Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Physics informed machine 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 397 records · Page 22
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Spatial Mapping of Riverbed Grain-Size Distribution Using Machine Learning

Recent alluvial sediments in riverbeds play a significant role in controlling hydrologic exchange flows (HEFs) in river systems. The alluvial layer is usually associated with strong heterogeneity in physical properties (e.g., permeability and hydraulic conductivity), which affects local HEFs and therefore biogeochemical processes. The spatial distribution of these physical properties needs to be determined to inform the numerical models used to reveal the realistic hydro-biogeochemical behaviors. Such information can be obtained based on the intrinsic link between sediment grain-size distribution and hydraulic properties where sediment texture information is available. However, grain-size measurements are usually spatially sparse and do not have adequate coverage and resolution, particularly for a relatively large domain such as the Hanford Reach of the Columbia River. In this paper, we adopted machine learning (ML) approaches for categorizing and mapping the spatial distributions of riverbed substrate grain size and filling in missing areas of substrate data using the ML models along the reach. Such ML models for substrate size mapping were trained at 13,372 locations using measured substrate sizes along with observed and simulated attributes, including bathymetric attributes (e.g., elevation, slope, and aspect ratio) from LIDAR and bathymetric surveys, and hydrodynamic properties (e.g., water depth, velocity, shear stress, and their statistical moments). An ensemble bagging-based ML technique, Random Forest, was adopted to identify the most influential factors as predictors to develop the predictive models with over-fitting issues addressed. The models were evaluated with respect to each individual substrate size class and the lumped group, and then used to generate the final substrate size maps covering all the grid cells in the numerical modeling domain.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Explicit physics-informed neural networks for nonlinear closure: The case of transport in tissues

In upscaling methods, closures for nonlinear problems present a well-known challenge. While a number of theoretical methods have been proposed for handling such closures, nonlinearities still remain a significant obstacle for many problems. In this work, we use a combination of formal upscaling and data-driven machine learning for explicitly closing a nonlinear transport and reaction process in multiscale tissues. The classical effectiveness factor model is used to formulate the macroscale reaction kinetics. We train a multilayer perceptron network using training data generated by direct numerical simulations over microscale examples. Once trained, the network is used in an algorithm for numerically solving the upscaled (coarse-grained) differential equation describing mass transport and reaction in two example tissues. The network is described as being explicit in the sense that the network is trained using macroscale concentrations and gradients of concentration as components of the feature space rather than incorporating them as part of a constraint in the optimization process. Network training and solutions to the macroscale transport equations were computed for two different tissues. The two tissue types (brain and liver) exhibit markedly different geometrical complexity and spatial scale (cell size and sample size). The upscaled solutions for the average concentration are compared with numerical solutions derived from the microscale concentration fields by a posteriori averaging. There are three outcomes of this work of particular note. 1) Our overall approach results in an upscaled nonlinear PDE. The PDE is closed using a neural network, and our approach results in the definition of the classical effectiveness factor for effecting closure. 2) We identify particular source terms for the closure problem that are important for representing the structure of the closure. These source terms involve macroscale concentrations and their gradients. We adopt these source terms to use as explicit features in the learning algorithm. We find the trained networks that include the macroscale source terms generate models that are able to predict the correction factor with increased fidelity over those that do not. 3) We find that the trained network exhibits good generalizability, and it is able to predict the effectiveness factor with high fidelity for realistically-structured tissues despite the significantly different scale and geometrical complexity of the two example tissue types. This latter result emphasizes our purposeful connection between conventional averaging methods with the use of machine learning for closure; this contrasts with some machine learning methods for upscaling where the exact form of the macroscale equation remains unknown.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

