ContourNet: Salient Local Contour Identification for Blob Detection in Plasma Fusion Simulation Data

  • Martin ImreEmail author
  • Jun Han
  • Julien Dominski
  • Michael Churchill
  • Ralph Kube
  • Choong-Seock Chang
  • Tom Peterka
  • Hanqi Guo
  • Chaoli Wang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11844)


We present ContourNet, a deep learning approach to identify salient local isocontours as blobs in large-scale 5D gyrokinetic tokamak simulation data. Blobs—regions of high turbulence that run along the edge wall down toward the diverter and can damage the tokamak—are non-well-defined features but have been empirically localized by isocontours in 2D normalized fluctuating density fields. The key of our study is to train ContourNet to follow the empirical rules to detect blobs over the time-varying simulation data. The architecture of ContourNet is a convolutional neural segmentation network: the inputs are the density field and a rasterized isocontour; the output is a set of isocontour encircling blobs. At the training stage, we feed the network with manually identified isocontours and propagated labels. At the inference stage, we extract isocontours from the segmented blob regions. Results show that our approach can achieve both high accuracy and performance, which enables scientists to understand the blob dynamics influencing the confinement of the plasma.


XGC plasma fusion Blob detection Local isocontour selection Segmentation 



This research was supported in part by the U.S. National Science Foundation through grants IIS-1455886, CNS-1629914, and DUE-1833129, and the U.S. Department of Energy through grant DE-AC02-06CH11357 and the Exascale Computing Project (17-SC-20-SC).


