Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “prediction methods”

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 1,063 records · Page 59
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

High throughput, accurate gene annotation through AI and HPC-enabled structural analysis

With the advances in next generation sequencing technologies, the number of sequenced genomes is growing exponentially, resulting in a technology bottleneck for the translation of sequence information into usable hypotheses about the function of each gene. We have proposed leveraging our leadership high-performance computing (HPC) resources to help break this annotation bottleneck. Here we design an HPC-based framework to infer gene function from gene sequence by incorporating information about protein structure and interactions predicted by deep learning approaches. Accurate functional prediction and gene annotation using computational methods will facilitate breakthroughs in the genomic sciences essential to understanding and harnessing life processes in bacteria, fungi and plants. The development and applications of the state-of-the-art deep neural networks to protein structural modeling, interaction prediction, sequence comparison, and quality assessment of protein structural models will be made possible by leadership computational resources. These HPC-enabled bioinformatics and molecular modeling tools will provide powerful insights into molecular functions of genes.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Physics-Informed Learning Machines for Multiscale and Multiphysics Problems (PHILMS) (Technical Report)

The research work at University of California Santa Barbara (UCSB) resulted in several new developments in the areas of scientific machine learning, numerical analysis, and practical methods for data-driven modeling, prediction, reductions, and simulation. Many of the projects were carried out in collaboration with members of the national laboratories at Sandia National Laboratories (SNL), Pacific Northwestern National Laboratories (PNNL), and other institutions. Results included developing new scientific machine learning methods, related theory and mathematical frameworks for analysis and training, data-driven numerical solvers, and related tools and software for scientific computation. During the support period, over 16+ papers were submitted for publication, and 4 open-source software packages were developed and released (available at http://atzberger.org/). In addition, 7+ students and 2 post-docs were mentored in collaboration with the laboratory staff for future careers in academia, government labs, and industry.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Kinetic Deep Learning v0.1

Here, we present a method that uses protein levels to predict times series of metabolite concentrations. Understanding this type of pathway dynamics is important in order to predict the behavior of the pathway and, more pragmatically, to be able to design biological systems (such as strains bioengineered to produce chemical products) reliably. Typically, for this purpose, kinetic models consisting of differential equations based on the Michaelis-Menten dynamics have been used in the past. However, these methods can rarely produce good fits to measured data time series. Possibly, this happens because the kinetic constants are unknown or are different from the ones measured in vivo, or perhaps because Michaelis-Menten dynamics is not a satisfactory description. In order to improve the predictive nature of these kinetic models we have eliminated the Michaelis-Menten description of pathway dynamics and we have substituted it by algorithms that automatically learn these dynamics from previously obtained metabolomics and proteomics data using machine learning approaches. Specifically, kinetic deep learning uses deep learning to map proteomics time series to metabolite concentration time series, instead of learning the first metabolite derivative and integrating in (as in the first version of kinetic learning). This approach is shown to provide good to excellent results with a data set specifically collected for this purpose.

