Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Prediction Accuracy”

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 415 records · Page 23
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

The Case for Strong Scaling in Deep Learning: Training Large 3D CNNs with Hybrid Parallelism

Here, we present scalable hybrid-parallel algorithms for training large-scale 3D convolutional neural networks. Deep learning-based emerging scientific workflows often require model training with large, high-dimensional samples, which can make training much more costly and even infeasible due to excessive memory usage. We solve these challenges by extensively applying hybrid parallelism throughout the end-to-end training pipeline, including both computations and I/O. Our hybrid-parallel algorithm extends the standard data parallelism with spatial parallelism, which partitions a single sample in the spatial domain, realizing strong scaling beyond the mini-batch dimension with a larger aggregated memory capacity. We evaluate our proposed training algorithms with two challenging 3D CNNs, CosmoFlow and 3D U-Net. Our comprehensive performance studies show that good weak and strong scaling can be achieved for both networks using up to 2K GPUs. More importantly, we enable training of CosmoFlow with much larger samples than previously possible, realizing an order-of-magnitude improvement in prediction accuracy.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Improved Frequency-Domain Steady-State Modeling of the Dual-Active-Bridge Converter Considering Finite ZVS Transition Time Effects

This article presents an improved analytical modeling (IAM) approach for the dual-active-bridge (DAB) converter in the frequency-domain. Specifically, finite transition times are incorporated into the improved modeling that are significant in DAB converters operated at high frequency. The IAM approach is first motivated by comparing traditional frequency-domain modeling against realistic simulation results in LTspice. Next, the IAM approach is mathematically developed in an iterative fashion, where the conventional frequency-domain approach is used as the initialization of the operational behavior of the converter. Subsequent iterations of the IAM algorithm incorporate finite rise- and falltimes of device output capacitances based on detailed switching behavior analyses, which may considerably perturb the desired modulation parameters (i.e., phase shift and zero states). While the initially proposed IAM approach demonstrates advantages over ideal modeling, it is still shown to exhibit errors when applied to device transitions with significant nonlinearity in parasitic output capacitance. To account for this, a three-slope approximation to the switching transition is then motivated and developed, which enables significantly improved steady-state prediction accuracy. Simulation and experimental results confirm unacceptable inaccuracies associated with the conventional frequency-domain modeling across a wide range of operating conditions, alongside enhanced accuracy provided by the proposed modeling approach.

14 SOLAR ENERGY↗
DOE OSTI2026

Leveraging Inequality-Constrained Data for Enhanced Liquidus Temperature Prediction in Nuclear Waste Glass Melts

Inequality-constrained data are frequently discarded in engineering, leading to significant information loss in data-scarce domains like glass characterization in nuclear waste vitrification. This paper presents a nonparametric censored-data regression framework based on an l1-norm optimization criterion that leverages slack variables to integrate left-, right-, and interval-constrained observations into training without distributional assumptions. Validated on synthetic data and a Physics-Informed Neural Network (PINN) for predicting liquidus temperature (TL), the method improved R2 from 0.60 to 0.89 and reduced Mean Absolute Error (MAE) by 48% (51.46 to 26.89?rC) on deterministic values. The traditional models failed to satisfy any inequality constraints while the proposed l1-norm PINN satisfies 81.25% of the constraints. The proposed framework effectively extracts actionable information from previously unusable data to enhance predictive accuracy, reduce epistemic uncertainty, and ensure physical consistency in complex industrial applications.

