SEARCH · Engineering Papers
Results for “computational physics applications”
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.
Performance of Julia for High Energy Physics Analyses
We argue that the Julia programming language is a compelling alternative to currently more common implementations in Python and C++ for common data analysis workflows in high energy physics. We compare the speed of implementations of different workflows in Julia with those in Python and C++. Furthermore, our studies show that the Julia implementations are competitive for tasks that are dominated by computational load rather than data access. For work that is dominated by data access, we demonstrate an application with concurrent file reading and parallel data processing.
SDA: a symbolic differential algebra package in C++
Truncated Power Series Algebra (TPSA), or Differential Algebra (DA), is a well-established tool in accelerator physics, commonly used for generating high-order maps of dynamic systems, as well as in symplectic tracking, normal form analysis, verified integration, optimization, and fast multipole methods. This package is the first to perform symbolic DA computations, enabling traceability of initial condition contributions and runtime reduction for repeated DA calculations, potentially expanding DA’s applications.
Multi-Fidelity Scheme for Accelerating 4D Finite Element Analysis for Mircoreactors
Next-generation microreactors are currently being designed to be operated terrestrial and extraterrestrial for remote surface power production. These systems will provide an alternative source of carbon-free energy that is versatile and can be utilized for various applications. These applications of microreactors have prompted the usage of high-fidelity unstructured finite element (FE) based approaches to provide time-dependent solutions for multiple physics fields. Computing these high-fidelity (4-D) solutions for multiple design iterations, physics fields, and transient events requires an immense computational cost. These high-fidelity solutions are computational expensive and the cost can be reduced through the implementation of less accurate low-fidelity solutions. Unlike the current fleet of commercial nuclear reactors, these next-gen systems present challenges due to the material and physical limitations required. Due to these constraints, the brute force technique of parameterizing important system characteristics determines whether a design meets the project objective. A system such as a nuclear reactor could have thousands of design parameters that affect system performance. In order to analyze the entire parameter space of such a complex system would require millions of CPU hours and countless design iterations. This costly approach is not practical due to regulatory and budget limitations. In this proposal, an approach that utilizes hybrid high-fidelity and low-fidelity FE models to reduce the computational cost of evaluating these applications in 4-D will be presented. The accuracy of the high-fidelity model and the computational efficiency of the low-fidelity model are taken advantage of to produce a solution that closely resembles the full order high-fidelity solution. By utilizing an unconverged coarse FE mesh, operation limits such as temperature, structural loading, etc., can be evaluated in an accelerated fashion and then can be spatially interpolated onto a finer mesh. The resulting error arising from the coarse mesh can be mitigated with a discrepancy function that actively quantifies and corrects the error in the coarse solution. This discrepancy function can be periodically updated with high-fidelity calculations across the temporal domain thus requiring less iterations on the fine mesh. As a result, the computational cost can be reduced for the evaluation and design iteration of microreactors. The proposal for this research contains three sections: Section 2 provides a literature review, Section 3 outlines the methodology for the proposed multi-fidelity scheme, and Section 4 displays preliminary results of the proposed research.
Automated Model for Improved Mapping of Country-Scale High-Resolution Coastal Bathymetry
Accurate and up-to-date maps of coastal bathymetry are critical for a variety of sectors from vessel navigation to port construction and are increasingly vital to inform coastal infrastructure management amid accelerating sea-level rise and more frequent and severe storm-surge events. The primary challenges to accurate and efficient bathymetric mapping from optical remote sensing are: accurately modeling light attenuation in both the atmosphere and water column; and inefficient data processing pipelines for highresolution satellite imagery. To address the effects of light attenuation within the water-column we have developed a novel physics-based bathymetry model that accounts for variations in water-column inherent optical properties on a pixel-by-pixel basis in optically-shallow aquatic environments, which represents a major advancement. For applications to satellite imagery, we have developed a software package that automatically applies the robust 6S atmospheric correction algorithm, estimates the bottom depth from the physics-based bathymetry model, which corrects for attenuation by suspended particulate matter and colored dissolved organic matter in the water column on a pixel-by-pixel basis, and leverages highperformance computing for rapid application to region-scale (e.g., CONUS) 2-meter resolution imagery datasets. Our approach is tailored to sensors that collect data at two-meter resolution with high return times for frequent updates. We mapped 591 WorldView satellite images for Florida, North Carolina, and Alaska and validated the maps against LiDAR-derived bathymetry data. Results show median RMSE of 1.75, 1.59, and 2.67 meters, respectively. By combining the strengths of Oak Ridge National Laboratory in high-performance computing and remote-sensing science with the water-column modeling expertise of Scripps Institution of Oceanography we advance the state of bathymetric mapping capability.
