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 793 records · Page 44
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Comparing Individualized Survival Predictions From Random Survival Forests and Multistate Models in the Presence of Missing Data: A Case Study of Patients With Oropharyngeal Cancer

Background: In recent years, interest in prognostic calculators for predicting patient health outcomes has grown with the popularity of personalized medicine. These calculators, which can inform treatment decisions, employ many different methods, each of which has advantages and disadvantages. Methods: We present a comparison of a multistate model (MSM) and a random survival forest (RSF) through a case study of prognostic predictions for patients with oropharyngeal squamous cell carcinoma. The MSM is highly structured and takes into account some aspects of the clinical context and knowledge about oropharyngeal cancer, while the RSF can be thought of as a black-box non-parametric approach. Key in this comparison are the high rate of missing values within these data and the different approaches used by the MSM and RSF to handle missingness. Results: We compare the accuracy (discrimination and calibration) of survival probabilities predicted by both approaches and use simulation studies to better understand how predictive accuracy is influenced by the approach to (1) handling missing data and (2) modeling structural/disease progression information present in the data. We conclude that both approaches have similar predictive accuracy, with a slight advantage going to the MSM. Conclusions: Although the MSM shows slightly better predictive ability than the RSF, consideration of other differences are key when selecting the best approach for addressing a specific research question. These key differences include the methods’ ability to incorporate domain knowledge, and their ability to handle missing data as well as their interpretability, and ease of implementation. Ultimately, selecting the statistical method that has the most potential to aid in clinical decisions requires thoughtful consideration of the specific goals.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

Environmental and ecological signals predict food shortages for subtropical populations of Australian flying foxes, reservoirs of Hendra virus

Food availability determines where and how animals use space across a landscape and, therefore, affects the risk of encounters leading to zoonotic spillover. This relationship is evident in Australian flying foxes (Pteropus spp.; fruit bats), where acute food shortages precede clusters of Hendra virus spillovers. Using machine learning, we predicted months of food shortages from climatological and ecological covariates (1996–2022) in subtropical Australia. Overall accuracy in predicting months of low food availability on a test set from 2018 up to 2022 reached 93.33 and 92.59% based on climatological and bat-level features, respectively. Seasonality and the Oceanic El Niño Index were the most important environmental features, while the number of bats in rescue centres and their body weights were the most important bat-level features. These models support predictive signals up to nine months in advance, facilitating action to mitigate spillover risk.

Pteropus↗
DOE OSTI2021

pnnl/mol_dgnn

Molecular dynamics simulations often rely on parameterized atomistic potentials, which can be inaccurate compared to ab initio simulation methods. However, dynamic ab initio simulations come with high computational cost. Deep learning techniques offer a method to obtain both high accuracy and low cost predictions of dynamics. Our method gives a prediction of the structural dynamics of a molecule accounting for the prior dynamics, giving high-accuracy predictions at low computational cost

Ashby, Michael↗
DOE OSTI2024

Multi-fidelity Fourier neural operator for fast modeling of large-scale geological carbon storage

Deep learning-based surrogate models have been widely applied in geological carbon storage (GCS) problems to accelerate the prediction of reservoir pressure and CO2 plume migration. Large amounts of data from physics-based numerical simulators are required to train a model to accurately predict the complex physical behaviors associated with this process. In practice, the available training data are always limited in large-scale 3D problems due to the high computational cost. Therefore, we propose to use a multi-fidelity Fourier neural operator (FNO) to solve large-scale GCS problems with more affordable multi-fidelity training datasets. FNO has a desirable grid-invariant property, which simplifies the transfer learning procedure between datasets with different discretization. Here, we first test the model efficacy on a GCS reservoir model being discretized into 110 k grid cells. The multi-fidelity model can predict with accuracy comparable to a high-fidelity model trained with the same amount of high-fidelity data with 81% less data generation costs. We further test the generalizability of the multi-fidelity model on a same reservoir model with a finer discretization of 1 million grid cells. This case was made more challenging by employing high-fidelity and low-fidelity datasets generated by different geostatistical models and reservoir simulators. We observe that the multi-fidelity FNO model can predict pressure fields with reasonable accuracy even when the high-fidelity data are extremely limited. The findings of this study can help for better understanding of the transferability of multi-fidelity deep learning surrogate models.

