Advertisement

GPU-Accelerated Simulation of Massive Spatial Data Based on the Modified Planar Rotator Model

  • Milan ŽukovičEmail author
  • Michal Borovský
  • Matúš Lach
  • Dionissios T. Hristopulos
Special Issue
  • 29 Downloads

Abstract

A novel Gibbs Markov random field for spatial data on Cartesian grids based on the modified planar rotator (MPR) model of statistical physics has been recently introduced for efficient and automatic interpolation of big data sets, such as satellite and radar images. The MPR model does not rely on Gaussian assumptions. Spatial correlations are captured via nearest-neighbor interactions between transformed variables. This allows vectorization of the model which, along with an efficient hybrid Monte Carlo algorithm, leads to fast execution times that scale approximately linearly with system size. The present study takes advantage of the short-range nature of the interactions between the MPR variables to parallelize the algorithm on graphics processing units (GPUs) in the Compute Unified Device Architecture programming environment. It is shown that, for the processors employed, the GPU implementation can lead to impressive computational speedups, up to almost 500 times on large grids, compared to single-processor calculations. Consequently, massive data sets comprising millions of data points can be automatically processed in less than one second on an ordinary GPU.

Keywords

Spatial interpolation Hybrid Monte Carlo Non-Gaussian model Conditional simulation GPU parallel computing CUDA 

Notes

Acknowledgements

This work was supported by the Scientific Grant Agency of Ministry of Education of Slovak Republic (Grant No. 1/0531/19). We also acknowledge support for a short visit by M. Ž. at the Technical University of Crete from the Hellenic Ministry of Education, Department of Inter-University Relations, the State Scholarships Foundation of Greece and the Slovak Republic’s Ministry of Education through the Bilateral Programme of Educational Exchanges between Greece and Slovakia.