LHC EFT WG note: SMEFT predictions, event reweighting, and simulation
This note provides a comprehensive overview of tools for predicting observables in the Standard Model effective field theory (SMEFT) at both tree level and one loop using event generators. We evaluate three primary methodologies–event reweighting, separate simulation of squared matrix elements, and full SMEFT process simulation–focusing on their statistical performance, computational efficiency, and potential biases. Each approach is assessed in terms of its accuracy, highlighting trade-offs between precision and resource demands. Practical insights into their applicability for high-energy physics analyses are offered, with particular attention to processes where SMEFT effects are significant. Additionally, we discuss the role of helicity in reweighting strategies and its impact on the quality of predictions. By comparing the methods across various LHC processes, this note provides guidance for selecting the most effective strategy for various SMEFT studies, ensuring robust predictions while optimizing computational resources.
Cost-optimized Automated Variance Reduction for Highly Angle-dependent Radiation Transport Analyses [Dissertation]
Monte Carlo variance-reduction techniques that directly bias particle direction have historically received limited attention despite being useful for many radiation transport applications such as those in which radiation travels through large regions with a low probability of colliding. One such technique is known as DXTRAN (short for deterministic transport) in the MCNP Monte Carlo radiation transport code. Until now, effectively applying DXTRAN in calculations is largely based on empirical observations of computational performance. Optimal DXTRAN parameters are identified through manual iteration. This work develops new mathematical descriptions of the DXTRAN variance-reduction process and demonstrates a new automated variance-reduction method that applies these mathematical formulations to determine the optimal application of DXTRAN in a given problem.
Celeritas R&D Report: Accelerating Geant4
Celeritas is a new Monte Carlo (MC) detector simulation code designed for computationally intensive applications on high-performance heterogeneous architectures. In the past two years Celeritas has advanced from prototyping a Graphics Processing Unit (GPU)-based single physics model in infinite medium to implementing a full set of electromagnetic (EM) physics processes in complex geometries. The current release of Celeritas, version 0.4, has incorporated full device-based navigation, an event loop in the presence of magnetic fields, and detector hit scoring. New functionality incorporates a scheduler to offload electromagnetic physics to the GPU within a Geant4-driven simulation, enabling straightforward integration of Celeritas into the high energy physics (HEP) experimental frameworks CMSSW and ATLAS FullSimLight. On the Perlmutter supercomputer, Celeritas performs EM physics between 3× and 18× faster using the machine’s Nvidia GPUs compared to using only CPUs, corresponding to an electrical power efficiency up to a factor of 5. When running a multithreaded Geant4 ATLAS test beam application with full hadronic physics, using Celeritas to accelerate the EM physics results in an overall simulation speedup of 1.7–2.2× on GPU and 1.2× on CPU. In a CMS test application using tt¯ events and the prototype Run 4 configuration, compared to Geant4 CPU, Celeritas with a Nvidia A100 improves overall throughput up to a factor of 2.7× but cannot be efficiently shared with more than 8 cores.
Perspective of Fermi’s golden rule and its generalizations in chemical physics
This perspective provides a succinct history of Fermi’s golden rule (FGR), an overview of its derivation, assumptions, and representative forms. Major applications of FGR, mostly in the field of chemical physics, are reviewed. These illustrate the broad applicability and success of FGR. Ambiguities and open issues encountered in practical applications of FGR are clarified. Recent advances in generalizations of FGR and computational methods for practical applications are addressed.
