Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “complex computing”

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 901 records · Page 50
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Performance Analysis of Traditional and Data-Parallel Primitive Implementations of Visualization and Analysis Kernels

Measurements of absolute runtime are useful as a summary of performance when studying parallel visualization and analysis methods on computational platforms of increasing concurrency and complexity. We can obtain even more insights by measuring and examining more detailed measures from hardware performance counters, such as the number of instructions executed by an algorithm implemented in a particular way, the amount of data moved to/from memory, memory hierarchy utilization levels via cache hit/miss ratios, and so forth. This work focuses on performance analysis on modern multi-core platforms of three different visualization and analysis kernels that are implemented in different ways: one is "traditional", using combinations of C++ and VTK, and the other uses a data-parallel approach using VTK-m. Our performance study consists of measurement and reporting of several different hardware performance counters on two different multi-core CPU platforms. The results reveal interesting performance differences between these two different approaches for implementing these kernels, results that would not be apparent using runtime as the only metric.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Enhancement of Industry Legacy Probabilistic Risk Assessment Methods and Tools

Probabilistic risk assessments (PRAs) are integral to nuclear power plant (NPP) operations, having tremendously benefitted the safety of the U.S. reactor fleet for decades. Insights obtained from the models have provided perspectives on a variety of applications, both at the plant and for the regulator. While these models are very useful, they are now being asked to represent and analyze aspects of the plant that were never envisioned by the initial PRA practitioners. Furthermore, heightened demands on the PRA models have led to increased computing power requirements. Additionally, as the complexity of the PRA models increased, the difficulty experienced by non-PRA experts in trying to understand these models, grasp the insights they provide, and effectively use that information has become problematic. The need for research to address key issues regarding PRA tools and methods has never been greater. Although the nuclear power industry has largely been well-served by these tools and methods, the underlying science is dated, remaining mostly unchanged for over two decades. Three areas were identified as most beneficial to address to maintain and improve the usefulness of the current practice legacy PRA tools: improvement in quantification speed, increased ability to efficiently model multi-hazard models, and improvement in modeling human action dependency in PRA. This report provides the outcomes from the FY2021 research into these three areas, identifying potential technical gaps and solutions, and charting the next steps forward to address current PRA challenges.

42 ENGINEERING↗
DOE OSTI2020

Parsimonious Inference Information-Theoretic Foundations for a Complete Theory of Machine Learning (CIS-LDRD Project 218313 Final Technical Report)

This work examines how we may cast machine learning within a complete Bayesian framework to quantify and suppress explanatory complexity from first principles. Our investigation into both the philosophy and mathematics of rational belief leads us to emphasize the critical role of Bayesian inference in learning well-justified predictions within a rigorous and complete extended logic. The Bayesian framework allows us to coherently account for evidence in the learned plausibility of potential explanations. As an extended logic, the Bayesian paradigm regards probability as a notion of degrees of truth. In order to satisfy critical properties of probability as a coherent measure, as well as maintain consistency with binary propositional logic, we arrive at Bayes' Theorem as the only justifiable mechanism to update our beliefs to account for empiracle evidence. Yet, in the machine learning paradigm, where explanations are unconstrained algorithmic abstractions, we arrive at a critical challenge: Bayesian inference requires prior belief. Conventional approaches fail to yield a consistent framework in which we could compare prior plausibility among the infinities of potential choices in learning architectures. The difficulty of articulating well-justified prior belief over abstract models is the provinence of memorization in traditional machine learning training practices. This becomes exceptionally problematic in the context of limited datasets, when we wish to learn justifiable predictions from only a small amount of data.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Physically rigorous reduced-order flow models of fractured subsurface environments without explosive computational cost

Fractured media models comprise discontinuities of multiple lengths (e.g. fracture lengths and apertures, wellbore area) that fall into the relatively insignificant length scales spanning millimeter-scale fractures to centimeter-scale wellbores in comparison to the extensions of the field of interest, and challenge the conventional discretization methods imposing highly-fine meshing and formidably large numerical cost. By utilizing the recent developments in the finite element analysis of electromagnetics that allow to represent material properties on a hierarchical geometry, this project develops computational capabilities to model fluid flow, heat conduction, transport and induced polarization in large-scale geologic environments that possess geometrically-complex fractures and man-made infrastructures without explosive computational cost. The computational efficiency and robustness of this multi-physics modeling tool are demonstrated by considering various highly-realistic complex geologic environments that are common in many energy and national security related engineering problems.

