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 217 records · Page 12
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

PINN surrogate of Li-ion battery models for parameter inference, Part II: Regularization and application of the pseudo-2D model

Bayesian parameter inference is useful to improve Li-ion battery diagnostics and can help formulate battery aging models. However, it is computationally intensive and cannot be easily repeated for multiple cycles, multiple operating conditions, or multiple replicate cells. To reduce the computational cost of Bayesian calibration, numerical solvers for physics-based models can be replaced with faster surrogates. A physics-informed neural network (PINN) is developed as a surrogate for the pseudo-2D (P2D) battery model calibration. For the P2D surrogate, additional training regularization was needed as compared to the PINN single-particle model (SPM) developed in Part I. Both the PINN SPM and P2D surrogate models are exercised for parameter inference and compared to data obtained from a direct numerical solution of the governing equations. A parameter inference study highlights the ability to use these PINNs to calibrate scaling parameters for the cathode Li diffusion and the anode exchange current density. By realizing computational speed-ups of ~2250x for the P2D model, as compared to using standard integrating methods, the PINN surrogates enable rapid state-of-health diagnostics. Finally, in the low-data availability scenario, the testing error was estimated to ~2 mV for the SPM surrogate and ~10 mV for the P2D surrogate which could be mitigated with additional data.

25 ENERGY STORAGE↗
DOE OSTI2024

PINN surrogate of Li-ion battery models for parameter inference, Part I: Implementation and multi-fidelity hierarchies for the single-particle model

To plan and optimize energy storage demands that account for Li-ion battery aging dynamics, techniques need to be developed to diagnose battery internal states accurately and rapidly. Here, this study seeks to reduce the computational resources needed to determine a battery's internal states by replacing physics-based Li-ion battery models - such as the single-particle model (SPM) and the pseudo-2D (P2D) model - with a physics-informed neural network (PINN) surrogate. The surrogate model makes high-throughput techniques, such as Bayesian calibration, tractable to determine battery internal parameters from voltage responses. This manuscript is the first of a two-part series that introduces PINN surrogates of Li-ion battery models for parameter inference (i.e., state-of-health diagnostics). In this first part, a method is presented for constructing a PINN surrogate of the SPM. A multi-fidelity hierarchical training, where several neural nets are trained with multiple physics-loss fidelities is shown to significantly improve the surrogate accuracy when only training on the governing equation residuals. The implementation is made available in a companion repository (https://github.com/NREL/PINNSTRIPES). The techniques used to develop a PINN surrogate of the SPM are extended in Part II for the PINN surrogate for the P2D battery model, and explore the Bayesian calibration capabilities of both surrogates.

25 ENERGY STORAGE↗
DOE OSTI2026

An interactive machine learning platform for analyzing multi-particle coincidence data from cold target recoil ion momentum spectroscopy

We present SCULPT (Supervised Clustering and Uncovering Latent Patterns with Training), a comprehensive software platform for analyzing tabulated high-dimensional multi-particle coincidence data from Cold Target Recoil Ion Momentum Spectroscopy (COLTRIMS) experiments. The software addresses critical challenges in modern momentum spectroscopy by integrating advanced machine learning techniques with physics-informed analysis in an interactive web-based environment. SCULPT implements uniform manifold approximation and projection for non-linear dimensionality reduction to reveal correlations in high-dimensional data. We also discuss potential extensions to deep autoencoders for feature learning and genetic programming for automated discovery of physically meaningful observables. A novel adaptive confidence scoring system provides quantitative reliability assessments by evaluating user-selected clustering quality metrics with predefined weights that reflect each metric’s robustness. The platform features configurable molecular profiles for different experimental systems, interactive visualization with selection tools, and comprehensive data filtering capabilities. Utilizing a subset of SCULPT’s capabilities, we analyze photo-double-ionization data measured using the COLTRIMS method for three-body dissociation of the D 2 O molecule, revealing distinct fragmentation channels and their correlations with physics parameters. The software’s modular architecture and web-based implementation make it accessible to the broader atomic and molecular physics community, significantly reducing the time required for complex multi-dimensional analyses. This opens the door to finding and isolating rare events exhibiting non-linear correlations on the fly during experimental measurements, which can help steer exploration and improve the efficiency of experiments.