Garcia-Morado, Erick↗
DOE OSTI2022

Integration of physiologically relevant photosynthetic energy flows into whole genome models of light‐driven metabolism

SUMMARY Characterizing photosynthetic productivity is necessary to understand the ecological contributions and biotechnology potential of plants, algae, and cyanobacteria. Light capture efficiency and photophysiology have long been characterized by measurements of chlorophyll fluorescence dynamics. However, these investigations typically do not consider the metabolic network downstream of light harvesting. By contrast, genome‐scale metabolic models capture species‐specific metabolic capabilities but have yet to incorporate the rapid regulation of the light harvesting apparatus. Here, we combine chlorophyll fluorescence parameters defining photosynthetic and non‐photosynthetic yield of absorbed light energy with a metabolic model of the pennate diatom Phaeodactylum tricornutum. This integration increases the model predictive accuracy regarding growth rate, intracellular oxygen production and consumption, and metabolic pathway usage. Through the quantification of excess electron transport, we uncover the sequential activation of non‐radiative energy dissipation processes, cross‐compartment electron shuttling, and non‐photochemical quenching as the rapid photoacclimation strategy in P. tricornutum. Interestingly, the photon absorption thresholds that trigger the transition between these mechanisms were consistent at low and high incident photon fluxes. We use this understanding to explore engineering strategies for rerouting cellular resources and excess light energy towards bioproducts in silico . Overall, we present a methodology for incorporating a common, informative data type into computational models of light‐driven metabolism and show its utilization within the design–build–test–learn cycle for engineering of photosynthetic organisms.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Predictive Modeling of Local Film-Cooling Flow on a Turbine Rotor Blade

Abstract In the turbine section of a modern gas turbine engine, components exposed to the main gas path flow rely on cooling air to maintain hardware durability targets. Therefore, monitoring turbine cooling flow is essential to the diagnostic and prognostic efficacy of a condition-based operation and maintenance (CBOM) approach. This study supports CBOM goals by leveraging supervised machine learning to estimate relative changes to local film-cooling flowrate using surface temperature measured on the pressure side of a rotating turbine blade operating at engine-relevant aerothermal conditions. Throughout the lifetime of a film-cooled turbine component, characteristics of the film-cooling flow—such as film trajectory and cooling effectiveness—vary as degradation-driven geometry distortions occur, which ultimately affects the relationship between the model input and the model output—film-cooling flowrate predictions. The present study addresses this complication by testing a data-driven model on multiple turbine blades of the same nominal design, but with each blade exhibiting different localized film-cooling flow characteristics. By testing the model in this manner, strategies for mitigating the detrimental effects of film-cooling flow characteristic variations on model performance were investigated, and the corresponding flowrate prediction accuracy was quantified.

Engineering↗
DOE OSTI2025

Model Form Error Correction for a Black-Box Thermal Battery Heat Transfer Simulation

Thermal batteries are crucial for supplying power to high-consequence engineering applications such as rockets. Computational simulations have been developed to predict thermal battery behavior, but these simulations often suffer from modeling errors, including model form uncertainty. Addressing this uncertainty can be achieved by quantifying either the model discrepancy in the output or the model form error (MFE) in the governing equation. MFE is particularly valuable as it can be better extrapolated beyond observed outputs, which is essential for predictions involving changes in external system loading, system configuration and geometry, or output quantities. This paper employs a state estimation approach to estimate MFE using experimental data and then utilizes machine learning (ML) to model its relationship with state variables. A nonintrusive technique is used to estimate MFE in a black-box thermal battery heat transfer simulation. The trained machine learning model for MFE is then applied to correct simulation predictions under extrapolated initial conditions and battery configurations. In conclusion, the methodology's performance is evaluated using additional experimental data, demonstrating its effectiveness in improving prediction accuracy.

Batteries↗
DOE OSTI2021

Hybrid Improved Empirical Mode Decomposition and Artificial Neural Network Model for the Prediction of Critical Heat Flux (CHF)

Three Hybrid artificial neural network (ANN) models namely radial basis function (RBF), generalized regression neural networks (GRNN), and multi-layer perceptron (MLP) combined with empirical mode decomposition (EMD) are developed for CHF predictive modelling using CHF experimental databases.First, the original experimental inputs data series are decomposed into several intrinsic mode functions (IMFs) and one residual by EMD, whose components are divided into high, medium and low components. The performance parameters of the hybrid models indicates that the root mean square error (RMSE) are 0.8831, 0.6522, and 0.4149; the mean absolute error (MAE) are 0.6697, 0.4636, and 0.1935. The values of the R-square of the developed prediction approach utilizing EMD-RBF, EMD-GRNN, and EMD-MLP models are 0.8553, 0.9302, and 0.9818, and the index of agreement are 0.9464, 0.9700, and 0.9894., The value of the R-square and the index of agreement of the proposed models are much higher than those of the simple models .The Pearson's test results show that the association strength between the measured and the predicted values of the proposed model EMD-MLP is the strongest. These results show the following: (a) compared with other related, recent studies, the prediction accuracy of the hybrid model EMD- MLP proposed in this research is the best hybrid model; (b) the proposed hybrid model (EMD-MLP) attains superior performance compared with simple models.

