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.
%0 Journal Article
%1 tkachev2019local
%A Tkachev, Gleb
%A Frey, Steffen
%A Ertl, Thomas
%D 2019
%J IEEE Transactions on Visualization and Computer Graphics
%K vis(us) visus:ertl visus:tkachegb visus visus:freysn from:gtkachev
%R 10.1109/TVCG.2019.2961893
%T Local Prediction Models for Spatiotemporal Volume Visualization
%X 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.
@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.},
added-at = {2020-01-10T13:37:33.000+0100},
author = {Tkachev, Gleb and Frey, Steffen and Ertl, Thomas},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/28b2c9006e55a886ca79f64b1302c9e1c/visus},
doi = {10.1109/TVCG.2019.2961893},
interhash = {c658c4630195f65d590c2bf52b163201},
intrahash = {8b2c9006e55a886ca79f64b1302c9e1c},
issn = {2160-9306},
journal = {IEEE Transactions on Visualization and Computer Graphics},
keywords = {vis(us) visus:ertl visus:tkachegb visus visus:freysn from:gtkachev},
timestamp = {2020-01-10T12:37:33.000+0100},
title = {Local Prediction Models for Spatiotemporal Volume Visualization},
year = 2019
}
