Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “input data”

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 1,621 records · Page 90
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Machine learning models inaccurately predict current and future high-latitude C balances

The high-latitude carbon (C) cycle is a key feedback to the global climate system, yet because of system complexity and data limitations, there is currently disagreement over whether the region is a source or sink of C. Recent advances in big data analytics and computing power have popularized the use of machine learning (ML) algorithms to upscale site measurements of ecosystem processes, and in some cases forecast the response of these processes to climate change. Due to data limitations, however, ML model predictions of these processes are almost never validated with independent datasets. To better understand and characterize the limitations of these methods, we develop an approach to independently evaluate ML upscaling and forecasting. We mimic data-driven upscaling and forecasting efforts by applying ML algorithms to different subsets of regional process-model simulation gridcells, and then test ML performance using the remaining gridcells. In this study, we simulate C fluxes and environmental data across Alaska using ecosys, a process-rich terrestrial ecosystem model, and then apply boosted regression tree ML algorithms to training data configurations that mirror and expand upon existing AmeriFLUX eddy-covariance data availability. We first show that a ML model trained using ecosys outputs from currently-available Alaska AmeriFLUX sites incorrectly predicts that Alaska is presently a modeled net C source. Increased spatial coverage of the training dataset improves ML predictions, halving the bias when 240 modeled sites are used instead of 15. However, even this more accurate ML model incorrectly predicts Alaska C fluxes under 21st century climate change because of changes in atmospheric CO 2 , litter inputs, and vegetation composition that have impacts on C fluxes which cannot be inferred from the training data. Our results provide key insights to future C flux upscaling efforts and expose the potential for inaccurate ML upscaling and forecasting of high-latitude C cycle dynamics.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

A Convolutional Neural Network Model for Battery Capacity Fade Curve Prediction using Early Life Data

Herein, early prediction of battery performance degradation trends can facilitate research of new materials and cell designs, rapid deployment of batteries in real-world applications, timely replacement of batteries in critical applications, and even the secondary use market. In this study, we design a convolutional neural network model to predict the entire battery capacity fade curve - a critical indicator of battery performance degradation - using first 100 cycles of data (~ three weeks of testing). We use the discharge voltage-capacity curves as input to the model and automate the feature extraction process through the convolutional layers of the network. Our approach can predict the per cycle capacity fade rate and rollover cycle (knee point) in the capacity fade curve, which indicate the onset of rapid capacity decay. On the publicly available graphite/LiFePO 4 battery dataset, optimized networks predict the capacity fade curves, rollover cycle, and end of life with 3.7% (worst-case), 19%, and 17% mean absolute percentage errors, respectively.

25 ENERGY STORAGE↗
DOE OSTI2020

Enhancing Streamflow Forecast and Extracting Insights Using Long-Short Term Memory Networks With Data Integration at Continental Scales

Recent observations with varied schedules and types (moving average, snapshot, or regularly spaced) can help to improve streamflow forecasts, but it is challenging to integrate them effectively. Based on a long short-term memory (LSTM) streamflow model, we tested multiple versions of a flexible procedure we call data integration (DI) to leverage recent discharge measurements to improve forecasts. DI accepts lagged inputs either directly or through a convolutional neural network unit. DI ubiquitously elevated streamflow forecast performance to unseen levels, reaching a record continental-scale median Nash-Sutcliffe Efficiency coefficient value of 0.86. Integrating moving-average discharge, discharge from the last few days, or even average discharge from the previous calendar month could all improve daily forecasts. Directly using lagged observations as inputs was comparable in performance to using the convolutional neural network unit. Importantly, we obtained valuable insights regarding hydrologic processes impacting LSTM and DI performance. Before applying DI, the base LSTM model worked well in mountainous or snow-dominated regions, but less well in regions with low discharge volumes (due to either low precipitation or high precipitation-energy synchronicity) and large interannual storage variability. DI was most beneficial in regions with high flow autocorrelation: it greatly reduced baseflow bias in groundwater-dominated western basins and also improved peak prediction for basins with dynamical surface water storage, such as the Prairie Potholes or Great Lakes regions. However, even DI cannot elevate performance in high-aridity basins with 1-day flash peaks. Despite this limitation, there is much promise for a deep-learning-based forecast paradigm due to its performance, automation, efficiency, and flexibility.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

From calibration to parameter learning: Harnessing the scaling effects of big data in geoscientific modeling

