Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Performance Modeling”

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 523 records · Page 29
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Waveform processing using neural network algorithms on the front-end electronics

In a multi-channel radiation detector readout system, waveform sampling, digitization, and raw data transmission to the data acquisition system constitute a conventional processing chain. The deposited energy on the sensor is estimated by extracting peak amplitudes, area under pulse envelopes from the raw data, and starting times of signals or time of arrivals. However, such quantities can be estimated using machine learning algorithms on the front-end Application-Specific Integrated Circuits (ASICs), often termed as “edge computing”. Edge computation offers enormous benefits, especially when the analytical forms are not fully known or the registered waveform suffers from noise and imperfections of practical implementations. In this work, we aim to predict peak amplitude from a single waveform snippet whose rising and falling edges containing only 3 to 4 samples. We thoroughly studied two well-accepted neural network algorithms, Multi-Layer Perceptron (MLP) and Convolutional Neural Network (CNN) by varying their model sizes. Further, to better fit front-end electronics, neural network model reduction techniques, such as network pruning methods and variable-bit quantization approaches, were also studied. By combining pruning and quantization, our best performing model has the size of 1.5 KB, reduced from 16.6 KB of its full model counterpart. It can reach mean absolute error of 0.034 comparing to that of a naive baseline of 0.135. Such parameter-efficient and predictive neural network models established feasibility and practicality of their deployment on front-end ASICs.

47 OTHER INSTRUMENTATION↗
DOE OSTI2025

Data imbalance in drug response prediction: multi-objective optimization approach in deep learning setting

Abstract Drug response prediction (DRP) methods tackle the complex task of associating the effectiveness of small molecules with the specific genetic makeup of the patient. Anti-cancer DRP is a particularly challenging task requiring costly experiments as underlying pathogenic mechanisms are broad and associated with multiple genomic pathways. The scientific community has exerted significant efforts to generate public drug screening datasets, giving a path to various machine learning models that attempt to reason over complex data space of small compounds and biological characteristics of tumors. However, the data depth is still lacking compared to application domains like computer vision or natural language processing domains, limiting current learning capabilities. To combat this issue and improves the generalizability of the DRP models, we are exploring strategies that explicitly address the imbalance in the DRP datasets. We reframe the problem as a multi-objective optimization across multiple drugs to maximize deep learning model performance. We implement this approach by constructing Multi-Objective Optimization Regularized by Loss Entropy loss function and plugging it into a Deep Learning model. We demonstrate the utility of proposed drug discovery methods and make suggestions for further potential application of the work to achieve desirable outcomes in the healthcare field.

Biochemistry & Molecular Biology↗
DOE OSTI2020

NEON AOP foliar trait maps, maps of model uncertainty estimates, and conifer map, East River, CO 2018

This data package contains mapped trait estimates and their uncertainties, and conifer map, for the National Ecological Observatory Network's Airborne Observation Platform survey data acquired over the Upper East River, Colorado in 2018. For full details, please see associated reference. in brief, trait models were developed independently for needle and non-needle leaf species using partial least squares regression (PLSR) using ground data from additional datasets: doi:10.15485/1618130, doi:10.15485/1618132, and doi:10.15485/1631278, merged with extracted spectral data from doi:10.15485/1618131. We separated vegetated pixels into needle and non-needle classes in order to generate a classification map based on the spectral differences between these leaf types (conifer.tif). We trained a deep learning model with custom architecture, detailed in Chadwick et al. In Press. The model performed with 0.998 true positive rate and 0.982 true negative rate, with ‘positives’ being non-needle identification. We then utilized PLSR to generate models of foliar traits for each leaf type. So that we could also map uncertainty in these predictions, we generated ten different models for needle and non-needle leaf species using different testing holdout sets of discrete sites. Each of these models was developed with a 100-fold cross validation procedure that utilized a 70% training set and 30% validation set with each fold, and then assessed based on the 10% of testing sites that were not included in that model’s development. The mean predicted value across the 10 models is used for the trait estimate in each pixel across the study area. The models are applied according to the leaf type designation in the conifer.tif map. The errors are the standard deviation across the 10 different models developed, with high error suggesting instability in model prediction and areas where values may not be reliable for ecological inference. These maps are only applied to areas with a NDVI > 0.5 to exclude non-vegetated areas. Shade masks could be applied to these data (doi:10.15485/1618131), but have not been for this data package. These data are also available on Google Earth Engine: https://code.earthengine.google.com/?asset=users/kdc/ER_NEON

