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 631 records · Page 35
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

On the Prediction of Aerosol-Cloud Interactions Within a Data-Driven Framework

Aerosol-cloud interactions (ACI) pose the largest uncertainty for climate projection. Among many challenges of understanding ACI, the question of whether ACI can be deterministically predicted has not been explicitly answered. Here we attempt to answer this question by predicting cloud droplet number concentration N c from aerosol number concentration N a and ambient conditions using a data-driven framework. We use aerosol properties, vertical velocity fluctuations, and meteorological states from the ACTIVATE field observations (2020–2022) as predictors to estimate N c . We show that the campaign-wide N c can be successfully predicted using machine learning models despite the strongly nonlinear and multi-scale nature of ACI. However, the observation-trained machine learning model fails to predict N c in individual cases while it successfully predicts N c of randomly selected data points that cover a broad spatiotemporal scale. This suggests that, within a data-driven framework, the N c prediction is uncertain at fine spatiotemporal scales.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Using a physics-informed neural network and fault zone acoustic monitoring to predict lab earthquakes

Abstract Predicting failure in solids has broad applications including earthquake prediction which remains an unattainable goal. However, recent machine learning work shows that laboratory earthquakes can be predicted using micro-failure events and temporal evolution of fault zone elastic properties. Remarkably, these results come from purely data-driven models trained with large datasets. Such data are equivalent to centuries of fault motion rendering application to tectonic faulting unclear. In addition, the underlying physics of such predictions is poorly understood. Here, we address scalability using a novel Physics-Informed Neural Network (PINN). Our model encodes fault physics in the deep learning loss function using time-lapse ultrasonic data. PINN models outperform data-driven models and significantly improve transfer learning for small training datasets and conditions outside those used in training. Our work suggests that PINN offers a promising path for machine learning-based failure prediction and, ultimately for improving our understanding of earthquake physics and prediction.

42 ENGINEERING↗
DOE OSTI2023

Vitamin interdependencies predicted by metagenomics-informed network analyses and validated in microbial community microcosms

Abstract Metagenomic or metabarcoding data are often used to predict microbial interactions in complex communities, but these predictions are rarely explored experimentally. Here, we use an organism abundance correlation network to investigate factors that control community organization in mine tailings-derived laboratory microbial consortia grown under dozens of conditions. The network is overlaid with metagenomic information about functional capacities to generate testable hypotheses. We develop a metric to predict the importance of each node within its local network environments relative to correlated vitamin auxotrophs, and predict that a Variovorax species is a hub as an important source of thiamine. Quantification of thiamine during the growth of Variovorax in minimal media show high levels of thiamine production, up to 100 mg/L. A few of the correlated thiamine auxotrophs are predicted to produce pantothenate, which we show is required for growth of Variovorax , supporting that a subset of vitamin-dependent interactions are mutualistic. A Cryptococcus yeast produces the B-vitamin pantothenate, and co-culturing with Variovorax leads to a 90-130-fold fitness increase for both organisms. Our study demonstrates the predictive power of metagenome-informed, microbial consortia-based network analyses for identifying microbial interactions that underpin the structure and functioning of microbial communities.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

UniKP: a unified framework for the prediction of enzyme kinetic parameters

Prediction of enzyme kinetic parameters is essential for designing and optimizing enzymes for various biotechnological and industrial applications, but the limited performance of current prediction tools on diverse tasks hinders their practical applications. Here, we introduce UniKP, a unified framework based on pretrained language models for the prediction of enzyme kinetic parameters, including enzyme turnover number (k cat ), Michaelis constant (K m ), and catalytic efficiency (k cat / K m ), from protein sequences and substrate structures. A two-layer framework derived from UniKP (EF-UniKP) has also been proposed to allow robust k cat prediction in considering environmental factors, including pH and temperature. In addition, four representative re-weighting methods are systematically explored to successfully reduce the prediction error in high-value prediction tasks. We have demonstrated the application of UniKP and EF-UniKP in several enzyme discovery and directed evolution tasks, leading to the identification of new enzymes and enzyme mutants with higher activity. UniKP is a valuable tool for deciphering the mechanisms of enzyme kinetics and enables novel insights into enzyme engineering and their industrial applications.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2020

