Search NASA⌕ Search

SEARCH · Search NASA

Results for “Training Analysis”

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 847 records · Page 47

SU-F-T-97: Outlier Identification in Radiation Therapy Knowledge Modeling

Purpose: To investigate the impact of outliers on knowledge modeling in radiation therapy, and develop a systematic workflow for identifying and analyzing geometric and dosimetric outliers using pelvic cases. Methods: Four groups (G1-G4) of pelvic plans were included: G1 (37 prostate cases), G2 (37 prostate plus lymph node cases), and G3 (37 prostate bed cases) are all clinical IMRT cases. G4 are 10 plans outside G1 re-planned with dynamic-arc to simulate dosimetric outliers. The workflow involves 2 steps: 1. identify geometric outliers, assess impact and clean up; 2. identify dosimetric outliers, assess impact and clean up.1. A baseline model was trained with all G1 cases. G2/G3 cases were then individually added to the baseline model as geometric outliers. The impact on the model was assessed by comparing leverage statistic of inliers (G1) and outliers (G2/G3). Receiver-operating-characteristics (ROC) analysis was performed to determine optimal threshold. 2. A separate baseline model was trained with 32 G1 cases. Each G4 case (dosimetric outliers) was then progressively added to perturb this model. DVH predictions were performed using these perturbed models for remaining 5 G1 cases. Normal tissue complication probability (NTCP) calculated from predicted DVH were used to evaluate dosimetric outliers’ impact. Results: The leverage of inliers and outliers was significantly different. The Area-Under-Curve (AUC) for differentiating G2 from G1 was 0.94 (threshold: 0.22) for bladder; and 0.80 (threshold: 0.10) for rectum. For differentiating G3 from G1, the AUC (threshold) was 0.68 (0.09) for bladder, 0.76 (0.08) for rectum. Significant increase in NTCP started from models with 4 dosimetric outliers for bladder (p<0.05), and with only 1 dosimetric outlier for rectum (p<0.05). Conclusion: We established a systematic workflow for identifying and analyzing geometric and dosimetric outliers, and investigated statistical metrics for detecting. Results validated the necessity for outlier detection and clean-up to enhance model quality in clinical practice. Research Grant: Varian master research grant.

60 APPLIED LIFE SCIENCES↗

A preliminary empirical evaluation of virtual reality as an instructional medium for visual-spatial tasks

We explored the training potential of Virtual Reality (VR) technology. Thirty-one adults were trained and tested on spatial skills in a VR. They learned a sequence of button and knob responses on a VR console and performed flawlessly on the same console. Half were trained with a rote strategy; the rest used a meaningful strategy. Response times were equivalent for both groups and decreased significantly over five test trials indicating that learning continued on VR tests. The same subjects practiced navigating through a VR building, which had three floors with four rooms on each floor. The dependent measure was the number of rooms traversed on routes that differed from training routes. Many subjects completed tests in the fewest rooms possible. All subjects learned configurational knowledge according to the criterion of taking paths that were significantly shorter than those predicted by a random walk as determined by a Monte Carlo analysis. The results were discussed as a departure point for empirically testing the training potential of VR technology.

Regian, J. Wesley↗

Application of Support Vector Regression to Derive Crater Depth/Diameter From Satellite Images

Through the study of impact crater shapes, one can draw important conclusions about the nature and evolution of planetary surfaces [e.g., 1-4].In particular, studying the depth (d) to diameter (D)ratio (d/D) of a population of impact craters, in combination with crater count statistics, can yield valuable insights regarding rates of erosion and burial[5]. Motivated by the great abundance of available planetary surface image data, the goal of this project is to develop an efficient way to estimate d/D from satellite images of impact craters for which stereo information is not available [6]. We set out to develop and train a machine learning algorithm to extract d/D from a dataset of synthetic impact crater images for which model d/D is known. The applications of machine learning to planetary science are numerous and diverse [7], including automatic planetary surface mapping [8] and the detection of impact craters [9]. Our algorithm makes use of Support Vector Regression (SVR), which is a type of Support Vector Machine (SVM) [10, 11].SVMs are a branch of supervised machine learning valued for their straightforward implementation and versatility in solving both classification and regression problems. In regression analysis, an SVR algorithm produces a hyperplane function to fit the training data points, as well as an ε-tube that surrounds the hyperplane. Tunable hyperparameters include the width of the ε-tube (ε) and the amount an algorithm is penalized for points which fall outside the ε-tube.

