SEARCH · Engineering Papers

Results for “predicted”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,783 records · Page 99

All sources NASA NTRS DOE OSTI

DOE OSTI2020

Crystal Structure Prediction of Binary Alloys via Deep Potential

Predicting crystal structure has been a challenging problem in physics and materials science for a long time. A reliable energy calculation engine combined with an efficient global search algorithm, such as particle swarm optimization algorithm or genetic algorithm, is needed to conduct crystal structure prediction. In recent years, machine learning-based interatomic potential energy surface models have been proposed, potentially allowing us to perform crystal structure prediction for systems with the accuracy of density functional theory (DFT) and the speed of empirical force fields. In this paper, we employ a previously developed Deep Potential model to predict the intermetallic compound of the aluminum–magnesium system, and find six meta-stable phases with negative or nearly zero formation energy. In particular, Mg 12 Al 8 shows excellent ductility and Mg 5 Al 27 has a high Young's modulus. Based on our benchmark results, we propose a relatively robust structure screening criterion that selects potentially stable structures from the Deep Potential-based convex hull and performs DFT refinement. By using this criterion, the computational cost needed to construct the convex hull with ab initio accuracy can be dramatically reduced.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2023

Data augmentation and multimodal learning for predicting drug response in patient-derived xenografts from gene expressions and histology images

Patient-derived xenografts (PDXs) are an appealing platform for preclinical drug studies. A primary challenge in modeling drug response prediction (DRP) with PDXs and neural networks (NNs) is the limited number of drug response samples. We investigate multimodal neural network (MM-Net) and data augmentation for DRP in PDXs. The MM-Net learns to predict response using drug descriptors, gene expressions (GE), and histology whole-slide images (WSIs). We explore whether combining WSIs with GE improves predictions as compared with models that use GE alone. We propose two data augmentation methods which allow us training multimodal and unimodal NNs without changing architectures with a single larger dataset: 1) combine single-drug and drug-pair treatments by homogenizing drug representations, and 2) augment drug-pairs which doubles the sample size of all drug-pair samples. Unimodal NNs which use GE are compared to assess the contribution of data augmentation. The NN that uses the original and the augmented drug-pair treatments as well as single-drug treatments outperforms NNs that ignore either the augmented drug-pairs or the single-drug treatments. In assessing the multimodal learning based on the MCC metric, MM-Net outperforms all the baselines. Our results show that data augmentation and integration of histology images with GE can improve prediction performance of drug response in PDXs.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2023

Deep learning methods for drug response prediction in cancer: Predominant and emerging trends

Cancer claims millions of lives yearly worldwide. While many therapies have been made available in recent years, by in large cancer remains unsolved. Exploiting computational predictive models to study and treat cancer holds great promise in improving drug development and personalized design of treatment plans, ultimately suppressing tumors, alleviating suffering, and prolonging lives of patients. A wave of recent papers demonstrates promising results in predicting cancer response to drug treatments while utilizing deep learning methods. These papers investigate diverse data representations, neural network architectures, learning methodologies, and evaluations schemes. However, deciphering promising predominant and emerging trends is difficult due to the variety of explored methods and lack of standardized framework for comparing drug response prediction models. To obtain a comprehensive landscape of deep learning methods, we conducted an extensive search and analysis of deep learning models that predict the response to single drug treatments. A total of 61 deep learning-based models have been curated, and summary plots were generated. Based on the analysis, observable patterns and prevalence of methods have been revealed. This review allows to better understand the current state of the field and identify major challenges and promising solution paths.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2026

Beyond microbial abundance: metadata integration enhances disease prediction in human microbiome studies

Multiple studies have highlighted the interaction of the human microbiome with physiological systems such as the gut, immune, liver, and skin, via key axes. Advances in sequencing technologies and high-performance computing have enabled the analysis of large-scale metagenomic data, facilitating the use of machine learning to predict disease likelihood from microbiome profiles. However, challenges such as compositionality, high dimensionality, sparsity, and limited sample sizes have hindered the development of actionable models. One strategy to improve these models is by incorporating key metadata from both the human host and sample collection/processing protocols. This remains challenging due to sparsity and inconsistency in metadata annotation and availability. In this paper, we introduce a machine learning-based pipeline for predicting human disease states by integrating host and protocol metadata with microbiome abundance profiles from 68 different studies, processed through a consistent pipeline. Our findings indicate that metadata can enhance machine learning predictions, particularly at higher taxonomic ranks like Kingdom and Phylum, though this effect diminishes at lower ranks. Our study leverages a large collection of microbiome datasets comprising 11,208 samples, therefore enhancing the robustness and statistical confidence of our findings. This work is a critical step toward utilizing microbiome and metadata for predicting diseases such as gastrointestinal infections, diabetes, cancer, and neurological disorders.