Abstract The behaviors and skills of models in many geosciences (e.g., hydrology and ecosystem sciences) strongly depend on spatially-varying parameters that need calibration. A well-calibrated model can reasonably propagate information from observations to unobserved variables via model physics, but traditional calibration is highly inefficient and results in non-unique solutions. Here we propose a novel differentiable parameter learning (dPL) framework that efficiently learns a global mapping between inputs (and optionally responses) and parameters. Crucially, dPL exhibits beneficial scaling curves not previously demonstrated to geoscientists: as training data increases, dPL achieves better performance, more physical coherence, and better generalizability (across space and uncalibrated variables), all with orders-of-magnitude lower computational cost. We demonstrate examples that learned from soil moisture and streamflow, where dPL drastically outperformed existing evolutionary and regionalization methods, or required only ~12.5% of the training data to achieve similar performance. The generic scheme promotes the integration of deep learning and process-based models, without mandating reimplementation.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Defect detection in atomic-resolution images via unsupervised learning with translational invariance

Abstract Crystallographic defects can now be routinely imaged at atomic resolution with aberration-corrected scanning transmission electron microscopy (STEM) at high speed, with the potential for vast volumes of data to be acquired in relatively short times or through autonomous experiments that can continue over very long periods. Automatic detection and classification of defects in the STEM images are needed in order to handle the data in an efficient way. However, like many other tasks related to object detection and identification in artificial intelligence, it is challenging to detect and identify defects from STEM images. Furthermore, it is difficult to deal with crystal structures that have many atoms and low symmetries. Previous methods used for defect detection and classification were based on supervised learning, which requires human-labeled data. In this work, we develop an approach for defect detection with unsupervised machine learning based on a one-class support vector machine (OCSVM). We introduce two schemes of image segmentation and data preprocessing, both of which involve taking the Patterson function of each segment as inputs. We demonstrate that this method can be applied to various defects, such as point and line defects in 2D materials and twin boundaries in 3D nanocrystals.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Reduced models for ETG transport in the tokamak pedestal

This paper reports on the development of reduced models for electron temperature gradient (ETG) driven transport in the pedestal. Model development is enabled by a set of 61 nonlinear gyrokinetic simulations with input parameters taken from pedestals in a broad range of experimental scenarios. The simulation data have been consolidated in a new database for gyrokinetic simulation data, the multiscale gyrokinetic database (MGKDB), facilitating the analysis. The modeling approach may be considered a generalization of the standard quasilinear mixing length procedure. The parameter η, the ratio of the density to temperature gradient scale length, emerges as the key parameter for formulating an effective saturation rule. With a single order-unity fitting coefficient, the model achieves an error of 15%. A similar model for ETG particle flux is also described. We also present simple algebraic expressions for the transport informed by an algorithm for symbolic regression.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2026

Electron energy loss spectroscopy study of ceria sinters and nanoparticles irradiated with swift heavy ions

The electronic energy loss spectra of ceria (CeO 2 ) irradiated with swift heavy ions (27 MeV Xe and 946 MeV Au) in the electronic slowing down regime were measured for bulk sintered samples and nanoparticles by using a double Cs-corrected transmission electron microscope. The low-loss region as well as the core-loss region, including the oxygen K-edge and cerium M 4, 5 white lines, were recorded. No strong lattice disorder was found in the low-loss peaks for both types of samples showing the same bulk oxygen plasmon loss peak at about 15 eV. However, there is a clear evidence of cerium reduction to the trivalent oxidation state after irradiation for the sintered samples as shown by the K-edge shape of oxygen and decrease of the Ce M 4 /M 5 intensity ratio. A similar change of the M 4 /M 5 intensity ratio was observed for the irradiated nanoparticles with respect to the virgin sample owing to the high energy input inside the nanograin. The effect of radiation damage on electron energy loss spectroscopy data is analyzed for both types of samples and irradiation conditions.

Crystallographic defects↗
DOE OSTI2025

A Morphological Model to Separate Resolved–Unresolved Sources in the DESI Legacy Surveys: Application in the LS4 Alert Stream

Separating resolved and unresolved sources in large imaging surveys is a fundamental step to enable downstream science, such as searching for extragalactic transients in wide-field time-domain surveys. Here we present our method to effectively separate point sources from the resolved, extended sources in the Dark Energy Spectroscopic Instrument (DESI) Legacy Surveys (LS). We develop a supervised machine learning model based on the Gradient Boosting algorithm XGBoost. The features input to the model are purely morphological and are derived from the tabulated LS data products. We train the model using ∼2 × 10 5 LS sources in the COSMOS field with HST morphological labels and evaluate the model performance on LS sources with spectroscopic classification from the DESI Data Release 1 (∼2 × 10 7 objects) and the Sloan Digital Sky Survey Data Release 17 (∼3 × 10 6 objects), as well as on ∼2 × 10 8 Gaia stars. A significant fraction of LS sources are not observed in every LS filter, and we therefore build a “Hybrid” model as a linear combination of two XGBoost models, each containing features combining aperture flux measurements from the “blue” (gr) and “red” (iz) filters. The Hybrid model shows a reasonable balance between sensitivity and robustness, and achieves higher accuracy and flexibility compared to the LS morphological typing. With the Hybrid model, we provide classification scores for ∼3 × 10 9 LS sources, making this the largest ever machine learning catalog separating resolved and unresolved sources. The catalog has been incorporated into the real-time pipeline of the La Silla Schmidt Southern Survey (LS4), enabling the identification of extragalactic transients within the LS4 alert stream.