Artificial neural networks↗
DOE OSTI2021

Gaussian process regression constrained by boundary value problems

We develop a framework for Gaussian processes regression constrained by boundary value problems. The framework may be applied to infer the solution of a well-posed boundary value problem with a known second-order differential operator and boundary conditions, but for which only scattered observations of the source term are available. Scattered observations of the solution may also be used in the regression. The framework combines co-kriging with the linear transformation of a Gaussian process together with the use of kernels given by spectral expansions in eigenfunctions of the boundary value problem. Furthermore, it benefits from a reduced-rank property of covariance matrices. We demonstrate that the resulting framework yields more accurate and stable solution inference as compared to physics-informed Gaussian process regression without boundary condition constraints.

42 ENGINEERING↗
DOE OSTI2025

Scaling Field-Theoretic Simulation for Multicomponent Mixtures with Neural Operators

Multicomponent polymer mixtures are ubiquitous in biological self-organization but are notoriously difficult to study computationally. Plagued by both slow single molecule relaxation times and slow equilibration within dense mixtures, molecular dynamics simulations are typically infeasible at the spatial scales required to study the stability of mesophase structure. Polymer field theories offer an attractive alternative, but analytical calculations are only tractable for mean-field theories and nearby perturbations, constraints that become especially problematic for fluctuation-induced effects such as coacervation. Here, we show that a recently developed technique for obtaining numerical solutions to partial differential equations based on operator learning, neural operators, lends itself to a highly scalable training strategy by parallelizing per-species operator maps. We illustrate the efficacy of our approach on six-component mixtures with randomly selected compositions and that it significantly outperforms the state-of-the-art pseudospectral integrators for field-theoretic simulations, especially as polymer lengths become long.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2021

When and why PINNs fail to train: A neural tangent kernel perspective

Physics-informed neural networks (PINNs) have lately received great attention thanks to their flexibility in tackling a wide range of forward and inverse problems involving partial differential equations. However, despite their noticeable empirical success, little is known about how such constrained neural networks behave during their training via gradient descent. More importantly, even less is known about why such models sometimes fail to train at all. Here in this work, we aim to investigate these questions through the lens of the Neural Tangent Kernel (NTK); a kernel that captures the behavior of fully-connected neural networks in the infinite width limit during training via gradient descent. Specifically, we derive the NTK of PINNs and prove that, under appropriate conditions, it converges to a deterministic kernel that stays constant during training in the infinite-width limit. This allows us to analyze the training dynamics of PINNs through the lens of their limiting NTK and find a remarkable discrepancy in the convergence rate of the different loss components contributing to the total training error. To address this fundamental pathology, we propose a novel gradient descent algorithm that utilizes the eigenvalues of the NTK to adaptively calibrate the convergence rate of the total training error. Finally, we perform a series of numerical experiments to verify the correctness of our theory and the practical effectiveness of the proposed algorithms.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2025

Optimizing the optimizer for physics-informed neural networks and Kolmogorov-Arnold networks

Physics-Informed Neural Networks (PINNs) have revolutionized the computation of PDE solutions by integrating partial differential equations (PDEs) into the neural network’s training process as soft constraints, becoming an important component of the scientific machine learning (SciML) ecosystem. More recently, physics-informed Kolmogorv-Arnold networks (PIKANs) have also shown to be effective and comparable in accuracy with PINNs. In their current implementation, both PINNs and PIKANs are mainly optimized using first-order methods like Adam, as well as quasi-Newton methods such as BFGS and its low-memory variant, L-BFGS. However, these optimizers often struggle with highly nonlinear and non-convex loss landscapes, leading to challenges such as slow convergence, local minima entrapment, and (non)degenerate saddle points. In this study, we investigate the performance of Self- Scaled BFGS (SSBFGS), Self-Scaled Broyden (SSBroyden) methods and other advanced quasi-Newton schemes, including BFGS and L-BFGS with different line search strategies. These methods dynamically rescale updates based on historical gradient information, thus enhancing training efficiency and accuracy. We systematically compare these optimizers – using both PINNs and PIKANs – on key challenging PDEs, including the Burgers, Allen-Cahn, Kuramoto-Sivashinsky, Ginzburg-Landau, and Stokes equations. Additionally, we evaluate the performance of SSBFGS and SSBroyden for Deep Operator Network (DeepONet) architectures, demonstrating their effectiveness for data-driven operator learning. Our findings provide state-of-the-art results with orders-of-magnitude accuracy improvements without the use of adaptive weights or any other enhancements typically employed in PINNs. More broadly, our work reveal insights into the effectiveness of quasi-Newton optimization strategies in significantly improving the convergence and accurate generalization of PINNs and PIKANs.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Stacked networks improve physics-informed training: Applications to neural networks and deep operator networks

