Browse
Submit Data
Databases
API
Help

Dataset Information

30 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Machine learning-accelerated computational fluid dynamics.

ABSTRACT: Numerical simulation of fluids plays an essential role in modeling many physical phenomena, such as weather, climate, aerodynamics, and plasma physics. Fluids are well described by the Navier-Stokes equations, but solving these equations at scale remains daunting, limited by the computational cost of resolving the smallest spatiotemporal features. This leads to unfavorable trade-offs between accuracy and tractability. Here we use end-to-end deep learning to improve approximations inside computational fluid dynamics for modeling two-dimensional turbulent flows. For both direct numerical simulation of turbulence and large-eddy simulation, our results are as accurate as baseline solvers with 8 to 10× finer resolution in each spatial dimension, resulting in 40- to 80-fold computational speedups. Our method remains stable during long simulations and generalizes to forcing functions and Reynolds numbers outside of the flows where it is trained, in contrast to black-box machine-learning approaches. Our approach exemplifies how scientific computing can leverage machine learning and hardware accelerators to improve simulations without sacrificing accuracy or generalization.

SUBMITTER: Kochkov D

PROVIDER: S-EPMC8166023 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Machine learning exciton dynamics.

Project description:Obtaining the exciton dynamics of large photosynthetic complexes by using mixed quantum mechanics/molecular mechanics (QM/MM) is computationally demanding. We propose a machine learning technique, multi-layer perceptrons, as a tool to reduce the time required to compute excited state energies. With this approach we predict time-dependent density functional theory (TDDFT) excited state energies of bacteriochlorophylls in the Fenna-Matthews-Olson (FMO) complex. Additionally we compute spectral densities and exciton populations from the predictions. Different methods to determine multi-layer perceptron training sets are introduced, leading to several initial data selections. In addition, we compute spectral densities and exciton populations. Once multi-layer perceptrons are trained, predicting excited state energies was found to be significantly faster than the corresponding QM/MM calculations. We showed that multi-layer perceptrons can successfully reproduce the energies of QM/MM calculations to a high degree of accuracy with prediction errors contained within 0.01 eV (0.5%). Spectral densities and exciton dynamics are also in agreement with the TDDFT results. The acceleration and accurate prediction of dynamics strongly encourage the combination of machine learning techniques with ab initio methods.

| S-EPMC6020119 | biostudies-literature

Computational fluid dynamics modelling in cardiovascular medicine.

Project description:This paper reviews the methods, benefits and challenges associated with the adoption and translation of computational fluid dynamics (CFD) modelling within cardiovascular medicine. CFD, a specialist area of mathematics and a branch of fluid mechanics, is used routinely in a diverse range of safety-critical engineering systems, which increasingly is being applied to the cardiovascular system. By facilitating rapid, economical, low-risk prototyping, CFD modelling has already revolutionised research and development of devices such as stents, valve prostheses, and ventricular assist devices. Combined with cardiovascular imaging, CFD simulation enables detailed characterisation of complex physiological pressure and flow fields and the computation of metrics which cannot be directly measured, for example, wall shear stress. CFD models are now being translated into clinical tools for physicians to use across the spectrum of coronary, valvular, congenital, myocardial and peripheral vascular diseases. CFD modelling is apposite for minimally-invasive patient assessment. Patient-specific (incorporating data unique to the individual) and multi-scale (combining models of different length- and time-scales) modelling enables individualised risk prediction and virtual treatment planning. This represents a significant departure from traditional dependence upon registry-based, population-averaged data. Model integration is progressively moving towards 'digital patient' or 'virtual physiological human' representations. When combined with population-scale numerical models, these models have the potential to reduce the cost, time and risk associated with clinical trials. The adoption of CFD modelling signals a new era in cardiovascular medicine. While potentially highly beneficial, a number of academic and commercial groups are addressing the associated methodological, regulatory, education- and service-related challenges.

| S-EPMC4717410 | biostudies-literature

Accelerated spin dynamics using deep learning corrections.