Machine-learned impurity level prediction for semiconductors: the example of Cd-based chalcogenides

The ability to predict the likelihood of impurity incorporation and their electronic energy levels in semiconductors is crucial for controlling its conductivity, and thus the semiconductor's performance in solar cells, photodiodes, and optoelectronics. The difficulty and expense of experimental and computational determination of impurity levels makes a data-driven machine learning approach appropriate. In this work, we show that a density functional theory-generated dataset of impurities in Cd-based chalcogenides CdTe, CdSe, and CdS can lead to accurate and generalizable predictive models of defect properties. By converting any semiconductor + impurity system into a set of numerical descriptors, regression models are developed for the impurity formation enthalpy and charge transition levels. These regression models can subsequently predict impurity properties in mixed anion CdX compounds (where X is a combination of Te, Se and S) fairly accurately, proving that although trained only on the end points, they are applicable to intermediate compositions. We make machine-learned predictions of the Fermi-level-dependent formation energies of hundreds of possible impurities in 5 chalcogenide compounds, and we suggest a list of impurities which can shift the equilibrium Fermi level in the semiconductor as determined by the dominant intrinsic defects. Machine learning predictions for the dominating impurities compare well with DFT predictions, revealing the power of machine-learned models in the quick screening of impurities likely to affect the optoelectronic behavior of semiconductors.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Predicting the influence of particle size on the glass transition temperature and viscosity of secondary organic material

Abstract Atmospheric aerosols can assume liquid, amorphous semi-solid or glassy, and crystalline phase states. Particle phase state plays a critical role in understanding and predicting aerosol impacts on human health, visibility, cloud formation, and climate. Melting point depression increases with decreasing particle diameter and is predicted by the Gibbs–Thompson relationship. This work reviews existing data on the melting point depression to constrain a simple parameterization of the process. The parameter $$\xi $$ ξ describes the degree to which particle size lowers the melting point and is found to vary between 300 and 1800 K nm for a wide range of particle compositions. The parameterization is used together with existing frameworks for modeling the temperature and RH dependence of viscosity to predict the influence of particle size on the glass transition temperature and viscosity of secondary organic aerosol formed from the oxidation of $$\alpha $$ α -pinene. Literature data are broadly consistent with the predictions. The model predicts a sharp decrease in viscosity for particles less than 100 nm in diameter. It is computationally efficient and suitable for inclusion in models to evaluate the potential influence of the phase change on atmospheric processes. New experimental data of the size-dependence of particle viscosity for atmospheric aerosol mimics are needed to thoroughly validate the predictions.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Machine learning-based microstructure prediction during laser sintering of alumina

Abstract Predicting material’s microstructure under new processing conditions is essential in advanced manufacturing and materials science. This is because the material’s microstructure hugely influences the material’s properties. We demonstrate an elegant machine learning algorithm that faithfully predicts the microstructure under new conditions, without the need of knowing the governing laws. We name this algorithm, RCWGAN-GP, which is regression-based conditional generative adversarial networks with Wasserstein loss function and gradient penalty. This algorithm was trained with experimental SEM micrographs from laser-sintered alumina under various laser powers. The RCWGAN-GP realistically regenerates the SEM micrographs under the trained laser powers. Impressively, it also faithfully predicts the alumina’s microstructure under unexplored laser powers. The predicted microstructure features, including the morphology of the sintered particles and the pores, match the experimental SEM micrographs very well. We further quantitatively examined the prediction accuracy of the RCWGAN-GP. We trained the algorithm with computer-created micrograph datasets of secondary-phase growth governed by the well-known Johnson–Mehl–Avrami (JMA) equation. The RCWGAN-GP accurately regenerates the micrographs at the trained time series, in terms of the grains’ shapes, sizes, and spatial distributions. More importantly, the predicted secondary phase fraction accurately follows the JMA curve.