Physics-informed neural networks and operator networks have shown promise for effectively solving equations modeling physical systems. However, these networks can happen to be difficult or impossible to train accurately. Here, we present a novel multifidelity framework for stacking physics-informed neural networks and operator networks that facilitates training. We successively build a chain of networks, where the output at one step can act as a low-fidelity input for training a longer chain, gradually increasing the expressivity of the learnt model. The equations imposed at each step of the iterative process can be the same or different (akin to simulated annealing). The iterative (stacking) nature of the proposed method allows us to learn progressively features of a solution which could have been hard to learn directly. Through benchmark problems including a nonlinear pendulum, the wave equation, and the viscous Burgers equation, we show how stacking can be used to improve the accuracy and reduce the required size of physics-informed neural networks and operator networks.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Characterizing possible failure modes in physics-informed neural networks (characterizing-pinns-failure-modes) v0.1.0

This software provides an implementation of the physics-informed neural network setup for different differential equations. It provides a way to solve differential equations using machine learning, via a physical constraint term in the loss function. Physics-informed neural networks are a popular approach, but here, the failures of such an approach are characterized and better solutions and training procedures are provided.

Krishnapriyan, Aditi↗
DOE OSTI2023

The Feasibility of Incorporating a 3D Velocity Model Into Earthquake Location Around Salt Lake City, UT Using a Physics Informed Neural Network

Earthquake location algorithms typically require travel time calculation. Doing this calculation in 3D, despite advances in algorithm efficiency and computational power, can still be prohibitively expensive in terms of resources and storage. Implementation of high-resolution 3D models in routine earthquake location would be a significant step forward in most of the world. Machine learning algorithms have potential to act as substitutes for travel time calculation algorithms or stored travel time tables. We investigate EikoNet - a physics informed neural network machine learning model that estimates travel times very quickly and comes with negligible memory-overhead. Specifically, we apply EikoNet to the Wasatch Fault Community Velocity Model (WFCVM), a highly detailed and complex 3D velocity model of the Salt Lake City, UT region. While routine locations in the area and studies of the 2020 Magna, UT earthquake sequence used a 1D velocity model, a 3D model may help better our understanding the structure of the major fault in the region. Our primary goal was to test the speed, memory requirements, and accuracy of EikoNet compared to a reference eikonal solver. We find that while the EikoNet is exceedingly fast and requires little memory overhead, achieving acceptable accuracy in estimated travel times is difficult and requires extensive computational resources.

58 GEOSCIENCES↗
DOE OSTI2024

Communication Network Layer State Estimation Measurement Model for a Cyber-Secure Smart Grid

Network communication has been proven to be a very important tool and a key factor in the recent development and progress of the power grid operation. It is also considered as the foundation for the smart grid because information and communication are integrated into electricity distribution to achieve reliable and accurate knowledge of the power grid. In previous years, absorbing energy from substations and delivering it to customers was the only type of interaction we knew between utility companies and customers. Presently, the growing connections of small distributed generation units caused by the cost reduction of most of the technologies used in generation and storage of electrical energy, along with the potential benefits of renewable energy have pushed many researchers to look into the improvement of information and communication technologies (ICT) in order to ensure a bidirectional flow of power and data. Moreover, the evolution of information and communication technologies and its applications to smart grid have converted the smart grid into a cyber-physical system where vulnerabilities and additional security challenges such as cyber-threats and cyber-attacks have emerged. Previously, we have demonstrated that using machine learning-based processing on data gathered from communication networks and the power grid was a promising solution for detecting cyber threats by implementing a co-simulation of cyber-security for cross-layer strategy. Since the majority of the challenges observed can only be solved in the network communication layer, we present in this work a physics-based state estimation model of the communication network system towards enhanced cyber-physical security of the smart grid. Information integration with the previously developed machine learning model is developed, providing a enhanced cyber-physical security application for the smart grid. Easy-to-implement model, without hard-to-derive parameters, highlight potential aspects of the model for real-life applications.

