Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “residual 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 163 records · Page 9
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Cross-reactive immunogenicity of group A streptococcal vaccines designed using a recurrent neural network to identify conserved M protein linear epitopes

The M protein of group A streptococci (Strep A) is a major virulence determinant and protective antigen. The N-terminal sequence of the protein defines the more than 200 M types of Strep A and also contains epitopes that elicit opsonic antibodies, some of which cross-react with heterologous M types. Current efforts to develop broadly protective M protein-based vaccines are directed at identifying potential cross-protective epitopes located in the N-terminal regions of cluster-related M proteins for use as vaccine antigens. In this study, we have used a comprehensive approach using the recurrent neural network ABCpred and IEDB epitope conservancy analysis tools to predict 16 residue linear B-cell epitopes from 117 clinically relevant M types of Strep A (~88% of global Strep A infections). Furthermore, to examine the immunogenicity of these epitope-based vaccines, nine peptides that together shared ≥60% sequence identity with 37 heterologous M proteins were incorporated into two recombinant hybrid protein vaccines, in which the epitopes were repeated 2 or 3 times, respectively. The combined immune responses of immunized rabbits showed that the vaccines elicited significant levels of antibodies against all nine vaccine epitopes present in homologous N-terminal 1–50 amino acid synthetic M peptides, as well as cross-reactive antibodies against 16 of 37 heterologous M peptides predicted to contain similar epitopes. The epitope-specificity of the cross-reactive antibodies was confirmed by ELISA inhibition assays and functional opsonic activity was assayed in HL-60-based bactericidal assays. The results provide important information for the future design of broadly protective M protein-based Strep A vaccines.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2021

Systematic KMTNet Planetary Anomaly Search. I. OGLE-2019-BLG-1053Lb, a Buried Terrestrial Planet

In order to exhume the buried signatures of “missing planetary caustics” in Korea Microlensing Telescope Network (KMTNet) data, we conducted a systematic anomaly search of the residuals from point-source point-lens fits, based on a modified version of the KMTNet EventFinder algorithm. This search revealed the lowest-mass-ratio planetary caustic to date in the microlensing event OGLE-2019-BLG-1053, for which the planetary signal had not been noticed before. The planetary system has a planet–host mass ratio of q = (1.25 ± 0.13) × 10{sup -5}. A Bayesian analysis yielded estimates of the mass of the host star, M{sub host}=0.61{sub -0.24}{sup +0.29} M{sub ⊙}, the mass of its planet, M{sub planet}=2.48{sub -0.98}{sup +1.19} M{sub ⊕}, the projected planet–host separation, a{sub ⊥}=3.4{sub -0.5}{sup +0.5} au, and the lens distance, D{sub L}=6.8{sub -0.9}{sup +0.6} kpc. The discovery of this very-low-mass-ratio planet illustrates the utility of our method and opens a new window for a large and homogeneous sample to study the microlensing planet–host mass ratio function down to q ~ 10{sup -5}.

47 OTHER INSTRUMENTATION↗
DOE OSTI2024

Monitoring covariance in multivariate time series: Comparing machine learning and statistical approaches

Abstract In complex systems with multiple variables monitored at high‐frequency, variables are not only temporally autocorrelated, but they may also be nonlinearly related or exhibit nonstationarity as the inputs or operation changes. One approach to handling such variables is to detrend them prior to monitoring and then apply control charts that assume independence and stationarity to the residuals. Monitoring controlled systems is even more challenging because the control strategy seeks to maintain variables at prespecified mean levels, and to compensate, correlations among variables may change, making monitoring the covariance essential. In this paper, a vector autoregressive model (VAR) is compared with a multivariate random forest (MRF) and a neural network (NN) for detrending multivariate time series prior to monitoring the covariance of the residuals using a multivariate exponentially weighted moving average (MEWMA) control chart. Machine learning models have an advantage when the data's structure is unknown or may change. We design a novel simulation study with nonlinear, nonstationary, and autocorrelated data to compare the different detrending models and subsequent covariance monitoring. The machine learning models have superior performance for nonlinear and strongly autocorrelated data and similar performance for linear data. An illustration with data from a reverse osmosis process is given.