42 ENGINEERING↗
DOE OSTI2024

Operational Analytics Studies for ATLAS Distributed Computing: Data Popularity Forecast and Utilization of the WLCG Centers

Operational analytics is the direction of research related to the analysis of the current state of computing processes and the prediction of future states in order to anticipate imbalances and take timely measures to stabilize a complex system. There are two relevant areas in ATLAS Distributed Computing that are currently the focus of studies: user physics analysis including the forecast of popularity of data samples among users, and evaluating WLCG centers for their readiness to process user analysis payloads. Studying these areas is challenging due to the complexity involved, as it requires a comprehensive understanding of numerous boundary conditions typically found in large-scale distributed computing infrastructures. Forecasts of data popularity are problematic without the categorization of user tasks by their types (data transformation or physics analysis), which do not always appear on the surface but may induce noise, which introduces significant distortions for predictive analysis. Evaluating the WLCG resources by their analysis workloads is also a challenging task as it is necessary to find a balance between the workload of the resource, its performance, the waiting time for jobs on it, as well as the volume of jobs that it processes. This is especially difficult in a heterogeneous computing environment, where legacy resources are used along with modern high-performance machines. We will look at these areas of research in detail and discuss what tools and methods are used in our work, demonstrating results already obtained.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Behavior and mechanisms of Doppler wind lidar error in complex terrain: stable flow case study at Perdigão

A numerical experiment is carried out investigating the magnitude of biases in ground-based lidar measurements in complex flow conditions. Biases assessed include those arising from flow curvature and from the interaction of turbulence with the wind field reconstruction (WFR) algorithms used by a WindCube lidars and anemometers. RANS-CFD and WRF-LES simulations were performed for the Perdig˜ao Field Experiment site for a range of atmospheric conditions. Virtual anemometer and lidar data were generated for four locations: two near exposed ridge tops and two in low-speed regions in the valley. The LES data at these four locations show that the scalar inflation terms (the relation between scalar and vector averaged wind speed) for virtual lidar and virtual cups agree very well with predictions using perturbation theory. While the lidar errors vary greatly with location and height, the contribution from the flow curvature tends to be larger than the differences arising from scalar inflation. For one lidar/mast pair near the ridge top, comparisons between simulations and measurements are carried out for a resonant mountain wave event on June 14th, 2017, and for the whole duration of the Perdigão campaign for winds perpendicular to the ridges. The lidar error during the mountain wave, a period of strong stability and low inversion height, is significantly larger than the campaign average. The sensitivity of the lidar error to atmospheric stability is confirmed by the RANS simulations, which suggests strong sensitivity of flow curvature error to stability conditions and to the shape of the wind speed profile near the top of the boundary layer.

17 WIND ENERGY↗
DOE OSTI2022

Kinetic Model for the Reduction of Cu II Sites by NO + NH 3 and Reoxidation of NH 3 -Solvated Cu I Sites by O 2 and NO in Cu-SSZ-13