astrostatistics↗
DOE OSTI2022

AI for Experimental Controls at Jefferson Lab

We report the AI for Experimental Controls project is developing an AI system to control and calibrate detector systems located at Jefferson Laboratory. Currently, calibrations are performed offline and require significant time and attention from experts. This work would reduce the amount of data and the amount of time spent calibrating in an offline setting. The first use case involves the Central Drift Chamber (CDC) located inside the GlueX spectrometer in Hall D. We use a combination of environmental and experimental data, such as atmospheric pressure, gas temperature, and the flux of incident particles as inputs to a sequential Neural Network (NN) to recommend a high voltage setting and the corresponding calibration constants in order to maintain consistent gain and optimal resolution throughout the experiment. Utilizing AI in this manner represents an initial shift from offline calibration towards near real time calibrations performed at Jefferson Laboratory.

47 OTHER INSTRUMENTATION↗
DOE OSTI2021

Simultaneous measurement of organic scintillator response to carbon and proton recoils

Organic scintillators are widely used for neutron detection in both basic nuclear physics and applications. While the proton light yield of organic scintillators has been extensively studied, measurements of the light yield from neutron interactions with carbon nuclei are scarce. Demonstrate a new approach for the simultaneous measurement of the proton and carbon light yield of organic scintillators. Provide new carbon light yield data for the EJ-309 liquid and EJ-204 plastic organic scintillators. A 33-MeV 2 H + beam from the 88-Inch Cyclotron at Lawrence Berkeley National Laboratory was impinged upon a 3-mm-thick Be target to produce a high-flux, broad-spectrum neutron beam. The double time-of-flight technique was extended to simultaneously measure the proton and carbon light yields of the organic scintillators, wherein the light output associated with the recoil particle was determined using np and nC elastic scattering kinematics. The proton and carbon light yield relations of the EJ-309 liquid and EJ-204 plastic organic scintillators were measured over a recoil energy range of approximately 0.3 to 1 MeV and 2 to 5 MeV, respectively, for EJ-309, and 0.2 to 0.5 MeV and 1 to 4 MeV, respectively, for EJ-204. Furthermore, these data provide new insight into the ionization quenching effect in organic scintillators and key input for simulation of the response of organic scintillators for both basic science and a broad range of applications.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2022

Mirror nucleon removal reactions in p-shell nuclei

Nucleon removal reactions have been shown to be an effective tool for studying the single particle structure of nuclei. This work continues efforts to experimentally probe and benchmark the reaction and structure models used to calculate the removal reaction cross sections when using microscopic nuclear structure inputs. Here, three different single nucleon removal reactions were performed, from p -shell nuclei with masses A = 7, 9, and 10. The residual nuclei from the reactions were detected in coincidence with γ rays to determine partial cross sections to individual final states. The eikonal direct-reaction model is combined with overlap functions and residual nucleus densities from microscopic, variational Monte Carlo calculations to provide consistent nuclear structure input to the partial cross section calculations. Comparisons of measured and calculated cross sections, including for mirror reactions, are presented. The analysis of the partial cross sections leading to the ground states shows a similar behavior to the one observed from analyses of inclusive cross sections using shell model nuclear structure input: the theoretical description of the removal process is in better agreement with the data when removing weakly bound nucleons, than when removing well-bound ones. The two mirror reaction pairs presented here show consistent results between the respective members of the pairs. The results obtained for the population of the excited states, however, show a systematically different trend that appears connected to the structure part of the calculation. Additional cases are needed to better understand the respective roles of structure and dynamical effects in the deviations.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2023

TopFusion: Using Topological Feature Space for Fusion and Imputation in Multi-Modal Data

We present a novel multi-modal data fusion technique using topological features. The method, TopFusion, leverages the flexibility of topological data analysis tools (namely persistent homology and persistence images) to map multi-modal datasets into a common feature space by forming a new multi-channel persistence image. Each channel in the image is representative of a view of the data from a modality-dependent filtration. We demonstrate that the topological perspective we take allows for more effective data reconstruction, i.e. imputation. In particular, by performing imputation in topological feature space we are able to outperform the same imputation techniques applied to raw data or alternatively derived features. We show that TopFusion representations can be used as input to downstream deep learning-based computer vision models and doing so achieves comparable performance to other fusion methods for classification on two multi-modal datasets.