E-PINNs: Epistemic Physics-Informed Neural Networks

Physics-informed neural networks (PINNs) have demonstrated promise as a framework for solving forward and inverse problems involving partial differential equations. Despite recent progress in the field, it remains challenging to quantify uncertainty in these networks. While techniques such as Bayesian PINNs (B-PINNs) provide a principled approach to capturing epistemic uncertainty through Bayesian inference, they can be computationally expensive for large-scale applications. In this work, we propose Epistemic Physics-Informed Neural Networks (E-PINNs), a framework that uses a small network, the epinet, to efficiently quantify epistemic uncertainty in PINNs. The proposed approach works as an add-on to existing, pre-trained PINNs with a small computational overhead. We demonstrate the applicability of the proposed framework in various test cases and compare the results with B-PINNs using Hamiltonian Monte Carlo (HMC) posterior estimation and dropout-equipped PINNs (Dropout-PINNs). In our experiments, E-PINNs achieve calibrated coverage with competitive sharpness at substantially lower cost. We demonstrate that when B-PINNs produce narrower bands, they under-cover in our tests. E-PINNs also show better calibration than Dropout-PINNs in these examples, indicating a favorable accuracy-efficiency trade-off.

AI for Science↗
DOE OSTI2026

Understanding and Predicting Pedestal Scenarios on NSTX-U (Final Technical Report)

This project investigated gyrokinetic instabilities in the NSTX pedestal, identified the major transport mechanisms (some of them novel) in the NSTX pedestal, and developed and validated a predictive modeling capability for pedestal transport in spherical tokamaks, with particular emphasis on NSTX discharges. The work combined first-principles gyrokinetic simulations, reduced transport models, integrated transport calculations with ASTRA, and exploratory machine learning tools. The central outcome is a practical modeling capability for pedestal temperature profiles based on reduced models informed and constrained by gyrokinetic physics.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2025

FM4NPP: A Scaling Foundation Model for Nuclear and Particle Physics

Large language models have revolutionized artificial intelligence by enabling large, generalizable models trained through self-supervision. This paradigm has inspired the development of scientific foundation models (FMs). However, applying this capability to experimental particle physics is challenging due to the sparse, spatially distributed nature of detector data, which differs dramatically from natural language. This work addresses if an FM for particle physics can scale and generalize across diverse tasks. We introduce a new dataset with more than 11 million particle collision events and a suite of downstream tasks and labeled data for evaluation. We propose a novel self-supervised training method for detector data and demonstrate its neural scalability with models that feature up to 188 million parameters. With frozen weights and task-specific adapters, this FM consistently outperforms baseline models across all downstream tasks. The performance also exhibits robust data-efficient adaptation. Further analysis reveals that the representations extracted by the FM are task-agnostic but can be specialized via a single linear mapping for different downstream tasks.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Improving Grid Awareness by Empowering Utilities with Machine Learning and Artificial Intelligence

Gap filling time series data typically depends on linear interpolation. More recently gap filling advancements include machine learning techniques. However, none leverage advanced learning approach that uses cohort training or a neighborhood informed approach, which is described in this report. The report also describes a physics informed approach using Reduced Order Models (ROM). There are several methods to capture the nature of the detailed system in aggregated models, however there is a trade-off for these methods developed for multiple applications. These methods have specific requirements and applications that includes consideration of dynamics or covering a larger range of operating conditions, etc. The various methods of aggregation are: 1) Thevenin equivalents for downstream networks 2) Equivalent feeder representation to capture downstream network losses accurately 3) Structured reduced order models for dynamics 4) System identification-based ROM (abstract dynamical model) Methods described in items 1 and 2 above are ideal for steady-state models and useful for this application. Of these two methods, based on the data availability, the targeted application, the reduced order model that is proposed to be developed is the equivalent feeder model representation. This includes a structure of the reduced order model whose parameters can be determined by the system load and losses with the meter measurements.

14 SOLAR ENERGY↗
DOE OSTI2025

hls4ml: A Flexible, Open-Source Platform for Deep Learning Acceleration on Reconfigurable Hardware

We present hls4ml, a free and open-source platform that translates machine learning (ML) models from modern deep learning frameworks into high-level synthesis (HLS) code that can be integrated into full designs for field-programmable gate arrays (FPGAs) or application-specific integrated circuits (ASICs). With its flexible and modular design, hls4ml supports a large number of deep learning frameworks and can target HLS compilers from several vendors, including Vitis HLS, Intel oneAPI and Catapult HLS. Together with a wider eco-system for software-hardware co-design, hls4ml has enabled the acceleration of ML inference in a wide range of commercial and scientific applications where low latency, resource usage, and power consumption are critical. In this paper, we describe the structure and functionality of the hls4ml platform. The overarching design considerations for the generated HLS code are discussed, together with selected performance results.