Mathieu, Reynold↗
DOE OSTI2021

Scalable Technologies Achieving Risk-Informed Condition-Based Predictive Maintenance Enhancing the Economic Performance of Operating Nuclear Power Plants

The primary objective of the research presented in this report is to develop scalable technologies that are deployable across plant assets and across the nuclear fleet to achieve risk-informed predictive maintenance (PdM) strategies at commercial nuclear power plants (NPPs). Over the years, the nuclear fleet has relied on labor-intensive and time-consuming preventive maintenance (PM) programs, driving up operation and maintenance (O&M) costs to achieve high capacity factors. A well-constructed risk-informed PdM approach for an identified plant asset has been developed in this research, taking advantage of advancements in data analytics, machine learning (ML), artificial intelligence (AI), physics-informed modeling, and visualization. These technologies would allow commercial NPPs to reliably transition from current labor-intensive PM programs to a technology driven PdM program, eliminating unnecessary O&M costs. The work presented in the report is being developed as part of a collaborative research effort between Idaho National Laboratory and Public Service Enterprise Group Nuclear, LLC. This report (1) reflects the results of work by LWRS Program researchers with PSEG, Nuclear LLC-owned Salem and Hope Creek Nuclear Power Plants; (2) presents utilization of circulating water system (CWS) heterogeneous data and fault modes from both the Salem and Hope Creek nuclear power plant sites to develop salient fault signatures associated with each fault mode; (3) describes the integration of component-level predictive models into a robust system-level model enabled by the federated-transfer learning; (4) describes the development of physics-informed model of circulating water pump and motor; (5) develops a scalable risk and economic model; and (6) outlines the development of a user-centric visualization application. The outcomes presented in this report lays the foundation and provides a much-needed technical basis to focus on explainability and trustworthiness of ML and AI-based technologies, as part of future research.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2023

Data-driven prediction of the output composition of an atmospheric pressure plasma jet

Cold atmospheric plasma (CAP) in open air hosts numerous chemical species engaged in thousands of chemical reactions. Comprehensive diagnosis of its chemical composition is important across various fields from medicine, where reactive oxygen and nitrogen play key roles, to surface modification. In applications, a centimeter-scale helium–air jet operates for minutes, featuring micrometer-sized streamers and an atmospheric pressure-induced collision frequency in the hundreds of GHz range. To address this intricate multi-scale issue, we introduce a machine learning approach: using a physics-informed neural network (PINN) to tackle the multi-scale complexities inherent in predicting the complete list of species concentrations, gas temperature, and electron temperature of a CAP jet supplied with a mixture of helium and air. Experimental measurements of O 3 , N 2 O, and NO 2 concentrations downstream of the plasma jet, combined with fundamental physics laws, the conservation of mass and charge, constrain the PINN, enabling it to predict the concentrations of all species that are not available from the experiment, along with gas and electron temperatures. The results, therefore, obey all the physical laws we provided and can have a chemical balance with the measured concentrations. In conclusion, this methodology holds promise for describing and potentially regulating complex systems with limited experimental datasets.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2025

Resolving turbulent magnetohydrodynamics: a hybrid operator-diffusion framework

We present a hybrid machine learning framework that combines physics-informed neural operators (PINOs) with score-based generative diffusion models to simulate the full spatio-temporal evolution of two-dimensional, incompressible, resistive magnetohydrodynamic turbulence across a broad range of Reynolds numbers (Re). The framework leverages the equation-constrained generalization capabilities of PINOs to predict coherent, low-frequency dynamics, while a conditional diffusion model stochastically corrects high-frequency residuals, enabling accurate modeling of fully developed turbulence. Trained on a comprehensive ensemble of high-fidelity simulations with Re ϵ {100, 250, 500, 750, 1000, 3000, 10000}, the approach achieves state-of-the-art accuracy in regimes previously inaccessible to deterministic surrogates. At Re = 1000 and 3000, the model faithfully reconstructs the full spectral energy distributions of both velocity and magnetic fields late into the simulation, capturing non-Gaussian statistics, intermittent structures, and cross-field correlations with high fidelity. At extreme turbulence levels (Re = 10 000), it remains the first surrogate capable of recovering the high-wavenumber evolution of the magnetic field, preserving large-scale morphology and enabling statistically meaningful predictions.