08 HYDROGEN↗
DOE OSTI2022

Improving deep learning performance for predicting large-scale geological ${{CO}_{2}}$ sequestration modeling through feature coarsening

Physics-based reservoir simulation for fluid flow in porous media is a numerical simulation method to predict the temporal-spatial patterns of state variables (e.g. pressure p) in porous media, and usually requires prohibitively high computational expense due to its non-linearity and the large number of degrees of freedom (DoF). This work describes a deep learning (DL) workflow to predict the pressure evolution as fluid flows in large-scale 3-dimensional(3D) heterogeneous porous media. In particular, we develop an efficient feature coarsening technique to extract the most representative information and perform the training and prediction of DL at the coarse scale, and further recover the resolution at the fine scale by spatial interpolation. We validate the DL approach to predict pressure field against physics-based simulation data for a field-scale 3D geologic CO 2 sequestration reservoir model. We evaluate the impact of feature coarsening on DL performance, and observe that the feature coarsening not only decreases the training time by >74% and reduces the memory consumption by >75%, but also maintains temporal error 0.63% on average. Besides, the DL workflow provides predictive efficiency with 1406 times speedup compared to physics-based numerical simulation. The key findings from this research significantly improve the training and prediction efficiency of deep learning model to deal with large-scale heterogeneous reservoir models, and thus it can also be further applied to accelerate workflows of history matching and reservoir optimization for close-loop reservoir management.

58 GEOSCIENCES↗
DOE OSTI2023

Predicting Kyasanur forest disease in resource-limited settings using event-based surveillance and transfer learning

In recent years, the reports of Kyasanur forest disease (KFD) breaking endemic barriers by spreading to new regions and crossing state boundaries is alarming. Effective disease surveillance and reporting systems are lacking for this emerging zoonosis, hence hindering control and prevention efforts. We compared time-series models using weather data with and without Event-Based Surveillance (EBS) information, i.e., news media reports and internet search trends, to predict monthly KFD cases in humans. We fitted Extreme Gradient Boosting (XGB) and Long Short-Term Memory models at the national and regional levels. We utilized the rich epidemiological data from endemic regions by applying Transfer Learning (TL) techniques to predict KFD cases in new outbreak regions where disease surveillance information was scarce. Overall, the inclusion of EBS data, in addition to the weather data, substantially increased the prediction performance across all models. The XGB method produced the best predictions at the national and regional levels. The TL techniques outperformed baseline models in predicting KFD in new outbreak regions. Novel sources of data and advanced machine-learning approaches, e.g., EBS and TL, show great potential towards increasing disease prediction capabilities in data-scarce scenarios and/or resource-limited settings, for better-informed decisions in the face of emerging zoonotic threats.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

High dimensional predictions of suicide risk in 4.2 million US Veterans using ensemble transfer learning

We present an ensemble transfer learning method to predict suicide from Veterans Affairs (VA) electronic medical records (EMR). A diverse set of base models was trained to predict a binary outcome constructed from reported suicide, suicide attempt, and overdose diagnoses with varying choices of study design and prediction methodology. Each model used twenty cross-sectional and 190 longitudinal variables observed in eight time intervals covering 7.5 years prior to the time of prediction. Ensembles of seven base models were created and fine-tuned with ten variables expected to change with study design and outcome definition in order to predict suicide and combined outcome in a prospective cohort. The ensemble models achieved c-statistics of 0.73 on 2-year suicide risk and 0.83 on the combined outcome when predicting on a prospective cohort of ~4.2 M veterans. The ensembles rely on nonlinear base models trained using a matched retrospective nested case-control (Rcc) study cohort and show good calibration across a diversity of subgroups, including risk strata, age, sex, race, and level of healthcare utilization. In addition, a linear Rcc base model provided a rich set of biological predictors, including indicators of suicide, substance use disorder, mental health diagnoses and treatments, hypoxia and vascular damage, and demographics. Similar content being viewed by others