Djeddou, Messaoud↗
DOE OSTI2024

Spread spectrum time domain reflectometry (SSTDR) and frequency domain reflectometry (FDR) cable inspection using machine learning

Cables are initially qualified for nuclear power plant use for 40 years. As plants extend their operating license to 60 and 80 years, justification for continued cable use must shift to a condition-based approach since it is cost prohibitive to completely replace cables that are likely still capable of performing their design function. The Pacific Northwest National Laboratory (PNNL) Accelerated and Real Time Experimental Nodal Analysis (ARENA) cable motor test bed was used to test the response of a commercial spread spectrum time domain reflectometry (SSTDR) system, a laboratory instrument software-controlled SSTDR, and a vector network analyzer-based frequency domain reflectometry (FDR) system to various cable anomalies. The three instrument systems were able to interrogate cables over a range of frequency bandwidths that can be helpful for human data analysis. Data were subjected to supervised and unsupervised machine learning (ML) analyses to distinguish normal undamaged cable responses from anomalous cable responses. Both supervised and unsupervised ML approaches produced encouraging results with an undamaged/anomalous prediction accuracy from 0.69% to 0.87%. Recommendations for further development and field implementation include increased and more balanced sample sets particularly including more training data.

SSTDR, FDR, Reflectometry, Machine Learning, ARENA↗
DOE OSTI2026

Scalable multiplexed machine learning gas sensor chips for food classification

Multiplexed gas sensor arrays combined with machine learning have unlocked previously inaccessible applications for scent-based sensing. Current platforms are limited by overlapping sensing materials with similar compositions, leading to highly correlated responses, or multistep deposition processes that hinder scalability. In this work, we developed a 16-element monolithic chip with fully distinct sensing layers, enabling a truly heterogeneous array. The system consists of highly sensitive carbon nanotube field effect transistors that are functionalized through a single-step microdispensing method compatible with automated pipetting systems. The resulting chip produces characteristic signal patterns in response to object-specific scent profiles and, when combined with machine learning algorithms, can perform automated object identification. We demonstrate the classification of 16 different objects, including food spoilage and nut allergens, with a 92.6% overall prediction accuracy.

Bassil, Carla [University of California, Berkeley,↗
DOE OSTI2026

Multi-strain analysis of Pseudomonas putida reveals the metabolic and genetic diversity of the species

Pseudomonas putida is a gram-negative bacterial species increasingly utilized in biotechnology due to its robust growth, ability to degrade aromatic compounds, solvent tolerance, and genetic tractability. In this study, we report a comprehensive multi-strain analysis of 164 P. putida strains based on the reconstruction of a pan-putida metabolic network and the formulation of strain-specific genome-scale metabolic models (GEMs). We performed whole-genome sequencing and hybrid assembly for 40 strains, contributing a ~8% increase to the available genomic data for P. putida . Furthermore, high-throughput phenotypic profiling using the Biolog phenotype microarray system for 24 strains on 190 unique carbon sources, along with 15 aromatic compounds not present on Biolog plates, yielded 4,920 unique strain-phenotype measurements. These data were leveraged to curate GEMs for 24 representative strains, including a refined model for strain KT2440, which comprised 1,480 genes and 2,191 metabolites, achieving a prediction accuracy of 91.2% in carbon utilization. Systematic comparison of genomes and GEMs revealed both conserved core pathways and significant allelic and functional divergence across strains, highlighting strain-specific variation in aromatic degradation. While pathways for protocatechuate and phenylacetate degradation were widely conserved, metabolic capabilities for compounds such as ferulate, phenol, and cresols varied markedly, suggesting adaptation to distinct ecological niches. Alleleome analysis of enzymes, such as PcaI and PcaJ, revealed distinct, functionally similar clades, indicating possible convergent evolution or horizontal gene transfer. These results provide computable resources and informative models for selecting P. putida strains with desired traits for biomanufacturing and bioremediation and offer insights into the evolution and phylogeny of the P. putida species.