58 GEOSCIENCES↗
NASA NTRS2014

Orbit Determination Accuracy Analysis of the Magnetospheric Multiscale Mission During Perigee Raise

The Goddard Space Flight Center (GSFC) Flight Dynamics Facility (FDF) will provide orbit determination and prediction support for the Magnetospheric Multiscale (MMS) mission during the missions commissioning period. The spacecraft will launch into a highly elliptical Earth orbit in 2015. Starting approximately four days after launch, a series of five large perigee-raising maneuvers will be executed near apogee on a nearly every-other-orbit cadence. This perigee-raise operations concept requires a high-accuracy estimate of the orbital state within one orbit following the maneuver for performance evaluation and a high-accuracy orbit prediction to correctly plan and execute the next maneuver in the sequence. During early mission design, a linear covariance analysis method was used to study orbit determination and prediction accuracy for this perigee-raising campaign. This paper provides a higher fidelity Monte Carlo analysis using the operational COTS extended Kalman filter implementation that was performed to validate the linear covariance analysis estimates and to better characterize orbit determination performance for actively maneuvering spacecraft in a highly elliptical orbit. The study finds that the COTS extended Kalman filter tool converges on accurate definitive orbit solutions quickly, but prediction accuracy through orbits with very low altitude perigees is degraded by the unpredictability of atmospheric density variation.

Determination↗
NASA NTRS2014

Orbit Determination Accuracy Analysis of the Magnetospheric Multiscale Mission During Perigee Raise

The Goddard Space Flight Center (GSFC) Flight Dynamics Facility (FDF) will provide orbit determination and prediction support for the Magnetospheric Multiscale (MMS) mission during the mission's commissioning period. The spacecraft will launch into a highly elliptical Earth orbit in 2015. Starting approximately four days after launch, a series of five large perigee-raising maneuvers will be executed near apogee on a nearly every-other-orbit cadence. This perigee-raise operations concept requires a high-accuracy estimate of the orbital state within one orbit following the maneuver for performance evaluation and a high-accuracy orbit prediction to correctly plan and execute the next maneuver in the sequence. During early mission design, a linear covariance analysis method was used to study orbit determination and prediction accuracy for this perigee-raising campaign. This paper provides a higher fidelity Monte Carlo analysis using the operational COTS extended Kalman filter implementation that was performed to validate the linear covariance analysis estimates and to better characterize orbit determination performance for actively maneuvering spacecraft in a highly elliptical orbit. The study finds that the COTS extended Kalman filter tool converges on accurate definitive orbit solutions quickly, but prediction accuracy through orbits with very low altitude perigees is degraded by the unpredictability of atmospheric density variation.

Multiscale↗
NASA NTRSDate not supplied

Improving GES Disc Data Search and Discovery Through AI Metadata Augmentation

NASA’s Goddard Earth Science (GES) Data and Information Services Center (DISC) is one of twelve data centers in NASA's Science Mission Directorate (SMD), providing vital earth science data to a diverse user base. To enhance the discoverability of this data, GES DISC employs a keyword search system, which leverages scientific keywords embedded in dataset metadata. However, the evolving nature of scientific applications of our data necessitates regular review and augmentation of these keywords. To address this, we developed a service to automatically predict missing science keywords in the metadata. This service constructs a knowledge graph from the latest GES DISC metadata within NASA’s Common Metadata Repository (CMR). Using an open-source library, we trained a machine learning model to predict absent science keywords in the metadata. Our preliminary results indicate that the model has high levels of accuracy at predicting science keywords in the dataset metadata when exposed to data not included in its training. These predicted keywords were then evaluated by GES DISC data curation scientists and compared against other AI tools for metadata augmentation. We aim to enhance the overall usability and accessibility of NASA’s earth science data by implementing this tool in our data curation processes.

