SEARCH · Engineering Papers

Results for “Surrogate Models”

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 1,063 records · Page 59

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Integrating Analytical Solutions and U-Net Model for Predicting Groundwater Contaminant Plumes in Pump-and-Treat Systems

Pump-and-treat (P&T) is a common technique for groundwater remediation involving the extraction and treatment of contaminated water above ground. Optimizing the design and operation of the P&T well network is essential for maximizing the system’s effectiveness and efficiency. However, this optimization often necessitates many model evaluations, leading to computationally demanding tasks. This study introduces a novel approach that integrates analytical solutions for groundwater dynamics with the U-Net (Ronneberger et al., 2015) deep learning framework to predict groundwater contaminant plume migration under dynamic pumping conditions. By incorporating the Thiem equation (Thiem, 1906) into the input preprocessing, the U-Net model transforms sparse well data into a continuous spatial field that captures the hydraulic impacts of pumping activities. This integration enables the model to leverage both deep learning capabilities and classical physics-based groundwater theories, enhancing prediction accuracy and computational efficiency. These advancements can facilitate rapid, large-scale evaluations of P&T optimization simulations, allowing for timely and effective decision-making in well placement and system management. We demonstrate the model's robust performance across both simplified transient 2D models and a more complex 3D heterogeneous site model at the 200 West P&T facility at the Hanford Site. The U-Net-based model offers substantial computational advantages, reducing simulation times significantly compared to full physics-based models and providing a powerful tool for rapid site evaluation and P&T system optimization, such as evaluating alternative P&T well network designs. Our findings highlight the potential of advanced machine learning models to significantly enhance the efficiency and sustainability of groundwater remediation efforts, offering a novel application of U-Net architecture in environmental science.

Pump-and-treat↗

DOE OSTI2021

Deterministic symbolic regression with derivative information: General methodology and application to equations of state

Symbolic regression methods simultaneously determine the model functional form and the regression parameter values by generating expression trees. Symbolic regression can capture the complexity of real–world phenomena but the use of deterministic optimization for symbolic regression has been limited due to the complexity of the search space of existing formulations. Herein we present a novel deterministic mixed–integer nonlinear programming formulation for symbolic regression that incorporates derivative constraints through auxiliary expression trees. By applying the chain rule to mathematical operations, binary expression trees are capable of representing the calculation of first and second derivatives. We apply this formulation to illustrative examples using derivative information to show increased model discrimination capability. In addition, we perform a case study of a thermodynamic equation of state to gain insight on valid functional forms with thermodynamics–based constraints on the first and second derivatives.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2025

Coarse Graining Discrete Element Method Information in Particle-in-Cell Length Scales Using a Machine Learning Approach

This report details the development of a machine learning (ML)-driven framework to coarse-grain inter-particle collision dynamics from high-fidelity Discrete Element Method (DEM) simulations to Particle-in-Cell (PIC) scales for gas-solid systems. Traditional PIC models, while computationally efficient, rely on empirical granular stress formulations that fail to capture the full complexity of collision physics, particularly the heterogeneity in particle dynamics. This study adopts a bottom-up approach, integrating insights from DEM simulations to improve the physical fidelity and interpretability of PIC-scale models.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2021

An adaptive approach to machine learning for compact particle accelerators

Abstract Machine learning (ML) tools are able to learn relationships between the inputs and outputs of large complex systems directly from data. However, for time-varying systems, the predictive capabilities of ML tools degrade if the systems are no longer accurately represented by the data with which the ML models were trained. For complex systems, re-training is only possible if the changes are slow relative to the rate at which large numbers of new input-output training data can be non-invasively recorded. In this work, we present an approach to deep learning for time-varying systems that does not require re-training, but uses instead an adaptive feedback in the architecture of deep convolutional neural networks (CNN). The feedback is based only on available system output measurements and is applied in the encoded low-dimensional dense layers of the encoder-decoder CNNs. First, we develop an inverse model of a complex accelerator system to map output beam measurements to input beam distributions, while both the accelerator components and the unknown input beam distribution vary rapidly with time. We then demonstrate our method on experimental measurements of the input and output beam distributions of the HiRES ultra-fast electron diffraction (UED) beam line at Lawrence Berkeley National Laboratory, and showcase its ability for automatic tracking of the time varying photocathode quantum efficiency map. Our method can be successfully used to aid both physics and ML-based surrogate online models to provide non-invasive beam diagnostics.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2021