Weix, Derek↗
DOE OSTI2021

Combination of deep neural network with attention mechanism enhances the explainability of protein contact prediction

Abstract Deep learning has emerged as a revolutionary technology for protein residue‐residue contact prediction since the 2012 CASP10 competition. Considerable advancements in the predictive power of the deep learning‐based contact predictions have been achieved since then. However, little effort has been put into interpreting the black‐box deep learning methods. Algorithms that can interpret the relationship between predicted contact maps and the internal mechanism of the deep learning architectures are needed to explore the essential components of contact inference and improve their explainability. In this study, we present an attention‐based convolutional neural network for protein contact prediction, which consists of two attention mechanism‐based modules: sequence attention and regional attention. Our benchmark results on the CASP13 free‐modeling targets demonstrate that the two attention modules added on top of existing typical deep learning models exhibit a complementary effect that contributes to prediction improvements. More importantly, the inclusion of the attention mechanism provides interpretable patterns that contain useful insights into the key fold‐determining residues in proteins. We expect the attention‐based model can provide a reliable and practically interpretable technique that helps break the current bottlenecks in explaining deep neural networks for contact prediction. The source code of our method is available at https://github.com/jianlin-cheng/InterpretContactMap .

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2026

Learning interpretable surface elasticity properties from bulk properties via neural network equation learners

Surface elasticity is central to understanding the mechanics and stability of surfaces and interfaces. It is characterized by quantities such as surface tension, residual surface stress, and surface stiffness. However their analytical expressions are typically difficult to derive from atomistic data, and depend strongly on modeling choices. This work presents a neural network-based equation learner which combines customized activation functions and connection-based pruning to discover parsimonious, closed-form equations for surface elasticity from atomistic simulations. Applying the method to seven face-centered cubic (FCC) metals, our equation learner uncovers interpretable equations that describe both low-Miller index and high-Miller index surface properties, capturing long-tail property distributions accurately. The discovered expressions are decoupled into two components: a universal, geometry-driven orientation function, and material-specific baseline coefficients. We find that lower-order properties such as surface tension are fundamentally geometry dependent, while higher-order properties such as surface stress and elasticity show more complex geometry and material dependence. We also relate material dependent coefficients to bulk properties, forming a clear map from bulk material properties to surface elasticity. Overall, this approach demonstrates that interpretable neurosymbolic machine learning can bridge the gap between atomistic simulations and physical laws, enabling the discovery of generalizable structure–property relationships for materials science phenomena such as surface elasticity.

Equation learning↗
DOE OSTI2026

Causality-respecting adaptive refinement for PINNs: enabling precise interface evolution in phase field modeling

Physics-informed neural networks (PINNs) have emerged as a powerful tool for solving physical systems described by partial differential equations (PDEs). However, their accuracy in dynamical systems, particularly those involving sharp moving boundaries with complex initial morphologies, remains a challenge. Here, this study introduces an approach combining residual-based adaptive refinement (RBAR) with causality-informed training to enhance the performance of PINNs in solving spatio-temporal PDEs. Our method employs a three-step iterative process: initial causality-based training, RBAR-guided domain refinement, and subsequent causality training on the refined mesh. Applied to the Allen-Cahn equation, a widely-used model in phase field simulations, our approach demonstrates significant improvements in solution accuracy and computational efficiency over traditional PINNs. Notably, we observe an ‘overshoot and relocate’ phenomenon in dynamic cases with complex morphologies, showcasing the method’s adaptive error correction capabilities. This synergistic interaction between RBAR and causality training enables accurate capture of interface evolution, even in challenging scenarios where traditional PINNs fail. Our framework not only resolves the limitations of uniform refinement strategies but also provides a generalizable methodology for solving a broad range of spatio-temporal PDEs. The enhanced performance of the RBAR–causality combined framework demonstrates its strong potential for advancing PINN-based modeling of physical systems characterized by complex, evolving interfaces.

Allen-Cahn equations↗
DOE OSTI2020

Network structure in alteration layer of boroaluminosilicate glass formed by aqueous corrosion

Exogenously-added LiCl has been shown to slightly accelerate the corrosion rate of a boroaluminosilicate glass called International Simple Glass (ISG) in aqueous solutions over forward- and residual-rate regimes, while KCl and CsCl impede. To understand the effect of exogenously added electrolytes on resulting hydrous species and the network structure of alteration layers, infrared spectroscopy was implemented. It was found that the fraction of molecular water relative to the surface-bound hydroxyl species is lower in the KCl and CsCl conditions compared to the LiCl and pure water conditions. An approximation for the spectral features of the thin surface films from an experimentally-obtained specular-reflectance infrared (SR-IR) spectrum was proposed; results indicate no significant difference in the Si-O bonding network of the alteration layers formed in the presence of exogenously added LiCl, KCl and CsCl. Furthermore, the observed change in corrosion rates might be linked to the relative abundance of molecular water species in the porous network, rather than the silicate bonding structure.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2026