In this work, a kinetic model is developed for the reduction of Cu II sites by NO + NH 3 and the reoxidation of NH 3 -solvated Cu I sites by O 2 and NO in Cu-SSZ-13. Fourier transform infrared (FTIR) spectroscopy and spatially resolved capillary inlet mass spectrometry (SpaciMS) measurements during transient reactor experiments are utilized to identify the rate parameters associated with NO + NH 3 RHC (reduction half-cycle), proposed to occur via two distinct pathways involving adsorbed NH 3 and gas-phase NH 3 . The resulting NO + NH 3 RHC model is validated using spatiotemporal N 2 measurements covering a wide range of temperatures (200–450 °C) and space velocities (53,000–640,000 h –1 ). N 2 O formation is observed and modeled during NO + NH 3 RHC, with quantitative validation under standard selective catalytic reduction (SCR) conditions. Experimentally measured enthalpic and entropic changes associated with O 2 adsorption on NH 3 -solvated Cu I (ZCu(NH 3 ) 2 ) complexes [ Kamasamudram, K. Catal. Today 2010 , 151 (3–4), 212-222], along with activation energies estimated computationally for the intercage diffusion of ZCu(NH 3 ) 2 complexes [ Paolucci, C. Science 2017 , 357 (6 354), 898-903], are incorporated into a mean field kinetic model for the low-temperature oxidation half-cycle (OHC). Significant NH 3 release is observed during the isothermal oxidation of Cu I sites, attributed to desorption of NH 3 ligands from NH 3 -solvated Cu II dimers (Z 2 Cu 2 (NH 3 ) 4 O 2 ). Reduction of these dimeric complexes leads to the consumption of one NO/Cu II , contradicting the expected reduction stoichiometry. Inclusion of a global Arrhenius rate for the NO titration of Z 2 Cu 2 (NH 3 ) 4 O 2 complexes provides accurate representations of standard SCR on reduced and oxidized catalysts, predicting transient NO and NH 3 consumption between 150 and 250 °C as a function of hydrothermal aging. Deactivation of low-temperature standard SCR by NH 3 is observed at high NH 3 pressures, modeled via the formation of superoxo amino (ZCu(NH 3 ) 3 OO*) complexes during NH 3 titration of Z 2 Cu 2 (NH 3 ) 4 O 2 complexes [ Negri, C. J. Am. Chem. Soc. 2020 , 142 (37), 15884-15896]. The redox kinetic model presented here provides a foundational description of active site redox during low-temperature standard SCR, combining the recent kinetic, spectroscopic, and computational findings on the mechanism of standard SCR over Cu-SSZ-13.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

An automated and portable method for selecting an optimal GPU frequency

Power consumption poses a significant challenge in current and emerging graphics processing unit (GPU) enabled high-performance computing systems. In modern GPUs, dynamic voltage frequency scaling (DVFS) appears to be a reliable control to regulate power consumption and performance. However, the DVFS design space is large - hence, brute-force approaches are infeasible to select the optimal frequency. Furthermore, no single frequency can be universally optimal for applications with varying computational intensities. Thus, the application's complexity and the availability of a wide range of frequency settings are a challenge in selecting the optimal frequency configuration for a given GPU workload. To that end, this paper proposes a systematic approach that consists of three steps. The feature characterization study identifies the fine-grain GPU utilization metrics that influence the power consumption and execution time of a given workload. To understand the performance, power, and energy consumption behaviors of a workload across GPU's DVFS design space, we derived analytical power and performance models using the identified fine-grain features. Here, it is shown that the same set of GPU utilization metrics can estimate both the power consumption and execution time while being agnostic of changes to frequency and input sizes. Applying a power control with the single objective of reducing power may cause performance degradation, leading to more energy consumption. A multi-objective approach is proposed to select the optimal GPU DVFS configuration for a workload that reduces power consumption with negligible degradation in performance. The evaluation was conducted using SPEC ACCEL benchmarks and three real applications - NAMD LAMMPS, and LSTM on NVIDIA GV100, GA100, and AMD MI210 GPUs. On average, real applications showed 29.6% energy savings with a performance loss of 5.2% on GA100 and 22.6% energy savings with a performance loss of 4.7% on GV100. Moreover, the proposed models are portable to real applications, GPU architectures, and vendors, and require metric collection at only the default frequency rather than all supported DVFS configurations. Additionally, we conducted a comparison between our models and the GPU assembly instructions (PTX)-based static models. The results revealed a significant reduction in the average error rates, with a decrease from 19.7% to 3.1% for power models and from 29.4% to 5.2% for performance models.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Subspace recursive Fermi-operator expansion strategies for large-scale DFT eigenvalue problems on HPC architectures