Kendall Gilbert↗
DOE OSTI2026

Full-stack Quantification of Variability in Predicting Ion Transport Properties using Machine-learned Interatomic Potentials

Machine-learned interatomic potentials (MLIPs) have become the state-of-the-art for performing accurate, scalable molecular dynamics (MD) simulations. It is therefore crucial to understand and quantify the reliability of MLIPs for downstream property predictions. Uncertainty in predicted properties can arise from limitations in first-principles training data, intrinsic MLIP model errors in representing the data, and the statistical noise introduced during subsequent MD simulations. Using ion transport in Li7P3S11 as a case study, we systematically assess the impact of training set size and selection, neural network stochasticity, and MD sampling statistics on predicted diffusivity and activation energy. We find that when using equivariant MLIP architectures with standard MD protocols, uncertainty arising from MD sampling dominates over model-induced errors. In contrast, MLIP errors relative to the underlying first-principles data are consistently minor. Given this, there are two main routes to improving the accuracy of predictions based on MLIP potentials: adopting higher accuracy reference data generation methods, and improving the MD sampling statistics.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Understanding the Physics Representation of Deep Learning Models in Environmental Applications

Deep learning (DL) models have been popular in earth and environmental modeling and analysis, which exhibit huge potential in capturing and reconstructing the non-linearity of relevant environmental processes. They are extensively used as analytical tools or emulators for multiple domains (atmosphere, land surface, ocean, and biogeochemistry). Despite their success, their internal working mechanism remains largely unknown. Such a lack of knowledge hinders the identification of physically consistent models that are fully adaptive to non-stationary climate, as well as the development of physics-informed machine learning such as physics-informed neural network (PINN). To establish preliminary knowledge and framework of such physics representation evaluation, this project focuses on an improved understanding of DL models in the environmental applications. DL models are increasingly applied to environmental modeling and prediction. However, they have been evaluated mostly from a performance perspective, and there is a gap in understanding how they represent the known physics internally. Such knowledge is especially critical when applying DL models under climate change conditions, where new inputs are likely outside the ranges of the training datasets. In this project, we reveal how the known physical processes are represented within DL models from both statistical and mechanistic perspectives. Leveraging the traditional model evaluations that focus more on the accuracies of predictions, we establish a framework that examines both the accuracy and physics representation of DL models. This analysis framework can identify DL models that make the correct predictions based on correct physics, thus enhancing the existing explainable artificial intelligence (explainable-AI) portfolio. It lays a foundation for developing novel metrics to evaluate the emerging DL models in environmental applications. This knowledge also informs the development of physics-informed DL models by revealing the direct connections between the known physical processes and specific model components or structures.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS1995

An evaluation of a coupled microstructural approach for the analysis of functionally graded composites via the finite-element method

A comparison is presented between the predictions of the finite-element analysis and a recently developed higher-order theory for functionally graded materials subjected to a thorough-thickness temperature gradient. In contrast to existing micromechanical theories that utilize classical (i.e., uncoupled) homogenization schemes to calculate micro-level and macro-level stress and displacement fields in materials with uniform or nonuniform fiber spacing (i.e., functionally graded materials), the new theory explicitly couples the microstructural details with the macrostructure of the composite. Previous thermo-elastic analysis has demonstrated that such coupling is necessary when: the temperature gradient is large with respect to the dimension of the reinforcement; the characteristic dimension of the reinforcement is large relative to the global dimensions of the composite and the number of reinforcing fibers or inclusions is small. In these circumstances, the standard micromechanical analyses based on the concept of the representative volume element used to determine average composite properties produce questionable results. The comparison between the predictions of the finite-element method and the higher-order theory presented herein establish the theory's accuracy in predicting thermal and stress fields within composites with a finite number of fibers in the thickness direction subjected to a thorough-thickness thermal gradient.