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Semi-supervised permutation invariant particle-level anomaly detection

The development of analysis methods to distinguish potential beyond the Standard Model phenomena in a model-agnostic way can significantly enhance the discovery reach in collider experiments. However, the typical machine learning (ML) algorithms employed for this task require fixed length and ordered inputs that break the natural permutation invariance in collision events. To address this, a semi-supervised anomaly detection tool is presented that takes a variable number of particle-level inputs and leverages a signal model to encode this information into a permutation invariant, event-level representation via supervised training with a Particle Flow Network (PFN). Data events are then encoded into this representation and given as input to an autoencoder for unsupervised ANomaly deTEction on particLe flOw latent sPacE (ANTELOPE), classifying anomalous events based on a low-level and permutation invariant input modeling. Performance of the ANTELOPE architecture is evaluated on simulated samples of hadronic processes in a high energy collider experiment, showing good capability to distinguish disparate models of new physics.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

Multi-module-based CVAE to predict HVCM faults in the SNS accelerator

We present a multi-module framework based on Conditional Variational Autoencoder (CVAE) to detect anomalies in the power signals coming from multiple High Voltage Converter Modulators (HVCMs). We condition the model with the specific modulator type to capture different representations of the $\mathcal{normal}$ waveforms and to improve the sensitivity of the model to identify a specific type of fault when we have limited samples for a given module type. We studied several Artificial Neural Network (ANN) architectures for our CVAE model and evaluated the model performance by looking at their loss landscape for stability and generalization. Our results for the Spallation Neutron Source (SNS) experimental data show that the trained model generalizes well to detecting multiple fault types for several HVCM module types. The results of this study can be used to improve the HVCM reliability and overall SNS uptime.

43 PARTICLE ACCELERATORS↗
DOE OSTI2024

Merged Observatory Data Files (MODFs): an integrated observational data product supporting process-oriented investigations and diagnostics

A large and ever-growing body of geophysical information is measured in campaigns and at specialized observatories as a part of scientific expeditions and experiments. These collections of observed data include many essential climate variables (as defined by the Global Climate Observing System) but are often distinguished by a wide range of additional non-routine measurements that are designed to not only document the state of the environment but also the drivers that contribute to that state. These field data are used not only to further understand environmental processes through observation-based studies but also to provide baseline data to test model performance and to codify understanding to improve predictive capabilities. To address the considerable barriers and difficulty in utilizing these diverse and complex data for observation–model research, the Merged Observatory Data File (MODF) concept has been developed. A MODF combines measurements from multiple instruments into a single file that complies with well-established data format and metadata practices and has been designed to parallel the development of corresponding Merged Model Data Files (MMDFs). Using the MODF and MMDF protocols will facilitate the evolution of model intercomparison projects into model intercomparison and improvement projects by putting observation and model data “on the same page” in a timely manner. The MODF concept was developed especially for weather forecast model studies in the Arctic. The surprisingly complex process of implementing MODFs in that context refined the concept itself. Thus, this article explains the concept of MODFs by providing details on the issues that were revealed and resolved during that first specific implementation. Detailed instructions are provided on how to make MODFs, and this article can be considered a MODF creation manual.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Assessing time-dependent temperature profile predictions using reduced transport models for high performing NSTX plasmas