Garcia Martin, Hector [Joint BioEnergy Institute (↗
DOE OSTI2024

Source of Processable Vitrimer Viscosities: Swap Frequencies and Steric Factors

Vitrimers exhibit high, processable viscosities, where other polymers do not, and are among the most promising polymers for closed-loop material circularity. We sought to investigate the underlying chemical kinetic factors that result in high viscosities for vitrimers, which are crucial to designing vitrimers with tunable viscosity. To interrogate these factors, we achieved the first simulated predictions of real vitrimer viscosities, using a novel kinetic Monte Carlo molecular dynamics method, overcoming the time and length scale gaps to predict experimental bulk viscosities. The vitrimer architecture investigated is based on poly(dimethylsiloxane) chains and vinylogous urethane bond swaps. We probed the effects of the extent of free swapping groups, %F, the activation energy, E A , and the steric factor, ρ. The steric factor is related to the intrinsic reaction probability for molecules with sufficient energy. All three factors were found to be significant, but the role of ρ was found to be the biggest and also the most underappreciated. The results show that the inclusion of accurate ρ is of critical importance for viscosity predictions, with the evidence suggesting that the typical assumption of ρ = 1 is not valid for vitrimers and that, indeed, very low steric factors are present in bond-swap vitrimers such that values of ρ < 10 –10 may be typical. This greatly influences the bond exchange rates and, ultimately, the viscosities. Recognition of this result is necessary for the prediction of vitrimer viscosities from molecular simulations and to make vitrimers by design from molecular dynamics. We also investigated the effects that E A , ρ, and the number of free swapping groups have upon vitreous range temperatures, TV, with respect to achieving a specific viscosity (η V = 1 × 10 8 Pa·s), as well as for a commonly reported higher viscosity extrapolation (η V = 1 × 10 12 Pa·s). The evidence suggests that vitrimers may follow universal curves for E A vs T V , as a function of ρ. Finally, this study achieves the first of these comparisons of molecular simulations to experiments and reveals critical insights toward creating vitrimers by design, while providing a route for the prediction of T V from kinetic Monte Carlo molecular dynamics simulations.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Impacts of phase state and water content on secondary organic aerosol formation and partitioning (Final Technical Report)

Secondary organic aerosols (SOA) account for a major fraction of particulate matter in the atmosphere, affecting climate, air quality, and public health. SOA formation and evolution are highly complex processes involving both chemical reactions and transport of molecules in air, at particle surfaces, and within particles. The state of the matter, or “phase state,” comprising SOA can vary from a liquid, over an amorphous semi-solid, to a glassy solid, depending on chemical composition, water content, relative humidity (RH), and temperature. The occurrence of glassy and amorphous semi-solid states can pose limitations on the rate of transport of molecules, affecting gas-particle interactions and challenging the treatment of SOA in atmospheric models. The objective of this project was to improve fundamental understanding of the interplay of the phase state of particles and water content on the evolution of SOA formation. We have developed a method to estimate the glass transition temperature (T g ) of organic compounds to predict the phase state and viscosity of SOA. This method has been applied to high resolution mass spectrometry data of various types of SOA, achieving a good agreement with viscosity measurements. In addition, the viscosity estimation method was implemented into a regional model CMAQ to simulate diel and seasonal variations of SOA phase state over the U.S. Applying kinetic multilayer modeling, we analyzed laboratory experiments and ARM field measurements (e.g., HI-SCALE) on kinetic limitations of amine uptake. We have also conducted numerical simulations to estimate equilibration timescales of SOA partitioning. Overall, we have evaluated the impacts of phase state and water content on SOA lifecycle that should contribute to reducing the uncertainty of SOA representation in regional climate and air quality predictions. The project has yielded 17 publications, in which DE-SC0018349 is explicitly acknowledged. Please see the list of publications as below, followed by summary of research activities.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Integrative teaching of metabolic modeling and flux analysis with interactive python modules

Abstract The modeling of rates of biochemical reactions—fluxes—in metabolic networks is widely used for both basic biological research and biotechnological applications. A number of different modeling methods have been developed to estimate and predict fluxes, including kinetic and constraint‐based (Metabolic Flux Analysis and flux balance analysis) approaches. Although different resources exist for teaching these methods individually, to‐date no resources have been developed to teach these approaches in an integrative way that equips learners with an understanding of each modeling paradigm, how they relate to one another, and the information that can be gleaned from each. We have developed a series of modeling simulations in Python to teach kinetic modeling, metabolic control analysis, 13C‐metabolic flux analysis, and flux balance analysis. These simulations are presented in a series of interactive notebooks with guided lesson plans and associated lecture notes. Learners assimilate key principles using models of simple metabolic networks by running simulations, generating and using data, and making and validating predictions about the effects of modifying model parameters. We used these simulations as the hands‐on computer laboratory component of a four‐day metabolic modeling workshop and participant survey results showed improvements in learners' self‐assessed competence and confidence in understanding and applying metabolic modeling techniques after having attended the workshop. The resources provided can be incorporated in their entirety or individually into courses and workshops on bioengineering and metabolic modeling at the undergraduate, graduate, or postgraduate level.