Pindera, Marek-Jerzy↗
NASA NTRS1984

An emulator for minimizing computer resources for finite element analysis

A computer code, SCOPE, has been developed for predicting the computer resources required for a given analysis code, computer hardware, and structural problem. The cost of running the code is a small fraction (about 3 percent) of the cost of performing the actual analysis. However, its accuracy in predicting the CPU and I/O resources depends intrinsically on the accuracy of calibration data that must be developed once for the computer hardware and the finite element analysis code of interest. Testing of the SCOPE code on the AMDAHL 470 V/8 computer and the ELAS finite element analysis program indicated small I/O errors (3.2 percent), larger CPU errors (17.8 percent), and negligible total errors (1.5 percent).

Melosh, R.↗
DOE OSTI2026

Machine learning identifies novel signatures of antifungal drug resistance in Saccharomycotina yeasts

Antifungal drug resistance is a major challenge in fungal infection management. Numerous genomic changes are known to contribute to acquired drug resistance in clinical isolates of specific pathogens, but whether they broadly explain natural resistance across entire lineages is unknown. We leveraged genomic, ecological, and phenotypic trait data from naturally sampled strains from nearly all known species in subphylum Saccharomycotina to examine the evolution of resistance to eight antifungal drugs. The phylogenetic distribution of drug resistance varied by drug; fluconazole resistance was widespread, while 5-fluorocytosine resistance was rare, except in Lipomycetales. A random forest algorithm trained on genomic data predicted drug-resistant yeasts with 54–75% accuracy. Fluconazole resistance was consistently predicted with the highest accuracy (75.2%). Furthermore, fluconazole resistance prediction accuracy was similar between models trained on genome-wide variation in the presence and number of InterPro protein annotations across Saccharomycotina (75.2%) and those trained on amino acid sequence alignment data of Erg11, a protein known to be involved in fluconazole resistance (74.3-74.9%). Interestingly, the top Erg11 residues for predicting fluconazole resistance across Saccharomycotina do not overlap with, are not spatially close to, and are less conserved than those previously linked to resistance in clinical isolates of Candida albicans. In silico deep mutational scanning of the C. albicans Erg11 protein reveals that amino acid variants implicated in clinical cases of resistance are almost universally destabilizing while variants in our most informative residues are energetically more neutral, explaining why the latter are much more common than the former in natural populations. Importantly, previous experimental analyses of C. albicans Erg11 have shown that amino acid variation in our most informative residues, despite having never been directly implicated in clinical cases, can directly contribute to resistance. Our results suggest that studies of natural resistance in yeast species never encountered in the clinic will yield a fuller understanding of antifungal drug resistance.

Harrison, Marie-Claire [Vanderbilt Univ., Nashvill↗
NASA NTRS1996

A Computational and Experimental Study of Nonlinear Aspects of Induced Drag

Despite the 80-year history of classical wing theory, considerable research has recently been directed toward planform and wake effects on induced drag. Nonlinear interactions between the trailing wake and the wing offer the possibility of reducing drag. The nonlinear effect of compressibility on induced drag characteristics may also influence wing design. This thesis deals with the prediction of these nonlinear aspects of induced drag and ways to exploit them. A potential benefit of only a few percent of the drag represents a large fuel savings for the world's commercial transport fleet. Computational methods must be applied carefully to obtain accurate induced drag predictions. Trefftz-plane drag integration is far more reliable than surface pressure integration, but is very sensitive to the accuracy of the force-free wake model. The practical use of Trefftz plane drag integration was extended to transonic flow with the Tranair full-potential code. The induced drag characteristics of a typical transport wing were studied with Tranair, a full-potential method, and A502, a high-order linear panel method to investigate changes in lift distribution and span efficiency due to compressibility. Modeling the force-free wake is a nonlinear problem, even when the flow governing equation is linear. A novel method was developed for computing the force-free wake shape. This hybrid wake-relaxation scheme couples the well-behaved nature of the discrete vortex wake with viscous-core modeling and the high-accuracy velocity prediction of the high-order panel method. The hybrid scheme produced converged wake shapes that allowed accurate Trefftz-plane integration. An unusual split-tip wing concept was studied for exploiting nonlinear wake interaction to reduced induced drag. This design exhibits significant nonlinear interactions between the wing and wake that produced a 12% reduction in induced drag compared to an equivalent elliptical wing at a lift coefficient of 0.7. The performance of the split-tip wing was also investigated by wing tunnel experiments. Induced drag was determined from force measurements by subtracting the estimated viscous drag, and from an analytical drag-decomposition method using a wake survey. The experimental results confirm the computational prediction.