Project description:Theoretical models capture very precisely the behaviour of magnetic materials at the microscopic level. This makes computer simulations of magnetic materials, such as spin dynamics simulations, accurately mimic experimental results. New approaches to efficient spin dynamics simulations are limited by integration time step barrier to solving the equations-of-motions of many-body problems. Using a short time step leads to an accurate but inefficient simulation regime whereas using a large time step leads to accumulation of numerical errors that render the whole simulation useless. In this paper, we use a Deep Learning method to compute the numerical errors of each large time step and use these computed errors to make corrections to achieve higher accuracy in our spin dynamics. We validate our method on the 3D Ferromagnetic Heisenberg cubic lattice over a range of temperatures. Here we show that the Deep Learning method can accelerate the simulation speed by 10 times while maintaining simulation accuracy and overcome the limitations of requiring small time steps in spin dynamic simulations.

| S-EPMC7426868 | biostudies-literature

Machine learning meets volcano plots: computational discovery of cross-coupling catalysts.

Project description:The application of modern machine learning to challenges in atomistic simulation is gaining attraction. We present new machine learning models that can predict the energy of the oxidative addition process between a transition metal complex and a substrate for C-C cross-coupling reactions. In turn, this quantity can be used as a descriptor to estimate the activity of homogeneous catalysts using molecular volcano plots. The versatility of this approach is illustrated for vast libraries of organometallic catalysts based on Pt, Pd, Ni, Cu, Ag, and Au combined with 91 ligands. Out-of-sample machine learning predictions were made on a total of 18 062 compounds leading to 557 catalyst candidates falling into the ideal thermodynamic window. This number was further refined by searching for candidates with an estimated price lower than 10 US$ per mmol. The 37 catalyst finalists are dominated by palladium phosphine ligand combinations but also include the earth abundant transition metal (Cu) with less common ligands. Our results indicate that modern statistical learning techniques can be applied to the computational discovery of readily available and promising catalyst candidates.

| S-EPMC6137445 | biostudies-other

Flow characteristics in a canine aneurysm model: a comparison of 4D accelerated phase-contrast MR measurements and computational fluid dynamics simulations.

Project description:Our purpose was to compare quantitatively velocity fields in and around experimental canine aneurysms as measured using an accelerated 4D PC-MR angiography (MRA) method and calculated based on animal-specific CFD simulations.Two animals with a surgically created bifurcation aneurysm were imaged using an accelerated 4D PC-MRA method. Meshes were created based on the geometries obtained from the PC-MRA and simulations using "subject-specific" pulsatile velocity waveforms and geometries were then solved using a commercial CFD solver. Qualitative visual assessments and quantitative comparisons of the time-resolved velocity fields obtained from the PC-MRA measurements and the CFD simulations were performed using a defined similarity metric combining both angular and magnitude differences of vector fields.PC-MRA and image-based CFD not only yielded visually consistent representations of 3D streamlines in and around both aneurysms, but also showed good agreement with regard to the spatial velocity distributions. The estimated similarity between time-resolved velocity fields from both techniques was reasonably high (mean value >0.60; one being the highest and zero being the lowest). Relative differences in inflow and outflow zones among selected planes were also reasonable (on the order of 10%-20%). The correlation between CFD-calculated and PC-MRA-measured time-averaged wall shear stresses was low (0.22 and 0.31, p < 0.001).In two experimental canine aneurysms, PC-MRA and image-based CFD showed favorable agreement in intra-aneurismal velocity fields. Combining these two complementary techniques likely will further improve the ability to characterize and interpret the complex flow that occurs in human intracranial aneurysms.

| S-EPMC3223510 | biostudies-other

Machine Learning Strategy for Accelerated Design of Polymer Dielectrics.

Project description:The ability to efficiently design new and advanced dielectric polymers is hampered by the lack of sufficient, reliable data on wide polymer chemical spaces, and the difficulty of generating such data given time and computational/experimental constraints. Here, we address the issue of accelerating polymer dielectrics design by extracting learning models from data generated by accurate state-of-the-art first principles computations for polymers occupying an important part of the chemical subspace. The polymers are 'fingerprinted' as simple, easily attainable numerical representations, which are mapped to the properties of interest using a machine learning algorithm to develop an on-demand property prediction model. Further, a genetic algorithm is utilised to optimise polymer constituent blocks in an evolutionary manner, thus directly leading to the design of polymers with given target properties. While this philosophy of learning to make instant predictions and design is demonstrated here for the example of polymer dielectrics, it is equally applicable to other classes of materials as well.

| S-EPMC4753456 | biostudies-literature

Machine learning-accelerated design and synthesis of polyelemental heterostructures.