Time-dependent, predictive simulations were performed with the 1.5D tokamak integrated modeling code TRANSP on a large set of well-analyzed, high performing discharges from the National Spherical Torus Experiment (NSTX) in order to evaluate how well modern reduced transport models can reproduce experimentally observed temperature profiles in spherical tokamaks. Overall, it is found that simulations using the Multi-Mode Model (MMM) more consistently agree with the NSTX observations than those using the Trapped Gyro-Landau Fluid (TGLF) model, despite TGLF requiring orders of magnitude greater computational cost. When considering all examined discharges, MMM has median overpredictions of electron temperature (T e ) and ion temperature (T i ) profiles of 28% and 27%, respectively, relative to the experiment. TGLF overpredicts T e by 46%, with much larger variance than MMM, and underpredicts T i by 25%. As the ratio of kinetic to magnetic field pressure (β) is increased across NSTX discharges, TGLF predicts lower T e and significant flattening of the T i profile, conflicting with NSTX observations. When using an electrostatic version of TGLF, both T e and T i are substantially overpredicted, underscoring the importance of electromagnetic turbulence in the high β spherical tokamak regime. Additionally, calculations with neural net surrogate models for TGLF were performed outside of TRANSP with a time slice flux matching transport solver, finding better agreement with experiment than the TRANSP simulations, highlighting the impact of different transport solvers and simulation techniques. Furthermore, the reasonable agreement with experiment of temperature profiles predicted by MMM motivates a more detailed examination of the sensitivities of the TRANSP simulations with MMM to different NSTX plasma regimes in a companion paper (Lestz et al Plasma Phys. Control. Fusion 67 105030), in preparation for self-consistent, time-dependent predictive modeling of NSTX-U scenarios.

Lestz, J. B. [General Atomics, San Diego, CA (Unit↗
DOE OSTI2023

Combining multitask and transfer learning with deep Gaussian processes for autotuning-based performance engineering

We combine deep Gaussian processes (DGPs) with multitask and transfer learning for the performance modeling and optimization of HPC applications. Deep Gaussian processes merge the uncertainty quantification advantage of Gaussian processes (GPs) with the predictive power of deep learning. Multitask and transfer learning allow for improved learning efficiency when several similar tasks are to be learned simultaneously and when previous learned models are sought to help in the learning of new tasks, respectively. A comparison with state-of-the-art autotuners shows the advantage of our approach on two application problems. In this article, we combine DGPs with multitask and transfer learning to allow for both an improved tuning of an application parameters on problems of interest but also the prediction of parameters on any potential problem the application might encounter.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Large-scale scenarios of electric vehicle charging with a data-driven model of control

Transportation electrification is forecast to bring millions of new electric vehicles to roads worldwide this decade. Planning to support those vehicles depends on detailed scenarios of their electricity demand in both uncontrolled and controlled or smart charging scenarios. In this work, we present a novel modeling approach to enable rapid generation of demand estimates that represent the impact of controlled charging for large-scale scenarios with millions of individual drivers. To model the effect of load modulation control on aggregate charging profiles, we propose a novel machine learning approach that replaces traditional optimization approaches. We demonstrate its performance modeling workplace charging control under a range of electricity rate schedules, achieving small errors (2.5%–4.5%) while accelerating computations by more than 4000 times. To generate the uncontrolled charging demand for scenarios with residential, workplace, and public charging we use statistical representations of a large data set of real charging sessions. We demonstrate the methodology by generating diverse sets of scenarios for California's charging demand in 2030 which consider multiple charging segments and controls, each run locally in under 50 s. We further demonstrate support for rate design by modeling the large-scale impact of a new, custom rate schedule for workplace charging.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2021

Material Interactions in Severe Accidents – Benchmarking the MELCOR V2.2 Eutectics Model for a BWR-3 MARK-I Station Blackout: Part I – Single Case Analysis