aromatics utilization↗
DOE OSTI2024

Topological Interpretability for Deep Learning

With the growing adoption of AI-based systems across everyday life, the need to understand their decision-making mechanisms is correspondingly increasing. The level at which we can trust the statistical inferences made from AI-based decision systems is an increasing concern, especially in high-risk systems such as criminal justice or medical diagnosis, where incorrect inferences may have tragic consequences. Despite their successes in providing solutions to problems involving real-world data, deep learning (DL) models cannot quantify the certainty of their predictions. These models are frequently quite confident, even when their solutions are incorrect. This work presents a method to infer prominent features in two DL classification models trained on clinical and non-clinical text by employing techniques from topological and geometric data analysis. We create a graph of a model's feature space and cluster the inputs into the graph's vertices by the similarity of features and prediction statistics. We then extract subgraphs demonstrating high-predictive accuracy for a given label. These subgraphs contain a wealth of information about features that the DL model has recognized as relevant to its decisions. We infer these features for a given label using a distance metric between probability measures, and demonstrate the stability of our method compared to the LIME and SHAP interpretability methods. This work establishes that we may gain insights into the decision mechanism of a DL model. This method allows us to ascertain if the model is making its decisions based on information germane to the problem or identifies extraneous patterns within the data.

Spannaus, Adam↗
DOE OSTI2021

pnnl/neural_ODE_ICLR2020

We show how to model discrete ordinary differential equations (ODE) with algebraic nonlinearities as deep neural networks with varying degrees of prior knowledge. We derive the stability guarantees of the network layers based on the implicit constraints imposed on the weight's eigenvalues. Moreover, we show how to use barrier methods to generically handle additional inequality constraints. We demonstrate the prediction accuracy of learned neural ODEs evaluated on open-loop simulations compared to ground truth dynamics with bi-linear terms.

Tuor, Aaron↗
DOE OSTI2026

Iterative ML and Experiments for Emerging VOCs

SAND2026-17074O Iterative ML and Experiments for Emerging VOCs is a tool that analyzes and predicts the behaviors of SARS-CoV-2 variants. It processes experimental data on ACE2 (the receptor for the SARS-CoV-2 virus that allows it to infect the cell) and antibody binding using machine learning models, including neural networks, to forecast ACE2 interactions and variant expression. The tool employs transfer learning and global epistasis modeling, integrating public datasets with proprietary data to enhance prediction accuracy. Additionally, it fits concentration-response curves to determine dissociation constants and generates visualizations to support research findings, thereby aiding in the identification of new antibodies for emerging variants of concern. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

Sheffield, Thomas [Sandia National Lab. (SNL-NM), ↗
DOE OSTI2022

$\mathrm{CROPSR}$: an automated platform for complex genome-wide $\mathrm{CRISPR}$ g$\mathrm{RNA}$ design and validation

CRISPR/Cas9 technology has become an important tool to generate targeted, highly specific genome mutations. The technology has great potential for crop improvement, as crop genomes are tailored to optimize specific traits over generations of breeding. Many crops have highly complex and polyploid genomes, particularly those used for bioenergy or bioproducts. The majority of tools currently available for designing and evaluating gRNAs for CRISPR experiments were developed based on mammalian genomes that do not share the characteristics or design criteria for crop genomes. We have developed an open source tool for genome-wide design and evaluation of gRNA sequences for CRISPR experiments, CROPSR. The genome-wide approach provides a significant decrease in the time required to design a CRISPR experiment, including validation through PCR, at the expense of an overhead compute time required once per genome, at the first run. To better cater to the needs of crop geneticists, restrictions imposed by other packages on design and evaluation of gRNA sequences were lifted. A new machine learning model was developed to provide scores while avoiding situations in which the currently available tools sometimes failed to provide guides for repetitive, A/T-rich genomic regions. We show that our gRNA scoring model provides a significant increase in prediction accuracy over existing tools, even in non-crop genomes. CROPSR provides the scientific community with new methods and a new workflow for performing CRISPR/Cas9 knockout experiments. CROPSR reduces the challenges of working in crops, and helps speed gRNA sequence design, evaluation and validation. We hope that the new software will accelerate discovery and reduce the number of failed experiments.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2026