LAF-Net: A Deep Residual and Cross-Attention Framework for Day-Ahead Load Forecasting: Preprint

Accurate day-ahead load forecasting is essential for reliable power system operations and market efficiency. System operators such as the Midcontinent Independent System Operator (MISO) rely on forecasts from multiple vendors, yet combining them effectively remains a persistent challenge due to vendor-specific biases. This paper presents a novel LSTM-Attention Fusion Network with Error Representation (LAF-Net) that enhances day-ahead hourly load forecasting through deep residual learning and multi-modal cross-attention. The proposed model builds a historical error memory from past vendor performance and dynamically queries it with future hour context to generate adaptive, hour-specific trust weights for each vendor. A bounded residual correction further refines forecasts by mitigating systematic and temporally localized errors. Tested on real MISO LBA data with multi-vendor forecasts, LAF-Net consistently outperforms the best vendor baseline across all 38 LBAs, achieving more than a 40% reduction in system-level mean absolute error (MAE) during peak load hours relative to the best vendor baseline.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

Static and Dynamic Thermomechanical Properties of Phase-Separated Epoxy Networks with Tuned Microstructures

Here, polymerization-induced phase separation is a useful method for the construction of heterogeneous epoxy networks with properties exceeding their homogeneous counterparts. In this work, we examine the static and dynamic thermomechanical properties of phase-separated epoxy networks salient to their application as encapsulants. Three heterogeneous epoxy-amine networks with nano-, meso-, and macro-phase-separated morphologies comprised of hard and soft domains are compared to a rigid, unstructured network. The glass transition profiles of the heterogeneous networks are complex, spanning many decades in the frequency domain. The nanophase-separated morphology leads to higher coefficient of thermal expansion, yet surprisingly is characterized by reduced residual stress. Under both quasi-static and dynamic compression (strain rates of order 10 –3 and 10 3 s –1 , respectively), the nanophase-separated network also exhibits higher modulus and strength. In split-Hopkinson bar experiments, the energy dissipation characteristics of the epoxy networks were nearly identical. Curiously, however, the Hugoniot response of the macro-phase-separated network determined by ballistic shockwave analysis indicates a remarkable ability of this material to mitigate shockwave propagation in comparison to many homogeneous and heterogeneous polymer materials. Collectively, this work reveals several previously unreported phenomena with respect to structure–property relationships in phase-separated epoxy networks, illustrating the potential value of systematically tuned microstructures for optimization of application-specific physical properties.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Flow over an espresso cup: inferring 3-D velocity and pressure fields from tomographic background oriented Schlieren via physics-informed neural networks

Tomographic background oriented Schlieren (Tomo-BOS) imaging measures density or temperature fields in three dimensions using multiple camera BOS projections, and is particularly useful for instantaneous flow visualizations of complex fluid dynamics problems. We propose a new method based on physics-informed neural networks (PINNs) to infer the full continuous three-dimensional (3-D) velocity and pressure fields from snapshots of 3-D temperature fields obtained by Tomo-BOS imaging. The PINNs seamlessly integrate the underlying physics of the observed fluid flow and the visualization data, hence enabling the inference of latent quantities using limited experimental data. In this hidden fluid mechanics paradigm, we train the neural network by minimizing a loss function composed of a data mismatch term and residual terms associated with the coupled Navier–Stokes and heat transfer equations. We first quantify the accuracy of the proposed method based on a two-dimensional synthetic data set for buoyancy-driven flow, and subsequently apply it to the Tomo-BOS data set, where we are able to infer the instantaneous velocity and pressure fields of the flow over an espresso cup based only on the temperature field provided by the Tomo-BOS imaging. Moreover, we conduct an independent PIV experiment to validate the PINN inference for the unsteady velocity field at a centre plane. To explain the observed flow physics, we also perform systematic PINN simulations at different Reynolds and Richardson numbers and quantify the variations in velocity and pressure fields. Furthermore, the results in this paper indicate that the proposed deep learning technique can become a promising direction in experimental fluid mechanics.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Utilization of an Advanced Sensor network to determine fuel heating value and Real-Time net unit heat rate during transient operation

