SEARCH · Engineering Papers
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.
Pseudo-data with simulated experimental errors can be generated to train an ensemble of Artificial Neural Networks (ANN) implemented on a regression to extract Transverse Momentum-dependent Distributions (TMDs). A preliminary analysis is presented on the reliability in extraction of the Sivers function imposed in the pseudo-data given the bounds on the experimental errors, data sparsity, and complexity of phase-space.
A growing reliance on the fast Monte Carlo (FastSim) will accompany the high luminosity and detector granularity expected in Phase 2. FastSim is roughly 10 times faster than equivalent GEANT4-based full simulation (FullSim). However, reduced accuracy of the FastSim affects some analysis variables and collections. To improve its accuracy, FastSim is refined using regression-based neural networks trained with ML. The status of FastSim refinement is presented. The results show improved agreement with the FullSim output and an improvement in correlations among output observables and external parameters.
Deep Neural Networks (DNNs) can provide clinicians with fast and accurate predictions that are highly valuable for high-stakes medical decision-making, such as in brain tumor segmentation and treatment planning. However, these models largely lack transparency about the uncertainty in their predictions, potentially giving clinicians a false sense of reliability that may lead to grave consequences in patient care. Growing calls for Transparent and Responsible AI have promoted Uncertainty Quantification (UQ) to capture and communicate uncertainty in a systematic and principled manner. However, traditional Bayesian UQ methods remain prohibitively costly for large, million-dimensional tumor segmentation DNNs such as the U-Net. In this work, we discuss a computationally-efficient UQ approach via the partially Bayesian neural networks (pBNN). In pBNN, only a single layer, strategically selected based on gradient-based sensitivity analysis, is targeted for Bayesian inference. We illustrate the effectiveness of pBNN in capturing the full uncertainty for a 7.8-million parameter U-Net. We also demonstrate how practitioners and model developers can use the pBNN's predictions to better understand the model's capabilities and behavior.
Anion exchange membranes (AEMs) play a vital role in the performance of water electrolyzers and fuel cells, yet their discovery and optimization remain challenging due to the complexity of structure–property relationships. In this study, we introduce a machine learning framework that leverages conditional graph neural networks (cGNNs) and descriptor-based models and a hybrid graph neural network (HGARE) to predict and interpret ionic conductivity. The descriptor-based pipeline employs principal component analysis (PCA), ablation, and SHAP analysis to identify factors governing anion conductivity, revealing electronic, topological, and compositional descriptors as key contributors. Beyond prediction, dimensionality reduction and clustering are performed by employing t-SNE and KMeans as well as SOM, which reveal distinct membranes clusters, some of which were enriched with high anion conductivity. Among graph-based approaches, the graph convolutional (GCN) achieved strong predictive performance, while the Hybrid Graph Autoencoder-Regressor Ensemble (HGARE) achieved the highest accuracy. Additionally, atom-level saliency maps from GCN provide spatial explanations for conductive behavior, revealing the importance of polarizable and flexible regions. This work contributes to the accelerated and data-driven design of high-performance AEMs.
Learning operators between infinitely dimensional spaces is an important learning task arising in machine learning, imaging science, mathematical modeling and simulations, etc. This paper studies the nonparametric estimation of Lipschitz operators using deep neural networks. Non-asymptotic upper bounds are derived for the generalization error of the empirical risk minimizer over a properly chosen network class. Under the assumption that the target operator exhibits a low dimensional structure, our error bounds decay as the training sample size increases, with an attractive fast rate depending on the intrinsic dimension in our estimation. Our assumptions cover most scenarios in real applications and our results give rise to fast rates by exploiting low dimensional structures of data in operator estimation. We also investigate the influence of network structures (e.g., network width, depth, and sparsity) on the generalization error of the neural network estimator and propose a general suggestion on the choice of network structures to maximize the learning efficiency quantitatively.
Summary of the challenge, approach, results, and impact of co-optimized machine-learned manifold models for research of large eddy simulation of turbulent combustion.
