Position within the page tree

Gleb Tkachev

M. Sc.

Doctoral Researcher
Visualization Research Center (VISUS)
Ertl Group

Contact

+49 711 685 88622
Email
Business card (VCF)

Allmandring 19
70569 Stuttgart
Deutschland
Room: 00.006

Publications

Publications:

2021
1. Tkachev, Gleb ; Frey, Steffen ; Ertl, Thomas: S4: Self-Supervised learning of Spatiotemporal Similarity. In: IEEE Transactions on Visualization and Computer Graphics, IEEE Transactions on Visualization and Computer Graphics. (2021) — ISBN 10.1109/TVCG.2021.3101418
  - BibTeX
  BibTeX
  @article{tkachev2021selfsupervised, abstract = {We introduce an ML-driven approach that enables interactive example-based queries for similar behavior in ensembles of spatiotemporal scientific data. This addresses an important use case in the visual exploration of simulation and experimental data, where data is often large, unlabeled and has no meaningful similarity measures available. We exploit the fact that nearby locations often exhibit similar behavior and train a Siamese Neural Network in a self-supervised fashion, learning an expressive latent space for spatiotemporal behavior. This space can be used to find similar behavior with just a few user-provided examples. We evaluate this approach on several ensemble datasets and compare with multiple existing methods, showing both qualitative and quantitative results.}, author = {Tkachev, Gleb and Frey, Steffen and Ertl, Thomas}, isbn = {10.1109/TVCG.2021.3101418}, journal = {IEEE Transactions on Visualization and Computer Graphics}, title = {S4: Self-Supervised learning of Spatiotemporal Similarity}, year = 2021 }
2. Heinemann, Moritz ; Frey, Steffen ; Tkachev, Gleb ; Straub, Alexander ; Sadlo, Filip ; Ertl, Thomas: Visual analysis of droplet dynamics in large-scale multiphase spray simulations. In: Journal of Visualization, Journal of Visualization. Bd. 24 (2021), Nr. 5, S. 943--961
  - BibTeX
  - Link
  BibTeX
  @article{heinemann2021visual, abstract = {We present a data-driven visual analysis approach for the in-depth exploration of large numbers of droplets. Understanding droplet dynamics in sprays is of interest across many scientific fields for both simulation scientists and engineers. In this paper, we analyze large-scale direct numerical simulation datasets of the two-phase flow of non-Newtonian jets. Our interactive visual analysis approach comprises various dedicated exploration modalities that are supplemented by directly linking to ParaView. This hybrid setup supports a detailed investigation of droplets, both in the spatial domain and in terms of physical quantities . Considering a large variety of extracted physical quantities for each droplet enables investigating different aspects of interest in our data. To get an overview of different types of characteristic behaviors, we cluster massive numbers of droplets to analyze different types of occurring behaviors via domain-specific pre-aggregation, as well as different methods and parameters. Extraordinary temporal patterns are of high interest, especially to investigate edge cases and detect potential simulation issues. For this, we use a neural network-based approach to predict the development of these physical quantities and identify irregularly advected droplets.}, author = {Heinemann, Moritz and Frey, Steffen and Tkachev, Gleb and Straub, Alexander and Sadlo, Filip and Ertl, Thomas}, day = 04, doi = {10.1007/s12650-021-00750-6}, issn = {1875-8975}, journal = {Journal of Visualization}, month = {05}, number = 5, pages = {943--961}, title = {Visual analysis of droplet dynamics in large-scale multiphase spray simulations}, url = {https://doi.org/10.1007/s12650-021-00750-6}, volume = 24, year = 2021 }
  Link
  https://doi.org/10.1007/s12650-021-00750-6
2019
1. Tkachev, Gleb ; Frey, Steffen ; Ertl, Thomas: Local Prediction Models for Spatiotemporal Volume Visualization. In: IEEE Transactions on Visualization and Computer Graphics, IEEE Transactions on Visualization and Computer Graphics. (2019)
  - BibTeX
  BibTeX
  @article{tkachev2019local, abstract = {We present a machine learning-based approach for detecting and visualizing complex behavior in spatiotemporal volumes. For this, we train models to predict future data values at a given position based on the past values in its neighborhood, capturing common temporal behavior in the data. We then evaluate the model's prediction on the same data. High prediction error means that the local behavior was too complex, unique or uncertain to be accurately captured during training, indicating spatiotemporal regions with interesting behavior. By training several models of varying capacity, we are able to detect spatiotemporal regions of various complexities. We aggregate the obtained prediction errors into a time series or spatial volumes and visualize them together to highlight regions of unpredictable behavior and how they differ between the models. We demonstrate two further volumetric applications: adaptive timestep selection and analysis of ensemble dissimilarity. We apply our technique to datasets from multiple application domains and demonstrate that we are able to produce meaningful results while making minimal assumptions about the underlying data.}, author = {Tkachev, Gleb and Frey, Steffen and Ertl, Thomas}, doi = {10.1109/TVCG.2019.2961893}, issn = {2160-9306}, journal = {IEEE Transactions on Visualization and Computer Graphics}, title = {Local Prediction Models for Spatiotemporal Volume Visualization}, year = 2019 }