L R Chin↗

FORCE Output Data Visualization

The Framework for Optimization of ResourCes and Economics (FORCE) is a collection of software tools, models, and datasets acquired and developed under the Integrated Energy Systems (IES) program to enable analysis of technical and economic viability of myriad IES configurations. Idaho National Laboratory is hosting a training session for FORCE users and developers, which is "Integrated Energy Systems Tools FORCE Overview and Training 2023." We will present data output visualization results with FORCE scenarios as examples and show how does the new design improve existing automated visualization for analysis results.

25 ENERGY STORAGE↗

Multi-Objective design of interlocking metasurfaces using conditional diffusion models

Unit cell design remains a major challenge for interlocking metasurfaces, a promising joining technology for dissimilar materials, due to the complex, competing, multivariate design space and the need for rapid adaptation to varying performance requirements. This study explores Conditional Diffusion Models as a design optimization tool for interlocking metasurfaces. Given the complex, competing, multivariate design space for interlocking metasurfaces, unit cell design remains a major challenge for this joining technology. We trained a conditional diffusion model on 25,000 finite element analysis-simulated interlocking metasurface unit cells to generate designs with tailored thermo-mechanical properties (tensile strength, shear strength, and thermal conductivity) based on specified performance criteria. The model demonstrated a success rate of approximately 72 % in producing designs that met specified property bounds. The conditional diffusion model generated both thermally resistive and conductive designs, revealing clear trends in design characteristics: taller, dendritic structures were advantageous for tensile loads, while shorter, robust designs excelled in shear applications. Our findings indicate that the model's performance is more influenced by the breadth of the design space than by the quantity of training data, highlighting the importance of expansive design domains for generating innovative solutions. This work establishes conditional diffusion models as a highly efficient and adaptable tool for rapid interlocking metasurface unit cell design, paving the way for advancements in multi-material joining technologies, as well as highlighting the justification to leverage conditional diffusion models as design tools across complex design domains.

Conditional diffusion models↗

Neural Network Based State of Health Diagnostics for an Automated Radioxenon Sampler/Analyzer

Artificial neural networks (ANNs) are used to determine the state-of-health (SOH) of the Automated Radioxenon Analyzer/Sampler (ARSA). ARSA is a gas collection and analysis system used for non-proliferation monitoring in detecting radioxenon released during nuclear tests. SOH diagnostics are important for automated, unmanned sensing systems so that remote detection and identification of problems can be made without onsite staff. Both recurrent and feed-forward ANNs are presented. The recurrent ANN is trained to predict sensor values based on current valve states, which control air flow, so that with only valve states the normal SOH sensor values can be predicted. Deviation between modeled value and actual is an indication of a potential problem. The feed-forward ANN acts as a nonlinear version of principal components analysis (PCA) and is trained to replicate the normal SOH sensor values. Because of ARSA’s complexity, this nonlinear PCA is better able to capture the relationships among the sensors than standard linear PCA and is applicable to both sensor validation and recognizing off-normal operating conditions. Both models provide valuable information to detect impending malfunctions before they occur to avoid unscheduled shutdown. Finally, the ability of ANN methods to predict the system state is presented.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗

Entry, Descent, and Landing Operations Analysis for the Stardust Re-Entry Capsule

On the morning of January 15, 2006, the Stardust capsule successfully landed at the Utah Test and Training range in northwest Utah returning cometary samples from the comet Wild-2. An overview of the entry, descent, and landing (EDL) trajectory analysis that was performed for targeting during the Stardust Mission Navigation Operations Phase upon final approach to Earth is described. In addition, how the predicted landing location and the resulting overall 99 percentile landing footprint ellipse obtained from a Monte Carlo analysis changed over the final days and hours prior to entry is also presented. The navigation and EDL operations effort accurately delivered the entry capsule to the desired landing site. The final landing location was 8.1 km from the target, which was well within the allowable landing area.

Desao, Prasun N.↗

Analysis-Specific Fast Simulation at the LHC with Deep Learning

Abstract We present a fast-simulation application based on a deep neural network, designed to create large analysis-specific datasets. Taking as an example the generation of W + jet events produced in $$\sqrt{s}=$$ s = 13 TeV proton–proton collisions, we train a neural network to model detector resolution effects as a transfer function acting on an analysis-specific set of relevant features, computed at generation level, i.e., in absence of detector effects. Based on this model, we propose a novel fast-simulation workflow that starts from a large amount of generator-level events to deliver large analysis-specific samples. The adoption of this approach would result in about an order-of-magnitude reduction in computing and storage requirements for the collision simulation workflow. This strategy could help the high energy physics community to face the computing challenges of the future High-Luminosity LHC.