In this study, we present the first simulation results of the formation of dislocation cell wall microstructures in tantalum subjected to shock loading. Dislocation patterns and cell wall formation are important to understanding the mechanical properties of the materials in which they spontaneously arise, and yet the processing and self-assembly mechanisms leading to their formation are poorly understood. By employing transmission electron microscopy and discrete dislocation dynamics, we propose a new mechanism involving coplanar dislocations and pseudo-dipole mixed dislocation arrays that is essential to the pattern formation process. Our large-scale 3D DDD simulations demonstrate the self-organization of dislocation networks into cell walls in deformed BCC metal (tantalum) persisting at strain ε = 20%. The simulation analysis captures several crucial aspects of how the dislocation cell pattern affects metal plasticity, as observed in experiments. Although experimental evidence is inconclusive regarding whether cell wall formation takes place at the shock front, after the shock, during release, or when the sample has had enough time to relax post-recovery, our simulations indicate cell wall formation occurs after the shock and before release. The extended Taylor hardening composite model effectively considers the non-uniform dislocation density when cell walls form and accurately describes the corresponding flow stress.
This work presents methods for evaluating the Power Transfer Distribution Factor (PTDF) and Line Outage Distribution Factor (LODF) matrices by employing sparse linear algebra for large-scale computing applications. These matrices play a critical role in many power system applications, such as the Unit Commitment Problem (UC), pre- and post-contingency power flow analysis, and transmission expansion. These matrices are typically dense, which means they require a significant amount of time and memory to be computed for large networks. However, by analyzing the structure of the matrices and their computation method, it is possible to use reduced memory methods based on sparse matrix operations. This paper shows that sparse linear algebra algorithms are faster and require less memory and time than traditional dense approaches. Additionally, we explore the effect of matrix sparsification by eliminating trailing digits on power flow calculations.
Pulse shape discrimination (PSD) capable detectors, such as He-4, that respond to neutron and gamma-ray 7 interactions have a threshold deposited energy value below which n/γ discrimination vanishes when using 8 conventional PSD algorithms. Recent attempts in applying supervised learning based artificial neural 9 networks for PSD use the pulses in the separated regions to train the networks so they can be used to classify 10 another set of separated pulses. In doing so, pulses previously indistinguishable are not recovered for 11 classification, which would have increased the number of neutron and gamma-ray pulses that could be used 12 for further analysis. Assuming the reason why conventional PSD algorithms have unseparated regions is 13 because the parameter space of the algorithms fail to capture the intrinsic (but subtle) distinguishing 14 behavior of some of the neutron and gamma-ray pulses, a cycle-consistent generative adversarial network 15 (CycleGAN) was trained to amplify those differences and extract well separated neutron and gamma-ray 16 clusters. Results show that, once the network is trained with pulses from separated and unseparated regions, 17 it was able to transform the pulses in the unseparated region to improve the PSD. Subsequent n/γ 18 classification was performed using deep residual network (ResNet) that takes pulses with 512 data points 19 as an input. Two different ResNets were explored – simple ResNet and modified ResNet which takes 20 segmented pulse inputs in the first layer and the corresponding time axis values in the last hidden layer. 21 The later approach enables the network to extract time correlated pulse features to enhance its ability to 22 capture the pulse behaviors relevant for PSD. Although it achieves slightly lower accuracy, 99.41% versus 23 99.89%, based on simply counting the number of correct n/γ labels assigned, compared to the simple 24 ResNet, the modified ResNets architecture was able to decreases the cross-entropy loss function by half, 25 which implies that the correct n/γ labels assigned are less likely to be accidental. PSD parameter 26 distributions based on n/γ classification by ResNet before and after transforming unseparated pulses using 27 CycleGAN show that by enhancing the separation between neutrons and gamma-rays, the transformation 28 helps improve the performance of classifier networks that are trained using labeled dataset. The 29 enhancement of neutron and gamma-ray separation by the CycleGAN increased the PSD figure of merit 30 (FOM) by up to 70% in some regions. Here, the results show that, if a given detector achieves clear separation 31 between neutron and gamma-ray pulses in any energy region, such neural network approaches can help 32 lower the energy threshold for the separation and increasing the number of neutron and gamma-ray pulses 33 that can be used for further analysis.
Aqueous corrosion of glass may result in the formation of an alteration layer in the glass surface of which chemical composition and network structure are different from those of the bulk glass. Since corrosion occurs far below the glass-transition temperature, the alteration layer cannot fully relax to the new structure with the lowest possible energy. Molecular dynamics simulations suggested that such a network will contain highly strained chemical bonds, which can be manifested as a stress in the alteration layer. Common techniques to measure stress in thin films or surface layers were found inadequate for thick monolithic glass samples corroded in water. Here, we explored the use of spectroscopic ellipsometry to test the presence of internal stress in the alteration layer formed by aqueous corrosion of glass. Furthermore, a procedure for analyses of spectroscopic ellipsometry data to determine birefringence in the alteration layer was developed. Findings with the established fitting procedure suggested that a stress builds up in the corroded surface layer of a boroaluminosilicate glass if there is a change in relative humidity, pH, or electrolyte concentration of the environment to which the glass surface is exposed. A similar process may occur in other types of glass, and it may affect the surface properties of corroded glass objects.