Project description:[Figure: see text].

| S-EPMC8694626 | biostudies-literature

Super-resolution 4D flow MRI to quantify aortic regurgitation using computational fluid dynamics and deep learning.

Project description:Changes in cardiovascular hemodynamics are closely related to the development of aortic regurgitation (AR), a type of valvular heart disease. Metrics derived from blood flows are used to indicate AR onset and evaluate its severity. These metrics can be non-invasively obtained using four-dimensional (4D) flow magnetic resonance imaging (MRI), where accuracy is primarily dependent on spatial resolution. However, insufficient resolution often results from limitations in 4D flow MRI and complex aortic regurgitation hemodynamics. To address this, computational fluid dynamics simulations were transformed into synthetic 4D flow MRI data and used to train a variety of neural networks. These networks generated super-resolution, full-field phase images with an upsample factor of 4. Results showed decreased velocity error, high structural similarity scores, and improved learning capabilities from previous work. Further validation was performed on two sets of in vivo 4D flow MRI data and demonstrated success in de-noising flow images. This approach presents an opportunity to comprehensively analyse AR hemodynamics in a non-invasive manner.

| S-EPMC10220149 | biostudies-literature

Computational Fluid Dynamics data for improving freeze-dryers design.

Project description:Computational Fluid Dynamics (CFD) can be used to simulate different parts of an industrial freeze-drying equipment and to properly design them; in particular data concerning the freeze-dryer chamber and the duct connecting the chamber with the condenser, with the valves and vanes eventually present are given here, and can be used to understand the behavior of the apparatus allowing an improved design. Pilot and large scale freeze-drying chambers have been considered; data of a detailed simulation of a complete pilot scale apparatus, including duct and condenser, are included. Data on conductance of an empty duct with different L/D ratio, on disk valves with different geometry, and on mushroom valve are presented. Velocity, pressure, temperature and composition fields are reported on selected planes for chambers and valves. Results of dynamic simulations are also presented, to evaluate possible performance of monitoring devices in the chamber. Some further data, with detailed interpretation and discussion of the presented data can be found in the related research article by Barresi et al. [1] and Marchisio et al. [2].

| S-EPMC6140831 | biostudies-other

Compressed-sensing accelerated 4D flow MRI of cerebrospinal fluid dynamics.

Project description:Background4D flow magnetic resonance imaging (MRI) of CSF can make an important contribution to the understanding of hydrodynamic changes in various neurological diseases but remains limited in clinical application due to long acquisition times. The aim of this study was to evaluate the accuracy of compressed SENSE accelerated MRI measurements of the spinal CSF flow.MethodsIn 20 healthy subjects 4D flow MRI of the CSF in the cervical spine was acquired using compressed sensitivity encoding [CSE, a combination of compressed sensing and parallel imaging (SENSE) provided by the manufacturer] with acceleration factors between 4 and 10. A conventional scan using SENSE was used as reference. Extracted parameters were peak velocity, absolute net flow, forward flow and backward flow. Bland-Altman analysis was performed to determine the scan-rescan reproducibility and the agreement between SENSE and compressed SENSE. Additionally, a time accumulated flow error was calculated. In one additional subject flow of the spinal canal at the level of the entire spinal cord was assessed.ResultsAveraged acquisition times were 10:21 min (SENSE), 9:31 min (CSE4), 6:25 min (CSE6), 4:53 min (CSE8) and 3:51 min (CSE10). Acquisition of the CSF flow surrounding the entire spinal cord took 14:40 min. Bland-Altman analysis showed good agreement for peak velocity, but slight overestimations for absolute net flow, forward flow and backward flow (<?1 ml/min) in CSE4-8. Results of the accumulated flow error were similar for CSE4 to CSE8.ConclusionA quantitative analysis of acceleration factors CSE4-10 showed that CSE with an acceleration factor up to 6 is feasible. This allows a scan time reduction of 40% and enables the acquisition and analysis of the CSF flow dynamics surrounding the entire spinal cord within a clinically acceptable scan time.

| S-EPMC7364783 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data