Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Prediction Accuracy”

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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Generating An Advanced Cross-section Library For HTGR Pebble Bed Depletion Calculations Using Reduced-Order Model Generation Techniques

For code development, Advanced Reactor Technologies - Gas Cooled Reactors Program (ART-GCR) rely on a collaboration with the Nuclear Energy Advanced Modeling and Simulation (NEAMS) program, but the cross sections generation and the methodology definition is part of this program area goals. Based on previous studies in FY23, the size of microscopic cross section libraries increases rapidly with the number of tabulations, requiring significant amount of memory and drastically slowing down the Griffin calculations when evaluating cross sections via the multivariate linear interpolation approach. Rising to these challenges, this work investigates constructing Reduced-order Models (ROMs) for the multi-group microscopic cross sections to accelerate the cross section evaluation in Griffin. A database of multigroup cross sections is first collected considering all possible parameters that a designer could change for optimization. Down-selection of the ROM techniques afterward shows Deep Neural Network (DNN) as the best candidate when jointly consider memory efficiency, predictive accuracy, computational cost, scalability, flexibility and ease of implementation of the algorithms in comparison to the multidimensional interpolation. This work develops a specific interface that enables the cross section predictions using pre-trained DNN models into Griffin leveraging the existing ROM capabilities. DNNs have been trained for all isotopes for use in Griffin. Preliminary Griffin testing shows that DNNs exhibit exceptional predictive accuracy and the use of DNNs provides orders of magnitude improvement in memory efficiency compared to conventional interpolation techniques. With such ROM techniques, it holds great promise to further increase the fidelity of the Pebble Bed Reactor (PBR) simulation by increasing the number of tabulations/state variables during cross section evaluation, while maintaining the computational cost affordable in Griffin.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
NASA NTRS1992

Interval prediction in structural dynamic analysis

Methods for assessing the predictive accuracy of structural dynamic models are examined with attention given to the effects of modal mass, stiffness, and damping uncertainties. The methods are based on a nondeterministic analysis called 'interval prediction' in which interval variables are used to describe parameters and responses that are unknown. Statistical databases for generic modeling uncertainties are derived from experimental data and incorporated analytically to evaluate responses. Covariance matrices of modal mass, stiffness, and damping parameters are propagated numerically in models of large space structures by means of three methods. The test data tend to fall within the predicted intervals of uncertainty determined by the statistical databases. The present findings demonstrate the suitability of using data from previously analyzed and tested space structures for assessing the predictive accuracy of an analytical model.

Hasselman, Timothy K.↗
NASA NTRS2016

Dynamic Filtering Improves Attentional State Prediction with fNIRS

Brain activity can predict a person's level of engagement in an attentional task. However, estimates of brain activity are often confounded by measurement artifacts and systemic physiological noise. The optimal method for filtering this noise - thereby increasing such state prediction accuracy - remains unclear. To investigate this, we asked study participants to perform an attentional task while we monitored their brain activity with functional near infrared spectroscopy (fNIRS). We observed higher state prediction accuracy when noise in the fNIRS hemoglobin [Hb] signals was filtered with a non-stationary (adaptive) model as compared to static regression (84% +/- 6% versus 72% +/- 15%).

Harrivel, Angela R.↗
DOE OSTI2025

ACES-GNN: can graph neural network learn to explain activity cliffs?

Graph Neural Networks (GNNs) have revolutionized molecular property prediction by leveraging graph-based representations, yet their opaque decision-making processes hinder broader adoption in drug discovery. This study introduces the Activity-Cliff-Explanation-Supervised GNN (ACES-GNN) framework, designed to simultaneously improve predictive accuracy and interpretability by integrating explanation supervision for activity cliffs (ACs) into GNN training. ACs, defined by structurally similar molecules with significant potency differences, pose challenges for traditional models due to their reliance on shared structural features. By aligning model attributions with chemist-friendly interpretations, the ACES-GNN framework bridges the gap between prediction and explanation. Validated across 30 pharmacological targets, ACES-GNN consistently enhances both predictive accuracy and attribution quality for ACs compared to unsupervised GNNs. Our results demonstrate a positive correlation between improved predictions and accurate explanations, offering a robust and adaptable framework to better understand and interpret ACs. This work underscores the potential of explanation-guided learning to advance interpretable artificial intelligence in molecular modeling and drug discovery.

