SEARCH · Engineering Papers

Results for “data driven 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.

SourceResearch connectionFrom yearThrough year

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

At least 1,765 records · Page 98

All sources NASA NTRS DOE OSTI

DOE OSTI2023

Relating storm-snow avalanche instabilities to data collected from the Differential Emissivity Imaging Disdrometer (DEID)

Storm-snow avalanches are challenging to forecast due to complex alpine terrain and during rapidly changing weather conditions. They can result in loss of lives and significant economic impact. We describe how a new device that continuously measures with high-frequency snowflake mass, size, density, and type, the Differential Emissivity Imaging Disdrometer (DEID), and show how the DEID can be used to aid avalanche forecasting when coupled with a storm-snow stability model. DEID measurements of snow accumulation, snow water equivalent (SWE), and snow density obtained during seventeen storms taken at the mid-Collins Snow-Study Plot at Alta Ski Area in Utah's Central Wasatch mountain range during winter 2020–2021 show excellent agreement with infrequent manual measurements. Additionally, two new variables, the Shape Density Index (SDI) and Complexity, are proposed and used to classify snowflake habit and estimate storm-snow shear strength. We illustrate how these DEID-derived data can be used to identify layers of concern in the storm snow such as density inversions, in real-time without digging snow pits. Furthermore, the DEID-data are used to run four variations of the SNOw Slope Stability model (SNOSS) for the storms investigated. The results are evaluated with data collected from tilt-board tests, infrasound measurements, and visual observations of avalanches. For a total fourteen storms analyzed, the DEID-driven SNOSS-modeled minimum stability index predicts the general stability of the storm-snow as indicated by observed avalanches, both natural and of unknown cause. Finally, the results provide a promising approach for nowcasting instabilities within storm-snow layers with a single instrument.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2023

Robustness of the Stochastic Parameterization of Subgrid-Scale Wind Variability in Sea Surface Fluxes

Abstract High-resolution numerical models have been used to develop statistical models of the enhancement of sea surface fluxes resulting from spatial variability of sea surface wind. In particular, studies have shown that flux enhancement is not a deterministic function of the resolved state. Previous studies focused on single geographical areas or used a single high-resolution numerical model. This study extends the development of such statistical models by considering six different high-resolution models, four different geographical regions, and three different 10-day periods, allowing for a systematic investigation of the robustness of both the deterministic and stochastic parts of the data-driven parameterization. Results indicate that the deterministic part, based on regressing the unresolved normalized flux onto resolved-scale normalized flux and precipitation, is broadly robust across different models, regions, and time periods. The statistical features of the stochastic part of the model (spatial and temporal autocorrelation and parameters of a Gaussian process fit to the regression residual) are also found to be robust and not strongly sensitive to the underlying model, modeled geographical region, or time period studied. Best-fit Gaussian process parameters display robust spatial heterogeneity across models, indicating potential for improvements to the statistical model. These results illustrate the potential for the development of a generic, explicitly stochastic parameterization of sea surface flux enhancements dependent on wind variability.

Endo, Kota↗

DOE OSTI2025

Physics-informed latent neural operator for real-time predictions of time-dependent parametric PDEs

Deep operator network (DeepONet) has shown significant promise as surrogate models for systems governed by partial differential equations (PDEs), enabling accurate mappings between infinite-dimensional function spaces. However, when applied to systems with high-dimensional input-output mappings arising from large numbers of spatial and temporal collocation points, these models often require heavily overparameterized networks, leading to long training times. Latent DeepONet addresses some of these challenges by introducing a two-step approach: first learning a reduced latent space using a separate model, followed by operator learning within this latent space. While efficient, this method is inherently data-driven and lacks mechanisms for incorporating physical laws, limiting its robustness and generalizability in data-scarce settings. Here, in this work, we propose PI-Latent-NO, a physics-informed latent neural operator framework that integrates governing physics directly into the learning process. Our architecture features two coupled DeepONets trained end-to-end: a Latent-DeepONet that learns a low-dimensional representation of the solution, and a Reconstruction-DeepONet that maps this latent representation back to the physical space. By embedding PDE constraints into the training via automatic differentiation, our method eliminates the need for labeled training data and ensures physics-consistent predictions. The proposed framework is both memory and compute-efficient, exhibiting near-constant scaling with problem size and demonstrating significant speedups over traditional physics-informed operator models. We validate our approach on a range of parametric PDEs, showcasing its accuracy, scalability, and suitability for real-time prediction in complex physical systems.