FOS: Computer and information sciences↗
DOE OSTI2025

Machine learning guided selection of broad-spectrum epitope-specific functional antibodies for "Disease X"

Our project established and demonstrated a transfer learning framework that enables prediction of antibody–antigen interactions across related viruses. The approach focused on three major activities: 1. Conserved region and epitope identification – We compared viral protein structures and sequences to identify shared receptor-binding domains and neutralizing epitope regions across variants and related viruses. These conserved features formed the foundation for discovering broadly functional antibodies. 2. Machine learning model development – We built neural network–based models that integrate epitope features with antibody sequence information. Instead of relying solely on structural or physical properties, the models learned transferable patterns that describe antibody binding potential across different viral families. 3. Transfer learning and validation – Using SARS-CoV-2 and Ebola as source systems, we successfully transferred learned epitope features to predict antibody interactions for SARS CoV-1 and Marburg virus. Iterative cycles of dataset generation, retraining, and evaluation improved generalization and predictive power, ensuring the framework can adapt to new threats.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Deconvoluting thermomechanical effects in X-ray diffraction data using machine learning

X-ray diffraction is ideal for probing the sub-surface state during complex or rapid thermomechanical loading of crystalline materials. However, challenges arise as the size of diffraction volumes increases due to spatial broadening and because of the inability to deconvolute the effects of different lattice deformation mechanisms. Here, we present a novel approach that uses combinations of physics-based modeling and machine learning to deconvolve thermal and mechanical elastic strains for diffraction data analysis. The method builds on a previous effort to extract thermal strain distribution information from diffraction data. The new approach is applied to extract the evolution of the thermomechanical state during laser melting of an Inconel 625 wall specimen which produces significant residual stress upon cooling. A combination of heat transfer and fluid flow, elasto-plasticity and X-ray diffraction simulations is used to generate training data for machine-learning (Gaussian process regression, GPR) models that map diffracted intensity distributions to underlying thermomechanical strain fields. First-principles density functional theory is used to determine accurate temperature-dependent thermal expansion and elastic stiffness used for elasto-plasticity modeling. The trained GPR models are found to be capable of deconvoluting the effects of thermal and mechanical strains, in addition to providing information about underlying strain distributions, even from complex diffraction patterns with irregularly shaped peaks.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Understanding the Effect of Sample Geometry on Temperature Distribution during Optical Floating Zone Crystal Growth in Vacuum Environment through Heat Transfer Modeling

Optical floating zone furnaces (OFZ) have had a transformative impact on fundamental science due to their ability to rapidly produce large single crystals of a wide variety of complex materials. However, a quantitative understanding of the OFZ growth environment is generally lacking due to the difficulty of measuring the local sample temperatures during OFZ growth, as well as to the general lack of information about the temperature-dependent physical parameters needed to model heat transfer. To overcome these challenges, we apply a physics-based heat transfer model, parametrized by measurements from synchrotron experiments and a machine-learning (ML) algorithm, to simulate the temperature distributions of samples heated in an OFZ furnace in a vacuum environment. This model is used to quantitatively understand how the sample maximum temperature and temperature gradient (key parameters that influence the success of crystal growth) are affected by the rod size, rod shape, and heat-zone position on the rod. The results of this study can be applied to make informed decisions on how crystal growth parameters can be tuned to modify temperature profiles and to optimize crystal growth outcomes even when data on internal sample temperature profiles (e.g., those obtained through in situ synchrotron experiments) are not accessible.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Constraining the Higgs potential with neural simulation-based inference for di-Higgs production

