phantom models to the same model loss on smaller GPU counts as larger tensor parallel models on larger GPU counts offering the possibility for even greater energy savings.

Seal, Sudip [ORNL] (ORCID:0000000332330656)↗