Estimating CO 2 fluxes through integrating spatial and temporal input layers via deep learning algorithms

Background Accurate estimation of net ecosystem exchange of CO 2 fluxes (Fc) is essential for understanding carbon cycle processes and assessing ecosystem carbon budgets. However, conventional modeling approaches often emphasize temporal dynamics while overlooking the pronounced spatial heterogeneity within the footprint of eddy covariance (EC) towers, potentially limiting predictive accuracy and interpretability of Fc estimates. To address this challenge, we developed a spatiotemporal model that integrates high-resolution footprint-weighted spatial information with sequential environmental drivers. Results The integrated model combines a deeper graph convolutional network to characterize fine-scale spatial variability within EC footprints and a gated recurrent unit network to capture temporal dependencies in biophysical conditions. Using multi-year flux tower observations, remote sensing vegetation indices and footprint modeling, we evaluate the proposed method across three land cover types. This spatiotemporal model consistently outperforms temporal-only and spatial-only baselines, achieving the highest overall accuracy (R 2 = 0.9569) and the lowest RMSE (1.8128 μmol m −2 s −1 ) and MAE (1.1939 μmol m −2 s −1 ). Performance gains are particularly evident in ecosystems with strong vegetation heterogeneity, where spatial structure substantially modulates Fc variability. Conclusions This study demonstrates the importance of joint modeling spatial heterogeneity and temporal dynamics for improving Fc estimation and provides a robust method for advancing footprint-based Fc estimates across diverse ecosystems, supporting refined assessments of terrestrial carbon fluxes, and enhancing scientific foundations for carbon studies.

CO2 flux estimate↗
DOE OSTI2024

Bayesian inference of structured latent spaces from neural population activity with the orthogonal stochastic linear mixing model

The brain produces diverse functions, from perceiving sounds to producing arm reaches, through the collective activity of populations of many neurons. Determining if and how the features of these exogenous variables (e.g., sound frequency, reach angle) are reflected in population neural activity is important for understanding how the brain operates. Often, high-dimensional neural population activity is confined to low-dimensional latent spaces. However, many current methods fail to extract latent spaces that are clearly structured by exogenous variables. This has contributed to a debate about whether or not brains should be thought of as dynamical systems or representational systems. Here, we developed a new latent process Bayesian regression framework, the orthogonal stochastic linear mixing model (OSLMM) which introduces an orthogonality constraint amongst time-varying mixture coefficients, and provide Markov chain Monte Carlo inference procedures. We demonstrate superior performance of OSLMM on latent trajectory recovery in synthetic experiments and show superior computational efficiency and prediction performance on several real-world benchmark data sets. We primarily focus on demonstrating the utility of OSLMM in two neural data sets: μ ECoG recordings from rat auditory cortex during presentation of pure tones and multi-single unit recordings form monkey motor cortex during complex arm reaching. We show that OSLMM achieves superior or comparable predictive accuracy of neural data and decoding of external variables (e.g., reach velocity). Most importantly, in both experimental contexts, we demonstrate that OSLMM latent trajectories directly reflect features of the sounds and reaches, demonstrating that neural dynamics are structured by neural representations. Together, these results demonstrate that OSLMM will be useful for the analysis of diverse, large-scale biological time-series datasets.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

A genome-scale metabolic model for the denitrifying bacterium Thauera sp. MZ1T accurately predicts degradation of pollutants and production of polymers