Mathematics and Computing↗

DOE OSTI2023

Integration of Computational Docking into Anti-Cancer Drug Response Prediction Models

Cancer is a heterogeneous disease in that tumors of the same histology type can respond differently to a treatment. Anti-cancer drug response prediction is of paramount importance for both drug development and patient treatment design. Although various computational methods and data have been used to develop drug response prediction models, it remains a challenging problem due to the complexities of cancer mechanisms and cancer-drug interactions. To better characterize the interaction between cancer and drugs, we investigate the feasibility of integrating computationally derived features of molecular mechanisms of action into prediction models. Specifically, we add docking scores of drug molecules and target proteins in combination with cancer gene expressions and molecular drug descriptors for building response models. The results demonstrate a marginal improvement in drug response prediction performance when adding docking scores as additional features, through tests on large drug screening data. We discuss the limitations of the current approach and provide the research community with a baseline dataset of the large-scale computational docking for anti-cancer drugs.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2021

Deep Learning-Based Hardness Prediction of Novel Refractory High-Entropy Alloys with Experimental Validation

Hardness is an essential property in the design of refractory high entropy alloys (RHEAs). This study shows how a neural network (NN) model can be used to predict the hardness of a RHEA, for the first time. We predicted the hardness of several alloys, including the novel C0.1Cr3Mo11.9Nb20Re15Ta30W20 using the NN model. The hardness predicted from the NN model was consistent with the available experimental results. The NN model prediction of C0.1Cr3Mo11.9Nb20Re15Ta30W20 was verified by experimentally synthesizing and investigating its microstructure properties and hardness. This model provides an alternative route to determine the Vickers hardness of RHEAs.

36 MATERIALS SCIENCE↗

DOE OSTI2023

Machine Learning-Based Model Predictive Control of Two-Time-Scale Systems

In this study, we present a general form of nonlinear two-time-scale systems, where singular perturbation analysis is used to separate the dynamics of the slow and fast subsystems. Machine learning techniques are utilized to approximate the dynamics of both subsystems. Specifically, a recurrent neural network (RNN) and a feedforward neural network (FNN) are used to predict the slow and fast state vectors, respectively. Moreover, we investigate the generalization error bounds for these machine learning models approximating the dynamics of two-time-scale systems. Next, under the assumption that the fast states are asymptotically stable, our focus shifts toward designing a Lyapunov-based model predictive control (LMPC) scheme that exclusively employs the RNN to predict the dynamics of the slow states. Additionally, we derive sufficient conditions to guarantee the closed-loop stability of the system under the sample-and-hold implementation of the controller. A nonlinear chemical process example is used to demonstrate the theory. In particular, two RNN models are constructed: one to model the full two-time-scale system and the other to predict solely the slow state vector. Both models are integrated within the LMPC scheme, and we compare their closed-loop performance while assessing the computational time required to execute the LMPC optimization problem.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

How Accurate Can Crystal Structure Predictions Be for High-Energy Molecular Crystals?

Molecular crystals have shallow potential energy landscapes, with multiple local minima separated by very small differences in total energy. Predicting molecular packing and molecular conformation in the crystal generally requires ab initio methods of high accuracy, especially when polymorphs are involved. We used dispersion-corrected density functional theory (DFT-D) to assess the capabilities of an evolutionary algorithm (EA) for the crystal structure prediction (CSP) of well-known but challenging high-energy molecular crystals (HMX, RDX, CL-20, and FOX-7). While providing the EA with the experimental conformation of the molecule quickly re-discovers the experimental packing, it is more realistic to start instead from a naïve, flat, or neutral initial conformation, which reflects the limited experimental knowledge we generally have in the computational design of molecular crystals. By doing so, and using fully flexible molecules in fully variable unit cells, we show that the experimental structures can be predicted in fewer than 20 generations. Nonetheless, one must be aware that some molecular crystals have naturally hindered evolutions, requiring as many attempts as there are space groups of interest to predict their structures, and some may require the accuracy of all-electron calculations to discriminate between closely ranked structures. To save resources in this computationally demanding process, we showed that a hybrid xTB/DFT-D approach could be considered in a subsequent study to push the limits of CSP beyond 200+ atoms and for cocrystals.

