Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “integrated gradients”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Radiation-induced bowing of SiC/SiC composites under neutron flux gradients—integral experimental data for model validation

Here, the radiation-induced swelling of SiC and its composites, including strong dependencies on temperature and dose, can drive significant lateral bowing in the presence of temperature and/or dose gradients. In recent years, simulations have been performed to assess the extent of bowing in SiC composite light-water reactor (LWR) fuel cladding and boiling water reactor (BWR) channel boxes. However, to date, no integral experimental data exist to validate these models. This work provides the first experimental bowing evaluation of three ∼380 mm long SiC composite specimens irradiated under varying neutron dose gradients (∼50°C–60°C, 0.03–0.06 dpa): two tubes (∼9.8 mm diameter) and a miniature BWR channel box (∼30 mm square). The measured radiation-induced length swelling (∼0.3%–0.7% linear) was consistently 10%–21% higher than values obtained from 3D finite element structural analyses with inputs from 3D radiation transport calculations. This discrepancy could be at least partially explained by differences in dose rate (∼10 -8 dpa/s) compared to the literature data (∼10-6 dpa/s) used to establish the dose-to-swelling correlations in the model. Nevertheless, the modeled bowing magnitudes (<2 mm) obtained from finite element analyses and simple analytical equations were within the bounds of the experimental measurements for all specimens. With improved confidence in the ability to predict the structural response and measure the macroscopic deformations, future experiments will target transient bowing under neutron flux gradients at representative LWR temperatures and assess whether grid spacers can mitigate the tens of millimeters of bowing that would otherwise be expected in ∼4 m long LWR components.

bowing↗
DOE OSTI2023

Planar turbulent wakes under pressure gradient: Integral and self-similarity analyses

By using a combination of integral and self-similarity analyses, the generalized analytical solutions for the mean transverse velocity and Reynolds shear stress are rigorously derived for the first time for the far field of planar turbulent wakes under arbitrary pressure gradients. Specifically, by assuming self-similarity for the mean axial velocity, the analytical formulation for the mean transverse velocity is obtained from the integral of the mean continuity equation, and the analytical formulation for the Reynolds shear stress is obtained from the integral of the momentum equation. The generalized analytical formulations for the mean transverse velocity and Reynolds shear stress consist of multiple components, each with its unique scale and physical mechanism. In the zero pressure gradient limit, the generalized formulations recover the single-scale equations reported by Wei, Liu, and Livescu. Furthermore, simpler approximate formulations for the mean transverse velocity and Reynolds shear stress are also obtained, and show excellent agreement with the experimental measurements. Here, the findings provide new insights into the properties of planar turbulent wakes under pressure gradients, filling some long-standing gaps in the existing literature.

42 ENGINEERING↗
DOE OSTI2023

SyReNN: A tool for analyzing deep neural networks

Deep Neural Networks (DNNs) are rapidly gaining popularity in a variety of important domains. Unfortunately, modern DNNs have been shown to be vulnerable to a variety of attacks and buggy behavior. This has motivated recent work in formally analyzing the properties of such DNNs. Furthermore, this paper introduces SyReNN, a tool for understanding and analyzing a DNN by computing its symbolic representation. The key insight is to decompose the DNN into linear functions. Our tool is designed for analyses using low-dimensional subsets of the input space, a unique design point in the space of DNN analysis tools. We describe the tool and the underlying theory, then evaluate its use and performance on three case studies: computing Integrated Gradients, visualizing a DNN’s decision boundaries, and repairing buggy DNNs.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Enhancing Multi-Step Reservoir Inflow Forecasting: A Time-Variant Encoder–Decoder Approach

Accurate reservoir inflow forecasting is vital for effective water resource management. Reliable forecasts enable operators to optimize storage and release strategies to meet competing sectoral demands—such as water supply, irrigation, and hydropower scheduling—while also mitigating flood and drought risks. To address this need, in this study, we propose a novel time-variant encoder–decoder (ED) model designed specifically to improve multi-step reservoir inflow forecasting, enabling accurate predictions of reservoir inflows up to seven days ahead. Unlike conventional ED-LSTM and recursive ED-LSTM models, which use fixed encoder parameters or recursively propagate predictions, our model incorporates an adaptive encoder structure that dynamically adjusts to evolving conditions at each forecast horizon. Additionally, we introduce the Expected Baseline Integrated Gradients (EB-IGs) method for variable importance analysis, enhancing interpretability of inflow by incorporating multiple baselines to capture a broader range of hydrometeorological conditions. The proposed methods are demonstrated at several diverse reservoirs across the United States. Our results show that they outperform traditional methods, particularly at longer lead times, while also offering insights into the key drivers of inflow forecasting. These advancements contribute to enhanced reservoir management through improved forecasting accuracy and practical decision-making insights under complex hydroclimatic conditions.