Here in this analysis, the two material interaction models available in the MELCOR code are benchmarked for a severe accident at a BWR under representative Fukushima Daiichi boundary conditions. This part of the benchmark investigates the impact of each material interaction model on accident progression through a detailed single case analysis. It is found that the eutectics model simulation exhibits more rapid accident progression for the duration of the accident. The slower accident progression exhibited by the interactive materials model simulation, however, allows for a greater degree of core material oxidation and hydrogen generation to occur, as well as elevated core temperatures during the ex-vessel accident phase. The eutectics model simulation exhibits more significant degradation of core components during the late in-vessel accident phase – more debris forms and relocates to the lower plenum before lower head failure. The larger debris bed observed in the eutectics model simulation also reaches higher temperatures, presenting a more significant thermal challenge to the lower head until its failure. At the end of the simulated accident scenario, however, core damage is comparable between both simulations due to significant core degradation that occurs during the ex-vessel phase in the interactive materials model simulation. A key difference between the two models’ performance is the maximum temperatures that can be reached in the core and therefore the maximum ΔT between any two components. When implementing the interactive materials model, users have the option to modify the liquefaction temperature of the ZrO 2 -interactive and UO 2 -interactive materials as a way to mimic early fuel rod failure due to material interactions. Through modification of the liquefaction of high melting point materials with significant mass, users may inadvertently limit maximum core temperatures for fuel, cladding, and debris components.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2020

Mitigation of Motor Stalling and FIDVR via Energy Storage Systems with Temporal Logic Specifications

The fault-induced delayed voltage recovery (FIDVR) phenomenon has been very common from the distribution system through the transmission system. It causes a delay on recovering significantly depressed local voltage after the fault is cleared, and it can also lead to more widespread cascading system failures. Mitigating this event with current control approaches is challenging and becoming a crucial issue. Here, a model predictive control-based strategy employing signal temporal logic specifications is proposed to help mitigate FIDVR. To this end, it investigates and extends a dynamic performance model allowing analytic insights into the system-wide impact of motor stalling and FIDVR. The proposed controller provides richer descriptions of voltage specifications addressing both magnitude and time simultaneously. We consider different control specifications with reactive power support from energy storage systems to prevent the voltage during/after the fault from dropping too low, and reduce the delay time of voltage recovery. The simulation results conducted with the IEEE 57 bus test network validate the proposed method and demonstrate the effectiveness of the mitigation strategy on FIDVR.

25 ENERGY STORAGE↗
DOE OSTI2022

A Spatiotemporal-Aware Weighting Scheme for Improving Climate Model Ensemble Predictions

Multimodel ensembling has been widely used to improve climate model predictions, and the improvement strongly depends on the ensembling scheme. In this work, we propose a Bayesian neural network (BNN) ensembling method, which combines climate models within a Bayesian model averaging framework, to improve the predictive capability of model ensembles. Our proposed BNN approach calculates spatiotemporally varying model weights and biases by leveraging individual models' simulation skill, calibrates the ensemble prediction against observations by considering observation data uncertainty, and quantifies epistemic uncertainty when extrapolating to new conditions. More importantly, the BNN method provides interpretability about which climate model contributes more to the ensemble prediction at which locations and times. Thus, beyond its predictive capability, the method also brings insights and understanding of the models to guide further model and data development. In this study, we design experiments using an ensemble of CMIP6 climate model simulations to illustrate the BNN ensembling method's capability with respect to prediction accuracy, interpretability, and uncertainty quantification (UQ). We demonstrate that BNN can correctly assign larger weights to the regions and seasons where the individual model fits the observation better. Moreover, its offered interpretability is consistent with our understanding of localized climate model performance. Additionally, BNN shows an increasing uncertainty when the prediction is farther away from the period with constrained data, which appropriately reflects our trustworthiness of the models in the changing climate.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Land Model Testbed: Accelerating Development, Benchmarking and Analysis of Land Surface Models

A Land Model Testbed (LMT), designed to provide a computational framework for systematically assessing model fidelity and supporting rapid development of complex multiscale models, offers a general-purpose workflow for conducting large ensemble simulations of multiple land surface models, post-processing large volumes of model output, and evaluating model results. It leverages existing tools for launching model simulations and the International Land Model Benchmarking (ILAMB) package for assessing model fidelity through comparison with best-available observational datasets. Increased complexity and proliferation of uncertain parameters in process representations in land surface models has driven the need for frequent and intensive testing and evaluating of models to quantify uncertainties and optimize parameters such that results are consistent with observations. The LMT described here meets these needs by providing tools to run thousands of ensemble simulations simultaneously and post-process their output files, by automating execution of an enhanced version of ILAMB with site-specific benchmarks and multivariate functional relationships, and by offering ensemble diagnostics and a customizable dashboard for displaying model performance metrics and associated graphics. We envision the LMT capabilities will serve as a foundational computational resource for a proposed user facility focused on terrestrial multiscale model--data integration.