Latent representations↗

DOE OSTI2024

On the Prediction of Aerosol-Cloud Interactions Within a Data-Driven Framework

Aerosol-cloud interactions (ACI) pose the largest uncertainty for climate projection. Among many challenges of understanding ACI, the question of whether ACI can be deterministically predicted has not been explicitly answered. Here we attempt to answer this question by predicting cloud droplet number concentration N c from aerosol number concentration N a and ambient conditions using a data-driven framework. We use aerosol properties, vertical velocity fluctuations, and meteorological states from the ACTIVATE field observations (2020–2022) as predictors to estimate N c . We show that the campaign-wide N c can be successfully predicted using machine learning models despite the strongly nonlinear and multi-scale nature of ACI. However, the observation-trained machine learning model fails to predict N c in individual cases while it successfully predicts N c of randomly selected data points that cover a broad spatiotemporal scale. This suggests that, within a data-driven framework, the N c prediction is uncertain at fine spatiotemporal scales.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2025

High-resolution climate model datasets for energy infrastructure planning in a renewable-dependent future

Electrification and renewables deployment efforts are amplifying the interdependence of the climate and energy systems. Increases in climate model resolution, which is now approaching that of reanalysis datasets and operational weather forecast models, present a unique opportunity to use future climate projections for energy infrastructure planning. In this Perspective, we review recent developments in high-resolution climate modeling, which have been driven by increased computing power and advanced software tools. We then look ahead to discuss how high-resolution climate data can be used to plan for a renewable-dependent future, and envision a unified climate-energy model framework that captures the two-way feedbacks between these interdependent systems.

climate change↗

DOE OSTI2025

Model Residuals as Shields: A Two-Level Formulation to Defend Smart Grids From Poisoning Attacks

The advancement of smart grids presents both vast opportunities and heightened cybersecurity risks. Data-driven defense mechanisms, though designed as a shield against these threats, can fall prey to poisoning attacks. We delve into regression settings, underscoring the imperative to fortify defenses against a spectrum of poison ratios, notably those above 0.5—an issue scarcely addressed in prior studies. Recognizing the susceptibilities of smart grids and their manipulable sensors, we exploit the very intent of poisoning attacks, compromising model accuracy, as our defense mechanism. Our proposed two-level optimization framework discerns between poisoned and authentic data based on model residuals, outperforming or matching existing methods in 72% to 77% of precision and 75% to 80% of recalls across various poisoning attacks, poison ratios, and datasets. Once the authentic data are identified, the trained model is adaptable for a variety of applications. Comprehensive evaluations on different smart grid datasets, pitted against myriad poisoning schemes, validate our methodology’s edge over existing methods. Here, we also shed light on the implications of model misspecification originating from temporal auto-correlation, a common feature in Internet of Things and smart grid data.

Adversarial machine learning (ML)↗

DOE OSTI2025

Computational Analysis and Optimized Modeling of Geomagnetically Induced Currents in Power Transformers

In this project we aim to better understand the effect of geomagnetically induced currents (GIC) on power transformers. Expanding upon our previous work focused on producing a methodology for accuracy-enhanced computation of GIC signatures (i.e., time-domain current magnitude variation for the event duration) from a combination of physics-based and data-driven computational tools, we propose the use of these GIC signatures as inputs for a physically-detailed and optimized model of the power transformer to investigate how GIC determination and transformer modeling influence the evaluation of GIC effects on the transformer operation, as well as in its interaction with the power grid.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2026

U-net architected deep material network training with microstructure local field information