42 ENGINEERING↗

DOE OSTI2021

A Method of Ground-Based Cloud Motion Predict: CCLSTM + SR-Net

Ground-based cloud images can provide information on weather and cloud conditions, which play an important role in cloud cover monitoring and photovoltaic power generation forecasting. However, the cloud motion prediction of ground-based cloud images still lacks advanced and complete methods, and traditional technologies based on image processing and motion vector calculation are difficult to predict cloud morphological changes. In this paper, we propose a cloud motion prediction method based on Cascade Causal Long Short-Term Memory (CCLSTM) and Super-Resolution Network (SR-Net). Firstly, CCLSTM is used to estimate the shape and speed of cloud motion. Secondly, the Super-Resolution Network is built based on perceptual losses to reconstruct the result of CCLSTM and, finally, make it clearer. We tested our method on Atmospheric Radiation Measurement (ARM) Climate Research Facility TSI (total sky imager) images. The experiments showed that the method is able to predict the sky cloud changes in the next few steps.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2023

Tidal Turbine Benchmarking Project: Stage I - Steady Flow Blind Predictions: Preprint

This paper presents the first blind prediction stage of the Tidal Turbine Benchmarking Project being conducted and funded by the UK's EPSRC and Supergen ORE Hub. In this first stage, only steady flow conditions, at low and elevated turbulence (3.1%) levels, were considered. Prior to the blind prediction stage, a large laboratory scale experiment was conducted in which a highly instrumented 1.6m diameter tidal rotor was towed through a large towing tank in well-defined flow conditions with and without an upstream turbulence grid. Details of the test campaign and rotor design were released as part of this community blind prediction exercise. Participants were invited to use a range of engineering modelling approaches to simulate the performance and loads of the turbine. 26 submissions were received from 12 groups from across academia and industry using solution techniques ranging from blade resolved computational fluid dynamics through actuator line, boundary integral element methods, vortex methods to engineering Blade Element Momentum methods. The comparisons between experiments and blind predictions were extremely positive helping to provide validation and uncertainty estimates for the models, but also validating the experimental tests themselves. The exercise demonstrated that the experimental turbine data provides a robust data set against which researchers and design engineers can test their models and implementations to ensure robustness in their processes, helping to reduce uncertainty and provide increased confidence in engineering processes. Furthermore, the data set provides the basis by which modellers can evaluate and refine approaches.

benchmarking↗

DOE OSTI2024

Predicting metabolic modules in incomplete bacterial genomes with MetaPathPredict

The reconstruction of complete microbial metabolic pathways using ‘omics data from environmental samples remains challenging. Computational pipelines for pathway reconstruction that utilize machine learning methods to predict the presence or absence of KEGG modules in incomplete genomes are lacking. Here, we present MetaPathPredict, a software tool that incorporates machine learning models to predict the presence of complete KEGG modules within bacterial genomic datasets. Using gene annotation data and information from the KEGG module database, MetaPathPredict employs deep learning models to predict the presence of KEGG modules in a genome. MetaPathPredict can be used as a command line tool or as a Python module, and both options are designed to be run locally or on a compute cluster. Benchmarks show that MetaPathPredict makes robust predictions of KEGG module presence within highly incomplete genomes.

