Search NASA⌕ Search

SEARCH · Search NASA

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

Integrated Design of Downwind Land-Based Wind Turbines using Analytic Gradients

Wind turbines are complex systems where component-level changes can have significant system-level effects. Effective wind turbine optimization generally requires an integrated analysis approach with a large number of design variables. Optimizing across large variable sets is orders of magnitude more efficient with gradient-based methods as compared with gradient-free method, particularly when using exact gradients. We have developed a wind turbine analysis set of over 100 components where 90% of the models provide numerically exact gradients through symbolic differentiation, automatic differentiation, and adjoint methods. This framework is applied to a specific design study focused on downwind land-based wind turbines. Downwind machines are of potential interest for large wind turbines where the blades are often constrained by the stiffness required to prevent a tower strike. The mass of these rotor blades may be reduced by utilizing a downwind configuration where the constraints on tower strike are less restrictive. The large turbines of this study range in power rating from 5-7MW and in diameter from 105m to 175m. The changes in blade mass and power production have important effects on the rest of the system, and thus the nacelle and tower systems are also optimized. For high-speed wind sites, downwind configurations do not appear advantageous. The decrease in blade mass (10%) is offset by increases in tower mass caused by the bending moment from the rotor-nacelle-assembly. For low-wind speed sites, the decrease in blade mass is more significant (25-30%) and shows potential for modest decreases in overall cost of energy (around 1-2%).

17 WIND ENERGY↗

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↗

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↗

SU-E-I-41: Non-Cartesian MR Image Reconstruction with Integrated Gradient Non-Linearity Correction

Purpose: Nonlinearities in the spatial encoding gradients of MRI systems cause geometric distortion in images. Typically, this is retrospectively corrected via image-domain interpolation (a.k.a., “gradwarp”) albeit with a loss of spatial resolution. For non-Cartesian MRI, the latter problem is exaggerated by noise and undersampling artifact. In this study, we describe a novel correction strategy that accounts for gradient nonlinearities during — rather than after — non-Cartesian MRI reconstruction, and demonstrate that this approach mitigates the resolution loss that can occur with standard methods. Methods: To test the proposed method, the American College of Radiology (ACR) quality control phantom was scanned on at 1.5 T (General Electric, v16.0, “zoom” gradient) using a 1.6x undersampled 3D non- Cartesian Shells trajectory (GRE, FOV=24 cm3, 120 shells, 16552 shots, 512 readout, matrix=2403). Image reconstruction was first performed via standard k-space density-compensated gridding and retrospectively corrected via cubic spline interpolation. Image reconstruction was then separately performed using a k-space and image-domain densitycompensated type-3 non-uniform fast Fourier transform (NUFFT), which provides a direct mapping between non-Cartesian k-space samples and warped image space voxel locations. Thus, no separate distortion correction procedure is needed for the proposed approach. The gradient distortion field was determined using vendor provided calibration data. Results: Phantom scan results show that both processing approaches successfully correct geometric distortion. However, visual inspection of the ACR phantom spatial resolution inserts shows that the proposed strategy preserves the resolution of the nominal (uncorrected) reconstruction while “gradwarp” imparts marked spatial blurring (especially for the 1.0 and 1.1 mm inserts) and thus resolution loss. Conclusion: We've presented a novel reconstruction strategy for non-Cartesian MRI that corrects for gradient nonlinearities during — rather than after — reconstruction, and thus better preserves image resolution than traditional interpolation-based methods. This approach is expected to be especially advantageous when imaging with non-standard magnet geometries. NIH RR018898; NIH EB10065.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Summary of QM02 Measurements