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

Improving streamflow predictions across CONUS by integrating advanced machine learning models and diverse data

Accurate streamflow prediction is crucial to understand climate impacts on water resources and develop effective adaption strategies. A global long short-term memory (LSTM) model, using data from multiple basins, can enhance streamflow prediction, yet acquiring detailed basin attributes remains a challenge. To overcome this, we introduce the Geo-vision transformer (ViT)-LSTM model, a novel approach that enriches LSTM predictions by integrating basin attributes derived from remote sensing with a ViT architecture. Applied to 531 basins across the Contiguous United States, our method demonstrated superior prediction accuracy in both temporal and spatiotemporal extrapolation scenarios. Geo-ViT-LSTM marks a significant advancement in land surface modeling, providing a more comprehensive and effective tool for better understanding the environment responses to climate change.

Tayal, Kshitij↗
NASA NTRS1987

NORAD/SPACECMD comments concerning the atmospheric density models

Recent models do not produce more accurate neutral densities (although they require more computer time), regardless of the level of solar activity. This implies that there has been no measurable improvement of the calculation of neutral density since the early 60s. With known solar flux and geomagnetic activity (Ap) inputs, the density evaluation needs improvement. For highly eccentric orbits which span low to high altitude, the accuracy generated which has an altitude limitation of 1000 km remains comparable with those obtained by more recent models. This implies that either the density at 1000 km and above is insignificant or that the values provided by the recent models at high altitudes may not be reliable or both. Prediction accuracies obtained through the use of precision data from the Defense Mapping Agency are generally comparable to those obtained by using operational sensor data. This implies that the prediction accuracy problem is not necessarily caused by less accurate observations. The definition of the mean solar flux F10.7 is not universal.

Liu, Joseph J. F.↗
DOE OSTI2025

SA-GAT-SR: self-adaptable graph attention networks with symbolic regression for high-fidelity material property prediction

Recent advances in machine learning have demonstrated an enormous utility of deep learning approaches, particularly Graph Neural Networks (GNNs) for materials science. These methods have emerged as powerful tools for high-throughput prediction of material properties, offering a compelling enhancement and alternative to traditional first-principles calculations. While the community has predominantly focused on developing increasingly complex and universal models to enhance predictive accuracy, such approaches often lack physical interpretability and insights into materials behavior. Here, we introduce a novel computational paradigm—Self-Adaptable Graph Attention Networks integrated with Symbolic Regression (SA-GAT-SR)—that synergistically combines the predictive capability of GNNs with the interpretative power of symbolic regression. Our framework employs a self-adaptable encoding algorithm that automatically identifies and adjust attention weights so as to screen critical features from an expansive 180-dimensional feature space while maintaining O(n) computational scaling. The integrated SR module subsequently distills these features into compact analytical expressions that explicitly reveal quantum-mechanically meaningful relationships, achieving 23 × acceleration compared to conventional SR implementations that heavily rely on first-principle calculations-derived features as input. This work suggests a new framework in computational materials science, bridging the gap between predictive accuracy and physical interpretability, offering valuable physical insights into material behavior.

36 MATERIALS SCIENCE↗
NASA NTRS2019

Isotopologue Consistency of Semi-Empirically Computed InfraRed Line Lists and Further Improvement for Rare Isotopologues: CO2 and SO2 Case Studies.