58 GEOSCIENCES↗
DOE OSTI2025

Explainable artificial intelligence relates perovskite luminescence images to current-voltage metrics

As the demand for low-cost, high-efficiency solar energy technologies grows, metal halide perovskite (MHP) solar cells have emerged as a promising candidate for next-generation photovoltaics due to their high power conversion efficiencies. However, their poor durability and issues with manufacturing consistency remain significant barriers to commercialization. In this work, we develop deep learning models to support materials characterization and provide insight into features and processes influencing performance. The models are trained using transfer learning of a pretrained model to predict relevant current-voltage (IV) metrics based on different combinations of input electroluminescence (EL) and photoluminescence (PL) images of MHP devices. We examine which image types are most informative in accurately predicting different IV metrics. Additionally, we use explainable artificial intelligence (XAI) techniques to provide insights into specific spatial features in the devices that drive differences in performance. We find that stabilized luminescence images (e.g. those collected after biasing the devices for at least 1 min) are better for predicting metrics of open-circuit voltage (by PL) and short-circuit current (by PL with EL), but that predicting fill factor and overall power output may use the time-evolution of EL images. Based on attribution masks generated by integrated gradients for each device performance metric, we further suggest different loss mechanisms associated with categories of large and small spatial defects. Overall, this case study highlights the potential applicability of XAI methodology for streamlining MHP device analysis and accelerating detailed understanding of the relationships between spatial defects and impacts on performance.

14 SOLAR ENERGY↗
DOE OSTI2025

River Dissolved Oxygen Prediction Using Machine Learning Models and Wireless Sensor Measurements

Simultaneous flooding&heat and droughts&heat events can potentially destabilize hydro-meteorological conditions to deteriorate the water quality of Neches River. Machine learning (ML) models utilizing wireless sensor measurements have been applied to predict water quality and optimize various water management strategies. This study aims to develop ML models to predict dissolved oxygen (DO) prediction under various hydro-meteorological conditions and enhance water management decision-making. Wireless sensor measurements of DO, water temperature, sample depth, conductivity, turbidity, and pH, along with discharge from the United States Geological Survey stations, are collected for model inputs at the Pine Island Bayou C749 station (PIB-C749) and Neches River Saltwater Barrier (SWB). Multilayer perceptron neural networks, recurrent neural networks, long short-term memory (LSTM), and bidirectional LSTM (BiLSTM) with and without attention mechanism (AT) are tested to determine the best model, which is applied the rolling forecast method to predict 14-day DO. Traditional and recurrent transfer learning (TL and RTL) methods are adopted to overcome insufficient data at the SWB. The input feature importance analysis using the integrated gradients (IG) algorithm is applied to determine dominant inputs. The results show LSTM-based models are capable handling long sequential data. AT-BiLSTM and RTL-LSTM demonstrate the best performance at the PIB-C749 (RMSE=0.054) and the SWB (RMSE=0.028), respectively. TL and RTL methods significantly improve model performance at the SWB. DO, temperature, and pH show higher importance, consistent with hydrodynamics and water chemistry. Both best models are applied to predict 14-day DO and demonstrate reasonable performance for decision-making. Hydro-meteorological conditions of 2017 flood and 2012 drought events are simulated and reveal that possible hypoxia occurs after flooding due to increasing temperature and turbidity, and DO concentration decreases significantly under heat and drought conditions. In conclusion, LSTM-based models utilizing wireless sensor data can be a timely and effective approach to make appropriate decisions on water resource management.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Data-based filtered dissipation rate modelling for multi-modal turbulent combustion: evaluating a priori model generalizability