Determining the form of the Higgs potential is one of the most exciting challenges of modern particle physics. Higgs pair production directly probes the Higgs self-coupling and should be observed in the near future at the High-Luminosity LHC. We explore how to improve the sensitivity to physics beyond the Standard Model through per-event kinematics for di-Higgs events. In particular, we employ machine learning through simulation-based inference to estimate per-event likelihood ratios and gauge potential sensitivity gains from including this kinematic information. In terms of the Standard Model Effective Field Theory, we find that adding a limited number of observables can help to remove degeneracies in Wilson coefficient likelihoods and significantly improve the experimental sensitivity.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

Estimating building occupancy: a machine learning system for day, night, and episodic events

Building occupancy research increasingly emphasizes understanding the social and physical dynamics of how people occupy space. Opportunities in the open source domain including social media, Volunteered Geographic Information, crowdsourcing, and sensor data have proliferated, resulting in the exploration of building occupancy dynamics at varying spatiotemporal scales. At Oak Ridge National Laboratory, research into building occupancies through the development of a global learning framework that accommodates exploitation of open source authoritative sources, including governmental census and surveys, journal articles, real estate databases, and more, to report national and subnational building occupancies across the world continues through the Population Density Tables (PDT) project. This probabilistic learning system accommodates expert knowledge, experience, and open-source data to capture local, socioeconomic, and cultural information about human activity. It does so through a systematic process of data harmonization techniques in the development of observation models for over 50 building types to dynamically update baseline estimates and report probabilistic diurnal and episodic building occupancy estimates. This discussion will explore how PDT is implemented at scale and expanded based on the development of observation model classes and will explain how to interpret and spatially apply the reported probability occupancy estimates and uncertainty.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2022

LANL Activities on Mechanistic Approach to Analyzing and Improving Unconventional Hydrocarbon Production

Hydrocarbon production from shale reservoirs is inherently inefficient and challenging since these are low permeability plays. In addition, there is a limited understanding of the fundamentals and the controlling mechanisms, further complicating how to optimize these plays. Herein, we summarize our experimental and computational efforts fully and partially supported by the fundamental shale portfolio to reveal unconventional shale fundamentals and devise development strategies to enhance extraction efficiency with a minimal environmental footprint. Integrating these fundamentals with machine learning, we outline a pathway to improve the predictive power of our models, which enhances the forecast quality of production, thereby improving the economics of operations in unconventional reservoirs. For instance, we have developed science informed workflows and platforms for optimizing pressure-drawdown at a site, which allow operators to make reservoir-management decisions that optimize recovery in consideration of future production. Recently, our work relies on the hybridization of physics-based prediction and machine learning, whereby accurate synthetic data (combined with available site data) can enable the application of machine learning methods for rapid forecasting and optimization. Consequently, the workflow and platform are readily extendable to operations at other sites, plays, and basins.

04 OIL SHALES AND TAR SANDS↗
DOE OSTI2024

Prediction of the Cu Oxidation State from EELS and XAS Spectra Using Supervised Machine Learning

Electron energy loss spectroscopy (EELS) and X-ray absorption spectroscopy (XAS) provide detailed information about distributions and locations of atoms, their coordination numbers and oxidation states, and the bonding characteristics [1]. However, analysis of XAS/EELS data often relies on matching the spectra of an unknown experimental sample to a series of simulated or experimental spectra of standard samples. Here, this limits analysis throughput and the ability to extract quantitative information from a sample.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

Science-informed Machine Learning to Increase Recovery Efficiency in Unconventional Reservoirs

Production of hydrocarbons from fractured, unconventional reservoirs is inherently inefficient. But machine learning offers a pathway both to increasing recovery efficiency at a site and to improving forecasts of production, thereby improving the economics of operations in unconventional reservoirs. Los Alamos—in partnership with DOE, NETL, and WVU—has been developing a science-informed workflow and platform for optimizing pressure-drawdown at a site, which will allow an operator to make reservoir-management decisions that optimize recovery in consideration of future production. This work relies on a hybridization of physics-based prediction and machine learning, whereby accurate synthetic data (in combination with available site data) can enable the application of machine learning methods for rapid forecasting and optimization. The physics-based prediction is built upon experimental and theoretical work to determine transport characteristics in shale at various scales, with an emphasis on materials from MSEEL-I; this fundamental shale R&D was conducted in partnership with DOE, NETL, and several other national labs. This work has resulted from a coordinated leveraging of developments across several projects within DOE FE30, along with internal investments from Los Alamos via LDRD. The development has utilized data from the MSEEL–I site for calibration and demonstration; however, the workflow and platform are readily extendable to operations at other sites, plays, and basins. This machine-learning method can aid operators to improve both recovery efficiency and competitiveness; to this end, future work would quantify processes for other plays/basins and integrate production details with economics.