Autoignition study of iso -cetane/tetralin blends at low temperature

iso-Cetane and tetralin are the two fuel components commonly considered in literature diesel surrogates, and are hydrocarbon classes representative of iso-alkanes and naphthoaromatics, respectively. Since both surrogate components are involved in the key reactions controlling the autoignition reactivity of diesel surrogates, autoignition studies of iso-cetane, tetralin, and their blending behavior at low temperatures can be helpful in developing/refining chemical kinetic models of diesel surrogates, in order to better predict diesel ignition response under low temperature combustion conditions. In this investigation, autoignition experiments of iso-cetane, tetralin, and their binary mixtures at varying blending ratios have been conducted in a rapid compression machine (RCM) in the temperature/pressure range of 630–930 K and 10–20 bar. For the neat fuel components, the newly-acquired RCM data have been compared with the literature experimental results at some overlapping conditions. In addition, a chemical kinetic model describing the oxidation of iso-cetane and tetralin compiled/updated from the diesel surrogate model developed by Lawrence Livermore National Laboratory is used to simulate the experimental datasets. It is shown that this model exhibits good agreement with the experimental results of tetralin and also predicts the total ignition delay times of iso-cetane at lower temperatures reasonably well. However, the current model fails to fully capture the increase of total ignition delay time with increasing amount of tetralin in the binary blends observed in the present RCM experiments. Therefore, chemical kinetic analyses of the current model are conducted to help identify possible reasons leading to the discrepancies between simulations and experiments. Furthermore, the chemical kinetic interactions between iso-cetane and tetralin are explored by including additional cross-reactions among iso-cetane, tetralin, and their fuel fragments in the current model to assess their effects on model predictions. As a result, based on the chemical kinetic analysis results, future direction for model refinements is discussed.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2020

Probabilistic risk-based Area of Review (AoR) determination for a deep-saline carbon storage site

Regulatory oversight of a geologic carbon sequestration (GCS) project relies on iterative estimations, throughout the project lifetime, of the area where increased risks to underground sources of drinking water (USDWs) may occur due to injection of CO2. This area, referred to as Area of Review (AoR), is typically delineated by predicting the migration of fluid between the reservoir and the lowermost USDW via an open wellbore using predictions from physics-based reservoir simulators. The inherent uncertainty in input parameters used in reservoir modeling therefore affects the accuracy of determining the AoR for a project. Furthermore, the standard analytical approaches for calculating a critical pressure to delineate the risk area yield an infinite AoR for cases where the injection reservoir is overpressured relative to the USDW. A methodology is presented in this paper to better characterize the risk to USDWs while accounting for the uncertainty in reservoir modeling, with an application to a permitted GCS project with an overpressured injection formation, FutureGen 2.0. The methodology is demonstrated using the National Risk Assessment Partnership’s open-source integrated assessment model (NRAP-Open-IAM) to develop a probabilistic estimate of impact risk to USDW quality. CO2 and pressure predictions from the reservoir modeling conducted using the STOMP-CO2 simulator for the FutureGen 2.0 site are used in a NRAP-Open-IAM model with reservoir, wellbore, and aquifer components to: (1) assess the extent of potential leakage into the USDW for the predicted reservoir pressure conditions; (2) evaluate the extent of potential impact using “no-net-degradation” thresholds; and (3) account for uncertainty in reservoir permeabilities.

03 NATURAL GAS↗

DOE OSTI2023

Applications of physics informed neural operators

Abstract We present a critical analysis of physics-informed neural operators (PINOs) to solve partial differential equations (PDEs) that are ubiquitous in the study and modeling of physics phenomena using carefully curated datasets. Further, we provide a benchmarking suite which can be used to evaluate PINOs in solving such problems. We first demonstrate that our methods reproduce the accuracy and performance of other neural operators published elsewhere in the literature to learn the 1D wave equation and the 1D Burgers equation. Thereafter, we apply our PINOs to learn new types of equations, including the 2D Burgers equation in the scalar, inviscid and vector types. Finally, we show that our approach is also applicable to learn the physics of the 2D linear and nonlinear shallow water equations, which involve three coupled PDEs. We release our artificial intelligence surrogates and scientific software to produce initial data and boundary conditions to study a broad range of physically motivated scenarios. We provide the source code , an interactive website to visualize the predictions of our PINOs, and a tutorial for their use at the Data and Learning Hub for Science .