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

Uncertainty quantification in multivariable regression for material property prediction with Bayesian neural networks

With the increased use of data-driven approaches and machine learning-based methods in material science, the importance of reliable uncertainty quantification (UQ) of the predicted variables for informed decision-making cannot be overstated. UQ in material property prediction poses unique challenges, including multi-scale and multi-physics nature of materials, intricate interactions between numerous factors, limited availability of large curated datasets, etc. In this work, we introduce a physics-informed Bayesian Neural Networks (BNNs) approach for UQ, which integrates knowledge from governing laws in materials to guide the models toward physically consistent predictions. To evaluate the approach, we present case studies for predicting the creep rupture life of steel alloys. Experimental validation with three datasets of creep tests demonstrates that this method produces point predictions and uncertainty estimations that are competitive or exceed the performance of conventional UQ methods such as Gaussian Process Regression. Additionally, we evaluate the suitability of employing UQ in an active learning scenario and report competitive performance. The most promising framework for creep life prediction is BNNs based on Markov Chain Monte Carlo approximation of the posterior distribution of network parameters, as it provided more reliable results in comparison to BNNs based on variational inference approximation or related NNs with probabilistic outputs.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Improving AlphaFold2-based protein tertiary structure prediction with MULTICOM in CASP15

Since the 14th Critical Assessment of Techniques for Protein Structure Prediction (CASP14), AlphaFold2 has become the standard method for protein tertiary structure prediction. One remaining challenge is to further improve its prediction. We developed a new version of the MULTICOM system to sample diverse multiple sequence alignments (MSAs) and structural templates to improve the input for AlphaFold2 to generate structural models. The models are then ranked by both the pairwise model similarity and AlphaFold2 self-reported model quality score. The top ranked models are refined by a novel structure alignment-based refinement method powered by Foldseek. Moreover, for a monomer target that is a subunit of a protein assembly (complex), MULTICOM integrates tertiary and quaternary structure predictions to account for tertiary structural changes induced by protein-protein interaction. The system participated in the tertiary structure prediction in 2022 CASP15 experiment. Our server predictor MULTICOM_refine ranked 3rd among 47 CASP15 server predictors and our human predictor MULTICOM ranked 7th among all 132 human and server predictors. The average GDT-TS score and TM-score of the first structural models that MULTICOM_refine predicted for 94 CASP15 domains are ~0.80 and ~0.92, 9.6% and 8.2% higher than ~0.73 and 0.85 of the standard AlphaFold2 predictor respectively.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Topological structure of complex predictions

Abstract Current complex prediction models are the result of fitting deep neural networks, graph convolutional networks or transducers to a set of training data. A key challenge with these models is that they are highly parameterized, which makes describing and interpreting the prediction strategies difficult. We use topological data analysis to transform these complex prediction models into a simplified topological view of the prediction landscape. The result is a map of the predictions that enables inspection of the model results with more specificity than dimensionality-reduction methods such as tSNE and UMAP. The methods scale up to large datasets across different domains. We present a case study of a transformer-based model previously designed to predict expression levels of a piece of DNA in thousands of genomic tracks. When the model is used to study mutations in the BRCA1 gene, our topological analysis shows that it is sensitive to the location of a mutation and the exon structure of BRCA1 in ways that cannot be found with tools based on dimensionality reduction. Moreover, the topological framework offers multiple ways to inspect results, including an error estimate that is more accurate than model uncertainty. Further studies show how these ideas produce useful results in graph-based learning and image classification.