59 BASIC BIOLOGICAL SCIENCES↗

NASA NTRS1988

Fatigue life prediction modeling for turbine hot section materials

This paper presents a summary of the life prediction methods developed under the NASA Lewis Research Center's Hot Section Technology (HOST) program. A major objective of the fatigue and fracture efforts under the HOST program was to significantly improve the analytic life prediction tools used by the aeronautical gas turbine engine industry. This has been achieved in the areas of high-temperature thermal and mechanical fatigue of bare and coated high-temperature superalloys. Such technical improvements will eventually reduce life cycle costs. The cyclic crack initiation and propagation resistance of nominally isotropic polycrystalline alloys and highly anisotropic single crystal alloys has been addressed. A sizeable data base has been generated for three alloys [cast PWA 1455 (B-1900 + Hf), wrought Inconel 718, and cast single crystal PWA 1480] in bare and coated conditions. Two coatings systems, diffusion aluminide (PWA 273) and plasma sprayed MCrAIY overlay (PWA 286) were employed. Life prediction modeling efforts were devoted to creep-fatigue interaction, oxidation, coatings interactions, multiaxiality of stress-strain states, mean stress effects, cumulative damage, and thermomechanical fatigue. The fatigue crack initiation life models developed to date include the Cyclic Damage Accumulation (CDA) Model of Pratt & Whitney and the Total Strain Version of Strainrange Partitioning (TS-SRP) of NASA Lewis for nominally isotropic materials, and the Tensile Hysteretic Energy Model of Pratt & Whitney for anisotropic superalloys. The fatigue model being developed by the General Electric Company is based upon the concepts of Path-lndependent Integrals (PII) for describing cyclic crack growth under complex nonlinear response at the crack tip due to thermomechanical loading conditions. A micromechanistic oxidation crack extension model has been derived by researchers at Syracuse University. The models are described and discussed in the paper. Only limited verification has been achieved to-date as several of the technical programs are still in progress and the verification tasks are scheduled, quite naturally, near the conclusion of the program. To-date, efforts have concentrated on development of independent models for cyclic constitutive behavior, cyclic crack initiation, and cyclic crack propagation. The transition between crack initiation and crack propagation has not been thoroughly researched as yet, and the integration of these models into a unified life prediction method has not been addressed.

Metal fatigue↗

NASA NTRS2016

Analyzing and Predicting Effort Associated with Finding and Fixing Software Faults

Context: Software developers spend a significant amount of time fixing faults. However, not many papers have addressed the actual effort needed to fix software faults. Objective: The objective of this paper is twofold: (1) analysis of the effort needed to fix software faults and how it was affected by several factors and (2) prediction of the level of fix implementation effort based on the information provided in software change requests. Method: The work is based on data related to 1200 failures, extracted from the change tracking system of a large NASA mission. The analysis includes descriptive and inferential statistics. Predictions are made using three supervised machine learning algorithms and three sampling techniques aimed at addressing the imbalanced data problem. Results: Our results show that (1) 83% of the total fix implementation effort was associated with only 20% of failures. (2) Both safety critical failures and post-release failures required three times more effort to fix compared to non-critical and pre-release counterparts, respectively. (3) Failures with fixes spread across multiple components or across multiple types of software artifacts required more effort. The spread across artifacts was more costly than spread across components. (4) Surprisingly, some types of faults associated with later life-cycle activities did not require significant effort. (5) The level of fix implementation effort was predicted with 73% overall accuracy using the original, imbalanced data. Using oversampling techniques improved the overall accuracy up to 77%. More importantly, oversampling significantly improved the prediction of the high level effort, from 31% to around 85%. Conclusions: This paper shows the importance of tying software failures to changes made to fix all associated faults, in one or more software components and/or in one or more software artifacts, and the benefit of studying how the spread of faults and other factors affect the fix implementation effort.

software fix implementation effort↗

NASA NTRS2017

Simulation-Based Height of Burst Map for Asteroid Airburst Damage Prediction

Entry and breakup models predict that airburst in the Earth's atmosphere is likely for asteroids up to approximately 200 meters in diameter. Objects of this size can deposit over 250 megatons of energy into the atmosphere. Fast-running ground damage prediction codes for such events rely heavily upon methods developed from nuclear weapons research to estimate the damage potential for an airburst at altitude. (Collins, 2005; Mathias, 2017; Hills and Goda, 1993). In particular, these tools rely upon the powerful yield scaling laws developed for point-source blasts that are used in conjunction with a Height of Burst (HOB) map to predict ground damage for an airburst of a specific energy at a given altitude. While this approach works extremely well for yields as large as tens of megatons, it becomes less accurate as yields increase to the hundreds of megatons potentially released by larger airburst events. This study revisits the assumptions underlying this approach and shows how atmospheric buoyancy becomes important as yield increases beyond a few megatons. We then use large-scale three-dimensional simulations to construct numerically generated height of burst maps that are appropriate at the higher energy levels associated with the entry of asteroids with diameters of hundreds of meters. These numerically generated HOB maps can then be incorporated into engineering methods for damage prediction, significantly improving their accuracy for asteroids with diameters greater than 80-100 m.