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Results and lessons learned from accelerating radio frequency modeling using machine learning [slides]

The “advanced tokamak” reactor concept is a leading candidate for a steady state fusion pilot plant. An advanced tokamak (AT) sustains a majority of the required plasma current with effects resulting from maintenance of the peaked pressure at the device center. This current is augmented by auxiliary current drive sources. These auxiliary actuators may consist of neutral particle beams and/or radio frequency (RF) systems such as lower hybrid current drive (LHCD) and high harmonic fast wave (HHFW) current drive using radio and microwaves from antennas. The primary focus of this work is to develop models of RF current profile control suitable for use in integrated modeling frameworks and for real-time control in experiments. Direct physics models of RF current drive can be computationally intensive. In order to achieve predictive times appropriate for the thousands of calls needed in real-time control of experiments and for use in integrated models, we will apply modern machine learning (ML) techniques to accelerate these models and interpolate their results. To generate the fast and accurate models for use in control level algorithms and integrated modeling we need to replace present models with high dimensional interpolation of their results. We will perform additional simulations across a broader parameter range for EAST and other tokamaks in different physics regimes (Alcator C-Mod, DIII-D, WEST, CFETR, ARC, ITER) and combine them into a larger database for training and testing of the ML models. Further testing of the control level models with experimental current profile data from EAST and C-Mod tokamaks will provide additional confirmation of the control level model before integration in a tokamak control system or integrated modeling suite. ML will be used to optimize the selection of training data consisting of RF current driven at different values of density profile, temperature profile, plasma current, and wavenumber. ML will also be used to facilitate classification of current drive from these input data. The output of this effort will be a validated classifier capable of determining the current drive profiles for HHFW CD and LHCD on a mille-second timescale. This will provide a breakthrough capability enabling real-time control of RF driven current profiles in experiments including ITER ICRF and use integrated modeling frameworks requiring thousands of current profile calculations in discharge simulations.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2025

Streaming Compression of Scientific Data via Weak-SINDy

Here, in this paper, a streaming weak-SINDy algorithm is developed specifically for compressing streaming scientific data. The production of scientific data, either via simulation or experiments, is undergoing a stage of exponential growth, which makes data compression important and often necessary for storing and utilizing large scientific data sets. As opposed to classical “offline” compression algorithms that perform compression on a readily available data set, streaming compression algorithms compress data “online” while the data generated from simulation or experiments is still flowing through the system. This feature makes streaming compression algorithms well suited for scientific data compression, where storing the full data set offline is often infeasible. This work proposes a new streaming compression algorithm, streaming weak-SINDy, which takes advantage of the underlying data characteristics during compression. The streaming weak-SINDy algorithm constructs feature matrices and target vectors in the online stage via a streaming integration method in a memory efficient manner. The feature matrices and target vectors are then used in the offline stage to build a model through a regression process that aims to recover equations that govern the evolution of the data. For compressing high-dimensional streaming data, we adopt a streaming proper orthogonal decomposition (POD) process to reduce the data dimension and then use the streaming weak-SINDy algorithm to compress the temporal data of the POD expansion. We propose modifications to the streaming weak-SINDy algorithm to accommodate the dynamically updated POD basis. By combining the built model from the streaming weak-SINDy algorithm and a small amount of data samples, the full data flow could be reconstructed accurately at a low memory cost, as shown in the numerical tests.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Artificial Intelligence-Aided Wind Plant Optimization for Nationwide Evaluation of Land Use and Economic Benefits of Wake Steering

If clean energy pathways are to harness massive increases in wind power, innovations with broad geographic viability will be needed to support buildout in diverse locations. However, geodiversity in impact potential is seldom captured in technology assessment. Here we propose a scalable approach to plant-level optimization using artificial intelligence to evaluate land sparing and economic benefits of wake steering at more than 6,800 plausible onshore wind locations in the USA. This emerging controls strategy optimizes plant energy production by directing turbine wakes. On the basis of estimates from our artificial intelligence model trained on engineering wind flow simulations, co-optimizing plant layouts with wake steering can reduce land requirements by an average of 18% per plant (site-specific benefits range from 2% to 34%), subject to errors and uncertainties in the flow model, wind resource estimates, buildout scenario and geographic factors. According to model estimates, wake steering is predicted to increase power production during high-value (relatively low wind) periods, boosting the annual revenue of individual plants by up to US$3.7 million (equivalent to US$13,000 MW-1 yr-1) but producing negligible gains in some settings. Consideration of wake steering’s geographic potential reveals divergent nationwide prospects for improved economics and siting flexibility.

deployment↗

DOE OSTI2021

Simple, low-cost and accurate data-driven geophysical forecasting with learned kernels

Modelling geophysical processes as low-dimensional dynamical systems and regressing their vector field from data is a promising approach for learning emulators of such systems. We show that when the kernel of these emulators is also learned from data (using kernel flows, a variant of cross-validation), then the resulting data-driven models are not only faster than equation-based models but are easier to train than neural networks such as the long short-term memory neural network. In addition, they are also more accurate and predictive than the latter. When trained on geophysical observational data, for example the weekly averaged global sea-surface temperature, considerable gains are also observed by the proposed technique in comparison with classical partial differential equation-based models in terms of forecast computational cost and accuracy. When trained on publicly available re-analysis data for the daily temperature of the North American continent, we observe significant improvements over classical baselines such as climatology and persistence-based forecast techniques. Although our experiments concern specific examples, the proposed approach is general, and our results support the viability of kernel methods (with learned kernels) for interpretable and computationally efficient geophysical forecasting for a large diversity of processes.