The dataset includes detailed anonymized public charging station usage from several rural stations on the ChargePoint and Shell Recharge Solutions (formerly Greenlots) networks situated in and around Athens, Ohio, a rural Appalachian community. Both Level 2 and DC fast charging stations are represented. Historical data in the set date back to 2019; additional data will be uploaded semiannually until the project's completion in 2023. Each charging session recorded includes information on date and time, location, charging station level, session duration, energy delivered, and fuel savings.
An electrode in cylindrical or pouch cell batteries contains millions of active particles embedded in a conductive network. Battery performance, such as voltage, capacity, and cyclic efficiency, is a collective response of the particle network. We use optical microscopy to measure the local, heterogeneous state of charge of individual particles upon charging and discharging. The optical reflectivity is proportional to Li composition in the ternary oxide LiNi x Mn y Co z O 2 (NMC) cathode. Through clustering analysis, we determine the scale of heterogeneity where a representative volume in the composite electrode contains 100 to 1,000 particles. The heterogeneous activity in the particle network can be described by Weibull defect population at the particle interface with the conductive matrix.
Near-real-time (NRT) streamflow data are critical importance for timely water resources management. Here, we developed an open-source tool, FlowStats, for NRT streamflow analysis and visualization in Germany, based on NRT meteorological data from the German Weather Service and simulated streamflow from a long short-term memory neural network (LSTM). The LSTM model achieved very good overall performance, median NSE of 0.80 for the test period across 1,479 catchments. FlowStats provides options for deriving various streamflow statistics, from normal and abnormal streamflow detection to drought and flood analyses. An example analysis from FlowStats revealed widespread below-normal to extreme low-flow conditions across Germany from March to May 2025, which weakened from June to September 2025. Drought analysis for September 2025 highlighted severe to extreme drought conditions in northwestern Germany, while flood classifications indicated that high-flow events occurred in southwestern Germany. FlowStats can be used for various hydrological assessments to support water resources management.
Energy management of transmission and distribution networks (T&D) is becoming more challenging with the accelerated adoption of distributed energy resources (DERs)-such as distributed photovoltaic generation and battery energy storage systems (BESS)-on the electric grid. To better analyze the impacts of DERs on both transmission and distribution systems, a comprehensive T&D co-simulation platform is developed. Further, with DERs more actively participating in system operation-e.g., by providing real-time grid services-their cyber vulnerability needs to be better understood to maintain system reliability. This paper discusses a cyber-physical events emulation-based T&D co-simulation platform to perform comprehensive cyber events emulations, physical simulation, and analysis of interdependent impacts. Results from the case studies-which show how cyber events on a synthetic distribution network can impact operations on the transmission and distribution network-validate that the proposed T&D cosimulation platform can perform cyber-physical events emulation and produce response in near realtime; therefore, with extensive simulation using the proposed co-simulation platform, the system operators can accumulate adequate training data for system situational awareness of grid anomalies.
Seismic waveform data recorded at stations can be thought of as a superposition of the signal from a source of interest and noise from other sources. Frequency‐based filtering methods for waveform denoising do not result in desired outcomes when the targeted signal and noise occupy similar frequency bands. Recently, denoising techniques based on deep‐learning convolutional neural networks (CNNs), in which a recorded waveform is decomposed into signal and noise components, have led to improved results. These CNN methods, which use short‐time Fourier transform representations of the time series, provide signal and noise masks for the input waveform. These masks are used to create denoised signal and designaled noise waveforms, respectively. However, advancements in the field of image denoising have shown the benefits of incorporating discrete wavelet transforms (DWTs) into CNN architectures to create multilevel wavelet CNN (MWCNN) models. The MWCNN model preserves the details of the input due to the good time–frequency localization of the DWT. In this report we use a data set of over 382,000 constructed seismograms recorded by the University of Utah Seismograph Stations network to compare the performance of CNN and MWCNN‐based denoising models. Evaluation of both models on constructed test data shows that the MWCNN model outperforms the CNN model in the ability to recover the ground‐truth signal component in terms of both waveform similarity and preservation of amplitude information. Model evaluation of real‐world data shows that both the CNN and MWCNN models outperform standard band‐pass filtering (BPF; average improvement in signal‐to‐noise ratio of 9.6 and 19.7 dB, respectively, with respect to BPF). Evaluation of continuous data suggests the MWCNN denoiser can improve both signal detection capabilities and phase arrival time estimates.