Chen, C.↗

DONUT: physics-aware machine learning for real-time X-ray nanodiffraction analysis

Coherent X-ray scattering techniques are critical for investigating the fundamental structural properties of materials at the nanoscale. While advancements have made these experiments more accessible, real-time analysis remains a significant bottleneck, often hindered by artifacts and computational demands. In scanning X-ray nanodiffraction microscopy, which is widely used to spatially resolve structural heterogeneities, this challenge is compounded by the convolution of the divergent beam with the sample’s local structure. To address this, we introduce DONUT (Diffraction with Optics for Nanobeam by Unsupervised Training), a physics-aware neural network designed for the rapid and automated analysis of nanobeam diffraction data. By incorporating a differentiable geometric diffraction model directly into its architecture, DONUT learns to predict crystal lattice strain and orientation in real-time. Crucially, this is achieved without reliance on labeled datasets or pre-training, overcoming a fundamental limitation for supervised machine learning in X-ray science. We demonstrate experimentally that DONUT accurately extracts all features within the data over 200 times more efficiently than conventional fitting methods.

Materials science↗

DONUT: Physics-aware Machine Learning for Real-time X-ray Nanodiffraction Analysis

SF-25-088 Coherent X-ray scattering techniques are critical for investigating the fundamental structural properties of materials at the nanoscale. While advancements have made these experiments more accessible, real-time analysis remains a significant bottleneck, often hindered by artifacts and computational demands. In scanning X-ray nanodiffraction microscopy, which is widely used to spatially resolve structural heterogeneities, this challenge is compounded by the convolution of the divergent beam with the sample’s local structure. To address this, we introduce DONUT (Diffraction with Optics for Nanobeam by Unsupervised Training), a physics-aware neural network designed for the rapid and automated analysis of nanobeam diffraction data. By incorporating a differentiable geometric diffraction model directly into its architecture, DONUT learns to predict crystal lattice strain and orientation in real-time. Crucially, this is achieved without reliance on labeled datasets or pre-training, overcoming a fundamental limitation for supervised machine learning in X-ray science. We demonstrate experimentally that DONUT accurately extracts all features within the data over 200 times more efficiently than conventional fitting methods.

Zhou, Tao [Argonne National Laboratory (ANL), Argo↗

An artificial neural network framework for reduced order modeling of transient flows

Here, this paper proposes a supervised machine learning framework for the non-intrusive model order reduction of unsteady fluid flows to provide accurate predictions of non-stationary state variables when the control parameter values vary. Our approach utilizes a training process from full-order scale direct numerical simulation data projected on proper orthogonal decomposition (POD) modes to achieve an artificial neural network (ANN) model with reduced memory requirements. This data-driven ANN framework allows for a nonlinear time evolution of the modal coefficients without performing a Galerkin projection. Our POD-ANN framework can thus be considered an equation-free approach for latent space dynamics evolution of nonlinear transient systems and can be applied to a wide range of physical and engineering applications. Within this framework we introduce two architectures, namely sequential network (SN) and residual network (RN), to train the trajectory of modal coefficients. We perform a systematic analysis of the performance of the proposed reduced order modeling approaches on prediction of a nonlinear wave-propagation problem governed by the viscous Burgers equation, a simplified prototype setting for transient flows. We find that the POD-ANN-RN yields stable and accurate results for test problems assessed both within inside and outside of the database range and performs significantly better than the standard intrusive Galerkin projection model. Finally, our results show that the proposed framework provides a non-intrusive alternative to the evolution of transient physics in a POD basis spanned space, and can be used as a robust predictive model order reduction tool for nonlinear dynamical systems.

42 ENGINEERING↗

Ensemble cure kinetics network (ECK-Net): A method to derive cure kinetics of thermosetting resin

This paper introduces an Ensemble Cure Kinetics Network (ECK-Net), a neural network (NN)–based framework for modeling the cure kinetics of thermosetting resins within a phenomenological context. ECK-Net replaces traditional analytic models, which require extensive chemical insight and multiple isothermal/non-isothermal experiments, with a data-driven surrogate that maps nonlinear relationships between temperature, degree of cure, and reaction rate from differential scanning calorimetry data. The proposed approach predicts input-dependent kinetic coefficients of a generalized nth-order reaction equation rather than reaction rates directly, enabling a single unified model to represent various epoxy systems without relying on iso-conversional analysis or predefined functional forms. To ensure robustness, multiple independently trained networks under different random initializations are blended through an ensemble strategy, effectively mitigating the stochastic variability inherent to neural networks. The framework is validated using experimental datasets from multiple resin systems, including aerospace-grade materials (Toray 3900-2, Cycom 5320-1, and Hexcel 8552) and a windmill-grade resin (RIMR 035c). The model accurately reproduces the temporal evolution of the degree of cure under manufacturers’ recommended cure cycles across all tested resins systems, yielding Pearson’s correlation coefficients of 0.992, 0.994, 0.993, 0.997, respectively. To demonstrate process-level applicability, the trained network was implemented within the Abaqus environment to simulate out-of-autoclave (OOA) curing process of the CFRP panel composed of Toray T830H-6K/3900-2D prepreg. The simulation results showed excellent agreement with experimental temperature response (maximum peak temperature, simulation: 189.6 °C, experiment: 188.5 °C) and the final degree of cure (simulation: 0.948, experiment: 0.960 ± 0.013), confirming ECK-Net’s capability as a reliable alternative to conventional cure kinetics modeling methods.