Computer Science↗
DOE OSTI2020

Molecular dynamics simulations for glass transition temperature predictions of polyhydroxyalkanoate biopolymers

Polyhydroxyalkanoates (PHAs) represent an emerging class of biosynthetic and biodegradable polyesters that exhibit considerable potential to replace petroleum-based plastics towards a sustainable future. Despite the promise, general structure–property mappings within this class of polymers remain largely unexplored. An efficient exploration of this vast chemical space calls for the development and validation of predictive methods for accurate estimation of a diverse range of properties for PHA-based polymers. Towards this aim, we present and validate in this work the results of our molecular dynamics (MD) simulation based approach aimed at predicting glass transition temperatures (T g ) of PHA-based polymers. Since generally available and widely used polymer forcefields exhibit a relatively poor performance for T g predictions, we have developed a new forcefield by modifying the polymer consistent force field (PCFF) via refining a selected set of torsion potentials of the polymer backbone using accurate density functional theory (DFT) computations. After carefully assessing the dependence of critical simulation parameters, such as, polymer chain length, number of polymer chains, supercell size, and thermal quenching rate used in the simulation, the applicability and transferability of the modified PCFF (mPCFF) is demonstrated by directly comparing the computed T g predictions of various polymers with different chemistries, polymer side chain lengths and functional groups forming the polymer side chains against the respective experimentally measured values. Furthermore, the transport properties such as self-diffusion coefficient and viscosity are computationally determined and their well-known correlation with the target properties is demonstrated. Lastly, we have employed the developed approach to predict T g values for a number of yet-to-be-synthesized PHA-based polymers with a diverse set of functional groups in the polymer side chains. The results are further rationalized by correlating the predicted T g values with the inter-chain H-bond formation tendencies of the different side chain functional groups. This work represents an important first step towards computationally guided design of PHA-based functional polymers and opens up new directions for a systematic investigation of composition- and configuration-dependent structure–property relationships in more complex binary and ternary copolymer systems.

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

Assessing cathode property prediction via exchange-correlation functionals with and without long-range dispersion corrections

In this work, we benchmark calculated interlayer spacings, average topotactic voltages, thermodynamic stabilities, and band gaps in layered lithium transition-metal oxides (TMOs) and their de-lithiated counterparts, which are used in lithium-ion batteries as positive electrode materials, against available experimental data. Specifically, we examine the accuracy of properties calculated within density functional theory (DFT) using eight different treatments of electron exchange-correlation: the strongly constrained and appropriately normed (SCAN) and Perdew–Burke–Ernzerhof (PBE) density functionals, Hubbard-U-corrected SCAN and PBE (i.e., SCAN+U and PBE+U), and SCAN(+U) and PBE(+U) with added long-range dispersion (D) interactions (i.e., DFT(+U)+D). van der Waals interactions are included respectively via the revised Vydrov-Van Voorhis (rVV10) for SCAN(+U) and the DFT-D3 for PBE(+U). We find that SCAN-based functionals predict larger voltages due to an underestimation of stability of the MO2 systems, while also predicting smaller interlayer spacings compared to their PBE-based counterparts. Furthermore, adding dispersion corrections to PBE has a greater effect on voltage predictions and interlayer spacings than with SCAN, indicating that DFT-SCAN – despite being a ground-state theory – fortuitously captures some short and medium-range dispersion interactions better than PBE. While SCAN-based and PBE-based functionals yield qualitatively similar band gap predictions, there is no significant quantitative improvement of SCAN-based functionals over the corresponding PBE-based versions. Finally, we expect SCAN-based functionals to yield more accurate property predictions than the respective PBE-based functionals for most TMOs, given SCAN's stronger theoretical underpinning and better predictions of systematic trends in interlayer spacings, intercalation voltages, and band gaps obtained in this work.

25 ENERGY STORAGE↗
DOE OSTI2023

Prediction of the structures and heats of formation of MO 2 , MO 3 , and M 2 O 5 for M = V, Nb, Ta, Pa