Changes in economic, technology, and environmental policies are resulting in a re-evaluation of the dependence on large central generation facilities and their associated transmission networks. Emerging concepts of smart communities/cities are examining the potential to leverage cleaner sources of generation, and the potential to integrate electricity generation with other municipal functions. When grid-connected, these generation assets can supplement the existing interconnections with the bulk transmission system, and in the event of an extreme event, they can provide power via networks of microgrids. While the design process for a single stand-alone microgrid is relatively well understood, the process of designing the infrastructure for networked microgrid operations has not been well studied. Because of the wide range of potential operational goals for microgrids, it is typical to follow the engineering process of developing an initial conceptual design, a preliminary design, a detailed design, and then a final as-built design. The conceptual design is typically completed without detailed engineering analysis, and the preliminary design is the first stage that requires it. This paper presents a process for developing the preliminary design for networked microgrids, which can then be used as a basis for the final as-built design.
Agrichemicals such as herbicides, fungicides, insecticides, and biocides are widely used in agriculture, yet some are associated with adverse effects in humans and the environment. While many of these chemicals have been extensively studied in vitro and are included in the EPA’s ToxCast program, comprehensive in vivo comparisons using RNA sequencing across structurally diverse agrichemicals, in a single screening platform, are lacking. In this study, we examined structurally diverse agrichemicals found in the U.S. Environmental Protection Agency’s (EPA) Toxcast Phase I and II library by statically exposing early life stage zebrafish at 6 h post fertilization (hpf) until 120 hpf at concentrations ranging from 0.25 to 100 µM. Morphological outcomes were assessed at 120 hpf across 10 endpoints, including yolk sac edema, craniofacial malformations, and axis abnormalities. Chemicals that produced robust concentration-response relationships were selected for transcriptomic profiling. For transcriptomic analysis, zebrafish were statically exposed to each chemical and sampled at 48 hpf, prior to the onset of morphological effects observed at 120 hpf. Differential expression analysis identified between 0 and 4,538 differentially expressed genes (DEGs) per chemical, with no clear correlation to morphological severity. Both DEG and co-expression network analyses revealed chemical-specific expression patterns that converged on shared biological pathways, including neurodevelopment and cytoskeletal organization. Key regulatory genes such as mylpfa and krt4 were identified within co-expression modules, suggesting their potential role in conserved toxicity mechanisms. Semantic similarity analysis of enriched gene ontology (GO) terms, when compared to existing datasets, highlighted gaps in the annotation of neurodevelopmental processes, indicating that some in vivo effects may not be fully captured by current curated resources. The results provide new insights into the modes of action of diverse agrichemicals and establish a framework for understanding how agrichemical structure relates to biological function in a vertebrate model.
This paper presents an uncertainty quantification (UQ) framework for the physics-based model prediction of material response with a large number of parameters. The application problem presented in this work is that of predicting creep in Grade 91 steel at 600°C. The material response is defined with a physically based microstructural model with constitutive equations emulating several observed phenomena in Grade 91 and embodied into an explicit geometry mesoscale finite element model for prior austenite grains and grain boundaries. Creep within the grains and in grain boundaries are represented by crystal plasticity for dislocation motion and a physics-based model for cavity growth and nucleation, respectively. The creep behavior of this material is influenced by several parameters, some of which have a wide range of variation based on experimental data. UQ combined with microstructural modeling can discover the core microstructural causes of experimental variability, leading to improved materials with lower variability in critical long-term material properties. In this study, we investigate the model's uncertainty to identify material properties that may be modified during production to increase creep life and analyze different components of the crystal plasticity model for improvements. For this purpose, a quantity of interest is defined as time to minimum creep rate, which correlates well to the creep failure of the material. A deep neural network model was trained and validated to be used as a surrogate for the finite element model. Then, a variance-based sensitivity analysis is performed on the surrogate model to find the Sobol indices of the input parameters in respect to the output quantity of interest. The Sobol indices are used to reduce the dimensionality of the model. Generalized polynomial chaos expansion is used on the reduced basis models to propagate the uncertainty from the input parameters to the quantity of interest using the deep neural network surrogate model. These results are benchmarked against uncertainty propagation using Monte Carlo simulations. In conclusion, the UQ performed through the reduced basis model captures almost all the uncertainty in the model with significantly fewer simulations, making it possible to perform the UQ directly via simulations with the finite element model rather than surrogate machine-learned models.