Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “predictive”

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 1,207 records · Page 67
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Uncertainty quantification of a deep learning fuel property prediction model

Deep learning models are being widely used in the field of combustion. Given the black-box nature of typical neural network based models, uncertainty quantification (UQ) is critical to ensure the reliability of predictions as well as the training datasets, and for a principled quantification of noise and its various sources. Deep learning surrogate models for predicting properties of chemical compounds and mixtures have been recently shown to be promising for enabling data-driven fuel design and optimization, with the ultimate goal of improving efficiency and lowering emissions from combustion engines. In this study, UQ is performed for a multi-task deep learning model that simultaneously predicts the research octane number (RON), Motor Octane Number (MON), and Yield Sooting Index (YSI) of pure components and multicomponent blends. The deep learning model is comprised of three smaller networks: Extractor 1, Extractor 2, and Predictor, and a mixing operator. The molecular fingerprints of individual components are encoded via Extractor 1 and Extractor 2, the mixing operator generates fingerprints for mixtures/blends based on linear mixing operation, and the predictor maps the fingerprint to the target properties. Two different classes of UQ methods, Monte Carlo ensemble methods and Bayesian neural networks (BNNs), are employed for quantifying the epistemic uncertainty. Combinations of Bernoulli and Gaussian distributions with DropConnect and DropOut techniques are explored as ensemble methods. All the DropConnect, DropOut and Bayesian layers are applied to the predictor network. Aleatoric uncertainty is modeled by assuming that each data point has an independent uncertainty associated with it. The results of the UQ study are further analyzed to compare the performance of BNN and ensemble methods. Although this study is confined to UQ of fuel property prediction, the methodologies are applicable to other deep learning frameworks that are being widely used in the combustion community.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2022

Monitoring and prediction of porosity in laser powder bed fusion using physics-informed meltpool signatures and machine learning

In this work we accomplished the monitoring and prediction of porosity in laser powder bed fusion (LPBF) additive manufacturing process. This objective was realized by extracting physics-informed meltpool signatures from an in-situ dual-wavelength imaging pyrometer, and subsequently, analyzing these signatures via computationally tractable machine learning approaches. Porosity in LPBF occurs despite extensive optimization of processing conditions due to stochastic causes. Hence, it is essential to continually monitor the process with in-situ sensors for detecting and mitigating incipient pore formation. In this work a tall cuboid-shaped part (10 mm × 10 mm × 137 mm, material ATI 718Plus) was built with controlled porosity by varying laser power and scanning speed. This test caused various types of porosity, such as lack-of-fusion and keyhole formation, with varying degrees of severity in the part. The meltpool was continuously monitored using a dual-wavelength imaging pyrometer installed in the machine. Physically intuitive process signatures, such as meltpool length, temperature distribution, and ejecta (spatter) characteristics, were extracted from the meltpool images. Subsequently, relatively simple machine learning models, e.g., K-Nearest Neighbors, were trained to predict both the severity and type of porosity as a function of these physics-informed meltpool signatures. These models resulted in a prediction accuracy exceeding 95% (statistical F1-score). The same analysis was carried out with a complex, black-box deep learning convolutional neural network which directly used the meltpool images instead of physics-informed features. The convolutional neural network produced a comparable F1-score in the range of 89–97%. Finally, these results demonstrate that using pragmatic, physics-informed meltpool signatures within a simple machine learning model is as effective for flaw prediction in LPBF as using a complex and computationally demanding black-box deep learning model.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Predicting metal-binding proteins and structures through integration of evolutionary-scale and physics-based modeling

Metals are essential elements in all living organisms, binding to approximately 50% of proteins. They serve to stabilize proteins, catalyze reactions, regulate activities, and fulfill various physiological and pathological functions. While there have been many advancements in determining the structures of protein-metal complexes, numerous metal-binding proteins still need to be identified through computational methods and validated through experiments. Here, to address this need, we have developed the ESMBind workflow, which combines evolutionary scale modeling (ESM) for metal-binding prediction and physics-based protein-metal modeling. Our approach utilizes the ESM-2 and ESM-IF models to predict metal-binding probability at the residue level. In addition, we have designed a metal-placement method and energy minimization technique to generate detailed 3D structures of protein-metal complexes. Our workflow outperforms other models in terms of residue and 3D-level predictions. To demonstrate its effectiveness, we applied the workflow to 142 uncharacterized fungal pathogen proteins and predicted metal-binding proteins involved in fungal infection and virulence.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Performance evaluation of automated data-driven feature extraction and selection methods for practical and scalable building energy consumption prediction models