Coal-fired utility boilers are being increasingly used as variable electricity generation to resolve the imbalance in the energy market from the expansion of intermittent renewable energy. The frequent transient operation required to meet residual energy demand has created a challenge for coal-fired units to operate efficiently. This work utilizes an advanced sensor network (ASN) to calculate net unit heat rate (NUHR) of a coal-fired boiler in real time through combustion calculations and statistical correlations to provide the tools for optimizing dynamic operation. Real-time heating values that were necessary to determine fuel input energy to calculate accurate NUHR were found using both fundamental and data-driven methods. Real-time NUHR shows distinct shifts that reflect changes in process conditions that will improve the ability to optimize transient operation. Data-driven heating value correlations had 24% lower root mean square error (RMSE) than the fundamental combustion calculation approach when compared to daily retrospective proximate analysis. Furthermore, the data-driven method RMSE improved by 7% with the inclusion of ASN data. Future work is to validate by comparing unit performance with and without the inclusion of NUHR as a control parameter for the dynamic neural network.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2023

Residual-based error correction for neural operator accelerated infinite-dimensional Bayesian inverse problems

We explore using neural operators, or neural network representations of nonlinear maps between function spaces, to accelerate infinite-dimensional Bayesian inverse problems (BIPs) with models governed by nonlinear parametric partial differential equations (PDEs). Neural operators have gained significant attention in recent years for their ability to approximate the parameter-to-solution maps defined by PDEs using as training data solutions of PDEs at a limited number of parameter samples. The computational cost of BIPs can be drastically reduced if the large number of PDE solves required for posterior characterization are replaced with evaluations of trained neural operators. However, reducing error in the resulting BIP solutions via reducing the approximation error of the neural operators in training can be challenging and unreliable. We provide an a priori error bound result that implies certain BIPs can be ill-conditioned to the approximation error of neural operators, thus leading to inaccessible accuracy requirements in training. To reliably deploy neural operators in BIPs, we consider a strategy for enhancing the performance of neural operators: correcting the prediction of a trained neural operator by solving a linear variational problem based on the PDE residual. We show that a trained neural operator with error correction can achieve a quadratic reduction of its approximation error, all while retaining substantial computational speedups of posterior sampling when models are governed by highly nonlinear PDEs. The strategy is applied to two numerical examples of BIPs based on a nonlinear reaction–diffusion problem and deformation of hyperelastic materials. We demonstrate that posterior representations of the two BIPs produced using trained neural operators are greatly and consistently enhanced by error correction.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Photometric redshift estimation with convolutional neural networks and galaxy images: Case study of resolving biases in data-driven methods

Deep-learning models have been increasingly exploited in astrophysical studies, but these data-driven algorithms are prone to producing biased outputs that are detrimental for subsequent analyses. In this work, we investigate two main forms of biases: class-dependent residuals, and mode collapse. We do this in a case study, in which we estimate photometric redshift as a classification problem using convolutional neural networks (CNNs) trained with galaxy images and associated spectroscopic redshifts. We focus on point estimates and propose a set of consecutive steps for resolving the two biases based on CNN models, involving representation learning with multichannel outputs, balancing the training data, and leveraging soft labels. The residuals can be viewed as a function of spectroscopic redshift or photometric redshift, and the biases with respect to these two definitions are incompatible and should be treated individually. We suggest that a prerequisite for resolving biases in photometric space is resolving biases in spectroscopic space. Experiments show that our methods can better control biases than benchmark methods, and they are robust in various implementing and training conditions with high-quality data. Our methods hold promises for future cosmological surveys that require a good constraint of biases, and they may be applied to regression problems and other studies that make use of data-driven models. Nonetheless, the bias-variance tradeoff and the requirement of sufficient statistics suggest that we need better methods and optimized data usage strategies.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2020

Room-temperature neutron and X-ray data collection of 3CL M pro from SARS-CoV-2

The replication of SARS-CoV-2 produces two large polyproteins, pp1a and pp1ab, that are inactive until cleavage by the viral chymotrypsin-like cysteine protease enzyme (3CL M pro ) into a series of smaller functional proteins. At the heart of 3CL M pro is an unusual catalytic dyad formed by the side chains of His41 and Cys145 and a coordinated water molecule. The catalytic mechanism by which the enzyme operates is still unknown, as crucial information on the protonation states within the active site is unclear. To experimentally determine the protonation states of the catalytic site and of the other residues in the substrate-binding cavity, and to visualize the hydrogen-bonding networks throughout the enzyme, room-temperature neutron and X-ray data were collected from a large H/D-exchanged crystal of ligand-free (apo) 3CL M pro .