Quantum mechanical calculations for material modeling using Kohn–Sham density functional theory (DFT) involve the solution of a nonlinear eigenvalue problem for N smallest eigenvector-eigenvalue pairs, with N proportional to the number of electrons in the material system. Here, these calculations are computationally demanding and have asymptotic cubic scaling complexity with the number of electrons. Large-scale matrix eigenvalue problems arising from the discretization of the Kohn–Sham DFT equations employing a systematically convergent basis traditionally rely on iterative orthogonal projection methods, which are shown to be computationally efficient and scalable on massively parallel computing architectures. However, as the size of the material system increases, these methods are known to incur dominant computational costs through the Rayleigh–Ritz projection step of the discretized Kohn–Sham Hamiltonian matrix and the subsequent subspace diagonalization of the projected matrix. This work explores the potential of polynomial expansion approaches based on recursive Fermi-operator expansion as an alternative to the subspace diagonalization of the projected Hamiltonian matrix to reduce the computational cost. Subsequently, we perform a detailed comparison of various recursive polynomial expansion approaches to the traditional approach of explicit diagonalization on both multi-node central processing unit and graphics processing unit architectures and assess their relative performance in terms of accuracy, computational efficiency, scaling behavior, and energy efficiency.

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

Structure and Reactivity of a High-Spin, Nonheme Iron(III)- Superoxo Complex Supported by Phosphinimide Ligands

Nonheme iron oxygenases utilize dioxygen to accomplish challenging chemical oxidations. Additionally, a further understanding of the Fe-O 2 intermediates implicated in these processes is challenged by their highly transient nature. To that end, we have developed a ligand platform featuring phosphinimide donors intended to stabilize oxidized, high-spin iron complexes. O 2 exposure of single crystals of a three-coordinate Fe(II) complex of this framework allowed for in crystallo trapping of a terminally bound Fe-O 2 complex suitable for XRD characterization. Spectroscopic and computational studies of this species support a high-spin Fe(III) center antiferromagnetically coupled to a superoxide ligand, similar to that proposed for numerous nonheme iron oxygenases. In addition to the apparent stability of this synthetic Fe-O 2 complex, its ability to engage in a range of stoichiometric and catalytic oxidation processes demonstrates that this iron-phosphinimide system is primed for development in modeling oxidizing bioinorganic intermediates and green oxidation chemistry.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Discerning Deception: An Empirically-Driven Agent-Based Model of Expert Evaluation of Scientific Content

Both human subject experiments and computational, modeling and simulations have been used to study detection of deception. This work aims to combine these two methods by integrating empirically-derived information (from human subject experiments) into agent-based models to generate novel insights into the complex problems of detection of disinformation content. Computational experiments are used to simulate across multiple scenarios for evaluation and decision-making regarding the validity of potentially deceptive scientific documents. Factors influencing the human agent behaviors in the model were identified through a human subject experiment that was conducted to evaluate and characterize decision making related to disinformation discernment. Correlation and regression analyses were used to translate insights from the human subjects experiment to inform the parameterization of agent features and scenario development. Three scenarios were evaluated with the agent-based models to help evaluate the replicability of the simulations (validation analysis) and assess the influence of human agent and document features (sensitivity analyses). A replication of the human participant experiment demonstrated that the agent-based simulations compare favorably to empirical findings. The agent-based modeling was then used to conduct sensitivity analysis on the accuracy of deception detection as a function of document proportions and human agent features. Results indicate that precision values are adversely impacted when the proportion of deceptive documents is lower in the overall sample, whereas recall values are more sensitive to changes in human agent features. These findings indicate important nuances in accuracy evaluations that should be further considered (including consideration of potential alternate metrics) in future agent-based models of disinformation. Additional areas for future exploration include extension of simulations to consider other ways to align the agent-based model design with psychological theory and inclusion of agent-agent interactions, especially as it pertains to sharing of scientific information within an organizational context.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2023

Predictor-corrector models for lightweight massive machine-type communications in Industry 4.0