  1. 1.
    Bajaj, C.L., Pascucci, V., Schikore, D.R.: The contour spectrum. In: Proceedings of IEEE Visualization Conference, pp. 167–173 (1997)Google Scholar
  2. 2.
    Bruckner, S., Möller, T.: Isosurface similarity maps. Comput. Graph. Forum 29(3), 773–782 (2010)CrossRefGoogle Scholar
  3. 3.
    Carr, H., Brian, D., Brian, D.: On histograms and isosurface statistics. IEEE Trans. Vis. Comput. Graph. 12(5), 1259–1266 (2006)CrossRefGoogle Scholar
  4. 4.
    Carr, H., Snoeyink, J., Axen, U.: Computing contour trees in all dimensions. In: Proceedings of ACM Symposium on Discrete Algorithms, pp. 918–926 (2000)Google Scholar
  5. 5.
    Carr, H., Snoeyink, J., Van De Panne, M.: Flexible isosurfaces: simplifying and displaying scalar topology using the contour tree. Comput. Geom. 43(1), 42–58 (2010)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Chang, C.S., et al.: Fast low-to-high confinement mode bifurcation dynamics in a tokamak edge plasma gyrokinetic simulation. Phys. Rev. Lett. 118(17), 1–6 (2017)CrossRefGoogle Scholar
  7. 7.
    Chang, C.S., Ku, S.: Spontaneous rotation sources in a quiescent tokamak edge plasma. Phys. Plasmas 15(6), 062510 (2008)CrossRefGoogle Scholar
  8. 8.
    Chang, C.S., et al.: Compressed ion temperature gradient turbulence in diverted tokamak edge. Phys. Plasmas 16(5), 056108 (2009)CrossRefGoogle Scholar
  9. 9.
    Churchill, R.M., Chang, C.S., Ku, S., Dominski, J.: Pedestal and edge electrostatic turbulence characteristics from an XGC1 gyrokinetic simulation. Plasma Phys. Control. Fusion 59(10), 105014 (2017)CrossRefGoogle Scholar
  10. 10.
    Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016, Part II. LNCS, vol. 9901, pp. 424–432. Springer, Cham (2016). Scholar
  11. 11.
    Davis, W.M., Ko, M.K., Maqueda, R.J., Roquemore, A.L., Scotti, F., Zweben, S.J.: Fast 2-D camera control, data acquisition, and database techniques for edge studies on NSTX. Fusion Eng. Des. 89(5), 717–720 (2014)CrossRefGoogle Scholar
  12. 12.
    Dice, L.R.: Measures of the amount of ecologic association between species. Ecology 26(3), 297–302 (1945)CrossRefGoogle Scholar
  13. 13.
    D’Ippolito, D., Myra, J., Zweben, S.: Convective transport by intermittent blob-filaments: comparison of theory and experiment. Phys. Plasmas 18(6), 060501 (2011)CrossRefGoogle Scholar
  14. 14.
    Haidacher, M., Bruckner, S., Groller, E.: Volume analysis using multimodal surface similarity. IEEE Trans. Vis. Comput. Graph. 17(12), 1969–1978 (2011)CrossRefGoogle Scholar
  15. 15.
    Imre, M., Tao, J., Wang, C.: Identifying nearly equally spaced isosurfaces for volumetric data sets. Comput. Graph. 72, 82–97 (2018)CrossRefGoogle Scholar
  16. 16.
    Kube, R., Garcia, O.E., LaBombard, B., Terry, J., Zweben, S.: Blob sizes and velocities in the alcator c-mod scrape-off layer. J. Nucl. Mater. 438, S505–S508 (2013)CrossRefGoogle Scholar
  17. 17.
    Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)Google Scholar
  18. 18.
    McKinley, R., et al.: Nabla-net: a deep dag-like convolutional architecture for biomedical image segmentation. In: Crimi, A., Menze, B., Maier, O., Reyes, M., Winzeck, S., Handels, H. (eds.) BrainLes 2016. LNCS, vol. 10154, pp. 119–128. Springer, Cham (2016). Scholar
  19. 19.
    Meyer, M., Scheidegger, C.E., Schreiner, J.M., Duffy, B., Carr, H., Silva, C.T.: Revisiting histograms and isosurface statistics. IEEE Trans. Vis. Comput. Graph. 14(6), 1659–1666 (2008)CrossRefGoogle Scholar
  20. 20.
    Milletari, F., Navab, N., Ahmadi, S.A.: V-Net: fully convolutional neural networks for volumetric medical image segmentation. In: Proceedings of International Conference on 3D Vision, pp. 565–571 (2016)Google Scholar
  21. 21.
    Pascucci, V., Cole-McLaughin, K., Scorzelli, G.: Multi-resolution computation and presentation of contour trees. LLNL Technical report number UCRL-PROC-208680. Lawrence Livermore National Laboratory, Livermore (2004) Google Scholar
  22. 22.
    Pekar, V., Wiemker, R., Hempel, D.: Fast detection of meaningful isosurfaces for volume data visualization. In: Proceedings of IEEE Visualization Conference, pp. 223–230 (2001)Google Scholar
  23. 23.
    Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015, Part III. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). Scholar
  24. 24.
    Seyedhosseini, M., Sajjadi, M., Tasdizen, T.: Image segmentation with cascaded hierarchical models and logistic disjunctive normal networks. In: Proceedings of IEEE International Conference on Computer Vision, pp. 2168–2175 (2013)Google Scholar
  25. 25.
    Tao, J., et al.: Exploring time-varying multivariate volume data using matrix of isosurface similarity maps. IEEE Trans. Vis. Comput. Graph. 25(1), 1236–1245 (2019)CrossRefGoogle Scholar
  26. 26.
    Wang, G., et al.: DeepIGeoS: a deep interactive geodesic framework for medical image segmentation. arXiv preprint: arXiv:1707.00652 (2017)
  27. 27.
    Wang, G., et al.: Interactive medical image segmentation using deep learning with image-specific fine tuning. IEEE Trans. Med. Imaging 37(7), 1562–1573 (2018)CrossRefGoogle Scholar
  28. 28.
    Wu, L., et al.: Towards real-time detection and tracking of spatio-temporal features: blob-filaments in fusion plasma. IEEE Trans. Big Data 2(3), 262–275 (2016)CrossRefGoogle Scholar
  29. 29.
    Zweben, S., et al.: Edge and SOL turbulence and blob variations over a large database in NSTX. Nucl. Fusion 55(9), 093035 (2015)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Martin Imre
    • 1
    Email author
  • Jun Han
    • 1
  • Julien Dominski
    • 3
  • Michael Churchill
    • 3
  • Ralph Kube
    • 3
  • Choong-Seock Chang
    • 3
  • Tom Peterka
    • 2
  • Hanqi Guo
    • 2
  • Chaoli Wang
    • 1
  1. 1.University of Notre DameNotre DameUSA
  2. 2.Argonne National LaboratoryLemontUSA
  3. 3.Princeton Plasma Physics LaboratoryPrincetonUSA

Personalised recommendations