04 OIL SHALES AND TAR SANDS↗
DOE OSTI2023

Data compression and inference in cosmology with self-supervised machine learning

ABSTRACT The influx of massive amounts of data from current and upcoming cosmological surveys necessitates compression schemes that can efficiently summarize the data with minimal loss of information. We introduce a method that leverages the paradigm of self-supervised machine learning in a novel manner to construct representative summaries of massive data sets using simulation-based augmentations. Deploying the method on hydrodynamical cosmological simulations, we show that it can deliver highly informative summaries, which can be used for a variety of downstream tasks, including precise and accurate parameter inference. We demonstrate how this paradigm can be used to construct summary representations that are insensitive to prescribed systematic effects, such as the influence of baryonic physics. Our results indicate that self-supervised machine learning techniques offer a promising new approach for compression of cosmological data as well as its analysis.

Astronomy & Astrophysics↗
DOE OSTI2023

Field evaluation of semi‐automated moisture estimation from geophysics using machine learning

Geophysical methods can provide three-dimensional (3D), spatially continuous estimates of soil moisture. However, point-to-point comparisons of geophysical properties to measure soil moisture data are frequently unsatisfactory, resulting in geophysics being used for qualitative purposes only. This is because (1) geophysics requires models that relate geophysical signals to soil moisture, (2) geophysical methods have potential uncertainties resulting from smoothing and artifacts introduced from processing and inversion, and (3) results from multiple geophysical methods are not easily combined within a single soil moisture estimation framework. To investigate these potential limitations, an irrigation experiment was performed wherein soil moisture was monitored through time, and several surface geophysical datasets indirectly sensitive to soil moisture were collected before and after irrigation: ground penetrating radar, electrical resistivity tomography (ERT), and frequency domain electromagnetics (FDEM). Data were exported in both raw and processed form, and then snapped to a common 3D grid to facilitate moisture prediction by standard calibration techniques, multivariate regression, and machine learning. A combination of inverted ERT data, raw FDEM, and inverted FDEM data was most informative for predicting soil moisture using a random regression forest model (one-thousand 60/40 training/test cross-validation folds produced root mean squared errors ranging from 0.025–0.046 cm 3 /cm 3 ). This cross-validated model was further supported by a separate evaluation using a test set from a physically separate portion of the study area. Machine learning was conducive to a semi-automated model-selection process that could be used for other sites and datasets to locally improve accuracy.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

MLPF: efficient machine-learned particle-flow reconstruction using graph neural networks

In general-purpose particle detectors, the particle-flow algorithm may be used to reconstruct a comprehensive particle-level view of the event by combining information from the calorimeters and the trackers, significantly improving the detector resolution for jets and the missing transverse momentum. In view of the planned high-luminosity upgrade of the CERN Large Hadron Collider (LHC), it is necessary to revisit existing reconstruction algorithms and ensure that both the physics and computational performance are sufficient in an environment with many simultaneous proton–proton interactions (pileup). Machine learning may offer a prospect for computationally efficient event reconstruction that is well-suited to heterogeneous computing platforms, while significantly improving the reconstruction quality over rule-based algorithms for granular detectors. We introduce MLPF, a novel, end-to-end trainable, machine-learned particle-flow algorithm based on parallelizable, computationally efficient, and scalable graph neural network optimized using a multi-task objective on simulated events. We report the physics and computational performance of the MLPF algorithm on a Monte Carlo dataset of top quark–antiquark pairs produced in proton–proton collisions in conditions similar to those expected for the high-luminosity LHC. The MLPF algorithm improves the physics response with respect to a rule-based benchmark algorithm and demonstrates computationally scalable particle-flow reconstruction in a high-pileup environment.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