Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “statistical learning”

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 811 records · Page 45
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Computing Nonlinear Power Spectra Across Dynamical Dark Energy Model Space with Neural ODEs

I show how to compute the nonlinear power spectrum across the entire $w(z)$ dynamical dark energy model space. Using synthetic ΛCDM data, I train a neural ordinary differential equation (ODE) to infer the evolution of the nonlinear matter power spectrum as a function of the background expansion and mean matter density across ∼9 Gyr of cosmic evolution. After training, the model generalises to any dynamical dark energy model parameterised by $w(z)$. With little optimisation, the neural ODE is accurate to within 4% up to $k = 5\, h\, {\mathrm Mpc}^{−1}$. Unlike simulation rescaling methods, neural ODEs naturally extend to summary statistics beyond the power spectrum that are sensitive to the growth history.

cosmology↗
DOE OSTI2022

A Topological Approach for Motion Track Discrimination

Detecting small targets at range is difficult because there is not enough spatial information present in an image sub-region containing the target to use correlation-based methods to differentiate it from dynamic confusers present in the scene. Moreover, this lack of spatial information also disqualifies the use of most state-of-the-art deep learning image-based classifiers. Here, we use characteristics of target tracks extracted from video sequences as data from which to derive distinguishing topological features that help robustly differentiate targets of interest from confusers. In particular, we calculate persistent homology from time-delayed embeddings of dynamic statistics calculated from motion tracks extracted from a wide field-of-view video stream. In short, we use topological methods to extract features related to target motion dynamics that are useful for classification and disambiguation and show that small targets can be detected at range with high probability.

Emerson, Tegan H.↗
DOE OSTI2026

Short-term electricity load forecasting: Application-driven evaluation of machine learning models across spatial and temporal scales

As we transition towards a decarbonized economy, the integration of variable renewable energy resources and new demands (e.g., electric vehicles, heat pumps) into the electricity grid places unprecedented pressure on grid operators to effectively anticipate and manage peak load. In this context, machine learning algorithms are proving to be indispensable for accurate short-term load forecasting, a crucial task to address these challenges. This study benchmarks 6 machine learning algorithms, including three neural networks and three tree-based algorithms, across various levels of spatial aggregation and time horizons (1, 4, 8, 24, and 48 h). The central contribution of this work is the comparison and analysis of load forecasting models not only based on statistical metrics, but also based on a novel error metric, which evaluates the cost implications of forecast errors for power system stakeholders. Results show that tree-based models outperform neural networks, based on statistical metrics, and yield less skewed error distributions for most spatial scales. However, through the lens of the novel error metric, neural networks are the more competitive choice, especially for forecast horizons that exceed 8 h. The study concludes with actionable recommendations to grid operators and highlights the need for the development of error metrics that link forecasting accuracy to operational costs. To promote transparency and open science, the datasets and Python code are open-sourced via a supplementary repository.

Houben, Nikolaus↗
DOE OSTI2026

RU-net for automatic characterization of TRISO fuel cross sections

During irradiation, phenomena such as kernel swelling and buffer densification may impact the performance of tristructural isotropic (TRISO) particle fuel. Post-irradiation microscopy is often used to identify these irradiation-induced morphologic changes. However, each fuel compact generally contains thousands of TRISO particles. Manually performing the work to get statistical information on these phenomena is cumbersome and subjective. Here, to reduce the subjectivity inherent in that process and to accelerate data analysis, we used convolutional neural networks (CNNs) to automatically segment cross-sectional images of microscopic TRISO layers. CNNs are a class of machine-learning algorithms specifically designed for processing structured grid data. They have gained popularity in recent years due to their remarkable performance in various computer vision tasks, including image classification, object detection, and image segmentation. In this research, we generated a large irradiated TRISO layer dataset with more than 2,000 microscopic images of cross-sectional TRISO particles and the corresponding annotated images. Based on these annotated images, we used different CNNs to automatically segment different TRISO layers. These CNNs include RU-Net (developed in this study), as well as three existing architectures: U-Net, Residual Network (ResNet), and Attention U-Net. The preliminary results show that the model based on RU-Net performs best in terms of Intersection over Union (IoU). Using CNN models, we can expedite the analysis of TRISO particle cross sections, significantly reducing the manual labor involved and improving the objectivity of the segmentation results.