Here, this study quantifies the impact of automated feature engineering methods (feature extraction and selection) on the quality and accuracy of machine learning models that predict building energy consumption. The case study compares model performance for three main scenarios: baseline (no feature extraction and selection), feature extraction only, and feature extraction combined with feature selection (filter and/or wrapper methods) for fully trained machine learning models for 200 metered/sub-metered energy measurements across 118 real buildings. For consistency, the same machine learning model architecture (a black box deep learning neural network with probabilistic forecast output) was used for all scenarios. Based on results, all feature engineering methods provided noticeable prediction accuracy improvements (e.g., 29%-68% median prediction improvement) compared to baseline scenarios. However, in this application, feature selection methods provide little practical value due to their limited performance gains and high computational cost. Smarter algorithm development supported by better computational environments will be needed before feature selection methods can reliably and efficiently improve predictive model performance.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

PARIS: Predicting application resilience using machine learning

The traditional method to study application resilience to errors in HPC applications uses fault injection (FI), a time-consuming approach. Furthermore, while analytical models have been built to overcome the inefficiencies of FI, they lack accuracy. In this paper, we present PARIS, a machine-learning method to predict application resilience that avoids the time-consuming process of random FI and provides higher prediction accuracy than analytical models. PARIS captures the implicit relationship between application characteristics and application resilience, which is difficult to capture using most analytical models. We overcome many technical challenges for feature construction, extraction, and selection to use machine learning in our prediction approach. Our evaluation on 16 HPC benchmarks shows that PARIS achieves high prediction accuracy. PARIS is up to 450x faster than random FI (49x on average). Compared to the state-of-the-art analytical model, PARIS is at least 63% better in terms of accuracy and has comparable execution time on average.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Effects of applied stress and grain size on creep-rupture lifetime prediction for Haynes 282 alloy

A multiple-heat set of tensile and creep-rupture data generated from a single laboratory was used to establish and evaluate predictive equations for the average creep-limited lifetime of an aged wrought Haynes 282 alloy using two different time- and temperature-compensated parametric models (those of Larson and Miller and Wilshire et al.). The range of temperatures and stresses used to produce the creep-rupture data used in the analyses revealed that two distinct regimes, above and below the proportional limit, were necessary for more accurate predictions of creep lifetimes over the range of conditions studied. Furthermore, a 2x difference in grain size amongst the three heats revealed a breakdown in the relationship between ultimate tensile strength and creep-rupture time, thus impacting the predictive ability of the Wilshire model. Finally, lifetime predictions based on the formulations from the respective models were compared to other available Haynes 282 datasets and found to reasonably replicate the experimental trends established in other studies.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Yield strength prediction of high-entropy alloys using machine learning

Yield strength at high temperature is an important parameter in the design and application of high entropy alloys (HEAs). However, the experimental measurement of yield strength at high temperature is quite costly, complicated, and time-consuming. Therefore, it is essential to identify and apply a robust method for the accurate prediction of yield strength at high temperature from the available experimental and simulation data. In this study, for the first time, a machine learning (ML) method based on the regression technique of random forest (RF) regressor is used to predict the yield strength of HEAs at the desired temperature. Further, the yield strengths of MoNbTaTiW and HfMoNbTaTiZr at 800 °C and 1200 °C, are predicted using the RF regressor model. We find that the results are consistent with the experimental reports, showing that the RF regressor model predicts the yield strength of HEAs at the desired temperatures with high accuracy.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Quantifying the drivers and predictability of seasonal changes in African fire

Africa contains some of the most vulnerable ecosystems to fires. Successful seasonal prediction of fire activity over these fire-prone regions remains a challenge and relies heavily on in-depth understanding of various driving mechanisms underlying fire evolution. Here, we assess the seasonal environmental drivers and predictability of African fire using the analytical framework of Stepwise Generalized Equilibrium Feedback Assessment (SGEFA) and machine learning techniques (MLTs). The impacts of sea-surface temperature, soil moisture, and leaf area index are quantified and found to dominate the fire seasonal variability by regulating regional burning condition and fuel supply. Compared with previously-identified atmospheric and socioeconomic predictors, these slowly evolving oceanic and terrestrial predictors are further identified to determine the seasonal predictability of fire activity in Africa. Our combined SGEFA-MLT approach achieves skillful prediction of African fire one month in advance and can be generalized to provide seasonal estimates of regional and global fire risk.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Preparing for the next pandemic via transfer learning from existing diseases with hierarchical multi-modal BERT: a study on COVID-19 outcome prediction