3CL Mpro↗
DOE OSTI2022

Impact of Polymer Rheology on Gel Treatment Performance of Horizontal Wells with Severe Channeling

Summary Gel treatment has been a cost-effective method to control the conformance of a reservoir with severe heterogeneity problems. The water channels in such reservoirs can be classified as open fractures or high permeability porous media with pore-throat network. Many simulation studies have been conducted to discuss gel treatment performance for conformance control. However, nobody considered the polymer rheology difference in open fractures and porous media in simulation. Previous simulation studies also ignored the residual resistance factor as a function of rock permeability rather than a constant parameter. In this study, a conceptual simulation model was established to simulate the linear flow system for the reservoir with horizontal wells considering the two factors mentioned above. The results demonstrate that the gel treatment always provides the better placement results in the open fracture type channel than pore-throat network type channel. Moreover, it is very necessary to consider residual resistance factor as a function of permeability, which is based on the experimental results and can provide much greater plugging efficiency in the higher permeable channels than constant residual resistance factor. Sensitivity analysis studies and multifactor analysis indicate that increasing oil viscosity and permeability ratio has a strong positive influence on conformance control results, which indicate in-situ gel treatment can be better applied in heavy or viscous oil reservoirs with fracture-like channels. Besides, the results also indicate that in reservoirs with severe channeling problem where channel velocity was high, the differences of gelant placement and profile improvement in models with two different types of channels could be enlarged greatly.

Engineering↗
DOE OSTI2024

LossLens: Diagnostics for Machine Learning Through Loss Landscape Visual Analytics

Modern machine learning often relies on optimizing a neural network's parameters using a loss function to learn complex features. Beyond training, examining the loss function with respect to a network's parameters (i.e., as a loss landscape) can reveal insights into the architecture and learning process. While the local structure of the loss landscape surrounding an individual solution can be characterized using a variety of approaches, the global structure of a loss landscape, which includes potentially many local minima corresponding to different solutions, remains far more difficult to conceptualize and visualize. To address this difficulty, we introduce LossLens, a visual analytics framework that explores loss landscapes at multiple scales. LossLens integrates metrics from global and local scales into a comprehensive visual representation, enhancing model diagnostics. Here we demonstrate LossLens through two case studies: visualizing how residual connections influence a ResNet-20, and visualizing how physical parameters influence a physics-informed neural network (PINN) solving a simple convection problem.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Generative $β$-hairpin design using a residue-based physicochemical property landscape

De novo peptide design is a new frontier that has broad application potential in the biological and biomedical fields. Most existing models for de novo peptide design are largely based on sequence homology that can be restricted based on evolutionarily derived protein sequences and lack the physicochemical context essential in protein folding. Generative machine learning for de novo peptide design is a promising way to synthesize theoretical data that are based on, but unique from, the observable universe. In this study, we created and tested a custom peptide generative adversarial network intended to design peptide sequences that can fold into the -hairpin secondary structure. This deep neural network model is designed to establish a preliminary foundation of the generative approach based on physicochemical and conformational properties of 20 canonical amino acids, for example, hydrophobicity and residue volume, using extant structure-specific sequence data from the PDB. The beta generative adversarial network model robustly distinguishes secondary structures of hairpin from α helix and intrinsically disordered peptides with an accuracy of up to 96% and generates artificial -hairpin peptide sequences with minimum sequence identities around 31% and 50% when compared against the current NCBI PDB and nonredundant databases, respectively. These results highlight the potential of generative models specifically anchored by physicochemical and conformational property features of amino acids to expand the sequence-to-structure landscape of proteins beyond evolutionary limits.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Identifying Sample Provenance From SEM/EDS Automated Particle Analysis via Few-Shot Learning Coupled With Similarity Graph Clustering

Automated particle analysis (APA) provides a vast amount of compositional data via energy-dispersive X-ray spectroscopy along with size and shape data via scanning electron microscopy for individual particles in a sample. In many instances, APA data are leveraged to support identification of the source of a sample based on the detection of particles of a specific composition. Often, the particles that provide context make up a minuscule portion of the sample. Additionally, the interpretation of complex samples can be difficult due to the diversity of compositions both in the mixture and within a particle. In this work, we demonstrate a method to compute and cluster similarity graphs that describe inter-particle relationships within a sample using a multi-modal few-shot learning neural network. Here, as a proof-of-concept, we show that samples known to have been exposed to gunshot residue can be distinguished from samples occasionally mistaken for gunshot residue. Our workflow builds upon standard APA techniques and data processing methods to unveil additional information in a readily interpretable and quantitatively comparable format.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