58 GEOSCIENCES↗

DOE OSTI2025

Wind Turbine Sound Setbacks and Supply Curves: Ordinances and Extrapolated Trends, 110 Hub Height, 130 Rotor Diameter

This dataset provides a comprehensive set of wind turbine sound setbacks from every residential structure in the contiguous United States (CONUS). A sound setback is defined as the minimum required distance between a residential structure and a hypothetical turbine installation site to ensure that modeled sound levels received at the residence do not exceed local sound ordinances, which are commonly expressed in A-weighted decibels (dBA). Therefore, sound setbacks are a local spatial assessment combining multiple factors, including the sound pressure curve as a function of the observer location (distance and direction) relative to the turbine, local sound regulations, and the geographical distribution of residential structures. The dataset is organized into multiple scenario-based products, detailed as follows: 1. Existing and extrapolated sound setbacks. An existing scenario characterizes sound setbacks only in states or counties that have implemented sound regulations as of 2022. The extrapolated scenarios extend a constant sound threshold to counties that lack explicit sound regulations, with thresholds ranging from 35 to 60 dBA, in 5-dBA increments reflecting the variation observed in current sound ordinances. 2. Sound setbacks in directional and worst scenarios. The directional scenario accounts for the distance and orientation of residential structures relative to a hypothetical turbine location, utilizing the turbine's sound emissions in that specific direction. In contrast, the worst scenario takes loudest sound level at each distance step from the turbine, irrespective of directional considerations, which aligns with current industry practice. 3. Supply curves for Open and Reference Access scenarios. This dataset includes supply curves generated by the reV model, which integrates each of the above sound setbacks into both Open and Reference siting scenarios. In addition, two Open and Reference baselines scenarios were included which do not consider sound setbacks for comparative analysis. All sound setback data are stored in TIF files, with partial maps of the data provided in PNG format. The values in the sound setback raster range from 0 to 1, representing the fraction of developable land within a 90 meter by 90 meter pixel due to sound ordinances. A value of 0 indicates areas where wind energy development is prohibited, while a value of 1 signifies areas fully permissible. The wind turbine parameters used in the sound modeling are based on the land-based turbine from International Energy Agency (IEA), featuring a rated electrical power of 3.4 MW, a rotor diameter of 130 meters, and a hub height of 110 meters. The atmospheric conditions, including wind speed/direction, turbulence, air temperature, relative humidity, and air pressure, that drive the sound generation are obtained from the WIND Toolkit dataset.

Array↗

DOE OSTI2022

Heuristic Computational Model for Predicting Lignin Solubility in Tailored Organic Solvents

Lignin is a random heteropolymer that has been extensively studied as a renewable source of aromatic precursors for high-value chemicals, biofuels, and bioplastics. A key challenge in lignin valorization is the structural and compositional heterogeneity of lignin feedstocks. Solvent-based approaches are commonly used to fractionate lignin to reduce this heterogeneity, but solvent selection can be challenging due to variability in lignin composition. In this work, we developed computational methods to predict good and poor organic solvents as a function of lignin composition. We analyzed 28 different linear pentamer structures, 18 from known libraries and 10 hypothetical polymers, and calculated their activity coefficients in 50 different organic solvents by using the conductor-like screening model for realistic solvents. We used these data to train a regression model that enabled the extensive investigation of the impact of solvent and monolignol compositions on predicted lignin solubility. The exhaustive exploration of solubility trends using model predictions revealed sets of solvents, identified using Kamlet–Taft parameters, that are predicted to promote lignin dissolution regardless of lignin composition. We further identified solvents expected to selectively isolate lignin fractions enriched in certain subunits. Furthermore, these results establish heuristic guidelines for solvent selection that can be used to tailor fractionation processes for lignin feedstocks of distinct composition or to design new processes that isolate fractions with higher proportions of selected subunits.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2025

Open-source generation of sigma profiles: impact of quantum chemistry and solvation treatment on machine learning performance