Nuclear–electronic orbital approach to quantization of protons in periodic electronic structure calculations
The nuclear–electronic orbital (NEO) method is a well-established approach for treating nuclei quantum mechanically in molecular systems beyond the usual Born–Oppenheimer approximation. In this work, we present a strategy to implement the NEO method for periodic electronic structure calculations, particularly focused on multicomponent density functional theory (DFT). The NEO-DFT method is implemented in an all-electron electronic structure code, FHI-aims, using a combination of analytical and numerical integration techniques as well as a resolution of the identity scheme to enhance computational efficiency. After validating this implementation, proof-of-concept applications are presented to illustrate the effects of quantized protons on the physical properties of extended systems, such as two-dimensional materials and liquid–semiconductor interfaces. Specifically, periodic NEO-DFT calculations are performed for a trans-polyacetylene chain, a hydrogen boride sheet, and a titanium oxide–water interface. The zero-point energy effects of the protons as well as electron–proton correlation are shown to noticeably impact the density of states and band structures for these systems. These developments provide a foundation for the application of multicomponent DFT to a wide range of other extended condensed matter systems.
Simulating the CMS High Granularity Calorimeter with ML
Detector simulation is a key component of physics analysis and related activities in CMS. In the upcoming High Luminosity LHC era, simulation will be required to use a smaller fraction of computing in order to satisfy resource constraints. At the same time, CMS will be upgraded with the new High Granularity Calorimeter (HGCal), which requires significantly more resources to simulate than the existing CMS calorimeters. This computing challenge motivates the use of generative machine learning models as surrogates to replace full physics-based simulation. We study the application of state-of-the-art diffusion models to simulate particle showers in the CMS HGCal. We will discuss methods to overcome the challenges posed by the high-dimensional, irregular geometry of the HGCal. The quality of the showers produced by the diffusion model will be assessed by comparison to the full GEANT4-based simulation. The increase in simulation throughput will be quantified and methods to accelerate the diffusion model inference will also be discussed.
Quantum Computing and Simulations for Energy Applications: Review and Perspective
Not Available
Application of Portable Parallelization Strategies for GPUs on track reconstruction kernels
Utilizing the computational power of GPUs is one of the key ingredients to meet the computing challenges presented to the next generation of High-Energy Physics (HEP) experiments. Unlike CPUs, developing software for GPUs often involves using architecturespecific programming languages promoted by the GPU vendors and hence limits the platform that the code can run on. Various portability solutions have been developed to achieve portable, performant software across different GPU vendors. Given the rapid evolution of these portability solutions, an early adoption of them in simple HEP testbed applications will help us understand the strengths and weaknesses of respective approaches.We apply several portability solutions, including Alpaka, Kokkos, SYCL and std::execution::par, on kernels for track propagation extracted from the mkFit project. We report on the development experience of the same application with different portability solutions, as well as their performance on GPUs, measured as the throughput of the kernels, from different manufacturers such as NVIDIA, AMD and Intel.
Exploration of the Application of Machine Learning to the improvement of Interatomic Potentials
Current methods for atomistic simulations of material systems suffer from limitations which restrict the ability of the simulation to correctly characterize certain material behavior and physical phenomena. Small scale ab initio (AIMD) modeling is highly accurate but is computationally expensive. Classical molecular dynamics (CMD) simulations use interatomic potentials (IPs) to describe larger systems at a reduced computational cost, but with a reduced accuracy. Creating more robust IPs enable more precise CMD simulations. In this thesis, the application of a specific machine learning process,artifical neural networks (ANNs), to the improvement of IPs and MD simulation is discussed.
Isotopic and Fuel Lattice Parameter Trends in Extended Enrichment and Higher Burnup LWR Fuel Vol I: PWR fuel
Commercial light water reactor (LWR) operators and fuel vendors in the United States are pursuing changes to nuclear fuel that include extended enrichment (EE) and accident-tolerant fuel (ATF) designs. The term EE (8% > 235 U > 5%) is used in this report to refer to a subset of high assay low-enriched uranium (HALEU) that is considered usable in commercial US LWRs in the near term. ATF features are designed to improve fuel system performance under accident conditions. One goal of EE is to improve fuel cycle economy by enabling fuel to be depleted to higher burnup than the typical current maximum pin burnup limits (62 gigawatt-days per metric ton of uranium [GWd/MTU]). Adoption of EE, ATF, and high burnup (HBU) fuels in the US commercial fleet requires a clear understanding of the effects on core physics parameters and used fuel isotopic content, as well as confidence in the accuracy of computer code predictions over an expanded range of materials, enrichment, and burnup. A thorough understanding of the applicability and adequacy of benchmark data (e.g., criticality, decay heat, isotopic content) for computer code validation is necessary to ensure that appropriate safety margins are maintained. To prepare for and support these potential changes, the effects of EE, ATF, and HBU are being assessed for selected representative LWR fuel designs. The project is divided into phases: this report summarizes the findings of Phase 1, which focuses on the lattice physics parameter and used fuel isotopic changes for a conventional Westinghouse 17×17 pressurized water reactor (PWR) design. The primary investigation tool is the SCALE Polaris code using the SCALE 56-group Evaluated Nuclear Data File (ENDF)/B-VII.1 cross sections. The goal of the current work is to (1) identify and explain important effects of EE and HBU (reactivity, lattice physics, and isotopic effects) assuming that PWR fuel design and usage remain similar to those for current enrichment fuel, (2) provide limited code-to-code comparisons with higher order cross section libraries and/or codes, and (3) identify any apparent anomalous trends in the results for further investigation.