Sreepathi, Sarat↗
DOE OSTI2023

AGR-5/6/7 Irradiation Disassembly and Metrology First Look

The Advanced Gas Reactor (AGR) Fuel Development and Qualification Program was established to perform research and development on tristructural isotropic (TRISO)-coated particle fuel to support deployment of high-temperature gas-cooled reactors (HTGRs), which are graphite-moderated nuclear reactors cooled with helium. This work continues as part of the Advanced Reactor Technologies (ART) TRISO Fuel Program. The overarching program goal is to provide a baseline fuel qualification data set to support licensing, deployment, and operation of HTGRs in the United States. To achieve these goals, the program includes fuel fabrication, irradiations of TRISO fuels and high-temperature materials (e.g., graphite), safety testing and post-irradiation examination (PIE), fuel performance modeling, and fission product transport and source term determination. The ART AGR program has conducted four distinct fuel irradiation experiments in the Advanced Test Reactor (ATR) at Idaho National Laboratory (INL). The first of these irradiation tests, designated AGR-1, began in ATR in December of 2006 and ended in November 2009. This experiment was primarily to act as a shakedown test of the multi-capsule test train design and to provide early data on fuel performance that would be used in fuel fabrication process development. AGR-1 fuel kernels were produced on an engineering scale, but the TRISO coatings and cylindrical fuel compacts were fabricated on a laboratory scale. The AGR-1 PIE was completed and the final report was published in 2015. The second irradiation test, AGR-2, started in ATR in June 2010 and ended in October 2013. The AGR-2 irradiation test was designed to provide fuel performance data for coated particles fabricated on an engineering-scale pilot line using a coater with an internal chamber diameter of 150 mm (6 in.). The final PIE report was published in 2021. AGR-3/4, a single irradiation that combined what were originally conceived as the third and fourth tests, was to support the refinement of fission product transport models and to assess the effects of sweep gas impurities on fuel performance and fission product transport. PIE of the AGR-3/4 experiment is still in progress as of this writing. The subject of this report is AGR-5/6/7, the final qualification test of AGR TRISO fuel made entirely at the engineering scale.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2023

Evaluating wind profiles in a numerical weather prediction model with Doppler lidar

We use Doppler lidar wind profiles from six locations around the globe to evaluate the wind profile forecasts in the boundary layer generated by the operational global Integrated Forecast System (IFS) from the European Centre for Medium-range Weather Forecasts (ECMWF). The six locations selected cover a variety of surfaces with different characteristics (rural, marine, mountainous urban, and coastal urban). We first validated the Doppler lidar observations at four locations by comparison with co-located radiosonde profiles to ensure that the Doppler lidar observations were of sufficient quality. The two observation types agree well, with the mean absolute error (MAE) in wind speed almost always less than 1 m s –1 . Large deviations in the wind direction were usually only seen for low wind speeds and are due to the wind direction uncertainty increasing rapidly as the wind speed tends to zero. Time–height composites of the wind evaluation with 1 h resolution were generated, and evaluation of the model winds showed that the IFS model performs best over marine and coastal locations, where the mean absolute wind vector error was usually less than 3 m s –1 at all heights within the boundary layer. Larger errors were seen in locations where the surface was more complex, especially in the wind direction. For example, in Granada, which is near a high mountain range, the IFS model failed to capture a commonly occurring mountain breeze, which is highly dependent on the sub-grid-size terrain features that are not resolved by the model. The uncertainty in the wind forecasts increased with forecast lead time, but no increase in the bias was seen. At one location, we conditionally performed the wind evaluation based on the presence or absence of a low-level jet diagnosed from the Doppler lidar observations. The model was able to reproduce the presence of the low-level jet, but the wind speed maximum was about 2 m s –1 lower than observed. This is attributed to the effective vertical resolution of the model being too coarse to create the strong gradients in wind speed observed. Our results show that Doppler lidar is a suitable instrument for evaluating the boundary layer wind profiles in atmospheric models.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Movement Models to Predict Low‐Altitude Flight of Soaring Birds Using Look‐Ahead Environmental Factors