Future Industry 4.0 scenarios are characterized by seamless integration between computational and physical processes. To achieve this objective, dense platforms made of small sensing nodes and other resource constraint devices are ubiquitously deployed. All these devices have a limited number of computational resources, just enough to perform the simple operation they are in charge of. The remaining operations are delegated to powerful gateways that manage sensing nodes, but resources are never unlimited, and as more and more devices are deployed on Industry 4.0 platforms, gateways present more problems to handle massive machine-type communications. Although the problems are diverse, those related to security are especially critical. To enable sensing nodes to establish secure communications, several semiconductor companies are currently promoting a new generation of devices based on Physical Unclonable Functions, whose usage grows every year in many real industrial scenarios. Those hardware devices do not consume any computational resource but force the gateway to keep large key-value catalogues for each individual node. In this context, memory usage is not scalable and processing delays increase exponentially with each new node on the platform. In this paper, we address this challenge through predictor-corrector models, representing the key-value catalogues. Models are mathematically complex, but we argue that they consume less computational resources than current approaches. The lightweight models are based on complex functions managed as Laurent series, cubic spline interpolations, and Boolean functions also developed as series. Unknown parameters in these models are predicted, and eventually corrected to calculate the output value for each given key. The initial parameters are based on the Kane Yee formula. An experimental analysis and a performance evaluation are provided in the experimental section, showing that the proposed approach causes a significant reduction in the resource consumption.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

MOOSE ProbML: Parallelizable Probabilistic Machine Learning and Uncertainty Quantification Capabilities

The Multiphysics Object Oriented Simulation Environment (MOOSE) is a widely used open- source finite element software for performing multiphysics multiscale simulations in a massively parallel fashion. Recently, the computational team at Idaho National Laboratory (INL) has implemented Probabilistic Machine Learning (ProbML) capabilities in MOOSE—in a parallelized fashion—and enable active learning with large-scale computational models for tasks such as surrogate model development, scale bridging, forward/inverse uncertainty quantification (UQ), Bayesian optimization, etc. This presentation summarizes these developments in MOOSE along with demonstrations on several real applications relevant to nuclear energy. At the fundamental level, samplers like Monte Carlo/Latin Hypercube, variance reduction, parallelized Markov Chain Monte Carlo (MCMC) support uncertainty propagation in both forward and inverse settings. These samplers can be integrated with the Gaussian processes (GP) suite in MOOSE, which offer several variants like scalar GPs, multi-output GPs, and deep GPs, to enable active learning. These GPs can be tuned using gradient-based optimization methods like Adam and its variants or gradient-free methods like the elliptical slice sampler (a variant of MCMC adept under Gaussian settings) for more complex covariance kernels or likelihoods whose gradient computations can be cumbersome. A variety of batch acquisition functions permit parallelized evaluation of the computational model and support different learning objectives with high efficiency like Bayesian inference, global surrogate development, optimization, etc. Furthermore, libtorch integration supports training, evaluation, and re-training of neural networks and other complex machine learning models in active learning settings. The impacts of these developments are shown on several real applications: (1) nuclear fuel inverse UQ and model inadequacy assessment using the Kennedy O’Hagan framework; (2) uncertainty aware surrogate modeling for additive manufacturing to predict field quantities; (3) nuclear reactor rare events analysis; and (4) complex fluid flow prediction using a global surrogate with quantified prediction uncertainty. Finally, the outlook of MOOSE ProbML is discussed for both outer-loop and inner-loop computations in the broad view to accelerate fuels and materials qualification, address gaps in knowledge and data, and assess new reactor/fuel systems.

11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2022

Nitrogen Atom Transfer Catalysis by Metallonitrene C−H Insertion: Photocatalytic Amidation of Aldehydes

Abstract C−H amination and amidation by catalytic nitrene transfer are well‐established and typically proceed via electrophilic attack of nitrenoid intermediates. In contrast, the insertion of (formal) terminal nitride ligands into C−H bonds is much less developed and catalytic nitrogen atom transfer remains unknown. We here report the synthesis of a formal terminal nitride complex of palladium. Photocrystallographic, magnetic, and computational characterization support the assignment as an authentic metallonitrene (Pd−N) with a diradical nitrogen ligand that is singly bonded to Pd II . Despite the subvalent nitrene character, selective C−H insertion with aldehydes follows nucleophilic selectivity. Transamidation of the benzamide product is enabled by reaction with N 3 SiMe 3 . Based on these results, a photocatalytic protocol for aldehyde C−H trimethylsilylamidation was developed that exhibits inverted, nucleophilic selectivity as compared to typical nitrene transfer catalysis. This first example of catalytic C−H nitrogen atom transfer offers facile access to primary amides after deprotection.