Composite curing↗

Scalability analysis of heavy-duty gas turbines using data-driven machine learning

With the increasing integration of variable renewable energy sources into power systems, the role of flexible power generation technologies like gas turbines (GT) in rapid grid balancing remains crucial. This sustained importance underscores the need for scaled and precise modeling of GT to ensure effective integration within evolving energy frameworks. While physics-driven GT models integrate thermodynamics, fluid dynamics, and combustion principles, they often rely on approximate mathematical representations to accommodate scaling that may not capture the actual complex dynamics for GTs and inertial effects associated to GTs with different ratings. In this study, a data-driven model is proposed using machine learning (ML) techniques to conduct GT scalability analysis and performance evaluation with high accuracy. The ML model, trained on data from various operating conditions and performance parameters, aims to uncover intricate relationships and patterns, resembling GT characteristics at different scales (ratings). The model is developed to capture complex system interaction and to adapt to changing operational scenarios at different capacities, providing valuable insights of power system dynamics. In this study, the real-time digital simulator platform was employed to generate training data for the ML model and assess its dynamic characteristics. The ultimate objective was to develop a detailed modeling framework based on governing equations and data-driven ML capable of predicting key performance indicators, in thermal systems such as GTs, including power output, speed, fuel consumption, and exhaust temperature under diverse operating conditions at different scales. The developed ML framework demonstrated high accuracy, with mean relative errors for GT power prediction, reference speed, exhaust temperature, and compressor pressure ratio (CPR) parameters consistently below 0.1% across typical load fluctuation scenarios. Maximum deviations were limited to approximately 0.5 K for exhaust temperature and 0.009 for CPR, underscoring the model’s ability to replicating dynamic GT behavior with high precision. The adaptability of the ML model enables its application across diverse operational conditions and its extension to other thermal systems. By leveraging advanced ML techniques, this study presents a robust and scalable modeling framework that enhances GT simulation precision, facilitating improved integration into evolving power systems.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Improved accuracy in quantitative laser-induced breakdown spectroscopy using sub-models

We report that accurate quantitative analysis of diverse geologic materials is one of the primary challenges faced by the Laser-Induced Breakdown Spectroscopy (LIBS)-based ChemCam instrument on the Mars Science Laboratory (MSL) rover. The SuperCam instrument on the Mars 2020 rover, as well as other LIBS instruments developed for geochemical analysis on Earth or other planets, will face the same challenge. Consequently, part of the ChemCam science team has focused on the development of improved multivariate analysis calibrations methods. Developing a single regression model capable of accurately determining the composition of very different target materials is difficult because the response of an element’s emission lines in LIBS spectra can vary with the concentration of other elements. We demonstrate a conceptually simple “submodel” method for improving the accuracy of quantitative LIBS analysis of diverse target materials. The method is based on training several regression models on sets of targets with limited composition ranges and then “blending” these “sub-models” into a single final result. Tests of the sub-model method show improvement in test set root mean squared error of prediction (RMSEP) for almost all cases. Lastly, the sub-model method, using partial least squares regression (PLS), is being used as part of the current ChemCam quantitative calibration, but the sub-model method is applicable to any multivariate regression method and may yield similar improvements.