The semi-empirical molecular rovibrational IR line lists, such as ExoMol, TheoReTs, and Ames, combine the experimental accuracy and theoretical power to reach better than 0.1 cm-1 accuracy for line positions and better than 80-90% agreement for line intensities. The quality of these existing semi-empirical IR lists allows further improvements of intensity and line positions for those unobserved minor isotopologues. This paper presents our new BTRHE (Best Theory + Reliable High-resolution Experiment) strategy implementation. For line intensity, the isotopologue consistency and the patterns of mass dependence in the Ames-296K SO2 and CO2 IR lists are quantitatively presented along the mass-inverse coordinates. The consistency and patterns are better than those in existing experimental data. The methodology proposed here can be used to identify inconsistencies, outliers, and mistakes in intensities, and help improve Effective Dipole Model (EDM) and molecular IR databases. We call for an experimental study on the 50006 and 60007 bands of CO2 628. For line position predictions, a simple approach combining the variational IR line lists with Effective Hamiltonian (EH) model may refine the effective rotational constants A0/B0/C0 and quartic centrifugal distortion constants of minor isotopologues. The prediction accuracy may be improved by two orders of magnitude, i.e. reaching 0-5 MHz prediction accuracy in the range of J<20-30, Ka<10-20, and 0.01-0.02 MHz accuracy for A0/B0/C0. Several important factors have been systematically investigated and discussed, e.g. convergence, uncertainties, higher order terms, fixing EH parameters, mass coordinates, etc. Amicrowave (MW) line set consisting of 644,636 strong transitions for all 30 isotopologues and corresponding refined EH(Ames) parameters are reported in the supplementary material. This approach may be easily extended to rovibrational bands, hot bands, and other molecular systems.

Xinchuan Huang↗
NASA NTRS2017

Filter Tuning Using the Chi-Squared Statistic

This paper examines the use of the Chi-square statistic as a means of evaluating filter performance. The goal of the process is to characterize the filter performance in the metric of covariance realism. The Chi-squared statistic is the value calculated to determine the realism of a covariance based on the prediction accuracy and the covariance values at a given point in time. Once calculated, it is the distribution of this statistic that provides insight on the accuracy of the covariance. The process of tuning an Extended Kalman Filter (EKF) for Aqua and Aura support is described, including examination of the measurement errors of available observation types, and methods of dealing with potentially volatile atmospheric drag modeling. Predictive accuracy and the distribution of the Chi-squared statistic, calculated from EKF solutions, are assessed.

Filter Tuning↗
DOE OSTI2022

Bayesian estimation of cross-section and errors of experiment and calculation for accurate prediction of neutronic characteristics

In some experiments, there might be a correlation of experimental errors such as an error caused by fabrication. The correlation of calculation errors also might exist among analyses of experiments. In the present study, considering these correlations, the cross-section and errors of experiment and calculation are adjusted for the accurate prediction of neutronic characteristics. The adjustment method is derived based on Bayesian theory. The 'a posteriori' distributions of cross-section and errors of experiment and calculation are obtained by the derivation. The case study is performed by using the benchmarks of light-water moderated experiments reported in ICSBEP. The error from fuel rod fabrication and measurement are included in the experiment error, and the error from the simplification of the benchmark model is included in the calculation error. Since these errors have a positive correlation among the benchmarks, the prediction accuracy is expected to be improved by considering these correlations. For the sensitivity analysis of the correlation among benchmarks, the correlation coefficient of experiment error and that of calculation error is assumed from 0.0 to 0.9. The results indicate that the prediction accuracy of the multiplication factor can be improved by increasing the correlation coefficient of experiment error and that of calculation error. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2024

Establishing performance metrics for quantitative non-targeted analysis: a demonstration using per- and polyfluoroalkyl substances

Abstract Non-targeted analysis (NTA) is an increasingly popular technique for characterizing undefined chemical analytes. Generating quantitative NTA (qNTA) concentration estimates requires the use of training data from calibration “surrogates,” which can yield diminished predictive performance relative to targeted analysis. To evaluate performance differences between targeted and qNTA approaches, we defined new metrics that convey predictive accuracy, uncertainty (using 95% inverse confidence intervals), and reliability (the extent to which confidence intervals contain true values). We calculated and examined these newly defined metrics across five quantitative approaches applied to a mixture of 29 per- and polyfluoroalkyl substances (PFAS). The quantitative approaches spanned a traditional targeted design using chemical-specific calibration curves to a generalizable qNTA design using bootstrap-sampled calibration values from “global” chemical surrogates. As expected, the targeted approaches performed best, with major benefits realized from matched calibration curves and internal standard correction. In comparison to the benchmark targeted approach, the most generalizable qNTA approach (using “global” surrogates) showed a decrease in accuracy by a factor of ~4, an increase in uncertainty by a factor of ~1000, and a decrease in reliability by ~5%, on average. Using “expert-selected” surrogates ( n = 3) instead of “global” surrogates ( n = 25) for qNTA yielded improvements in predictive accuracy (by ~1.5×) and uncertainty (by ~70×) but at the cost of further-reduced reliability (by ~5%). Overall, our results illustrate the utility of qNTA approaches for a subclass of emerging contaminants and present a framework on which to develop new approaches for more complex use cases. Graphical Abstract