Manifold-based models offer a computationally efficient alternative to directly transporting the thermochemical state in computational simulations of turbulent reacting flows, projecting the high-dimensional thermochemical state-space onto a low-dimensional manifold. Recent efforts have yielded a manifold-based model applicable to multi-modal combustion, enabling reconstruction of the thermochemical state from solutions to two-dimensional manifold equations in mixture fraction and generalized progress variable that are parameterised by three scalar dissipation rates. In coarse-grained simulations such as Large Eddy Simulation (LES), closure of the multi-modal manifold equations and subfilter variances/covariance requires closure of three filtered scalar dissipation rates. Here, the present work adopts a data-based approach, providing closure for the three filtered scalar dissipation rates via deep neural networks (DNNs). High-fidelity datasets corresponding to an autoigniting n-dodecane jet flame and a bluff body swirl-stabilized confined lifted spray flame of two aviation fuels (Jet-A and C1) with different ignition propensities are leveraged to generate training data that spans a diverse range of thermodynamic conditions and combustion modes, including low- and high-temperature ignition regimes in addition to premixed and nonpremixed behaviour. A final DNN model is trained to enforce inherent physical constraints by learning nonlinear functional transformations of the three filtered scalar dissipation rates. The generalizability of this constrained DNN model is demonstrated a priori via conditional statistics evaluated on the lifted spray flame with C1–a configuration that had not been included in the training data. Excellent DNN agreement with conditional DNS statistics is observed, and integrated gradients are computed to identify the most sensitive input variables. The similarity of the marginal PDFs of the most informative input variables and outputs across configurations are quantified via the Wasserstein metric, demonstrating that data-based models may successfully generalize to unseen parametric conditions so long as the most informative input variables share similar distributions across training and testing datasets.

Data-based modelling↗
DOE OSTI2025

Massive νs through the CNN lens: interpreting the field-level neutrino mass information in weak lensing

Modern cosmological surveys probe the Universe deep into the nonlinear regime, where massive neutrinos suppress cosmic structure. Traditional cosmological analyses, which use the 2-point correlation function to extract information, are no longer optimal in the nonlinear regime, and there is thus much interest in extracting beyond-2-point information to improve constraints on neutrino mass. Quantifying and interpreting the beyond-2-point information is thus a pressing task. We study the field-level information in weak lensing convergence maps using convolution neural networks. We find that the network performance increases as higher source redshifts and smaller scales are considered — investigating up to a source redshift of 2.5 and ℓ max ≃ 10 4 — verifying that massive neutrinos leave a distinct effect on weak lensing. However, the performance of the network significantly drops after scaling out the 2-point information from the maps, implying that most of the field-level information can be found in the 2-point correlation function alone. We quantify these findings in terms of the likelihood ratio and also use Integrated Gradient saliency maps to interpret which parts of the map the network is learning the most from. We find that, in the absence of noise, the network extracts a similar amount of information from the most overdense and underdense regions. However, upon adding noise, the information in underdense regions is distorted as noise disproportionately washes out void-like structures.

Golshan, Malika [University of California, Berkele↗
DOE OSTI2022

Estimating cluster masses from SDSS multiband images with transfer learning

ABSTRACT The total masses of galaxy clusters characterize many aspects of astrophysics and the underlying cosmology. It is crucial to obtain reliable and accurate mass estimates for numerous galaxy clusters over a wide range of redshifts and mass scales. We present a transfer-learning approach to estimate cluster masses using the ugriz-band images in the SDSS Data Release 12. The target masses are derived from X-ray or SZ measurements that are only available for a small subset of the clusters. We designed a semisupervised deep learning model consisting of two convolutional neural networks. In the first network, a feature extractor is trained to classify the SDSS photometric bands. The second network takes the previously trained features as inputs to estimate their total masses. The training and testing processes in this work depend purely on real observational data. Our algorithm reaches a mean absolute error (MAE) of 0.232 dex on average and 0.214 dex for the best fold. The performance is comparable to that given by redMaPPer, 0.192 dex. We have further applied a joint integrated gradient and class activation mapping method to interpret such a two-step neural network. The performance of our algorithm is likely to improve as the size of training data set increases. This proof-of-concept experiment demonstrates the potential of deep learning in maximizing the scientific return of the current and future large cluster surveys.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2026

Search for HH → bbτ⁺τ⁻ Using Run 3 Scouting Data Analyze b-tagging and tau-tagging Performance with Unified Particle Transformer