The Deep Material Network (DMN) has recently emerged as a powerful reduced-order modeling framework for simulating the mechanical response of heterogeneous materials such as composites. Unlike most data-driven approaches that directly learn a material’s response under prescribed loading, the DMN acts as a homogenization operator, learning the kinematic constraints and mechanical interactions of the underlying microstructure. However, traditional DMN training relies exclusively on homogenized effective properties derived from Direct Numerical Simulations (DNS), discarding the rich local field data that govern microstructural interactions. In this work, we extend the DMN framework to incorporate such local field information into the offline training process. Utilizing a U-Net architecture, we augment the DMN training objective to include the first and second statistical moments of the local stress fields obtained from linear DNS. This ensures that the learned network topology not only fits the effective stiffness but also accurately reflects the internal local stress and strain partitioning of the microstructure. The results confirm that supervising the localization process during training yields a superior surrogate model, reducing local prediction errors by an order of magnitude and significantly improving generalization to unseen nonlinear constitutive behaviors compared to traditional DMNs.

36 MATERIALS SCIENCE↗

DOE OSTI2023

Online Model-Free Chance-Constrained Distribution System Voltage Control Using DERs: Preprint

This paper proposes an online data-driven distributed energy resource management system (DERMS) optimization method using chance-constrained formulation to address distribution system voltage regulation. This is achieved via the local sensitivity factor (LSF)-enabled reformulation of the DER control into a linear programming (LP) problem, which is easy and computationally efficient to solve. The LSF is estimated using online measurements and does not need the assumption of node load information. The latter is usually required for existing optimization-based methods but is difficult to obtain in practice. To mitigate measurement uncertainties, a scenario-based chance-constrained formulation is constructed. Compared with other control methods, the results carried out in a realistic distribution system show that the proposed method can effectively eliminate voltage violation issues.

chance-constrained optimization↗

NASA NTRS2005

Spatial Predictive Modeling and Remote Sensing of Land Use Change in the Chesapeake Bay Watershed

This project was focused on modeling the processes by which increasing demand for developed land uses, brought about by changes in the regional economy and the socio-demographics of the region, are translated into a changing spatial pattern of land use. Our study focused on a portion of the Chesapeake Bay Watershed where the spatial patterns of sprawl represent a set of conditions generally prevalent in much of the U.S. Working in the region permitted us access to (i) a time-series of multi-scale and multi-temporal (including historical) satellite imagery and (ii) an established network of collaborating partners and agencies willing to share resources and to utilize developed techniques and model results. In addition, a unique parcel-level tax assessment database and linked parcel boundary maps exists for two counties in the Maryland portion of this region that made it possible to establish a historical cross-section time-series database of parcel level development decisions. Scenario analyses of future land use dynamics provided critical quantitative insight into the impact of alternative land management and policy decisions. These also have been specifically aimed at addressing growth control policies aimed at curbing exurban (sprawl) development. Our initial technical approach included three components: (i) spatial econometric modeling of the development decision, (ii) remote sensing of suburban change and residential land use density, including comparisons of past change from Landsat analyses and more traditional sources, and (iii) linkages between the two through variable initialization and supplementation of parcel level data. To these we added a fourth component, (iv) cellular automata modeling of urbanization, which proved to be a valuable addition to the project. This project has generated both remote sensing and spatially explicit socio-economic data to estimate and calibrate the parameters for two different types of land use change models and has undertaken analyses of these models. One (the CA model) is driven largely by observations on past patterns of land use change, while the other (the EC model) is driven by mechanisms of the land use change decision at the parcel level. Our project may be the first serious attempt at developing both types of models for the same area, using as much common data as possible. We have identified the strengths and weaknesses of the two approaches and plan to continue to revise each model in the light of new data and new lessons learned through continued collaboration. Questions, approaches, findings, publication and presentation lists concerning the research are also presented.