Structures for the mono-, di-, and tri-bridge isomers of M 2 O 5 as well as those for the MO 2 and MO 3 fragments for M = V, Nb, Ta, and Pa were optimized at the density functional theory (DFT) level. Single point CCSD(T) calculations extrapolated to the complete basis set (CBS) limit at the DFT geometries were used to predict the energetics. Here, the lowest energy dimer isomer was the di-bridge for M = V and Nb and the tri-bridge for M = Ta and Pa. The di-bridge isomers were predicted to be composed of MO 2 + and MO 3 - fragments, whereas the mono- and tri-bridge are two MO 2 + fragments linked by an O 2 - . The heats of formation of M 2 O 5 dimers, as well as MO 2 and MO 3 neutral and ionic species were predicted using the Feller–Peterson–Dixon (FPD) approach. The heats of formation of the MF 5 species were calculated to provide additional benchmarks. Dimerization energies to form the M 2 O 5 dimers are predicted to become more negative going down group 5 and range from -29 to -45 kcal mol -1 . The ionization energies (IEs) for VO 2 and TaO 2 are essentially the same at 8.75 eV whereas the IEs for NbO 2 and PaO 2 are 8.10 and 6.25 eV, respectively. The predicted adiabatic electron affinities (AEAs) range from 3.75 eV to 4.45 eV for the MO 3 species and vertical detachment energies from 4.21 to 4.59 eV for MO 3 - . The calculated M[double bond, length as m-dash]O bond dissociation energies increase from 143 kcal mol -1 for M = V to ~170 kcal mol -1 for M = Nb and Ta to ~200 kcal mol -1 for M = Pa. The M–O bond dissociation energies are all similar ranging from 97 to 107 kcal mol -1 . Natural bond analysis provided insights into the types of chemical bonds in terms of their ionic character. Pa 2 O 5 is predicted to behave like an actinyl species dominated by the interactions of approximately linear PaO 2 + groups.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

Probabilistic Prediction of Geomagnetic Storms and the K p index

Geomagnetic activity is often described using summary indices to summarize the likelihood of space weather impacts, as well as when parameterizing space weather models. The geomagnetic index K p in particular, is widely used for these purposes. Current state-of-the-art forecast models provide deterministic K p predictions using a variety of methods – including empirically-derived functions, physics-based models, and neural networks – but do not provide uncertainty estimates associated with the forecast. This paper provides a sample methodology to generate a 3-hour-ahead K p prediction with uncertainty bounds and from this provide a probabilistic geomagnetic storm forecast. Specifically, we have used a two-layered architecture to separately predict storm (K p ≥ 5 – ) and non-storm cases. As solar wind-driven models are limited in their ability to predict the onset of transient-driven activity we also introduce a model variant using solar X-ray flux to assess whether simple models including proxies for solar activity can improve the predictions of geomagnetic storm activity with lead times longer than the L1-to-Earth propagation time. By comparing the performance of these models we show that including operationally-available information about solar irradiance enhances the ability of predictive models to capture the onset of geomagnetic storms and that this can be achieved while also enabling probabilistic forecasts.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

Predicting Hugoniot equation of state in erythritol with ab initio and reactive molecular dynamics

Erythritol has been proposed as an inert surrogate for developing theoretical and computational models to study aging in energetic materials. In this work, we present a comparison of mechanical and shock properties of erythritol computed using the ReaxFF reactive force field and from ab initio calculations employing density functional theory (DFT). We screened eight different ReaxFF parameterizations, of which the CHO parameters developed for hydrocarbon oxidation provide the most accurate predictions of mechanical properties and the crystal structure of erythritol. Further validation of the applicability of this ReaxFF parameterization for modeling erythritol is demonstrated by comparing predictions of the elastic constants, crystal structure, vibrational density of states, and Hugoniot curves against DFT calculations. The ReaxFF predictions are in close agreement with the DFT simulations for the elastic constants and shock Hugoniot when the crystal is loaded along its c axis but show as much as 30% disagreement in the elastic constants in the ab plane and 12% difference in shock pressures when shocked along the a or b crystal axes. Last, we compare thermomechanical properties predicted from classical molecular dynamics with those calculated using the quasi-harmonic approximation and show that quantum mechanical effects produce large discrepancies in the computed values of heat capacity and thermal expansion coefficients compared with classical assumptions. Combining classical molecular dynamics predictions of mechanical behavior with phonon-based calculations of thermal behaviors, we show that predicted shock-induced temperatures for pressures up to 6.5 GPa do not exceed the pressure-dependent melting point of erythritol.

Hu, Jing↗