Pu, Shirley (ORCID:0000000201223797)↗
NASA NTRS1991

Assessing damping uncertainty in space structures with fuzzy sets

NASA has been interested in the development of methods for evaluating the predictive accuracy of structural dynamic models. This interest stems from the use of mathematical models in evaluating the structural integrity of all spacecraft prior to flight. Space structures are often too large and too weak to be tested fully assembled in a ground test lab. The predictive accuracy of a model depends on the nature and extent of its experimental verification. The further the test conditions depart from in-service conditions, the less accurate the model will be. Structural damping is known to be one source of uncertainty in models. The uncertainty in damping is explored in order to evaluate the accuracy of dynamic models. A simple mass-spring-dashpot system is used to illustrate a comparison among three methods for propagating uncertainty in structural dynamics models: the First Order Method, the Numerical Simulation Method, and the Fuzzy Set Method. The Fuzzy Set Method is shown to bound the range of possible responses and thus to provide a valuable limiting check on the First Order Method near resonant conditions. Fuzzy Methods are a relative inexpensive alternative to numerical simulation.

Ross, Timothy J.↗
DOE OSTI2020

Comparison of heart rate obtained from shorter duration Holter recordings to 24-hour mean heart rate in dogs with atrial fibrillation

The objective of this study was to evaluate the accuracy of short duration electrocardiographic (ECG) recordings extracted from ambulatory continuous ECG (Holter) to assess 24-hour mean heart rate in dogs with atrial fibrillation. In this retrospective study, Holter recordings obtained from 20 dogs with atrial fibrillation were selected for analysis. Ten out of 20 dogs were receiving drugs to control heart rate at the time of Holter evaluation. From the Holter recordings, heart rate averages were calculated for various sample durations (fiveminutes, 30 minutes, one-hour, two-hours, and three-hours) for each dog. Percentage of these shorter duration ECG obtained HR averages that fell within ±10%, ±15% and ± 20% of 24-hour mean heart rate was determined for each sample duration and for each dog. Seventy five percent of heart rate averages obtained from three-hour ECG recordings fell within ±10% of 24-hour mean HR. All the heart rate averages obtained from two-hour ECG recordings fell within ±20% of 24-hour mean heart rate. Based on the results of this study it can be concluded that the duration of the ECG recording affects the prediction accuracy for 24-hour Holter mean HR. Only two and three hours of Holter recordings provided all heart rate averages within ±20% of 24-hour mean heart rate. No significant differences were noted in the prediction accuracy of shorter duration ECG recordings based on rate control therapy status. Further prospective studies are needed to assess the accuracy of HR obtained at home using various ECG recording devices to predict 24-hour mean heart rate in dogs with atrial fibrillation.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS2017