Goetz, Scott J.↗

DOE OSTI2023

Hybrid Attack Graph Generation with Graph Convolutional Deep-Q Learning

Critical infrastructures such as power grids have become increasingly complex, connected, and vulnerable to adverse scenarios, including cyber and physical attacks and faults. Effective risk mitigation for such cyber-physical energy systems (CPES), requires preemptive knowledge of likely adversarial attack scenarios. Hybrid Attack Graph (HAG) is a structured way to represent an adversarial scenario as an attack sequence using a threat model. However, the scarcity of documented attack sequences hinders analysts and CPES planners’ ability to identify credible attack scenarios for a given CPES. We propose a data-driven Graph Convolutional Deep-Q Network (GCDQ) to address this data challenge through generating HAGs. By leveraging limited real-world observations from the MITRE ATT&CK knowledge base, our GCDQ model synthesizes realistic graphs with the targeted attribute of minimum detectability via reinforcement learning. This generative model is the first step in creating a tool to substantially boost the attack sequence dataset and enhance the performance of CPS defense-related tasks by providing insights into likely attack sequences with given attributes.

deep learning, artificial intelligence↗

DOE OSTI2024

Modeling plasticity-mediated void growth at the single crystal scale: A physics-informed machine learning approach

Modeling the evolution of voids during plastic flow as well as their effects on plastic dissipation is critical for both component manufacturing and lifetime estimation purposes. To this end, we propose a rate-dependent constitutive model to homogenize the effects of semi-randomly distributed voids on single crystal plasticity whilst capturing void interaction and plastic anisotropy. Here, this present work focuses on the case of face centered cubic crystals to introduce an anisotropic gauge function applicable within the crystal plasticity formalism. The approach combines analytical methods to describe the micromechanics of the system in combination with symbolic regression to capture analytically intractable mechanisms from data. The hybrid framework uses a physics-informed genetic programming-based symbolic regression algorithm to solve a multiform optimization problem simultaneously producing a new gauge function and a new strain rate equation. This is also a multi-objective optimization problem with many competing objectives. A new search and selection step is introduced to the genetic algorithm that promotes convergence toward a global solution that better satisfies all the objectives. Overall, the symbolic equations produced leverage data-driven methods to achieve greater accuracy than comparable alternatives on an analytically intractable problem while maintaining model transparency.

36 MATERIALS SCIENCE↗

DOE OSTI2023

MACHINE LEARNING-ENABLED PREDICTION OF TRANSIENT INJECTION MAP IN AUTOMOTIVE INJECTORS WITH UNCERTAINTY QUANTIFICATION

Accurate prediction of injection profiles is a critical aspect of linking injector operation with engine performance and emissions. However, highly resolved injector simulations can take one to two weeks of wall-clock time, which is incompatible with engine design cycles with desired turnaround times of less than a day. Hence, it is important to reduce the time-to-solution of the internal flow simulations by several orders of magnitude to make it compatible with engine simulations. This work demonstrates a data-driven approach for tackling the computational overhead of injector simulations, whereby the transient injection profiles are emulated for a side-oriented, single-hole diesel injector using a Bayesian machine-learning framework. First, an interpretable Bayesian learning strategy was employed to understand the effect of design parameters on the total void fraction field. Then, autoencoders are utilized for efficient dimensionality reduction of the flowfields. Gaussian process models are finally used to predict the spatiotemporal void fraction field at the injector exit for unknown operating conditions. The Gaussian process models produce principled uncertainty estimates associated with the emulated flowfields, which provide the engine designer with valuable information of where the data-driven predictions can be trusted in the design space. The Bayesian flowfield predictions are compared with the corresponding predictions from a deep neural network, which has been transfer-learned from static needle simulations from a previous work by the authors. The emulation framework can predict the void fraction field at the exit of the orifice within a few seconds, thus achieving a speed-up factor of up to 38 x 10(6) over the traditional simulation-based approach of generating transient injection maps.

machine learning↗

NASA NTRS1999

Assimilation of Satellite Altimeter Data With a Four Dimensional Model of the Japan Sea