Diffusion-Integrated Neural Operators↗
DOE OSTI2023

Crustal Scale Travel Time Prediction with the SALSA3D Framework and Machine Learning

The SALSA3D project aims to improve our models used in travel time prediction. The current version uses tomographic modeling for propagation through the Earth’s mantle because of the large number (order of millions) of observations of seismic phases which primarily traverse the Earth’s mantle and the ability to pose the travel time problem as a set of linear equations. However, all seismic rays traverse the crust to reach receivers at the surface and therefore models of propagation through the crust are required. Therefore, the primary motivation for this study is to explore how to increase the scope of the SALSA3D project to phases which travel primarily through the crust. In this report, we evaluate new, machine learning based and physics-based methods to model these travel times for integration into the SALSA3D framework. Our results suggest that using our existing physics-based travel time tomography method is a viable approach for the regional to global scale, but better predictive capabilities can be achieved through a neural network trained on the region of interest for near-regional offsets. We suggest future iterations of SALSA3D should incorporate machine learning tools such as Physics-Informed Neural Networks or Bayesian Neural Networks.

58 GEOSCIENCES↗
DOE OSTI2021

Toward Urban Water Security: Broadening the Use of Machine Learning Methods for Mitigating Urban Water Hazards

Due to the complex interactions of human activity and the hydrological cycle, achieving urban water security requires comprehensive planning processes that address urban water hazards using a holistic approach. However, the effective implementation of such an approach requires the collection and curation of large amounts of disparate data, and reliable methods for modeling processes that may be co-evolutionary yet traditionally represented in non-integrable ways. In recent decades, many hydrological studies have utilized advanced machine learning and information technologies to approximate and predict physical processes, yet none have synthesized these methods into a comprehensive urban water security plan. In this paper, we review ways in which advanced machine learning techniques have been applied to specific aspects of the hydrological cycle and discuss their potential applications for addressing challenges in mitigating multiple water hazards over urban areas. We also describe a vision that integrates these machine learning applications into a comprehensive watershed-to-community planning workflow for smart-cities management of urban water resources.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Snow distribution patterns revisited: A physics-based and machine learning hybrid approach to snow distribution mapping in the sub-Arctic Supporting Data

Snow in the Arctic and sub-Arctic is highly variable at fine scales, with deep drifts and shallow scoured areas creating a complex pattern of snow on the landscape. This fine-scale variation in snow is driven primarily by landscape and vegetation properties. Some landscape features, such as river beds, will rapidly fill in with snow during the wintertime due to high winds, while shrubs will trap blowing snow, resulting in drifts. Meanwhile, snow will blow off of exposed areas, resulting in abnormally shallow snow. These complex interactions between wind, vegetation, and terrain are difficult to represent well with physically-based models, but machine learning techniques have shown promise in the past. Here, we propose a hybrid modeling approach, where we use machine learning derived snow pattern maps to inform SnowModel, a physically-based snow process model. We develop and test this technique at the Teller 27 Seward Peninsula NGEE-Arctic study site. This dataset includes 5 *.nc files of model inputs and outputs plus one user guide (*.pdf). We present the data we use to drive SnowModel (vegetation type, digital elevation model), the snow pattern maps used to inform SnowModel (Standardized Depth Values maps, Machine Learning Snow Distribution Pattern), and our machine learning, SnowModel, and Hybrid snow depth and snow water equivalent results. The Next-Generation Ecosystem Experiments: Arctic (NGEE Arctic), a research effort to reduce uncertainty in Earth System Models by developing a predictive understanding of carbon-rich Arctic ecosystems and feedbacks to climate. NGEE Arctic was supported by the Department of Energy's Office of Biological and Environmental Research. The NGEE Arctic project had two field research sites: 1) located within the Arctic polygonal tundra coastal region on the Barrow Environmental Observatory (BEO) and the North Slope near Utqiagvik (Barrow), Alaska and 2) multiple areas on the discontinuous permafrost region of the Seward Peninsula north of Nome, Alaska. Through observations, experiments, and synthesis with existing datasets, NGEE Arctic provided an enhanced knowledge base for multi-scale modeling and contributed to improved process representation at global pan-Arctic scales within the Department of Energy's Earth system Model (the Energy Exascale Earth System Model, or E3SM), and specifically within the E3SM Land Model component (ELM).

54 ENVIRONMENTAL SCIENCES↗