Kaste, Joshua A. M.↗
DOE OSTI2022

CASM — A software package for first-principles based study of multicomponent crystalline solids

CASM is a software package that enables first-principles based studies of crystalline materials. It has been designed to treat coupled chemical, mechanical, vibrational, and magnetic degrees of freedom to determine ground state and finite temperature properties of crystals. The symmetry of the underlying parent crystal structure is used to enumerate perturbations of the parent crystal structure and generate derivative structures which can be input to first-principles calculations in order to explore the ground state energy landscape. CASM algorithmically constructs cluster expansions that fully couple discrete and continuous degrees of freedom, and generates highly efficient code to evaluate the cluster expansion basis functions. Widely used machine learning methods are integrated for fitting expansion coefficients to first-principle calculations. The fully parameterized cluster expansions can be combined with (kinetic) Monte Carlo methods to calculate finite temperature thermodynamic and kinetic properties. CASM Alloy Manager identifies distinct parent crystal structures in an alloy system, creating individual projects for each, and integrating the results. The integrated infrastructure facilitates the linkage between first-principles statistical mechanics predictions with higher length scale computational methods, such as phase field simulations. In conclusion, CASM projects are designed to be easy to share in repositories, to re-use, and to extend to include additional chemical species or types of degrees of freedom.

36 MATERIALS SCIENCE↗
DOE OSTI2021

A probabilistic creep model incorporating test condition, initial damage, and material property uncertainty

Uncertainty is prevalent in the creep resistance of alloys, where at elevated temperature and low pressure, rupture can range across logarithmic decades. In this study, a probabilistic continuum-damage-mechanics (CDM)-based model is derived to capture the uncertainty of creep resistance. To meet this objective, creep data for alloy 304 Stainless Steel is gathered. A constitutive model, “Sinh”, is calibrated deterministically to determine the statistical variability of the material properties. Three sources of uncertainty are injected into the model: test condition (stress and temperature), initial damage, and material properties. Probabilistic simulations are carried out by (a) calibrating probability distribution functions (pdfs) for each source of uncertainty (b) randomly sampling the pdfs using Monte Carlo methods and (c) executing simulations to replicate the uncertain creep behavior. A sensitivity analysis is performed to evaluate the relative effect of each source of uncertainty. In full probabilistic simulations, the cumulative uncertainty of creep behavior is evaluated. The probabilistic model accurately predicts the creep deformation and rupture of the available experiments. The probabilistic model is validated for interpolation but lacks extrapolation ability. Several future works are proposed to further improve the model.

36 MATERIALS SCIENCE↗
DOE OSTI2023

RCSB Protein Data Bank: visualizing groups of experimentally determined PDB structures alongside computed structure models of proteins

Recent advances in Artificial Intelligence and Machine Learning (e.g., AlphaFold, RosettaFold, and ESMFold) enable prediction of three-dimensional (3D) protein structures from amino acid sequences alone at accuracies comparable to lower-resolution experimental methods. These tools have been employed to predict structures across entire proteomes and the results of large-scale metagenomic sequence studies, yielding an exponential increase in available biomolecular 3D structural information. Given the enormous volume of this newly computed biostructure data, there is an urgent need for robust tools to manage, search, cluster, and visualize large collections of structures. Equally important is the capability to efficiently summarize and visualize metadata, biological/biochemical annotations, and structural features, particularly when working with vast numbers of protein structures of both experimental origin from the Protein Data Bank (PDB) and computationally-predicted models. Moreover, researchers require advanced visualization techniques that support interactive exploration of multiple sequences and structural alignments. This paper introduces a suite of tools provided on the RCSB PDB research-focused web portal RCSB. org, tailor-made for efficient management, search, organization, and visualization of this burgeoning corpus of 3D macromolecular structure data.