Abstract Developing prediction models for emerging infectious diseases from relatively small numbers of cases is a critical need for improving pandemic preparedness. Using COVID-19 as an exemplar, we propose a transfer learning methodology for developing predictive models from multi-modal electronic healthcare records by leveraging information from more prevalent diseases with shared clinical characteristics. Our novel hierarchical, multi-modal model ( $${\textsc {TransMED}}$$ T R A N S MED ) integrates baseline risk factors from the natural language processing of clinical notes at admission, time-series measurements of biomarkers obtained from laboratory tests, and discrete diagnostic, procedure and drug codes. We demonstrate the alignment of $${\textsc {TransMED}}$$ T R A N S MED ’s predictions with well-established clinical knowledge about COVID-19 through univariate and multivariate risk factor driven sub-cohort analysis. $${\textsc {TransMED}}$$ T R A N S MED ’s superior performance over state-of-the-art methods shows that leveraging patient data across modalities and transferring prior knowledge from similar disorders is critical for accurate prediction of patient outcomes, and this approach may serve as an important tool in the early response to future pandemics.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Prediction of chronic kidney disease progression using recurrent neural network and electronic health records

Chronic kidney disease (CKD) is a progressive loss in kidney function. Early detection of patients who will progress to late-stage CKD is of paramount importance for patient care. To address this, we develop a pipeline to process longitudinal electronic heath records (EHRs) and construct recurrent neural network (RNN) models to predict CKD progression from stages II/III to stages IV/V. The RNN model generates predictions based on time-series records of patients, including repeated lab tests and other clinical variables. Our investigation reveals that using a single variable, the recorded estimated glomerular filtration rate (eGFR) over time, the RNN model achieves an average area under the receiver operating characteristic curve (AUROC) of 0.957 for predicting future CKD progression. When additional clinical variables, such as demographics, vital information, lab test results, and health behaviors, are incorporated, the average AUROC increases to 0.967. In both scenarios, the standard deviation of the AUROC across cross-validation trials is less than 0.01, indicating a stable and high prediction accuracy. Our analysis results demonstrate the proposed RNN model outperforms existing standard approaches, including static and dynamic Cox proportional hazards models, random forest, and LightGBM. The utilization of the RNN model and the time-series data of previous eGFR measurements underscores its potential as a straightforward and effective tool for assessing the clinical risk of CKD patients concerning their disease progression.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2026

From molecular to macroscopic: predicting liquid–liquid phase equilibria and small-angle scattering of mixtures of organic liquids from atomistic simulation using Kirkwood–Buff theory

Macroscopic phase equilibria between solutions define the functionality of many biological and industrial processes, yet they are challenging to predict due to the inherent complexity of liquids containing large molecules. This work introduces an approach for the purely predictive calculation of such phase equilibria in temperature-composition space from molecular dynamics (MD) simulations at one temperature in the single-phase region. We use an approach developed previously to obtain the entropic and enthalpic contributions to the free energy of mixing from the atomic-scale information given by MD simulations via Kirkwood–Buff theory. This allows us to accurately estimate the free energy of mixing as a function of temperature, and thus obtain liquid–liquid phase equilibria, including liquid–liquid critical points, associated binodal and spinodal lines, and composition fluctuations across a region of temperature and composition. Results for binary malonamide–alkane systems are validated by comparison to a direct experimental probe of the fluctuations: the small angle X-ray scattering intensity near zero wavenumber. The MDKB → Phase method demonstrated here provides a significant improvement in predicting liquid–liquid equilibria and free energy as a function of temperature for our systems of interest compared to conventional thermodynamic models. The accurate performance of this purely predictive approach lies in its preservation of atomistic details when determining thermodynamic properties. Furthermore, its inherent extensibility to multi-component systems will likely make the MDKB → Phase approach a valuable general tool for connecting molecular interactions to macroscopic phase equilibria and for the computational screening of materials for targeted thermodynamic behavior.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2021

Hydrologic Regionalization under Data Scarcity: Implications for Streamflow Prediction