Smith, Stephen C.↗
NASA NTRSDate not supplied

Improved Prediction of Losses with Large Eddy Simulation in a Low-Pressure Turbine

There is a need to improve predictions of losses resulting from large eddy simulations (LES) of low-pressure turbines (LPT) in gas turbines. This may be done by assessing the accuracy of predictions against validation data and understanding the source of any inaccuracies. LES is a promising approach for capturing the laminar/turbulent transition process in a LPT. In previous studies, the authors utilized LES to model the flow field over a Variable Speed Power Turbine (VSPT) blade and successfully captured characteristic features of separation/reattachment and transition on the suction side at both the cruise (positive incidence) and take-off conditions (negative incidence) and as well, simulated the effect of freestream turbulence (FST) on those phenomena. The predicted pressure loading profiles agreed well with the experimental data for both a high and a low FST case at a Reynolds number of Reex=220,000. In this paper, we present wake profiles resulting from computations for a range of FST values. Although the predicted wake profiles for the lowest FST case (Tu=0.5%) matched the experimental data, at higher FST (Tu=10-15%,) the wake was wider than the experimentally measured wake and for both cases were displaced laterally when compared to the experimental measurements. In our investigation of the causes of the said discrepancies we have identified important effects which could strongly influence the predicted wake profile. Predicted losses were improved by assuring the validity of the flow solution. This was done by utilizing spectral analysis to scrutinize the dynamic behavior of the wake and determine solution accuracy resulting from low mesh density and low accuracy of convective modeling.

CFD↗
NASA NTRS2022

Improved Prediction of Losses with Large Eddy Simulation in a Low-Pressure Turbine

There is a need to improve predictions of losses resulting from large eddy simulations (LES) of low-pressure turbines (LPT) in gas turbines. This may be done by assessing the accuracy of predictions against validation data and understanding the source of any inaccuracies. LES is a promising approach for capturing the laminar/turbulent transition process in a LPT. In previous studies, the authors utilized LES to model the flow field over a Variable Speed Power Turbine (VSPT) blade and successfully captured characteristic features of separation/reattachment and transition on the suction side at both the cruise (positive incidence) and take-off conditions (negative incidence) and as well, simulated the effect of free-stream turbulence (FST) on those phenomena. The predicted pressure loading profiles agreed well with the experimental data for both a high and a low FST case at a Reynolds number of Re(ex)=220,000. In this paper, we present wake profiles resulting from computations for a range of FST values. Although the predicted wake profiles for the lowest FST case (Tu=0.5%) matched the experimental data, at higher FST (Tu=10-15%,) the wake was wider than the experimentally measured wake and for both cases were displaced laterally when compared to the experimental measurements. In our investigation of the causes of the said discrepancies we have identified important effects which could strongly influence the predicted wake profile. Predicted losses were improved by assuring the validity of the flow solution. This was done by utilizing spectral analysis to scrutinize the dynamic behavior of the wake and determine solution accuracy resulting from low mesh density and low accuracy of convective modeling.