47 OTHER INSTRUMENTATION↗

Strategies and Software for Machine Learning Accelerated Discovery in Transition Metal Chemistry

Machine learning the electronic structure of open shell transition metal complexes presents unique challenges, including robust and automated data set generation. In this report we introduce tools that simplify data acquisition from density functional theory (DFT) and validation of trained machine learning models using the molSimplify automatic design (mAD) workflow. We demonstrate this workflow by training and comparing the performance of LASSO, kernel ridge regression (KRR), and artificial neural network (ANN) models using heuristic, topological revised autocorrelation (RAC) descriptors we have recently introduced for machine learning inorganic chemistry. On a series of open shell transition metal complexes, we evaluate set aside test errors of these models for predicting the HOMO level and HOMO–LUMO gap. The best performing models are ANNs, which show 0.15 and 0.25 eV test set mean absolute errors on the HOMO level and HOMO–LUMO gap, respectively. Poor performing KRR models using the full 153-feature RAC set are improved to nearly the same performance as the ANNs when trained on down-selected subsets of 20–30 features. Analysis of the essential descriptors for HOMO level and HOMO–LUMO gap prediction as well as comparison to subsets previously obtained for other properties reveal the paramount importance of nonlocal, steric properties in determining frontier molecular orbital energetics. We demonstrate our model performance on diverse complexes and in the discovery of molecules with target HOMO–LUMO gaps from a large 15,000 molecule design space in minutes rather than days that full DFT evaluation would require.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Enhance Low Level Temperature and Moisture Profiles Through Combining NUCAPS, ABI Observations, and RTMA Analysis

Thermodynamic information from low levels in the atmosphere is crucial for operational weather forecasts and meteorological researchers. The NOAA Unique Combined Atmospheric Processing System (NUCAPS) sounding products have been proven beneficial to fill the data gap between synoptic radiosonde observations (RAOBs). However, compared with the upper troposphere, the accuracy of NUCAPS soundings in the low levels still needs improvement. In this study, a deep neural network (DNN) is applied to fuse multiple data sources to enhance the NUCAPS temperature and moisture profiles in the lower atmosphere. The network is developed by combining satellite observations, including NUCAPS sounding retrievals and high resolution geostationary satellite observations from the Advanced Baseline Imager, and surface analysis from the Real-Time Mesoscale Analysis (RTMA) as inputs, while collocated soundings from ECMWF re-analysis version 5 are used as the benchmark for the training. The performance of the model is evaluated by using the independent testing data set, data from a different year, as well as collocated RAOBs, showing improvement to the temperature and moisture profiles by reducing the root-mean-squared-error (RMSE) by more than 30% in the lower atmosphere (from 700 hPa to surface) in both clear sky and partially cloudy conditions. A convective event from June 18, 2017 is presented to illustrate the application of the enhanced low level soundings on high impact weather events. The enhanced soundings from fused data capture the large surface-based convective available potential energy structures in the preconvection environment, which is very useful for severe storm nowcasting and forecasting applications.

54 ENVIRONMENTAL SCIENCES↗

Empowering Machine Learning Forecasting of Labquake Using Event‐Based Features and Clustering Characteristics

Abstract Following recent advances of machine learning (ML), we present a novel approach to extract spatiotemporal seismo‐mechanical features from Acoustic Emission (AE) catalogs to empower ML‐based forecasting. The AE data were recorded during laboratory stick‐slip experiments on granite samples cut by rough faults. Based on the features computed for a past time window, a random forest (RF) classifier is used to forecast the occurrence of a large magnitude event ( M AE > 3.5) in the next time window. Event‐based features allow us to associate informative time‐space characteristics to each feature and nearest‐neighbor clustering analysis enables us to separate background and clustered seismicity and train individual models. The results show that the separation of AEs enhances the forecasting accuracy from 73.2% for the entire catalog up to 82.1% and 89.0% if background and clustered events are used separately. The presented new approach may be upscaled for applications to forecast tectonic earthquakes.

Karimpouli, Sadegh↗

The data-driven future of high-energy-density physics

High-energy-density physics is the field of physics concerned with studying matter at extremely high temperatures and densities. Such conditions produce highly nonlinear plasmas, in which several phenomena that can normally be treated independently of one another become strongly coupled. The study of these plasmas is important for our understanding of astrophysics, nuclear fusion and fundamental physics—however, the nonlinearities and strong couplings present in these extreme physical systems makes them very difficult to understand theoretically or to optimize experimentally. Here we argue that machine learning models and data-driven methods are in the process of reshaping our exploration of these extreme systems that have hitherto proved far too nonlinear for human researchers. Furthermore, from a fundamental perspective, our understanding can be improved by the way in which machine learning models can rapidly discover complex interactions in large datasets. From a practical point of view, the newest generation of extreme physics facilities can perform experiments multiple times a second (as opposed to approximately daily), thus moving away from human-based control towards automatic control based on real-time interpretation of diagnostic data and updates of the physics model. To make the most of these emerging opportunities, we suggest proposals for the community in terms of research design, training, best practice and support for synthetic diagnostics and data analysis.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