11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2024

DiffESM: Conditional Emulation of Temperature and Precipitation in Earth System Models With 3D Diffusion Models

Earth system models (ESMs) are essential for understanding the interaction between human activities and the Earth's climate. However, the computational demands of ESMs often limit the number of simulations that can be run, hindering the robust analysis of risks associated with extreme weather events. While low-cost climate emulators have emerged as an alternative to emulate ESMs and enable rapid analysis of future climate, many of these emulators only provide output on at most a monthly frequency. This temporal resolution is insufficient for analyzing events that require daily characterization, such as heat waves or heavy precipitation. We propose using diffusion models, a class of generative deep learning models, to effectively downscale ESM output from a monthly to a daily frequency. Trained on a handful of ESM realizations, reflecting a wide range of radiative forcings, our DiffESM model takes monthly mean precipitation or temperature as input, and is capable of producing daily values with statistical characteristics close to ESM output. Combined with a low-cost emulator providing monthly means, this approach requires only a small fraction of the computational resources needed to run a large ensemble. We evaluate model behavior using a number of extreme metrics, showing that DiffESM closely matches the spatio-temporal behavior of the ESM output it emulates in terms of the frequency and spatial characteristics of phenomena such as heat waves, dry spells, or rainfall intensity.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Genetic programming for interpretable, data-driven continuum damage models.

The damage mechanisms that lead to failure in engineering alloys have been studied extensively, but converting this knowledge into constitutive models that are suitable for engineering-scale analysis remains a challenge. Evolution laws for continuum damage have been developed in the past and have proven effective but suffer from many non-physical assumptions that inhibit the overall accuracy of the model. Further, the assumptions inherent in these existing models prevent them from being applicable to a broad class of materials. At the same time, computational models of fine-scale damage mechanisms continue to advance making it tractable to generate large training data sets through computer simulation. Data-driven machine learning approaches can leverage these data sets to avoid making limiting assumptions, and instead produce models directly from the results of microstructural simulations and/or experiments. Many of these machine learning approaches are rapid and accurate, but they offer little to no insight into the underlying relationships among state variables being discovered. Conversely, genetic programming symbolic regression (GPSR) is a machine learning method that produces analytic expressions relating the state variables, allowing maximal insight and interpretability. To that end, we propose using GPSR as a data-driven method of obtaining microstructurally informed continuum damage models. Data is generated using microstructural simulations of damage evolution, parameterized over microstructural statistics (i.e., pore shape) and nominally applied deformations. Analytic expressions for damage evolution are obtained from the data using GPSR, and these expressions are then utilized within a continuum constitutive model. Overall, this approach is a promising method of automatically obtaining analytic relations describing constitutive phenomena in a material.

Buche, Michael Robert↗
DOE OSTI2022

Neural-network learning of SPOD latent dynamics

Here, we aim to reconstruct the latent space dynamics of high dimensional, quasi-stationary systems using model order reduction via the spectral proper orthogonal decomposition (SPOD). The proposed method is based on three fundamental steps: in the first, once that the mean flow field has been subtracted from the realizations (also referred to as snapshots), we compress the data from a high-dimensional representation to a lower dimensional one by constructing the SPOD latent space; in the second, we build the time-dependent coefficients by projecting the snapshots containing the fluctuations onto the SPOD basis and we learn their evolution in time with the aid of recurrent neural networks; in the third, we reconstruct the high-dimensional data from the learnt lower -dimensional representation. The proposed method is demonstrated on two different test cases, namely, a compressible jet flow, and a geophysical problem known as the Madden-Julian Oscillation. An extensive comparison between SPOD and the equivalent POD-based counterpart is provided and differences between the two approaches are highlighted. The numerical results suggest that the proposed model is able to provide low rank predictions of complex statistically stationary data and to provide insights into the evolution of phenomena characterized by specific range of frequencies. The comparison between POD and SPOD surrogate strategies highlights the need for further work on the characterization of the interplay of error between data reduction techniques and neural network forecasts.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Generic and ML Workloads in an HPC Datacenter: Node Energy, Job Failures, and Node-Job Analysis