Burst Map↗

NASA NTRS2017

Real-Time Prediction of Safety Margins in the National Airspace

Underlying all operations in the National Airspace System (NAS) is the concept of safety. Safety, as defined by acceptable levels of risk, is to be maintained at all times. The real-time safety monitoring (RTSM) framework is under development to provide an automated system to quantify safety in the NAS, estimate the current level of safety, and predict the future evolution of safety and the occurrence of events that pose an increased risk to flights so that these occurrences can be managed strategically rather than mitigated reactively. This paper presents the mathematical framework, the models, and the monitoring and prediction algorithms used to achieve this. RTSM computes safety as expressed through a set of safety margins based on user-defined safety metrics, thresolds, and events. Sources of uncertainty are modeled and propagated through the predictions in order to compute the probabilistic evolution of safety and the probability of events that introduce increased risk to operations. A prototype implementation is discussed and results demonstrating feasibility are presented. The results highlight the kinds of predictions that can be computed and the fidelity that is currently achieved.

national airspace system↗

NASA NTRS2020

Predicting Gate Conflicts at Charlotte Douglas International Airport Using NASA ATD-2 Fused Data Sources

NASA is conducting the Airspace Technology Demonstration-2 to evaluate an Integrated Arrival, Departure, and Surface (IADS) traffic management system. The IADS system is powered by real-time System Wide Information Management feeds which provide an accurate and high fidelity view of the lifecycle of a flight. This data can be leveraged to drive efficiencies in the National Airspace System. For non safety critical applications there is opportunity for third party service providers to offer this type of data-driven prediction service in near real-time. This paper investigates the gate conflict prediction problem as a concrete use case which could help drive efficiencies. We model gate conflicts as a regression problem and describe the iterative process of model building, model validation, and evaluation used to assess the efficacy of our approach. We quantify our predictive accuracy and identify paths for improvement. Through this iterative process we hope to evolve our models and methods to a near real-time prediction service.

Airspace Technology Demonstration 2↗

NASA NTRS2021

A New Method for Predicting Turbulent Flow Reattachment Location: Application of Stratford Criterion for Reattaching Flows

A new method for predicting turbulent flow reattachment location has been developed. The method predicts the reattachment location using the surface static pressure distribution and requires only a single empirical parameter. The method is based on the well-known Stratford’s flow separation criterion, which results from an approximate solution to the equations of motion within the boundary layer. Because of the large pressure rise, the original Stratford separation criterion is not valid for reattaching flows. In order to apply the Stratford criterion for reattaching flows, the reference location was moved to the pressure drop conditions instead of pressure rise conditions. In addition, the pressure distribution was scaled using a technique that was originally introduced for supersonic base flows. A new empirical parameter was also obtained for the modified Stratford criterion. The method has been tested for 30 different separated flow configurations from the literature. The variety of test cases include subsonic flows, transonic flows, 2D flows, and axisymmetric flows, with experimental as well as high resolution numerical simulation results. The flow reattachment predictions with the new method agree very well with the reported data. The error is less than 5% and typically about 2%. The new method is an extremely simple and a quick way of finding the reattachment location. Given the complexities of the existing experimental techniques for finding the reattachment location, the method easily and quickly provides the flow reattachment location, which could be used to estimate the physical extent of separation bubbles, as a performance index for flow control methods, or to assess the predictive capability of turbulence models.

Flow reattachment location↗

NASA NTRSDate not supplied

Predicting contamination accumulation in facilities with limited data

In preparation for the James Webb Space Telescope (JWST) launch at Centre Spatial Guyanias (CSG) in French Guiana, particulate contamination accumulation predictions were necessary for each facility in which the hardware would be exposed because the Telescope would be uncovered in each of the facilities and had strict particulate requirements. These included facilities for final integration and testing, fueling, transportation and encapsulation. Minimal heritage data existed from CSG and previous launch campaigns to use as a basis for contamination predictions. Data from the Automatic Transfer Vehicle and Herschel & Planck launch campaigns were used in conjunction with facility monitoring data provided by ESA and data collected during JWST working group visits to CSG. These campaigns were conducted at varying cleanliness levels that were typically less stringent than JWST requirements. Each facility was evaluated using the data provided and likely performance improvement with the addition of High Efficiency Particulate Air filter (HEPA) banks operating when possible. Once the launch campaign was completed, the predicted fallout was compared with actual data collected throughout the campaign. Based on the actual measurements, JWST’s primary and secondary mirrors turned out to be much cleaner than what was predicted.

James Webb Space Telescope, contamination, cleanro↗