A data assimilation is carried out to detect the variability of the Japan Sea circulation in the range from a few days to several years and from eddy to basin scale. The model applied in this study is the same 1/6 degree GFDL MOM1 as Kim and Yoon (1999) but is driven by ECMWF daily wind stress, heat and fresh water fluxes. The satellite altimeter data of TOPEX/POSEIDON, ERS-1 (phase C and G) and -2 are assimilated by an approximate Kalman filter (Fukumori and M.Rizzoli, 1995). The approximation is made by seeking an asymptotic steady error covariance matrix (Fukumori et al., 1993) and by introducing a coarser grid model for the innovation (data-model misfit). The coarse grid model is defined on 1/2 degree horizontal resolution and consists of the barotropic stream function, first baroclinic displacement and velocity amplitudes. The assimilated estimates explain about 6cm sea level variability of the data (approximately 12cm in the southern part), which is much larger than the previous reduced-gravity model and TOPEX/POSEIDON altimeter data assimilation (Hirose et al., 1999). The impacts of the T/P and ERS data on the filtered estimates are comparable. The result also shows high correlation to subsurface water temperatures measured by CTD. Many of the mesoscale eddies/disturbances travel east-northeastward with the advection speed of 1-3cm/s though most of them generated in the western region can not pass over the Oki Spur. The quasi-biennial variability found by Hirose and Ostrovskii (1999) did not show clear propagation pattern. The shallow Oki Spur may work as a "western boundary" to this signal. This is more plausible estimation than by the R-G model which has no bottom topography.

Hirose, Naoki↗

DOE OSTI2021

Uplift and Seismicity Driven by Magmatic Inflation at Sierra Negra Volcano, Galápagos Islands

Abstract Although episodes of surface uplift and elevated seismicity precede many volcanic eruptions, their temporal evolution is often complex, and apparently in contradiction to simple trends predicted by mechanical deformation models. Here, we use continuous global positioning system and seismic data recorded at Sierra Negra volcano, Galápagos Islands, to show how the edifice responded to stress changes driven by magma accumulation in a shallow sill. The rate of uplift varied during the 13 years and 6.5 m of inflation before the 2018 eruption. The number of earthquakes per unit of uplift increased exponentially with total uplift as the differential stress increased. Accordingly, the temporal seismicity rate varied in time as a function of both the total uplift and the uplift rate. The Gutenberg‐Richter b ‐value decreased as a function of total uplift. In the final six months before the eruption, a sequence of large ( M > 4) earthquakes regulated the state of stress on the fault, each being followed by 2–3 days of postseismic quiescence, and retarding the increase in seismicity rate. These earthquakes did not affect the overall uplift rate. Subsidence of 8.5 m accompanied the 2‐month eruption. On resumption of uplift, the number of earthquakes per unit of uplift was very low, and the b ‐value high, reflecting the relaxed stress state of the fault system. These observations show that crustal deformation becomes increasingly brittle at higher stress states, and supports theoretical models based on elastic‐brittle mechanics. They suggest that joint interpretation of deformation and seismicity is key for forecasting future eruptions in similar volcanic settings.

Bell, Andrew Forbes↗

DOE OSTI2026

SPRUCE FT-ICR MS, Bulk Chemistry, and Mass Loss from Litter Decomposition Study in Experimental Plots, Marcell Experimental Forest, Minnesota, 2015-2017

This dataset contains molecular, bulk chemical, and mass loss measurements from a litter decomposition study at the Spruce and Peatland Responses Under Changing Environments (SPRUCE) experimental site within the Marcell Experimental Forest in northern Minnesota, USA. This site is in a Sphagnum spp. ombrotrophic bog forest. Litterbags were deployed into the peat in September 2015 across three warming levels (+0, +4.5, and +9°C) under ambient and elevated carbon dioxide (CO₂ - +500 ppm) and retrieved after roughly 0.5, 1, and 2 years of field incubation (2015-09-23 to 2017-08-02). Litterbags containing six peatland litter types: black spruce needles (Picea mariana - SPL), spruce fine roots (SPR), Sphagnum angustifolium (ANG), Sphagnum magellanicum (MAG), Labrador tea leaves (Rhododendron groenlandicum - LTL), and Labrador tea roots (LTR). Molecular composition of water-soluble organic matter extracts was characterized using Fourier Transform Ion Cyclotron Resonance Mass Spectrometry (FT-ICR MS) at 9.4 Tesla, operated in negative ion mode with electrospray ionization, providing molecular formula assignments and compound-class distributions across the decomposition time series. Bulk chemical characterization included elemental analysis (percent carbon, nitrogen, and phosphorus) and Fourier Transform Infrared Spectroscopy (FTIR) to quantify functional group composition. Litter mass loss was tracked gravimetrically at each retrieval interval, expressed as percent mass remaining relative to initial dry mass for each litter type and treatment combination. These data are valuable for understanding how vegetation shifts driven by increased atmospheric CO2 and temperature in peatlands alter litter inputs and organic matter stabilization trajectories, with implications for projecting and modeling peatland carbon cycling. This dataset contains two data files in comma-separated value (.csv) format. Additional metadata are provided: two data dictionaries and a file-level metadata file in comma separate (.csv) format and a user guide in PDF (*.pdf) format.