HPC datacenters offer a backbone to the modern digital society. Increasingly, they run Machine Learning (ML) jobs next to generic, compute-intensive workloads, supporting science, business, and other decision-making processes. However, understanding how ML jobs impact the operation of HPC datacenters, relative to generic jobs, remains desirable but understudied. In this work, we leverage long-term operational data, collected from a national-scale production HPC datacenter, and statistically compare how ML and generic jobs can impact the performance, failures, resource utilization, and energy consumption of HPC datacenters. Our study provides key insights, e.g., ML-related power usage causes GPU nodes to run into temperature limitations, median/mean runtime and failure rates are higher for ML jobs than for generic jobs, both ML and generic jobs exhibit highly variable arrival processes and resource demands, significant amounts of energy are spent on unsuccessfully terminating jobs, and concurrent jobs tend to terminate in the same state. We open-source our cleaned-up data traces on Zenodo (https://doi. org/10.5281/zenodo.13685426), and provide our analysis toolkit as software hosted on GitHub (https://github.com/atlarge-research/2024-icpads-hpc-workload-characterization). This study offers multiple benefits for data center administrators, who can improve operational efficiency, and for researchers, who can further improve system designs, scheduling techniques, etc.

crossanalysis↗
DOE OSTI2022

Evaluation of artificial neural network performance for classification of potato plants infected with potato virus Y using spectral data on multiple varieties and genotypes

Potato virus Y (Potyviridae, PVY) is a plant virus that poses a significant threat to potato producers on a global basis. The pathogen has disrupted seed potato supplies and negatively impacted yield and quality of commercial potato crops. The potato industry currently manages PVY infection levels via insecticide applications, regional seed certification programs that rely on field scouting to visually assess individual plants for infection status, and destructive and costly tissue sampling coupled with laboratory assays. Despite these efforts, PVY continues to confound potato industry stakeholders resulting in economic harm. Remote sensing and machine learning provide for the development of new tools to more accurately detect and spatially quantify PVY-infected plants versus the current state of the art. However, there is a need to understand how the occurrence of many different potato varieties impact the dynamics of developing models to detect potato plants impacted with PVY and their potential effectiveness. This study evaluates classification modelling outcomes using spectral datasets collected in different temporal and spatial environments (greenhouse and a production field) on multiple potato varieties consisting of labelled instances of plants infected with PVY and those not infected with the virus. A modelling framework was developed to support iterative modelling runs using artificial neural network (ANN) architectures configured as binary classifiers to develop sample populations to support statistical analysis on model performance using specific spectral subsets. When using spectral data to detect PVY-infected plants, ANN models achieved the highest mean accuracy of 0.894 on a single variety. Conversely, the same ANN model architecture only achieved a mean accuracy of 0.575 on a spectral data set representing 29 potato breeding lines. Additionally, statistical analysis indicates spectral regions including the red edge, near infrared and shortwave infrared contain more important spectral features for the ANN classifier introduced in this research.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2021

Lessons Learned in Employing Data Analytics to Predict Oxidation Kinetics and Spallation Behavior of High-Temperature NiCr-Based Alloys

Machine learning (ML) can offer many advantages in predicting material properties over traditional materials development methods based solely on limited experimental investigations or physical-based simulations with the capability to reduce development cost, risk, and time. However, so far, limited efforts have been made to predict alloy oxidation kinetics and spallation behavior via ML due to the lack of consistently measured and sufficient experimental data and the inherent complexity in oxidation behavior of multicomponent high-temperature alloys. A previous study reported the ability of ML to predict oxidation kinetics of NiCr-based alloys as a function of alloy composition and operating conditions. Here, the performance of a ML model in predicting rate constants and spallation probability was evaluated in light of the roles of the data distribution of the experimental dataset (data analytics), the alloy composition, the exposure environment and the chosen oxidation approach to extracting kinetic values from the measured mass changes (but using either a simple parabolic law or a statistical cyclic oxidation model). Potential strategies to improve the predictions and enhance the extrapolative capability of the previously trained model will be discussed.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Learning new physics from data: A symmetrized approach