Schmidt‐Räntsch, Till↗
DOE OSTI2022

Nitrogen Atom Transfer Catalysis by Metallonitrene C−H Insertion: Photocatalytic Amidation of Aldehydes

Abstract C−H amination and amidation by catalytic nitrene transfer are well‐established and typically proceed via electrophilic attack of nitrenoid intermediates. In contrast, the insertion of (formal) terminal nitride ligands into C−H bonds is much less developed and catalytic nitrogen atom transfer remains unknown. We here report the synthesis of a formal terminal nitride complex of palladium. Photocrystallographic, magnetic, and computational characterization support the assignment as an authentic metallonitrene (Pd−N) with a diradical nitrogen ligand that is singly bonded to Pd II . Despite the subvalent nitrene character, selective C−H insertion with aldehydes follows nucleophilic selectivity. Transamidation of the benzamide product is enabled by reaction with N 3 SiMe 3 . Based on these results, a photocatalytic protocol for aldehyde C−H trimethylsilylamidation was developed that exhibits inverted, nucleophilic selectivity as compared to typical nitrene transfer catalysis. This first example of catalytic C−H nitrogen atom transfer offers facile access to primary amides after deprotection.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

A Dataset of CFD Simulated Industrial Furnace Images for Conditional Automatic Generation with GANs

The steel industry is constantly looking for ways to automate processes and improve efficiency. A standard practice in industry is to simulate how complex systems will operate before they are actually used. Some complex systems, including steel industry processes such as blast furnaces, require complex physics-based simulations utilizing computational fluid dynamics (CFD). These CFD physics-based simulations are very accurate but can take significant time and computational resources to process, resulting in challenges for the implementation of the models in real-world operational environments. In recent years, deep learning (DL) has been considered as a substitute for these CFD models. DL models can be trained on validated CFD simulation data and then used for industrial process inference. Previous DL-based solutions have made great contributions for industrial automation but are currently missing the additional visualization component that CFD simulations also provide. In this paper, we propose a dataset for simple DL generative approaches that can help to address this issue. The dataset and methodology under development to approach this prediction are discussed in this work.

Calix, Ricardo↗
DOE OSTI2024

Light-ray wave functions and integrability

Using integrability, we construct (to leading order in perturbation theory) the explicit form of twist-three light-ray operators in planar $\mathcal{N}$ = 4 SYM. This construction allows us to directly compute analytically continued CFT data at complex spin. We derive analytically the “magic” decoupling zeroes previously observed numerically. Using the Baxter equation, we also show that certain Regge trajectories merge together into a single unifying Riemann surface. Perhaps more surprisingly, we find that this unification of Regge trajectories is not unique. If we organize twist-three operators differently into what we call “cousin trajectories” we find infinitely more possible continuations. We speculate about which of these remarkable features of twist-three operators might generalize to other operators, other regimes and other theories.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2022

Physics-informed neural networks (PINNs) for fluid mechanics: a review

Despite the significant progress over the last 50 years in simulating flow problems using numerical discretization of the Navier–Stokes equations (NSE), we still cannot incorporate seamlessly noisy data into existing algorithms, mesh-generation is complex, and we cannot tackle high-dimensional problems governed by parametrized NSE. Moreover, solving inverse flow problems is often prohibitively expensive and requires complex and expensive formulations and new computer codes. Here, we review flow physics-informed learning, integrating seamlessly data and mathematical models, and implement them using physics-informed neural networks (PINNs). Here, we demonstrate the effectiveness of PINNs for inverse problems related to three-dimensional wake flows, supersonic flows, and biomedical flows.

42 ENGINEERING↗