The denitrifying bacterium Thauera sp . MZ1T, a common member of microbial communities in wastewater treatment facilities, can produce different compounds from a range of carbon (C) and nitrogen (N) sources under aerobic and anaerobic conditions. In these different conditions, Thauera modifies its metabolism to produce different compounds that influence the microbial community. In particular, Thauera sp . MZ1T produces different exopolysaccharides with floc-forming properties, impacting the physical disposition of wastewater consortia and the efficiency of nutrient assimilation by the microbial community. Under N-limiting conditions, Thauera sp . MZ1T decreases its growth rate and accelerates the accumulation of polyhydroxyalkanoate-related (PHA) compounds including polyhydroxybutyrate (PHB), which plays a fundamental role as C and energy storage in this β-proteobacterium. However, the metabolic mechanisms employed by Thauera sp . MZ1T to assimilate and catabolize many of the different C and N sources under aerobic and anaerobic conditions remain unknown. Systems biology approaches such as genome-scale metabolic modeling have been successfully used to unveil complex metabolic mechanisms for various microorganisms. Here, we developed a comprehensive metabolic model (M-model) for Thauera sp . MZ1T ( i Thauera861), consisting of 1,744 metabolites, 2,384 reactions, and 861 genes. We validated the model experimentally using over 70 different C and N sources under both aerobic and anaerobic conditions. i Thauera861 achieved a prediction accuracy of 95% for growth on various C and N sources and close to 85% for assimilation of aromatic compounds under denitrifying conditions. The M-model was subsequently deployed to determine the effects of substrates, oxygen presence, and the C:N ratio on the production of PHB and exopolysaccharides (EPS), showing the highest polymer yields are achieved with nucleotides and amino acids under aerobic conditions. This comprehensive M-model will help reveal the metabolic processes by which this ubiquitous species influences communities in wastewater treatment systems and natural environments.

Tec-Campos, Diego (ORCID:0000000188194150)↗
DOE OSTI2022

Rock Physics-Based Data Assimilation of Integrated Continuous Active-Source Seismic and Pressure Monitoring Data during Geological Carbon Storage

Summary There has been substantial controversy concerning the role of geological carbon storage (GCS) in sequestering anthropogenic carbon emissions to mitigate climate change and global warming. Arguments center on the inability to monitor a geological storage site precisely and continuously, especially highlighting the associated costs and spatiotemporal trade-offs when using conventional subsurface monitoring techniques (well logs, core samples, chemical tracers, and 4D seismics). Active surveillance of GCS sites is essential for managing and mitigating potential leaks but is also required by regulation. With the goal of enhancing the monitoring capability at GCS sites, we present a rock physics-based joint data assimilation model to study a popular GCS site at Cranfield, Mississippi, USA. Synthetic continuous active-source seismic monitoring (CASSM) data (in the form of Vp and Qp measurements) and wellbore pressure monitoring data are assimilated with an ensemble of reservoir realizations to monitor gas saturation and reservoir pressure changes over a period of 100 years. Synthetic seismic attributes are generated using rock physics models (RPMs) and wellbore pressure monitoring data are extracted from the ground truth. Two assimilation methods, ensemble Kalman filter (EnKF) and ensemble Kalman smoother (EnKS), are tested in an observation system simulation experiment (OSSE) environment to assess the prediction accuracy of the individual and composite observation systems. The joint monitoring system achieves more accurate estimates of gas saturation and pressure, across the time span from start of injection to end of forecast, as compared to a single type of monitoring tool and irrespective of data assimilation algorithm choice. These results indicate that jointly assimilated data from two types of sensors (in this case, crosswell seismic and downhole pressure) may lead to a more risk-reducing monitoring design. One would expect that more data, vis-à-vis inclusion of a new sensor type, will improve the accuracy of any GCS monitoring system. However, from a practical standpoint, one important question is whether such a gain in accuracy is worth the additional cost associated with the new sensor. This paper focuses on quantifying the gain in accuracy, such that a practitioner can answer this question.

Engineering↗