Filter Tuning Using the Chi-Squared Statistic

The Goddard Space Flight Center (GSFC) Flight Dynamics Facility (FDF) performs orbit determination (OD) for the Aqua and Aura satellites. Both satellites are located in low Earth orbit (LEO), and are part of what is considered the A-Train satellite constellation. Both spacecraft are currently in the science phase of their respective missions. The FDF has recently been tasked with delivering definitive covariance for each satellite.The main source of orbit determination used for these missions is the Orbit Determination Toolkit developed by Analytical Graphics Inc. (AGI). This software uses an Extended Kalman Filter (EKF) to estimate the states of both spacecraft. The filter incorporates force modelling, ground station and space network measurements to determine spacecraft states. It also generates a covariance at each measurement. This covariance can be useful for evaluating the overall performance of the tracking data measurements and the filter itself. An accurate covariance is also useful for covariance propagation which is utilized in collision avoidance operations. It is also valuable when attempting to determine if the current orbital solution will meet mission requirements in the future.This paper examines the use of the Chi-square statistic as a means of evaluating filter performance. The Chi-square statistic is calculated to determine the realism of a covariance based on the prediction accuracy and the covariance values at a given point in time. Once calculated, it is the distribution of this statistic that provides insight on the accuracy of the covariance.For the EKF to correctly calculate the covariance, error models associated with tracking data measurements must be accurately tuned. Over estimating or under estimating these error values can have detrimental effects on the overall filter performance. The filter incorporates ground station measurements, which can be tuned based on the accuracy of the individual ground stations. It also includes measurements from the NASA space network (SN), which can be affected by the assumed accuracy of the TDRS satellite state at the time of the measurement.The force modelling in the EKF is also an important factor that affects the propagation accuracy and covariance sizing. The dominant force in the LEO orbit regime is the drag force caused by atmospheric drag. Accurate accounting of the drag force is especially important for the accuracy of the propagated state. The implementation of a box and wing model to improve drag estimation accuracy, and its overall effect on the covariance state is explored.The process of tuning the EKF for Aqua and Aura support is described, including examination of the measurement errors of available observation types (Doppler and range), and methods of dealing with potentially volatile atmospheric drag modeling. Predictive accuracy and the distribution of the Chi-square statistic, calculated based of the ODTK EKF solutions, are assessed versus accepted norms for the orbit regime.

Covariance Analysis↗
DOE OSTI2024

Prognostic analysis of high-flow nasal cannula therapy and non-invasive ventilation in mild to moderate hypoxemia patients and construction of a machine learning model for 48-h intubation prediction—a retrospective analysis of the MIMIC database

Background This study aims to investigate the clinical outcome between high-flow nasal cannula (HFNC) and non-invasive ventilation (NIV) therapy in mild to moderate hypoxemic patients on the first ICU day and to develop a predictive model of 48-h intubation. Methods The study included adult patients from the MIMIC III and IV databases who first initiated HFNC or NIV therapy due to mild to moderate hypoxemia (100 < PaO2/FiO2 ≤ 300). The 48-h and 30-day intubation rates were compared using cross-sectional and survival analysis. Nine machine learning and six ensemble algorithms were deployed to construct the 48-h intubation predictive models, of which the optimal model was determined by its prediction accuracy. The top 10 risk and protective factors were identified using the Shapley interpretation algorithm. Result A total of 123,042 patients were screened, of which, 673 were from the MIMIC IV database for ventilation therapy comparison (HFNC n = 363, NIV n = 310) and 48-h intubation predictive model construction (training dataset n = 471, internal validation set n = 202) and 408 were from the MIMIC III database for external validation. The NIV group had a lower intubation rate (23.1% vs. 16.1%, p = 0.001), ICU 28-day mortality (18.5% vs. 11.6%, p = 0.014), and in-hospital mortality (19.6% vs. 11.9%, p = 0.007) compared to the HFNC group. Survival analysis showed that the total and 48-h intubation rates were not significantly different. The ensemble AdaBoost decision tree model (internal and external validation set AUROC 0.878, 0.726) had the best predictive accuracy performance. The model Shapley algorithm showed Sequential Organ Failure Assessment (SOFA), acute physiology scores (APSIII), the minimum and maximum lactate value as risk factors for early failure and age, the maximum PaCO 2 and PH value, Glasgow Coma Scale (GCS), the minimum PaO 2 /FiO 2 ratio, and PaO 2 value as protective factors. Conclusion NIV was associated with lower intubation rate and ICU 28-day and in-hospital mortality. Further survival analysis reinforced that the effect of NIV on the intubation rate might partly be attributed to the other impact factors. The ensemble AdaBoost decision tree model may assist clinicians in making clinical decisions, and early organ function support to improve patients’ SOFA, APSIII, GCS, PaCO 2 , PaO 2 , PH, PaO 2 /FiO 2 ratio, and lactate values can reduce the early failure rate and improve patient prognosis.