2. Tabiai, Ilyass ; Tkachev, Gleb ; Diehl, Patrick ; Frey, Steffen ; Ertl, Thomas ; Therriault, Daniel ; Lévesque, Martin: Hybrid image processing approach for autonomous crack area detection and tracking using local digital image correlation results applied to single-fiber interfacial debonding. In: Engineering Fracture Mechanics, Engineering Fracture Mechanics. Bd. 216 (2019), S. 106485
  - BibTeX
  - Link
  BibTeX
  @article{tabiai2019hybrid, abstract = {Local digital image correlation is a popular method for accurate full field displacement measurements. However, the technique struggles at autonomously tracking emerging and propagating cracks. We proposed a hybrid approach which utilizes image processing techniques in combination with local digital image correlation to autonomously monitor cracks in a mechanically loaded specimen. Our approach can extract and track crack surfaces and provide a volume-based visualization of the crack growth. This approach was applied to single-fiber composite experimental results with interfacial debonding from the literature. Results quantitatively show that strong interfacial fiber/matrix bonding leads to slower interfacial crack growth, delays interfacial crack growth in the matrix, requires higher loadings for crack growth and shows a specific crack path distinct from the one obtained for weak interfaces. The approach was also validated against a manual approach where a domain scientist extracts a crack using a polygon extraction tool. The method can be used on any local digital image correlation results involving damage observations.}, author = {Tabiai, Ilyass and Tkachev, Gleb and Diehl, Patrick and Frey, Steffen and Ertl, Thomas and Therriault, Daniel and Lévesque, Martin}, doi = {https://doi.org/10.1016/j.engfracmech.2019.106485}, issn = {0013-7944}, journal = {Engineering Fracture Mechanics}, pages = 106485, title = {Hybrid image processing approach for autonomous crack area detection and tracking using local digital image correlation results applied to single-fiber interfacial debonding}, url = {http://www.sciencedirect.com/science/article/pii/S0013794418312530}, volume = 216, year = 2019 }
  Link
  http://www.sciencedirect.com/science/article/pii/S0013794418312530
2017
1. Tkachev, Gleb ; Frey, Steffen ; Müller, Christoph ; Bruder, Valentin ; Ertl, Thomas: Prediction of Distributed Volume Visualization Performance to Support Render Hardware Acquisition. In: Proceedings of the Eurographics Symposium on Parallel Graphics and Visualization (EGPGV), Proceedings of the Eurographics Symposium on Parallel Graphics and Visualization (EGPGV) : Eurographics Association, 2017, S. 11–20
  - BibTeX
  - Link
  BibTeX
  @inproceedings{tkachev2017prediction, abstract = {We present our data-driven, neural network-based approach to predicting the performance of a distributed GPU volume renderer for supporting cluster equipment acquisition. On the basis of timing measurements from a single cluster as well as from individual GPUs, we are able to predict the performance gain of upgrading an existing cluster with additional or faster GPUs, or even purchasing of a new cluster with a comparable network configuration. To achieve this, we employ neural networks to capture complex performance characteristics. However, merely relying on them for the prediction would require the collection of training data on multiple clusters with different hardware, which is impractical in most cases. Therefore, we propose a two-level approach to prediction, distinguishing between node and cluster level. On the node level, we generate performance histograms on individual nodes to capture local rendering performance. These performance histograms are then used to emulate the performance of different rendering hardware for cluster-level measurement runs. Crucially, this variety allows the neural network to capture the compositing performance of a cluster separately from the rendering performance on individual nodes. Therefore, we just need a performance histogram of the GPU of interest to generate a prediction. We demonstrate the utility of our approach using different cluster configurations as well as a range of image and volume resolutions.}, author = {Tkachev, Gleb and Frey, Steffen and Müller, Christoph and Bruder, Valentin and Ertl, Thomas}, doi = {10.2312/pgv.20171089}, journal = {Proceedings of the Eurographics Symposium on Parallel Graphics and Visualization (EGPGV)}, pages = {11-20}, publisher = {Eurographics Association}, title = {Prediction of Distributed Volume Visualization Performance to Support Render Hardware Acquisition}, url = {http://dx.doi.org/10.2312/pgv.20171089}, year = 2017 }
  Link
  http://dx.doi.org/10.2312/pgv.20171089

Gleb Tkachev

Contact

Publications

2021

BibTeX

BibTeX

Link

2019

BibTeX

BibTeX

Link

2017

BibTeX

Link

Audience

Formalities

Services

Organization

Gleb Tkachev

Contact

Publications

2021

BibTeX

BibTeX

Link

2019

BibTeX

BibTeX

Link

2017

BibTeX

Link

Here you can reach us

Audience

Formalities

Services

Organization