Identification of Combustion Trajectories Using t-Distributed Stochastic Neighbor Embedding (t-SNE)

  • E. FooladgarEmail author
  • C. Duwig
Conference paper
Part of the ERCOFTAC Series book series (ERCO, volume 25)


With increasing computational power, direct numerical and large eddy simulation (DNS and LES) of reacting flows with complex chemistry are becoming common, e.g. Yoo et al (Proc Combust Inst, 34(2):2985–2993, 2013, [1]), Duwig and Iudiciani (Fuel 123:256–273, 2014, [2]), Fooladgar et al (Comput Fluids 146:42–50, 2017, [3]). The resulting data which may occupy hundreds of gigabytes of storage, consists of millions to billions of points each of which is described by tens to hundreds of chemical species. To explore and analyze this large, high-dimensional data, conventional visualization techniques such as scatter plots, histograms and pairs plots are limited. Human visual perception is well tuned to identify patterns and trends in graphs with one or a few data variables at a time, calling for new automated identification tools.



The financial support of the Swedish Energy Agency (Energimyndigheten) is greatly acknowledged. The simulations were run on LUNARC and HPC2N super-computing facilities within SNIC ressource allocation.


  1. 1.
    Yoo, C.S., Luo, Z., Lu, T., Kim, H., Chen, J.H.: A DNS study of ignition characteristics of a lean iso-octane/air mixture under HCCI and SACI conditions. Proc. Combust. Inst. 34(2), 2985–2993 (2013)CrossRefGoogle Scholar
  2. 2.
    Duwig, C., Iudiciani, P.: Large Eddy Simulation of turbulent combustion in a stagnation point reverse flow combustor using detailed chemistry. Fuel 123, 256–273 (2014)CrossRefGoogle Scholar
  3. 3.
    Fooladgar, E., Chan, C.K., Nogenmyr, K.J.: An accelerated computation of combustion with finite-rate chemistry using LES and an open source library for In-Situ-Adaptive Tabulation. Comput. Fluids 146, 42–50 (2017)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Maaten, L.V.D., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(Nov), 2579–2605 (2008)Google Scholar
  5. 5.
    Hamel, P., Eck, D.: Learning features from music audio with deep belief networks. In: ISMIR. Utrecht, The Netherlands, pp. 339–344 (2010)Google Scholar
  6. 6.
    Jamieson, A.R., Giger, M.L., Drukker, K., Li, H., Yuan, Y., Bhooshan, N.: Exploring nonlinear feature space dimension reduction and data representation in breast CADx with Laplacian eigenmaps and t-SNE. Med. Phys. 37(1), 339–351 (2010)CrossRefGoogle Scholar
  7. 7.
    Wallach, I., Lilien, R.: The protein-small-molecule database, a non-redundant structural resource for the analysis of protein-ligand binding. Bioinformatics 25(5), 615–620 (2009)CrossRefGoogle Scholar
  8. 8.
    Birjandtalab, J., Pouyan, M.B., Nourani, M.: Nonlinear dimension reduction for EEG-based epileptic seizure detection. In: 2016 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI). IEEE, pp. 595–598 (2016)Google Scholar
  9. 9.
    Van Der Maaten, L.: Accelerating t-SNE using tree-based algorithms. J. Mach. Learn. Res. 15(1), 3221–3245 (2014)MathSciNetzbMATHGoogle Scholar
  10. 10.
    Duwig, C., Stankovic, D., Fuchs, L., Li, G., Gutmark, E.: Experimental and numerical study of flameless combustion in a model gas turbine combustor. Combust. Sci. Technol. 180(2), 279–295 (2007)CrossRefGoogle Scholar
  11. 11.
    Chemical-Kinetic Mechanisms for Combustion Applications, Mechanical and Aerospace Engineering, University of California at San Diego.

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.KTH MechanicsLinné FLOW Centre, Royal Institute of TechnologyStockholmSweden

Personalised recommendations