Myers, Audun D.↗
DOE OSTI2022

CONGO²: Scalable Online Anomaly Detection and Localization in Power Electronics Networks

Rapid and accurate detection and localization of electronic disturbances simultaneously are important for preventing its potential damages and determining potential remedies. Existing anomaly detection methods are severely limited by the low accuracy, the expensive computational cost and the need for highly trained personnel. There is an urgent need for a scalable online algorithm for in-field analysis of large-scale power electronics networks. Here in this paper, we propose a fast and accurate algorithm for anomaly detection and localization of power electronics networks: stratified colored-node graph (CONGO2). This algorithm hierarchically models the change of correlated waveforms and then correlated sensors using the colored-node graph. By aggregating the change of each sensor with its neighbors’ inputs, we can spontaneously identify and localize the anomaly that cannot be detected by data collected from a single sensor. As our proposed method only focuses on the changes within a short time frame, it is highly computational efficient and only needs small data storage. Thus, our method is ideal for online and reliable anomaly detection and localization of large-scale power electronic networks. Compared to existing anomaly detection methods, our method is entirely data-driven without training data, highly accurate and reliable for wide-spectrum anomalies detection, and more importantly, capable of both detection and localization. Thus, it is ideal for infield deployment for large-scale power electronic networks. As illustrated by a distributed energy resources (DERs) power grid with 37-node, our method can effectively detect and localize various cyber and physical attacks.

42 ENGINEERING↗
DOE OSTI2022

Data-Driven Dynamic Modeling in Power Systems: A Fresh Look on Inverter-Based Resource Modeling

Here, this article introduces ways to identify dynamic system models using measurement data. In power system analysis, a static model represents the time-invariant input-output relationship of a system, while a dynamic model describes the behavior of the system over time. For example, how will a system transit from one steady-state operation point to another?

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2020

Data-driven predictive probability density function control of fiber length stochastic distribution shaping in refining process

Pulp is the most important raw material in paper in paper industries, whose Fiber Length Stochastic Distribution (FLSD) shaping directly determines the energy consumption and paper quality of the subsequent papermaking processes. However, the mean and variance are insufficient to describe the output FLSD shaping, which display non-Gaussian distribution properties. Therefore, the traditional control, method based on the mean and variance of fiber length is difficult to control the FLSD shaping effectively. In this paper, a novel data-driven predictive probability density function (PDF) control method is proposed for output FLSD shaping in refining process. Primarily, in order to improve the approximation accuracy of the PDF employing RBF neural network, the parameters (center value and width) of each RBF basis functions are tuned via utilizing iterative learning control (ILC) law, and the corresponding estimations of weights law can be obtained. Secondly, considering that the conventional linear model of weights vector has drawbacks of low accuracy and weak generalization ability, random vector functional link networks (RVFLNs) based data driven nonlinear modelling method is employed to characterize the prediction model between the input variables and weights vector. Finally, in order to reduce the randomness of the output FLSD, a minimum entropy control method under mean constraint is employed to design the predictive PDF controller for the output FLSD shaping with the help of the established nonlinear stochastic distribution model. Both simulations and experiments are given to illustrate the effectiveness and practicability of the proposed method.

Probability debsity function, Fiber length distrib↗
DOE OSTI2023

BOOTS: Bayesian Optimization for Optimal Test Selection

BOOTS is a package for optimal selection of candidate operating points in large-scale manufacturing applications. It is designed to optimally select operating points to maximize predicted values of product quality and resource efficiency according to a data-driven model. The package is based on the use of a multi-input multi-output (MIMO) Gaussian process model to describe the relationships between inputs (operating points) and outputs (product quality and resource efficiency). This package does not provide any site- or process-specific information.

Villez, Kris [Oak Ridge National Laboratory (ORNL)↗
DOE OSTI2023

Parameter Identification for Battery Abuse Reaction Kinetics Models Using DSC Analysis [SWR-23-87]

This code estimates the parameters as inputs for NREL’s abuse reaction kinetics model using Differential scanning calorimetry (DSC) experimental data. The parameters for calculating the rates of abuse reactions among battery cell components at elevated temperatures include frequency factor, activation energy, and reaction orders. The least-squared method is employed to fit the reaction model to DSC data. The code is implemented in MATLAB.

Yang, Chuanbo↗