Emerging applications: Neuromorphic computing and reservoir computing
The emergence of doped hafnium oxide (HfO 2 )-based ferroelectric films has enabled highly scalable and silicon-compatible ferroelectric devices, opening new frontiers in neuromorphic and reservoir computing. Among these, ferroelectric field-effect transistors (FeFETs) are particularly promising due to their analog memory characteristics and unique polarization dynamics. These properties make FeFETs ideal candidates for artificial synapses in neuromorphic architectures, supporting deep neural networks and spiking neural networks based on leaky-integrate-and-fire (LIF) mechanisms. Beyond neuromorphic computing, FeFETs also play a crucial role in physical reservoir computing, leveraging their intrinsic nonlinear and history-dependent behavior for efficient real-time learning. This approach offers significant advantages for time-series processing and edge artificial intelligence (AI) applications, addressing the growing need for energy-efficient computing. As a result, this article explores the principles, key demonstrations, and future potential of FeFET-based neuromorphic and reservoir computing, highlighting their impact on next-generation AI hardware.
Modeling Data Flows with Network Calculus in Cyber-Physical Systems: Enabling Feature Analysis for Anomaly Detection Applications
The electric grid is becoming increasingly cyber-physical with the addition of smart technologies, new communication interfaces, and automated grid-support functions. Because of this, it is no longer sufficient to only study the physical system dynamics, but the cyber system must also be monitored as well to examine cyber-physical interactions and effects on the overall system. To address this gap for both operational and security needs, cyber-physical situational awareness is needed to monitor the system to detect any faults or malicious activity. Techniques and models to understand the physical system (the power system operation) exist, but methods to study the cyber system are needed, which can assist in understanding how the network traffic and changes to network conditions affect applications such as data analysis, intrusion detection systems (IDS), and anomaly detection. In this paper, we examine and develop models of data flows in communication networks of cyber-physical systems (CPSs) and explore how network calculus can be utilized to develop those models for CPSs, with a focus on anomaly and intrusion detection. This provides a foundation for methods to examine how changes to behavior in the CPS can be modeled and for investigating cyber effects in CPSs in anomaly detection applications.
Automatic Differentiation in MetaPhysicL and Its Applications in MOOSE
Efficient solution via Newton’s method of nonlinear systems of equations requires an accurate representation of the Jacobian, corresponding to the derivatives of the component residual equations with respect to the degrees of freedom. In practice these systems of equations often arise from spatial discretization of partial differential equations used to model physical phenomena. These equations may involve domain motion or material equations that are complex functions of the systems’ degrees of freedom. Computing the Jacobian by hand in these situations is arduous and prone to error. Finite difference approximations of the Jacobian or its action are prone to truncation error, especially in multiphysics settings. Symbolic differentiation packages may be used, but often result in an excessive number of terms in realistic model scenarios. An alternative to symbolic and numerical differentiation is automatic differentiation (AD), which propagates derivatives with every elementary operation of a computer program, corresponding to continual application of the chain rule. Automatic differentiation offers the guarantee of an exact Jacobian at a relatively small overhead cost. In this work, we outline the adoption of AD in the Multiphysics Object Oriented Simulation Environment (MOOSE) via the MetaPhysicL package. We describe the application of MOOSE’s AD capability to several sets of physics that were previously infeasible to model via hand-coded or Jacobian-free simulation techniques, including arbitrary Lagrangian-Eulerian and level-set simulations of laser melt pools, phase-field simulations with free energies provided through neural networks, and metallic nuclear fuel simulations that require inner Newton loop calculation of nonlinear material properties.