B-tagging and tau-tagging performances play an important role in the search for the rare event HH → bbτ⁺τ⁻. A transformer-based neural network, Unified Particle Transformer, is applied for both tagging tasks, and Run 3 proton–proton collision scouting data at center-of-mass energy of 13.6 TeV is used. The scouting data stream accepts events at a much higher rate compared to traditional triggers, but stores only the objects reconstructed in the trigger, no low-level detector information. Therefore, existing taggers trained for the offline event reconstruction cannot be used. Analysis of the SoftMax plots, ROC/AUC curves, confusion matrix, accuracy and losses are used to evaluate model performance. Specifically, the tagging efficiency of the signal and misidentification probability across multiple background processes are compared for varying working points. Different training samples with distinct distributions of jet flavors are utilized and related model performances are analyzed. Interpretability methods, such as Integrated Gradients, may further be applied to study the input features’ influence on the model’s decisions, providing insights into potential improvements.

Chen, Blair [Purdue U., West Lafayette; Fermilab]↗
DOE OSTI2021

Rational design of mechanically robust Ni-rich cathode materials via concentration gradient strategy

Mechanical integrity issues such as particle cracking are considered one of the leading causes of structural deterioration and limited long-term cycle stability for Ni-rich cathode materials of Li-ion batteries. Indeed, the detrimental effects generated from the crack formation are not yet entirely addressed. Here, applying physicochemical and electrochemical ex situ and in situ characterizations, the effect of Co and Mn on the mechanical properties of the Ni-rich material are thoroughly investigated. As a result, we successfully mitigate the particle cracking issue in Ni-rich cathodes via rational concentration gradient design without sacrificing the electrode capacity. Our result reveals that the Co-enriched surface design in Ni-rich particles benefits from its low stiffness, which can effectively suppress the formation of particle cracking. Meanwhile, the Mn-enriched core limits internal expansion and improve structural integrity. The concentration gradient design also promotes morphological stability and cycling performances in Li metal coin cell configuration.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Enhancing ACPF Analysis: Integrating Newton-Raphson Method with Gradient Descent and Computational Graphs

This paper presents a new method for enhancing Alternating Current Power Flow (ACPF) analysis. The method integrates the Newton-Raphson (NR) method with Enhanced-Gradient Descent (GD) and computational graphs. The integration of renewable energy sources in power systems introduces variability and unpredictability, and this method addresses these challenges. It leverages the robustness of NR for accurate approximations and the flexibility of GD for handling variable conditions, all without requiring Jacobian matrix inversion. Furthermore, computational graphs provide a structured and visual framework that simplifies and systematizes the application of these methods. The goal of this fusion is to overcome the limitations of traditional ACPF methods and improve the resilience, adaptability, and efficiency of modern power grid analyses. We validate the effectiveness of our advanced algorithm through comprehensive testing on established IEEE benchmark systems. Furthermore, our findings demonstrate that our approach not only speeds up the convergence process but also ensures consistent performance across diverse system states, representing a significant advancement in power flow computation.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

Improved filters for angular filter refractometry

Angular filter refractometry is an optical diagnostic that measures the absolute contours of a line-integrated density gradient by placing a filter with alternating opaque and transparent zones in the focal plane of a probe beam, which produce corresponding alternating light and dark regions in the image plane. Identifying transitions between these regions with specific zones on the angular filter (AF) allows the line-integrated density to be determined, but the sign of the density gradient at each transition is degenerate and must be broken using other information about the object plasma. Additional features from diffraction in the filter plane often complicate data analysis. Here, in this paper, we present an improved AF design that uses a stochastic pixel pattern with a sinusoidal radial profile to minimize unwanted diffraction effects in the image caused by the sharp edges of the filter bands. We also present a technique in which a pair of AFs with different patterns on two branches of the same probe beam can be used to break the density gradient degeneracy. Both techniques are demonstrated using a synthetic diagnostic and data collected on the OMEGA EP (extended performance) laser.