3D visualization↗
DOE OSTI2024

Accelerate microstructure evolution simulation using graph neural networks with adaptive spatiotemporal resolution

Abstract Surrogate models driven by sizeable datasets and scientific machine-learning methods have emerged as an attractive microstructure simulation tool with the potential to deliver predictive microstructure evolution dynamics with huge savings in computational costs. Taking 2D and 3D grain growth simulations as an example, we present a completely overhauled computational framework based on graph neural networks with not only excellent agreement to both the ground truth phase-field methods and theoretical predictions, but enhanced accuracy and efficiency compared to previous works based on convolutional neural networks. These improvements can be attributed to the graph representation, both improved predictive power and a more flexible data structure amenable to adaptive mesh refinement. As the simulated microstructures coarsen, our method can adaptively adopt remeshed grids and larger timesteps to achieve further speedup. The data-to-model pipeline with training procedures together with the source codes are provided.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Predicting the formation of fractionally doped perovskite oxides by a function-confined machine learning method

Abstract Fractionally doped perovskites oxides (FDPOs) have demonstrated ubiquitous applications such as energy conversion, storage and harvesting, catalysis, sensor, superconductor, ferroelectric, piezoelectric, magnetic, and luminescence. Hence, an accurate, cost-effective, and easy-to-use methodology to discover new compositions is much needed. Here, we developed a function-confined machine learning methodology to discover new FDPOs with high prediction accuracy from limited experimental data. By focusing on a specific application, namely solar thermochemical hydrogen production, we collected 632 training data and defined 21 desirable features. Our gradient boosting classifier model achieved a high prediction accuracy of 95.4% and a high F1 score of 0.921. Furthermore, when verified on additional 36 experimental data from existing literature, the model showed a prediction accuracy of 94.4%. With the help of this machine learning approach, we identified and synthesized 11 new FDPO compositions, 7 of which are relevant for solar thermochemical hydrogen production. We believe this confined machine learning methodology can be used to discover, from limited data, FDPOs with other specific application purposes.

08 HYDROGEN↗
DOE OSTI2021

Failure prediction and estimation of failure parameters

Machine-learning methods and apparatus are disclosed to determine frictional state or other parameters in an earthquake zone or other failing medium, using acoustic emission, seismic waves, or other detectable indicators of microscopic processes. Predictions of future failures are demonstrated in different regimes. A classifier is trained using time series of acoustic emission data along with historic data of frictional state or failure events. In disclosed examples, random forests and gradient boost trees are used, and grid-search or EGO procedures are used for hyperparameter tuning. Once trained, the classifier can be applied to testing or live data in order to assess a frictional state, assess seismic hazard, or make predictions regarding a future failure event. The technology has been developed in a double direct shear apparatus, but can be widely applied to seismic faults, other terrestrial failures, or failures in man-made structures. Variations are disclosed.

Johnson, Paul Allan↗
DOE OSTI2023

Hybrid physics-based and machine learning tools for materials assessment

In this work, we develop novel physics-based and machine learning computational techniques to predict fundamental properties of metallic systems that affect radiation damage behavior in reactor structural materials. Oftentimes, atomistic predictions of engineering alloys simplify chemical compositions to a single element to reduce computational cost and complexity, introducing large sources of uncertainty and potentially missing important behavior. In addition, engineering alloys such as SS 316 are particularly challenging to simulate with first principles methods because of the additional degrees of freedom introduced by magnetic natures of the constituent elements, and very little data of this type exists within the literature. These novel methods aim to improve the qualitative prediction of radiation damage in engineering alloys by more accurately simulating their compositions, both by accelerating the computations and by developing novel analyses.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2022

Machine Learning Models for Binary Molecular Classification using VUV Absorption Spectra