LES-LDKM↗
DOE OSTI2025

Deep-learning-based domain adaptation for cavity fault prediction at Jefferson Laboratory

Superconducting radio-frequency (SRF) cavities are the core components of the Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab, providing high-power electron beams for nuclear physics experiments. The facility comprises 418 SRF cavities, and any fault in these cavities can lead to interruptions in the electron beam supply. Cavity faults are the leading cause of beam trips in CEBAF. Predicting and mitigating those faults before onset can help maintain normal operation. Existing models face challenges in distinguishing between normal and fault signals when changes occur in the underlying time-series data, from changes in control software, operational parameters, or the environment. This work proposes a deep learning domain adaptation model that leverages transfer learning to address fault prediction challenges by improving accuracy. The model is trained and fine-tuned using a dataset collected for faulty and normal operation using a data acquisition system in CEBAF. Our deep learning-based domain adaptation model achieves a prediction accuracy of 89.61% of the fault and normal signals. The developed model effectively predicts normal running signals compared to the baseline approach without domain adaptation. This capacity is essential for the fault prediction task in the CEBAF because of heavily imbalanced data containing vast amounts of normal signals. The model performs well for predicting faults several hundred milliseconds before the fault onset compared to other models where no adaptation is applied. Incorporating deep learning-based domain adaptation techniques will significantly improve the fault prediction performance.

Rahman, Md Monibor [Old Dominion Univ., Norfolk, V↗
DOE OSTI2024

Machine learning enables identification of an alternative yeast galactose utilization pathway

How genomic differences contribute to phenotypic differences is a major question in biology. The recently characterized genomes, isolation environments, and qualitative patterns of growth on 122 sources and conditions of 1,154 strains from 1,049 fungal species (nearly all known) in the yeast subphylum Saccharomycotina provide a powerful, yet complex, dataset for addressing this question. We used a random forest algorithm trained on these genomic, metabolic, and environmental data to predict growth on several carbon sources with high accuracy. Known structural genes involved in assimilation of these sources and presence/absence patterns of growth in other sources were important features contributing to prediction accuracy. By further examining growth on galactose, we found that it can be predicted with high accuracy from either genomic (92.2%) or growth data (82.6%) but not from isolation environment data (65.6%). Prediction accuracy was even higher (93.3%) when we combined genomic and growth data. After the GALactose utilization genes, the most important feature for predicting growth on galactose was growth on galactitol, raising the hypothesis that several species in two orders, Serinales and Pichiales (containing the emerging pathogen Candida auris and the genus Ogataea, respectively), have an alternative galactose utilization pathway because they lack the GAL genes. Growth and biochemical assays confirmed that several of these species utilize galactose through an alternative oxidoreductive D-galactose pathway, rather than the canonical GAL pathway. Machine learning approaches are powerful for investigating the evolution of the yeast genotype–phenotype map, and their application will uncover novel biology, even in well-studied traits.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Data-driven analysis and prediction of stable phases for high-entropy alloy design

High-entropy alloys (HEAs) represent a promising class of materials with exceptional structural and functional properties. However, their design and optimization pose challenges due to the large composition-phase space coupled with the complex and diverse nature of the phase formation dynamics. In this study, a data-driven approach that utilizes machine learning (ML) techniques to predict HEA phases and their composition-dependent phases is proposed. By employing a comprehensive dataset comprising 5692 experimental records encompassing 50 elements and 11 phase categories, we compare the performance of various ML models. Our analysis identifies the most influential features for accurate phase prediction. Furthermore, the class imbalance is addressed by employing data augmentation methods, raising the number of records to 1500 in each category, and ensuring a balanced representation of phase categories. The results show that XGBoost and Random Forest consistently outperform the other models, achieving 86% accuracy in predicting all phases. Additionally, this work provides an extensive analysis of HEA phase formers, showing the contributions of elements and features to the presence of specific phases. We also examine the impact of including different phases on ML model accuracy and feature significance. Notably, the findings underscore the need for ML model selection based on specific applications and desired predictions, as feature importance varies across models and phases. This study significantly advances the understanding of HEA phase formation, enabling targeted alloy design and fostering progress in the field of materials science.

36 MATERIALS SCIENCE↗