SSR-VFD: Spatial Super-Resolution for Vector Field Data Analysis and Visualization

Guo, Li; Ye, Shaojie; Han, Jun; Zheng, Hao; Gao, Han; Chen, Danny Z.; Wang, Jianxun; Wang, Chaoli

doi:10.1109/pacificvis48177.2020.8737

Cited by 53 publications

(39 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of neural-network-based inference of data samples in the context of in situ visualization was demonstrated by Han and Wang (2020), by letting networks learn to infer missing time steps between 3D simulation results. Guo et al (2020) designed a deep learning framework that produces spatial superresolution of 3D vector field data. They demonstrate the downsampling of vector field data at simulation time and upsample the reduced data back to the original resolution.…”

Section: Upscaling Of Images and Physical Fieldsmentioning

confidence: 99%

See 1 more Smart Citation

A comparative study of convolutional neural network models for wind field downscaling

Höhlein

Kern

Hewson

et al. 2020

Meteorological Applications

View full text Add to dashboard Cite

We analyze the applicability of convolutional neural network (CNN) architectures for downscaling of short‐range forecasts of near‐surface winds on extended spatial domains. Short‐range wind forecasts (at the 100 m level) from European Centre for Medium Range Weather Forecasts ERA5 reanalysis initial conditions at 31 km horizontal resolution are downscaled to mimic high resolution (HRES) (deterministic) short‐range forecasts at 9 km resolution. We evaluate the downscaling quality of four exemplary CNN architectures and compare these against a multilinear regression model. We conduct a qualitative and quantitative comparison of model predictions and examine whether the predictive skill of CNNs can be enhanced by incorporating additional atmospheric variables, such as geopotential height and forecast surface roughness, or static high‐resolution fields, like land–sea mask and topography. We further propose DeepRU, a novel U‐Net‐based CNN architecture, which is able to infer situation‐dependent wind structures that cannot be reconstructed by other models. Inferring a target 9 km resolution wind field from the low‐resolution input fields over the Alpine area takes less than 10 ms on our graphics processing unit target architecture, which compares favorably to an overhead in simulation time of minutes or hours between low‐ and high‐resolution forecast simulations.

show abstract

Section: Upscaling Of Images and Physical Fieldsmentioning

confidence: 99%

“…Guo et al . (2020) designed a deep learning framework that produces spatial super‐resolution of 3D vector field data. They demonstrate the downsampling of vector field data at simulation time and upsample the reduced data back to the original resolution.…”

Section: Related Workmentioning

confidence: 99%

A comparative study of convolutional neural network models for wind field downscaling

Höhlein

Kern

Hewson

et al. 2020

Meteorological Applications

View full text Add to dashboard Cite

show abstract

“…In recent years, the scientific visualization community has seen an increased adoption of deep learning ( [6, 15, 23-25, 27, 36, 62]), including multiple research projects that consider vector field data ( [19,21,22,31,32,39,48]). With respect to exploratory Lagrangianbased particle advection schemes, the use of deep learning has not previously been studied to the best of our knowledge.…”

Section: Introductionmentioning

confidence: 99%

Exploratory Lagrangian-Based Particle Tracing Using Deep Learning

Han,

Sane,

Johnson

2021

Preprint

View full text Add to dashboard Cite

Time-varying vector fields produced by computational fluid dynamics simulations are often prohibitively large and pose challenges for accurate interactive analysis and exploration. To address these challenges, reduced Lagrangian representations have been increasingly researched as a means to improve scientific time-varying vector field exploration capabilities. This paper presents a novel deep neural network-based particle tracing method to explore time-varying vector fields represented by Lagrangian flow maps. In our workflow, in situ processing is first utilized to extract Lagrangian flow maps, and deep neural networks then use the extracted data to learn flow field behavior. Using a trained model to predict new particle trajectories offers a fixed small memory footprint and fast inference. To demonstrate and evaluate the proposed method, we perform an in-depth study of performance using a well-known analytical data set, the Double Gyre. Our study considers two flow map extraction strategies as well as the impact of the number of training samples and integration durations on efficacy, evaluates multiple sampling options for training and testing, and informs hyperparameter settings. Overall, we find our method requires a fixed memory footprint of 10.5 MB to encode a Lagrangian representation of a time-varying vector field while maintaining accuracy. For post hoc analysis, loading the trained model costs only two seconds, significantly reducing the burden of I/O when reading data for visualization. Moreover, our parallel implementation can infer one hundred locations for each of two thousand new pathlines across the entire temporal resolution in 1.3 seconds using one NVIDIA Titan RTX GPU.

show abstract

“…Machine learning techniques have recently been explored to improve the efficiency and accuracy of traditional numerical methods. Successful applications include nonlinear model order reduction [1,2,3], model augmentation [4,5,6], and super-resolution [7,8,9]. Neural networks have also been used to replace traditional PDE-based solvers, and serve as a standalone prediction tool.…”

Section: Introductionmentioning

confidence: 99%

Conditionally Parameterized, Discretization-Aware Neural Networks for Mesh-Based Modeling of Physical Systems

Xu¹,

Pradhan²,

Duraisamy³

2021

Preprint

View full text Add to dashboard Cite

The numerical simulations of physical systems are heavily dependent on meshbased models. While neural networks have been extensively explored to assist such tasks, they often ignore the interactions or hierarchical relations between input features, and process them as concatenated mixtures. In this work, we generalize the idea of conditional parametrization -using trainable functions of input parameters to generate the weights of a neural network, and extend them in a flexible way to encode information critical to the numerical simulations. Inspired by discretized numerical methods, choices of the parameters include physical quantities and mesh topology features. The functional relation between the modeled features and the parameters are built into the network architecture. The method is implemented on different networks, which are applied to several frontier scientific machine learning tasks, including the discovery of unmodeled physics, superresolution of coarse fields, and the simulation of unsteady flows with chemical reactions. The results show that the conditionally parameterized networks provide superior performance compared to their traditional counterparts. A network architecture named CP-GNet is also proposed as the first deep learning model capable of standalone prediction of reacting flows on irregular meshes.Preprint. Under review.

show abstract

SSR-VFD: Spatial Super-Resolution for Vector Field Data Analysis and Visualization

Cited by 53 publications

References 19 publications

A comparative study of convolutional neural network models for wind field downscaling

A comparative study of convolutional neural network models for wind field downscaling

Exploratory Lagrangian-Based Particle Tracing Using Deep Learning

Conditionally Parameterized, Discretization-Aware Neural Networks for Mesh-Based Modeling of Physical Systems

Contact Info

Product

Resources

About