Thousands of person years have been invested in searches for new physics (NP), the majority of them motivated by theoretical considerations. Yet, no evidence of beyond the Standard Model physics has been found. This suggests that model-agnostic searches might be an important key to explore NP, and help discover unexpected phenomena which can inspire future theoretical developments. A possible strategy for such searches is identifying asymmetries between data samples that are expected to be symmetric within the Standard Model. We propose exploiting neural networks (NNs) to quickly fit and statistically test the differences between two samples. Our method is based on an earlier work, originally designed for inferring the deviations of an observed dataset from that of a much larger reference dataset. We present a symmetric formalism, generalizing the original one, avoiding fine-tuning of the NN parameters and any constraints on the relative sizes of the samples. Our formalism could be used to detect small symmetry violations, extending the discovery potential of current and future particle physics experiments.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Deep learning-based predictive models for laser direct drive at the Omega Laser Facility

The rich and complex physics of inertial confinement fusion provides a unique and challenging space for high-fidelity first-principles modeling. Consequently, simulation codes that are used to design experiments are computationally expensive and lack the predictive capability required for extensive parameter exploration in search of a high-performing design for laser direct drive. In this article, we present two deep-learning-based predictive models intended to address these difficulties. The first model (TL DNN) acts as a fast emulator of simulations as well as experiments at the Omega Laser Facility. This model is trained on a simulation database and subsequently calibrated on experimental data using transfer learning. To facilitate the development of this model, an autoencoder is developed to reduce the dimensionality of the input space by compressing the laser pulse input. The model predicts key experimental scalar observables of Omega experiments with high accuracy and minimal computational cost. This deep neural net enables rapid exploration of a high-dimensional input parameter space for an optimal implosion design. The second model (DNN SM+) aims to extend the statistical modeling work of Lees et al. [Phys. Rev. Lett. 127, 105001 (2021)], by increasing the complexity of the model space and allowing for coupling between degradation terms. Since the model capacity of DNN SM+ is higher than the model of Lees et al., DNN SM+ can potentially provide an improvement in predictive capability, and we use this model to provide insight into complicated degradation dependencies.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2026

Observation of 𝑡⁢𝑊⁢𝑍 Production at the CMS Experiment

The first observation of single top quark production in association with a 𝑊 and a 𝑍 boson in proton-proton collisions is reported. The analysis uses data at center-of-mass energies of 13 and 13.6 TeV recorded with the CMS detector at the CERN LHC, corresponding to a total integrated luminosity of 200 fb −1 . Events with three or four charged leptons, which can be electrons or muons, are selected. Advanced machine-learning algorithms and improved reconstruction methods, compared to an earlier analysis, result in an unprecedented sensitivity to 𝑡⁢𝑊⁢𝑍 production. The measured cross sections for 𝑡⁢𝑊⁢𝑍 production are 248 ± 52 fb and 242 ± 77 fb for $\sqrt{s}$ =13 and 13.6 TeV, respectively. The signal is established with a statistical significance of 5.8 standard deviations, with 3.5 expected, compared to the background-only hypothesis.

Hayrapetyan, Aram [Yerevan Physics Institute]↗
DOE OSTI2022

Model-Form Epistemic Uncertainty Quantification for Modeling with Differential Equations: Application to Epidemiology