This note summarizes both the beam-based and various laboratory measurements of quadrupole magnets, units 387 and 428, used for QM02 in the LCLS Injector. These were undertaken because of a consistent discrepancy between accelerator model predictions and beam observations which seemed to indicate a weak QM02. A report 'QM02 Strength Measurement', by Welch and Wu, describes the discrepancy and beam-based measurements on unit 387. Subsequently, unit 387 was replaced by unit 428, refinements were made to analysis of the beam-based measurements were made, and additional magnetic measurements were made on unit 387 in the lab. These new results are summarized in this note. The principle results are: (1) Laboratory measurements of integrated gradient for the same magnet, or for different magnets of the same type, are all within 1% of each other at gradients of interest. These cases cover three independent types of measurements, disassembly/reassembly of the units, and extended periods of time between measurements. (2) Standardization, or lack thereof, can cause integrated gradient errors of approximately 0.2 kG, which can amount to a few percent of the strength of the magnet depending on the setting. (3) Model-independent beam-based measurements indicate the magnets are actually weaker than expected by about 2 percent, but these measurements are subject to the uncertainty of the BPMS1 location. (4) The standardization cycle is effective. (5) The stainless steel BPM vacuum chamber inside the magnets has no significant effect on the beam. The discrepancy between the accelerator model predictions and the actual orbit response is not resolved, but the evidence points away from magnetic strength errors as the source. Differences between the model locations and effective locations of BPM's is a possible culprit. This idea is explored in Section 2. Table 1 summarizes the measurement activities that were performed on the units. The dates listed correspond to the date when the relevent series of runs was completed.

43 PARTICLE ACCELERATORS↗

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↗

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↗

Better HMC integrators for dynamical simulations

We show how to improve the molecular dynamics step of Hybrid Monte Carlo, both by tuning the integrator using Poisson brackets measurements and by the use of force gradient integrators. We present results for moderate lattice sizes.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Generalizable Class Solutions for Treatment Planning of Spinal Stereotactic Body Radiation Therapy

Purpose: Spinal stereotactic body radiation therapy (SBRT) continues to emerge as an effective therapeutic approach to spinal metastases; however, treatment planning and delivery remain resource intensive at many centers, which may hamper efficient implementation in clinical practice. We sought to develop a generalizable class solution approach for spinal SBRT treatment planning that would allow confidence that a given plan provides optimal target coverage, reduce integral dose, and maximize planning efficiency. Methods and Materials: We examined 91 patients treated with spinal SBRT at our institution. Treatment plans were categorized by lesion location, clinical target volume (CTV) configuration, and dose fractionation scheme, and then analyzed to determine the technically achievable dose gradient. A radial cord expansion was subtracted from the CTV to yield a planning CTV (pCTV) construct for plan evaluation. We reviewed the treatment plans with respect to target coverage, dose gradient, integral dose, conformality, and maximum cord dose to select the best plans and develop a set of class solutions. Results: The class solution technique generated plans that maintained target coverage and improved conformality (1.2-fold increase in the 95% van't Riet Conformation Number describing the conformality of a reference dose to the target) while reducing normal tissue integral dose (1.3-fold decrease in the volume receiving 4 Gy (V{sub 4Gy}) and machine output (19% monitor unit (MU) reduction). In trials of planning efficiency, the class solution technique reduced treatment planning time by 30% to 60% and MUs required by {approx}20%: an effect independent of prior planning experience. Conclusions: We have developed a set of class solutions for spinal SBRT that incorporate a pCTV metric for plan evaluation while yielding dosimetrically superior treatment plans with increased planning efficiency. Our technique thus allows for efficient, reproducible, and high-quality spinal SBRT treatment planning.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

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↗

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↗

Optical generation of a spatially variant two-dimensional lattice structure by using a phase only spatial light modulator

We propose a simple and straightforward method to generate spatially variant lattice structures by optical interference lithography method. Using this method, it is possible to independently vary the orientation and period of the two-dimensional lattice. The method consists of two steps which are: numerical synthesis of corresponding phase mask by employing a two-dimensional integrated gradient calculations and experimental implementation of synthesized phase mask by making use of a phase only spatial light modulator in an optical 4f Fourier filtering setup. As a working example, we provide the experimental fabrication of a spatially variant square lattice structure which has the possibility to guide a Gaussian beam through a 90° bend by photonic crystal self-collimation phenomena. The method is digitally reconfigurable, is completely scalable, and could be extended to other kind of lattices as well.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

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↗

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↗