Continuous streamflow prediction is crucial in many applications of water resources planning and management. However, streamflow prediction is challenging, particularly in data-scarce regions. Here, we demonstrate an approach to regionalize the flow duration curve for predicting daily streamflow in the data-scare region of the central Himalayas. We developed a regression-based model to estimate streamflow at various segments of a flow duration curve by incorporating basin characteristics and climate variables. This study analyzes the sensitivities of proximity and characteristics between the donor (gauged) and receptor (ungauged) basins for time-series streamflow prediction. Our results show that regionalization techniques perform better in low to medium flows over high flows. Our findings are significant in the central Himalayan regional context to inform operational and management decisions in water sector projects like hydropower plants, which generally rely on low-to-medium streamflow information. Although the quantitative results are region-specific, the approach and insights are generalizable to the Himalayan region.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Probabilistic modeling and prediction of out-of-plane unidirectional composite lamina properties

Computational simulation provides an efficient means to predict the behavior of customized hybrid material configurations using validated, physics-based models. One limitation to this approach is the quality and quantity of available data to characterize the many constituent input properties. Therefore, a systematic approach to identify the most influential parameters on the hybrid behavior and quantify the corresponding uncertainty in predictive capabilities is required. Here, an approach using Bayesian multimodel inference and imprecise global sensitivity analysis is presented to investigate the effects of sparse constituent data on the prediction of composite material properties. The methodology allows the identification, using quantified uncertainties, of the most influential constituent material parameters for specified homogenized properties. This sensitivity analysis further enables a dimension reduction when assessing the influence of uncertainties on material properties and can be used to inform testing programs of the constituent properties that require additional testing/data collection in order to minimize uncertainty in macro-scale composite properties. The methodology is specifically demonstrated on the prediction and sensitivity analysis of out-of-plane mechanical properties of a unidirectional lamina.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Examining transport and integrated modeling predictive capabilities for negative-triangularity scenarios

This paper investigates the predictive capabilities of TGYRO and TGLF models in assessing the performance of negative triangularity (NT) plasmas compared to positive triangularity (PT) plasmas in fusion devices. TGYRO predicts kinetic profiles, while TGLF analyzes turbulent transport. The study reveals that TGYRO reasonably predicts NT profiles similar to PT, although it overpredicts the high-power scenarios where there is increased experimental MHD activity. TGLF analysis finds reduced linear growth rates in NT and altered flux spectra relative to PT. Additionally, the TGLF SAT0 saturation model is observed to predict high-k transport and a reduction of particle transport with the electron temperature gradient. These findings are further corroborated by core-pedestal modeling using the Stability Transport Equilibrium Pedestal workflow, showing stronger confinement improvements in NT, particularly at higher power densities for the SAT0 saturation model. Furthermore, the study underscores the importance of accurately capturing turbulence saturation mechanisms for NT in order to project its performance accurately in fusion reactors.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2023

Integrated deep learning framework for unstable event identification and disruption prediction of tokamak plasmas

Abstract The ability to identify underlying disruption precursors is key to disruption avoidance. In this paper, we present an integrated deep learning (DL) based model that combines disruption prediction with the identification of several disruption precursors like rotating modes, locked modes, H-to-L back transitions and radiative collapses. The first part of our study demonstrates that the DL-based unstable event identifier trained on 160 manually labeled DIII-D shots can achieve, on average, 84% event identification rate of various frequent unstable events (like H-L back transition, locked mode, radiative collapse, rotating MHD mode, large sawtooth crash), and the trained identifier can be adapted to label unseen discharges, thus expanding the original manually labeled database. Based on these results, the integrated DL-based framework is developed using a combined database of manually labeled and automatically labeled DIII-D data, and it shows state-of-the-art (AUC = 0.940) disruption prediction and event identification abilities on DIII-D. Through cross-machine numerical disruption prediction studies using this new integrated model and leveraging the C-Mod, DIII-D, and EAST disruption warning databases, we demonstrate the improved cross-machine disruption prediction ability and extended warning time of the new model compared with a baseline predictor. In addition, the trained integrated model shows qualitatively good cross-machine event identification ability. Given a labeled dataset, the strategy presented in this paper, i.e. one that combines a disruption predictor with an event identifier module, can be applied to upgrade any neural network based disruption predictor. The results presented here inform possible development strategies of machine learning based disruption avoidance algorithms for future tokamaks and highlight the importance of building comprehensive databases with unstable event information on current machines.

plasma instabilities↗
DOE OSTI2024

Performance prediction applying different reduced turbulence models to the SMART tokamak