Modeling real-world phenomena to any degree of accuracy is a challenge that the scientific research community has navigated since its foundation. Lack of information and limited computational and observational resources necessitate modeling assumptions which, when invalid, lead to model-form error (MFE). The work reported herein explored a novel method to represent model-form uncertainty (MFU) that combines Bayesian statistics with the emerging field of universal differential equations (UDEs). The fundamental principle behind UDEs is simple: use known equational forms that govern a dynamical system when you have them; then incorporate data-driven approaches – in this case neural networks (NNs) – embedded within the governing equations to learn the interacting terms that were underrepresented. Utilizing epidemiology as our motivating exemplar, this report will highlight the challenges of modeling novel infectious diseases while introducing ways to incorporate NN approximations to MFE. Prior to embarking on a Bayesian calibration, we first explored methods to augment the standard (non-Bayesian) UDE training procedure to account for uncertainty and increase robustness of training. In addition, it is often the case that uncertainty in observations is significant; this may be due to randomness or lack of precision in the measurement process. This uncertainty typically manifests as “noisy” observations which deviate from a true underlying signal. To account for such variability, the NN approximation to MFE is endowed with a probabilistic representation and is updated using available observational data in a Bayesian framework. By representing the MFU explicitly and deploying an embedded, data-driven model, this approach enables an agile, expressive, and interpretable method for representing MFU. In this report we will provide evidence that Bayesian UDEs show promise as a novel framework for any science-based, data-driven MFU representation; while emphasizing that significant advances must be made in the calibration of Bayesian NNs to ensure a robust calibration procedure.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Bayesian operator inference for data-driven reduced-order modeling

This work proposes a Bayesian inference method for the reduced-order modeling of time-dependent systems. Informed by the structure of the governing equations, the task of learning a reduced-order model from data is posed as a Bayesian inverse problem with Gaussian prior and likelihood. The resulting posterior distribution characterizes the operators defining the reduced-order model, hence the predictions subsequently issued by the reduced-order model are endowed with uncertainty. The statistical moments of these predictions are estimated via a Monte Carlo sampling of the posterior distribution. Since the reduced models are fast to solve, this sampling is computationally efficient. Furthermore, the proposed Bayesian framework provides a statistical interpretation of the regularization term that is present in the deterministic operator inference problem, and the empirical Bayes approach of maximum marginal likelihood suggests a selection algorithm for the regularization hyperparameters. The proposed method is demonstrated on two examples: the compressible Euler equations with noise-corrupted observations, and a single-injector combustion process.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Accounting for erroneous model structures in biokinetic process models

In engineering practice, model-based design requires not only a good process-based model, but also a good description of stochastic disturbances and measurement errors to learn credible parameter values from observations. However, typical methods use Gaussian error models, which often cannot describe the complex temporal patterns of residuals. Consequently, this results in overconfidence in the identified parameters and, in turn, optimistic reactor designs. Here, we assess the strengths and weaknesses of a method to statistically describe these patterns with autocorrelated error models. This method produces increased widths of the credible prediction intervals following the inclusion of the bias term, in turn leading to more conservative design choices. However, we also show that the augmented error model is not a universal tool, as its application cannot guarantee the desired reliability of the resulting wastewater reactor design.

42 ENGINEERING↗
DOE OSTI2022

Predicting initial dissolution rates using structural features from molecular dynamics simulations

Predicting chemical durability of glass materials is important for various applications from daily life such as drink glass and kitchen ware to advanced technologies such as nuclear waste disposal and biomedicine. In this work, we explored prediction of initial dissolution rate through structural features from molecular dynamics (MD) simulations for a wide range of glass compositions (total 28) including borosilicate and aluminosilicate glasses, ZrO 2 -containing and V 2 O 5 -containing boroaluminosilicate glasses. The initial dissolution rates (r 0 ) measured experimentally at 90 °C with varying solution conditions were correlated with structural features (e.g., polyhedral linkages and non-bridging oxygen species) obtained from MD simulations, either from this study or from literature. Since hydrolysis of the glass network through breaking of the network former linkages (e.g., Si-O-Si, Si-O-Al, etc.) is a critical step of network glass dissolution, the statistics of these linkages obtained from MD were correlated to r0 through linear regression, where the coefficient of determination (R 2 ) and root mean square error are found to be 0.949 and 0.681, respectively. This model was compared and discussed with existing models developed by various approaches including machine learning, the kinetic rate equation, topological constraint theory, and other descriptors from MD simulations. The discussion provides insights on future model improvements to predict glass dissolution. In addition, the impact of V 2 O 5 on the glass dissolution was examined in detail, implicating that the impact is not the same across all glass compositions and test conditions.

36 MATERIALS SCIENCE↗