47 OTHER INSTRUMENTATION↗
DOE OSTI2023

Assessing carbon storage capacity and saturation across six central US grasslands using data–model integration

Abstract. Future global changes will impact carbon (C) fluxes and pools in most terrestrial ecosystems and the feedback of terrestrial carbon cycling to atmospheric CO2. Determining the vulnerability of C in ecosystems to future environmental change is thus vital for targeted land management and policy. The C capacity of an ecosystem is a function of its C inputs (e.g., net primary productivity – NPP) and how long C remains in the system before being respired back to the atmosphere. The proportion of C capacity currently stored by an ecosystem (i.e., its C saturation) provides information about the potential for long-term C pools to be altered by environmental and land management regimes. We estimated C capacity, C saturation, NPP, and ecosystem C residence time in six US grasslands spanning temperature and precipitation gradients by integrating high temporal resolution C pool and flux data with a process-based C model. As expected, NPP across grasslands was strongly correlated with mean annual precipitation (MAP), yet C residence time was not related to MAP or mean annual temperature (MAT). We link soil temperature, soil moisture, and inherent C turnover rates (potentially due to microbial function and tissue quality) as determinants of carbon residence time. Overall, we found that intermediates between extremes in moisture and temperature had low C saturation, indicating that C in these grasslands may trend upwards and be buffered against global change impacts. Hot and dry grasslands had greatest C saturation due to both small C inputs through NPP and high C turnover rates during soil moisture conditions favorable for microbial activity. Additionally, leaching of soil C during monsoon events may lead to C loss. C saturation was also high in tallgrass prairie due to frequent fire that reduced inputs of aboveground plant material. Accordingly, we suggest that both hot, dry ecosystems and those frequently disturbed should be subject to careful land management and policy decisions to prevent losses of C stored in these systems.

58 GEOSCIENCES↗
DOE OSTI2026

Structure preservation using discrete gradients in the Vlasov-Poisson-Landau system

We present a novel structure-preserving framework for solving the Vlasov-Poisson-Landau system of equations using a particle in cell (PIC) discretization combined with discrete gradient time integrators. The Vlasov-Poisson-Landau system is an accurate model for studying hot plasma dynamics at a kinetic scale where small-angle Coulomb collisions dominate. Our scheme guarantees conservation of mass, momentum and energy as well as preservation of the monotonicity of entropy production in both the time-continuous and discrete systems. We employ the conservative integrator for both the Hamiltonian Vlasov-Poisson equations and the dissipative Landau equation using the PETSc library (www.mcs.anl.gov/petsc) to showcase structure-preserving properties.

Discrete gradients↗
DOE OSTI2024

AI-Driven Detector Design for the EIC (Final Technical Report)

We developed an optimization workflow based on DNN-based fast-simulation and reconstruction algorithms. We used these methods to advance the design of calorimeter systems for the Electron-Ion Collider (EIC). This DNN-driven optimization provides a blueprint for integrating gradient-based methods into detector-design workflows. All software pipelines and methods have been released publicly and incorporated into the EIC collaboration’s physics studies, broadening their impact. Three journal articles detailing the methods developed here serve as a reference for the design and optimal use of next generation high-granularity calorimeter systems in nuclear and particle physics.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2023

MaNGA DynPop – II. Global stellar population, gradients, and star-formation histories from integral-field spectroscopy of 10K galaxies: link with galaxy rotation, shape, and total-density gradients

ABSTRACT This is the second paper of the Mapping Nearby Galaxies at Apache Point Observatory (MaNGA) Dynamics and stellar Population (DynPop) series, which analyses the global stellar population, radial gradients, and non-parametric star-formation history of ∼10K galaxies from the MaNGA Survey final data release 17 and relates them with dynamical properties of galaxies. We confirm the correlation between the stellar population properties and the stellar velocity dispersion σe, but also find that younger galaxies are more metal-poor at fixed σe. Stellar age, metallicity, and mass-to-light ratio (M*/L) all decrease with increasing galaxy rotation, while their radial gradients become more negative (i.e. lower value at the outskirts). The exception is the slow rotators, which also appear to have significantly negative metallicity gradients, confirming the mass–metallicity gradient correlation. Massive disc galaxies in the green valley, on the $(\sigma _{\rm e},\rm age)$ plane, show the most negative age and metallicity gradients, consistent with their old central bulges surrounded by young star-forming discs and metal-poor gas accretion. Galaxies with high σe, steep total mass-density slope, low dark matter fraction, high M*/L, and high metallicity have the highest star-formation rate at earlier times, and are currently quenched. We also discover a population of low-mass star-forming galaxies with low rotation but physically distinct from the massive slow rotators. A catalogue of these stellar population properties is provided publicly.

Astronomy & Astrophysics↗