The SMall Aspect Ratio Tokamak (SMART) is currently being commissioned at the University of Seville and will be able to compare the performance of positive and negative triangularity plasmas at low aspect ratio. Predictive simulations have been performed for different machine scenarios and heating schemes using the TRANSP code. The objectives of these simulations are to predict the parameters expected in positive triangularity plasmas, to guide diagnostic development, and to validate transport models. Several reduced turbulence models have been used to predict electron and ion temperatures for the operational phase 2. All models provide similar results from approximately mid-radius to the separatrix but important discrepancies are found in the core region. These positive triangularity results are compared with experiments from a similar size machine like GLOBUS-M2. The multi-mode model (MMM) shows the best agreement. Simulations with different boundary conditions have been performed and no strong differences have been observed between them. The impact of neutral beam injection (NBI) on the predicted profiles has also been addressed. Rotation reduces turbulence levels so higher temperatures are achieved when included in the simulations. Studying the different contributions to the thermal diffusivities, it is observed that electron temperature gradient (ETG) turbulence dominates at the plasma core while micro-tearing modes (MTM) dominate at the edge in the electron channel. In the ion channel, the neoclassical contribution is dominant at the core and at the very edge while the Weiland component, which includes ion temperature gradient mode (ITG), trapped electron mode (TEM), kinetic ballooning mode (KBM), peeling mode (PM) and collisionless and collision dominated magnetohydrodynamic (MHD) modes governs the mid-radius region. For phase 3, two plasmas with different electron densities have been studied. The case with lower density matches well a specific discharge of GLOBUS-M2. The higher density plasma shows high performance with β N ≈ 3.8.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2026

TRANSP-TGLF core predictive modeling of the JET DT baseline scenario

In recent years, an intense modeling activity has been focused on preparing and analyzing the second JET Deuterium–Tritium (D–T) experimental campaign DTE2. Among the numerous scientific outcomes of this campaign was the unique opportunity to test and validate the state of the art of modeling tools with fusion-relevant DT plasmas using the full metallic ITER-like wall in different scenarios. This work reports on the core predictive modeling of plasma density, electron and ion temperatures (n e , T e , T i ) performed using TRANSP (Pankin et al 2025 Comput. Phys. Commun. 312 109611) coupled with Trapped Gyro-Landau Fluid (TGLF)-SAT2 (Kinsey et al 2008 Phys. Plasmas 15 055908), (Staebler et al 2021 Nucl. Fusion 61 116007) for the JET D–T baseline scenario (I p = 3.5 MA, q 95 = 3, β N < 2, with pellet pacing) (Garzotti et al 2025 Plasma Phys. Control. Fusion 67 075011). The sensitivity to different input parameters, as the $\vec{E}$ x $\vec{B}$ shear parameterization and the values of the kinetic quantities at the boundary of the prediction domain (ρ = 0.85) has been assessed, identifying the confidence interval of the prediction results. In particular, the dependence of the electron density profile on the particle source parameters has been studied, identifying the ionization source as the main cause for the density gradient under-prediction obtained by TRANSP-TGLF, reported in (Hyun-Tae et al 2023 Nucl. Fusion 63 112004).

JET↗
DOE OSTI2022

Robust and scalable uncertainty estimation with conformal prediction for machine-learned interatomic potentials

Abstract Uncertainty quantification (UQ) is important to machine learning (ML) force fields to assess the level of confidence during prediction, as ML models are not inherently physical and can therefore yield catastrophically incorrect predictions. Established a-posteriori UQ methods, including ensemble methods, the dropout method, the delta method, and various heuristic distance metrics, have limitations such as being computationally challenging for large models due to model re-training. In addition, the uncertainty estimates are often not rigorously calibrated. In this work, we propose combining the distribution-free UQ method, known as conformal prediction (CP), with the distances in the neural network’s latent space to estimate the uncertainty of energies predicted by neural network force fields. We evaluate this method (CP+latent) along with other UQ methods on two essential aspects, calibration, and sharpness, and find this method to be both calibrated and sharp under the assumption of independent and identically-distributed (i.i.d.) data. We show that the method is relatively insensitive to hyperparameters selected, and test the limitations of the method when the i.i.d. assumption is violated. Finally, we demonstrate that this method can be readily applied to trained neural network force fields with traditional and graph neural network architectures to obtain estimates of uncertainty with low computational costs on a training dataset of 1 million images to showcase its scalability and portability. Incorporating the CP method with latent distances offers a calibrated, sharp and efficient strategy to estimate the uncertainty of neural network force fields. In addition, the CP approach can also function as a promising strategy for calibrating uncertainty estimated by other approaches.

74 ATOMIC AND MOLECULAR PHYSICS↗