Fu, Wei↗
DOE OSTI2026

Virtual refrigerant charge sensing algorithm for residential CO₂ heat pumps

Natural refrigerants are increasingly adopted in next-generation heat pump systems, among which CO₂ heat pumps have attracted significant attention. However, due to their high operating pressures, the leakage risk is higher, resulting in undercharge conditions and degraded heat pump performance. Thus, developing an accurate refrigerant charge level detection technique is necessary to guarantee safe and efficient operation. Although virtual refrigerant charge (VRC) level calculation algorithms for CO₂ heat pumps exist, they typically rely on empirically selected features without a systematic selection framework, leading to multicollinearity and potential overfitting, which limit their prediction accuracy and generalizability. To address these issues, this study proposes a VRC algorithm framework with a systematic feature selection method that identifies physically meaningful and statistically significant features, and is applied using a residential CO₂ heat pump as a case study. The method is extended from previous work on conventional refrigerants to account for charge behavior in CO₂ gas coolers. The selected features include gas cooler outlet density, evaporator pressure, and superheat temperature. The results demonstrate that the proposed feature selection method significantly improves prediction accuracy compared to existing VRC approaches. A relatively small training dataset (∼30 samples) is sufficient for feature identification and model development. The developed algorithm achieves less than 3% prediction error under both undercharge and overcharge conditions, representing reductions of 46.7% and 35.3% compared to two recent reference VRC algorithms for transcritical CO₂ heat pumps reported in the literature. The proposed algorithm and feature selection method enhance leakage detection capability, facilitate the deployment of CO₂ heat pump systems, and contribute to reduced energy waste and maintenance costs.

Guo, Fangzhou [Lawrence Berkeley National Laborato↗
DOE OSTI2024

Transformer-powered surrogates close the ICF simulation-experiment gap with extremely limited data

Abstract Recent advances in machine learning, specifically transformer architecture, have led to significant advancements in commercial domains. These powerful models have demonstrated superior capability to learn complex relationships and often generalize better to new data and problems. This paper presents a novel transformer-powered approach for enhancing prediction accuracy in multi-modal output scenarios, where sparse experimental data is supplemented with simulation data. The proposed approach integrates transformer-based architecture with a novel graph-based hyper-parameter optimization technique. The resulting system not only effectively reduces simulation bias, but also achieves superior prediction accuracy compared to the prior method. We demonstrate the efficacy of our approach on inertial confinement fusion experiments, where only 10 shots of real-world data are available, as well as synthetic versions of these experiments.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

High Accuracy Indicators of Androgen Suppression Therapy Failure for Prostate Cancer—A Modeling Study

Prostate cancer is a serious public health concern in the United States. The primary obstacle to effective long-term management for prostate cancer patients is the eventual development of treatment resistance. Due to the uniquely chaotic nature of the neoplastic genome, it is difficult to determine the evolution of tumor composition over the course of treatment. Hence, a drug is often applied continuously past the point of effectiveness, thereby losing any potential treatment combination with that drug permanently to resistance. If a clinician is aware of the timing of resistance to a particular drug, then they may have a crucial opportunity to adjust the treatment to retain the drug’s usefulness in a potential treatment combination or strategy. In this study, we investigate new methods of predicting treatment failure due to treatment resistance using a novel mechanistic model built on an evolutionary interpretation of Droop cell quota theory. We analyze our proposed methods using patient PSA and androgen data from a clinical trial of intermittent treatment with androgen deprivation therapy. Our results produce two indicators of treatment failure. The first indicator, proposed from the evolutionary nature of the cancer population, is calculated using our mathematical model with a predictive accuracy of 87.3% (sensitivity: 96.1%, specificity: 65%). The second indicator, conjectured from the implication of the first indicator, is calculated directly from serum androgen and PSA data with a predictive accuracy of 88.7% (sensitivity: 90.2%, specificity: 85%). Our results demonstrate the potential and feasibility of using an evolutionary tumor dynamics model in combination with the appropriate data to aid in the adaptive management of prostate cancer.

59 BASIC BIOLOGICAL SCIENCES↗