The combination of machine learning (ML) models with chemistry-related tasks requires the description of molecular structures in a machine-readable way. The nature of these so-called molecular descriptors has a direct and major impact on the performance of ML models and remains an open problem in the field. Structural descriptors like SMILES strings or molecular graphs lack size-independence and can be memory intensive. Machine-learned descriptors can be of low dimensionality and constant size but lack physical significance and human interpretability. Sigma profiles, which are unnormalized histograms of the surface charge distributions of solvated molecules, combine physical significance with low dimensionality and size-independence, making them a suitable candidate for a universal molecular descriptor. However, their widespread adoption in ML applications requires open access to sigma profile generation, which is currently not available. This work details the development of OpenSPGen – an open-source tool for generating sigma profiles. Also presented are studies on the effect of different settings on the efficacy of the generated sigma profiles at predicting thermophysical material properties when used as inputs to a Gaussian process as a simple surrogate ML model. We find that a higher level of theory does not translate to more accurate results. We also provide further recommendations for sigma profile calculation and use in ML models.

Salih, Fathya Y. M. [University of Notre Dame, IN ↗

DOE OSTI2026

Adaptive Computing and Multi-Fidelity Learning

We describe our ongoing research in adaptive computing. Our goal is to use a combination of low- and high-fidelity simulation models to enable computationally efficient optimization and uncertainty quantification. We develop optimization formulations that take into account the compute resources currently available, which act as a constraint with regards to the fidelity level simulation we can run while maximizing information gain. We will discuss a few application examples that can benefit from this approach, especially when considering challenges arising in scaling up experiments and simulations.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Modeling the effects of active wake mixing on wake behavior through large-scale coherent structures

The use of active wake mixing (AWM) to mitigate downstream turbine wakes has created new opportunities for reducing power losses in wind farms. However, many current analytical or semi-empirical wake models do not capture the flow instabilities that are excited through the blade pitch actuation. In this work, we develop a framework, which accounts for the impacts of the large-scale coherent structures and turbulence on the mean flow, for modeling AWM. The framework uses a triple-decomposition approach for the unsteady flow field and models the mean flow and fine-scale turbulence with a parabolized Reynolds-averaged Navier–Stokes (RANS) system. The wave components are modeled using a simplified spatial linear stability formulation that captures the growth and evolution of the coherent structures. Comparisons with high-fidelity large eddy simulations (LESs) of the turbine wakes showed that this framework was able to capture the additional wake mixing and faster wake recovery in the far-wake regions for both the pulse and helix AWM strategies with minimal computational expense. In the near-wake region, some differences are observed in both the RANS velocity profiles and initial growth of the large-scale structures, which may be due to some simplifying assumptions used in the model.

17 WIND ENERGY↗

DOE OSTI2022

Long-term missing value imputation for time series data using deep neural networks

We present an approach that uses a deep learning model, in particular, a MultiLayer Perceptron, for estimating the missing values of a variable in multivariate time series data. We focus on filling a long continuous gap (e.g., multiple months of missing daily observations) rather than on individual randomly missing observations. Our proposed gap filling algorithm uses an automated method for determining the optimal MLP model architecture, thus allowing for optimal prediction performance for the given time series. We tested our approach by filling gaps of various lengths (three months to three years) in three environmental datasets with different time series characteristics, namely daily groundwater levels, daily soil moisture, and hourly Net Ecosystem Exchange. We compared the accuracy of the gap-filled values obtained with our approach to the widely used R-based time series gap filling methods ImputeTS and mtsdi. The results indicate that using an MLP for filling a large gap leads to better results, especially when the data behave nonlinearly. Thus, our approach enables the use of datasets that have a large gap in one variable, which is common in many long-term environmental monitoring observations.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

The Impact of Sound Ordinances on the Land-Based Wind Technical Potential of the United States

The rapid rise of sound ordinances has affected wind energy siting across state, county and local jurisdictions. Quantifying this impact on wind energy potential is required for effective energy planning. However, complex turbine sound modelling combined with evolving policies have contributed to limited understanding of these policies' impact on national wind technical potential. Here we develop an approach to evaluate wind turbine sound profiles across the United States and calculate setback distances from residential structures to translate sound-related policies into spatial turbine siting criteria. Compared to a baseline scenario that ignores sound, we find an 8% reduction in wind energy capacity when accounting for existing sound ordinances. Further, extrapolating a 45-A-weighted decibel (dBA) limit nationwide shows a 29% decline, disproportionately taken from high-quality and low-cost wind capacity. This reveals sound ordinances as a major factor in determining wind technical potential that could challenge US decarbonization goals reliant on wind energy.

17 WIND ENERGY↗