decomposition↗

DOE OSTI2020

Dynamical Mass Estimates of the β Pictoris Planetary System through Gaussian Process Stellar Activity Modeling

Nearly 15 yr of radial velocity (RV) monitoring and direct imaging enabled the detection of two giant planets orbiting the young, nearby star β Pictoris. The δ Scuti pulsations of the star, which overwhelm planetary signals, need to be carefully suppressed. In this work, we independently revisit the analysis of the RV data following a different approach than available in the literature to model the activity of the star. We show that a Gaussian process (GP) with a stochastically driven damped harmonic oscillator kernel can model the δ Scuti pulsations. It provides similar results to parametric models but with a simpler framework, using only three hyperparameters. It also enables us to model poorly sampled RV data that were excluded from previous analyses, hence extending the RV baseline by nearly five years. Altogether, the orbit and mass of both planets can be constrained from RV only, which was not possible with the parametric modeling. To characterize the system more accurately, we also perform a joint fit of all available relative astrometry and RV data. Our orbital solutions for β Pic b favor a low eccentricity of 0.029$_{−0.024}^{+0.061}$ and a relatively short period of 21.1$_{−0.8}^{+2.0}$ yr. The orbit of β Pic c is eccentric with 0.206$_{−0.063}^{+0.074}$ with a period of 3.36 ± 0.03 yr. We find model-independent masses of 11.7 ± 1.4 and 8.5 ± 0.5 M Jup for β Pic b and c, respectively, assuming coplanarity. The mass of β Pic b is consistent with the hottest start evolutionary models, at an age of 25 ± 3 Myr. A direct detection of β Pic c would provide a second calibration measurement in a coeval system.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2020

Progress on Understanding Rayleigh–Taylor Flow and Mixing Using Synergy Between Simulation, Modeling, and Experiment

Simultaneous advances in numerical methods and computing, theoretical techniques, and experimental diagnostics have all led independently to better understanding of Rayleigh–Taylor (RT) instability, turbulence, and mixing. In particular, experiments have provided significant motivation for many simulation and modeling studies, as well as validation data. Numerical simulations have also provided data that is not currently measurable or very difficult to measure accurately in RT unstable flows. Thus, simulations have also motivated new measurements in this class of buoyancy-driven flows. This overview discusses simulation and modeling studies synergistic with experiments and examples of how experiments have motivated simulations and models of RT instability, flow, and mixing. First, a brief summary of measured experimental and calculated simulation quantities, of experimental approaches, and of issues and challenges in the simulation and modeling of RT experiments is presented. Implicit large-eddy, direct numerical, and large-eddy simulations validated using RT experimental data are then discussed. This is followed by a discussion of modeling using analytical, modal, buoyancy–drag, and turbulent transport models of RT mixing experiments. The discussion will focus on three-dimensional RT mixing arising from multimode perturbations. Finally, this focused review concludes with a perspective on future simulation, modeling, and experimental directions for further research. Research in simulation and modeling of RT unstable flows, coupled with experiments, has made significant progress over the past several decades. This overview serves as an opportunity to both discuss progress and to stimulate future research on simulation and modeling of this unique class of hydrodynamically unstable turbulent flows.

42 ENGINEERING↗