Machine learning methods were combined with differential absorption spectroscopy measurements in the vacuum-ultraviolet region (5.167 – 9.920 eV) in order to develop predictive capabilities for inferring molecular structure from the spectra. Several types of species were analyzed and, for modeling purposes, were defined using a single classification: (1) alkane, (2) conjugation with oxygen (e.g. diacetyl, ethyl vinyl ether), (3) non-conjugated alkene (e.g. 1-butene, 1,4-cyclohexadiene), (4) oxygen-containing (e.g. 1-butanol, tetrahydrofuran), or (5) cyclic (e.g. cyclopentane, cyclohexanone). The latter molecular classification excluded cyclic ethers. Several modeling methods were employed in the analysis of 102 absorption spectra, 24 of which were measured for the first time. The primary objective was to identify suitable methods that enable accurate predictions of molecular structure classifications with minimized statistical uncertainties. Rather than identifying a single, unifying method to reliably predict molecular structure contributions to VUV absorption spectra, coordination is required among a particular method, the type of molecular structure detail (e.g. conjugation), and absorption region of interest. The latter is accomplished using a binning approach, wherein absorption regions of ~0.5 eV were utilized rather than the entire ~4.8 eV range. Photon energy binning enabled analysis of region-specific predictions of accuracy, precision, and recall. The outcome from the binning approach is that, rather than utilizing the entire spectrum, optimal determination of molecular structure using machine learning methods depends on the absorption region. Furthermore, the present work provides separate machine learning models for each molecular classification, which enables the identification of multi-functional species relevant to atmospheric chemistry and combustion chemistry, where isomer-resolved speciation is critical to understanding complex reaction networks.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

ML-Based Power System Stability Assessment Considering Network Topology Changes: WECC 20,000+ Bus System Case Study

Modern power grids are fast-changing and thus require real-time monitoring and online stability assessment. With the rapid development of machine learning (ML) techniques, using data-driven models to provide fast and accurate estimations of power system stability marginal information, such as frequency nadir for frequency stability and critical clearing time (CCT) for transient stability, have become possible. However, despite the numerous research on ML-based methods for frequency nadir and CCT prediction, there is limited work on the impact of different network topology changes. Furthermore, most previous studies only focused on small or synthetic systems, and there is a lack of research on actual large power system models. In this paper, the above issues are addressed by studying the actual U.S. Western Electricity Coordinating Council (WECC) system model with more than 20,000 buses. Massive simulations are conducted in PowerWorld Simulator to study the impact of various topology change scenarios on both frequency stability and transient stability. System operating information is extracted from the success dispatch cases of various network topologies to generate a comprehensive dataset for ML-based models. Two ML methods, random forest (RF) and multilayer perceptron (MLP) neural network, are trained and tested for both frequency nadir prediction and CCT prediction. Test results have proven the models are capable of online stability assessment for large power networks such as the WECC system with sufficient accuracy.

critical clearing time↗
DOE OSTI2021

Long-term carbon emission reduction potential of building retrofits with dynamically changing electricity emission factors

Buildings account for approximately 36% of the United States' total carbon emissions and building retrofits have great potential to reduce carbon emissions. Current research adopts a constant electricity emission factor although it changes over time due to the increase of renewable energy generation. Here, to accurately predict emission reduction potential of building retrofits, this study develops a novel method by using dynamically changing electricity emission factors. Using medium office buildings as an example, we predicted emission reduction of eight building retrofit measures from 2020 to 2050 in five locations in the U.S. with distinct climates and renewable adoption rates. To evaluate emission reduction potential sensitivity to the compositions of electricity generation, five scenarios for renewable energy adoptions are investigated. The results reveal several new phenomena on emission reduction potential of building retrofits for medium offices in the U.S.: (1) it decreases from 2026 to 2050; (2) it has the same trend with coal usage; and (3) it reaches the maximum under the high renewable cost scenario. Based on the results, it is recommended that building retrofits should focus on 1) improving lighting and equipment efficiency; 2) locations with higher coal usage rate, and 3) buildings under the high renewable cost scenario. The new method can also be used for predicting emission reduction potential of the building sector in the U.S. by applying to other building types and regions.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