Advances in fine-scale movement modeling of soaring birds can aid efforts to understand and resolve the impacts of anthropogenic activities on such birds. Soaring birds often rely on underlying terrain and low-altitude updrafts to govern their flights at rotor-swept altitudes (≤ 200 m above ground level), which puts them at risk of collision with wind turbines. We developed a data-driven Markov model at 1-s resolution that predicts the fine-scale flight behavior of golden eagles (Aquila chrysaetos) as a function of ecological covariates at the current location as well as those within an eagle's line of sight. We only considered ecological covariates that are readily available in real-time (ground elevation and wind conditions). Latent factors (age, sex, species, behavioral intent, migratory status) were intentionally left out of the model. We calibrated the model using golden eagle telemetry data collected in two different ecoregions of the United States. Given a starting location, the calibrated model simulates multiple stochastic 3D paths to produce a time-explicit and spatially explicit risk map of turbine collisions. We discovered an empirical relation between the rate of change of heading and the orographic updraft conditions within an eagle's line of sight. Our model performed most effectively when predicting predominantly-soaring flights at rotor-swept altitudes during wind conditions in which turbines are likely to be operational. The calibrated model could be used in concert with automated eagle detection and turbine curtailment technologies. Specifically, once an eagle is detected by those systems, our model could then provide accurate predictions of turbines the eagle is likely to interact with in the near term.

17 WIND ENERGY↗
DOE OSTI2025

Generalizable Image Segmentation for Microstructure Characterization Through Integrated SEM and EBSD Analysis

We demonstrate generalizable semantic segmentation using minimal ground truth data. Correlated scanning electron microscopy (SEM) images and electron backscatter diffraction (EBSD) measurements of frictionstir processed 316L stainless steel plates were used to train deep learning models for grain boundary segmentation. Secondary electron (SE) imaging taken at an accelerating voltage of 10 keV correlated to EBSD-derived grain boundaries produced the best performing model. Notably, an ensemble of three models trained on a single SE image produced accurate segmentation over a series of BSE images of samples manufactured under different processing parameters, with a resultant mean absolute error in grain size of 0.34 µm. The striking generalizability of the models likely results from the similar escape depths of the SE training input and the EBSD training output and the reduced probability of dislocation artifacts appearing in the image. This finding highlights the importance of considering the physical principles behind imaging in the development of robust segmentation models for microstructure characterization.

Taufique, Mohammad Fuad Nur↗
DOE OSTI2020

Interactive Visual Study of Multiple Attributes Learning Model of X-Ray Scattering Images

Existing interactive visualization tools for deep learning are mostly applied to the training, debugging, and refinement of neural network models working on natural images. However, visual analytics tools are lacking for the specific application of x-ray image classification with multiple structural attributes. In this paper, we present an interactive system for domain scientists to visually study the multiple attributes learning models applied to x-ray scattering images. It allows domain scientists to interactively explore this important type of scientific images in embedded spaces that are defined on the model prediction output, the actual labels, and the discovered feature space of neural networks. Users are allowed to flexibly select instance images, their clusters, and compare them regarding the specified visual representation of attributes. The exploration is guided by the manifestation of model performance related to mutual relationships among attributes, which often affect the learning accuracy and effectiveness. The system thus supports domain scientists to improve the training dataset and model, find questionable attributes labels, and identify outlier images or spurious data clusters. Case studies and scientists feedback demonstrate its functionalities and usefulness.

97 MATHEMATICS AND COMPUTING↗