References

  1. Atkinson P, Zhang J, Goodchild MF (2014) Scale in spatial information and analysis. CRC Press, Boca RatonGoogle Scholar
  2. Caers J, Hoffman T (2006) The probability perturbation method: a new look at Bayesian inverse modeling. Math Geol 38(1):81–100CrossRefGoogle Scholar
  3. Cheng T (2013) Accelerating universal kriging interpolation algorithm using CUDA-enabled GPU. Comput Geosci 54:178–183CrossRefGoogle Scholar
  4. Cheng T, Li D, Wang Q (2010) On parallelizing universal kriging interpolation based on OpenMP. In: Qingping G, Yucheng G (eds) 2010 ninth international symposium on distributed computing and applications to business, engineering and science (DCABES 2010). IEEE Computer Society, Los Alamitos, pp 36–39CrossRefGoogle Scholar
  5. Cressie N, Johannesson G (2018) Fixed rank kriging for very large spatial data sets. J R Stat Soc: Ser B (Stat Methodol) 70(1):209–226CrossRefGoogle Scholar
  6. Creutz M (1987) Overrelaxation and Monte Carlo simulation. Phys Rev D 36(2):515–519CrossRefGoogle Scholar
  7. de Ravé EG, Jiménez-Hornero F, Ariza-Villaverde A, Gómez-López J (2014) Using general-purpose computing on graphics processing units (GPGPU) to accelerate the ordinary kriging algorithm. Comput Geosci 64:1–6CrossRefGoogle Scholar
  8. Drummond IT, Horgan RR (1987) The effective permeability of a random medium. J Phys A: Math Gen 20(14):4661CrossRefGoogle Scholar
  9. Furrer R, Genton MG, Nychka D (2006) Covariance tapering for interpolation of large spatial datasets. J Comput Graph Stat 15(3):502–523CrossRefGoogle Scholar
  10. Guan Q, Kyriakidis PC, Goodchild MF (2011) A parallel computing approach to fast geostatistical areal interpolation. Int J Geogr Inf Sci 25(8):1241–1267CrossRefGoogle Scholar
  11. Harris M (2013) How to access global memory efficiently in CUDA C/C++ KernelsGoogle Scholar
  12. Hartman L, Hössjer O (2008) Fast kriging of large data sets with Gaussian Markov random fields. Comput Stat Data Anal 52(5):2331–2349CrossRefGoogle Scholar
  13. Hristopulos D (2003) Spartan Gibbs random field models for geostatistical applications. SIAM J Sci Comput 24(6):2125–2162CrossRefGoogle Scholar
  14. Hristopulos DT (2015) Stochastic local interaction (SLI) model. Comput Geosci 85((PB)):26–37CrossRefGoogle Scholar
  15. Hristopulos DT, Christakos G (2001) Practical calculation of non-Gaussian multivariate moments in spatiotemporal Bayesian maximum entropy analysis. Math Geol 33(5):543–568CrossRefGoogle Scholar
  16. Hristopulos DT, Elogne SN (2007) Analytic properties and covariance functions for a new class of generalized Gibbs random fields. IEEE Trans Inf Theory 53(12):4667–4679CrossRefGoogle Scholar
  17. Hu H, Shu H (2015) An improved coarse-grained parallel algorithm for computational acceleration of ordinary kriging interpolation. Comput Geosci 78:44–52CrossRefGoogle Scholar
  18. Žukovič M, Hristopulos DT (2018) Gibbs markov random fields with continuous values based on the modified planar rotator model. Phys Rev E 98(6):062135CrossRefGoogle Scholar
  19. Ingram B, Cornford D, Evans D (2008) Fast algorithms for automatic mapping with space-limited covariance functions. Stoch Env Res Risk Assess 22(5):661–670CrossRefGoogle Scholar
  20. Katzil Y, Doytsher Y (2000) Height estimation methods for filling gaps in gridded DTM. J Surv Eng 126(4):145–162CrossRefGoogle Scholar
  21. Kaufman CG, Schervish MJ, Nychka DW (2008) Covariance tapering for likelihood-based estimation in large spatial data sets. J Am Stat Assoc 103(484):1545–1555CrossRefGoogle Scholar
  22. Kerry KE, Hawick KA (1998) Kriging interpolation on high-performance computers. In: Sloot P, Bubak M, Hertzberger B (eds) High-performance computing and networking. Springer, Berlin, pp 429–438CrossRefGoogle Scholar
  23. Majumdar A, Gelfand AE (2007) Multivariate spatial modeling for geostatistical data using convolved covariance functions. Math Geol 39(2):225–245CrossRefGoogle Scholar
  24. Marcotte D, Allard D (2018) Half-tapering strategy for conditional simulation with large datasets. Stoch Environ Res Risk Assess 32(1):279–294CrossRefGoogle Scholar
  25. Mei G (2014) Evaluating the power of GPU acceleration for IDW interpolation algorithm. Sci World J 2014:1715741–8Google Scholar
  26. Mei G, Xu L, Xu N (2017) Accelerating adaptive inverse distance weighting interpolation algorithm on a graphics processing unit. Open Sci 4(9):170436Google Scholar
  27. Metropolis N, Rosenbluth AW, Rosenbluth MN, Teller AH, Teller E (1953) Equation of state calculations by fast computing machines. J Chem Phys 21(6):1087–1092CrossRefGoogle Scholar
  28. Norberg T, Rosén L, Baran A, Baran S (2002) On modelling discrete geological structures as Markov random fields. Math Geol 34(1):63–77CrossRefGoogle Scholar
  29. Nvidia (2019a) Cuda C Best Practices Guide Google Scholar
  30. Nvidia (2019b) CUDA C Programming Guide, version 10.1Google Scholar
  31. Pesquer L, Cortés A, Pons X (2011) Parallel ordinary kriging interpolation incorporating automatic variogram fitting. Comput Geosci 37(4):464–473CrossRefGoogle Scholar
  32. Poggio L, Gimona A, Brown I (2012) Spatio-temporal MODIS EVI gap filling under cloud cover: an example in Scotland. ISPRS J Photogramm Remote Sens 72:56–72CrossRefGoogle Scholar
  33. Rue H, Held L (2005) Gaussian Markov random fields: theory and applications. Chapman and Hall/CRC, Boca RatonCrossRefGoogle Scholar
  34. Savitzky A, Golay MJ (1964) Smoothing and differentiation of data by simplified least squares procedures. Anal Chem 36(8):1627–1639CrossRefGoogle Scholar
  35. Sickles JE, Shadwick DS (2007) Effects of missing seasonal data on estimates of period means of dry and wet deposition. Atmos Environ 41(23):4931–4939CrossRefGoogle Scholar
  36. Stein A, van der Meer FD, Gorte B (2002) Spatial statistics for remote sensing, vol 1. Kluwer, DordrechtCrossRefGoogle Scholar
  37. Stojanovic N, Stojanovic D (2014) High performance processing and analysis of geospatial data using CUDA on GPU. Adv Electr Comput Eng 14(4):109–114CrossRefGoogle Scholar
  38. Tahmasebi P, Sahimi M, Mariethoz G, Hezarkhani A (2012) Accelerating geostatistical simulations using graphics processing units (GPU). Comput Geosci 46:51–59CrossRefGoogle Scholar
  39. Wackernagel H (2003) Multivariate geostatistics, 3rd edn. Springer, BerlinCrossRefGoogle Scholar
  40. Weigel M (2011) Simulating spin models on GPU. Comput Phys Commun 182(9):1833–1836. ISSN 0010-4655, Computer Physics Communications Special Edition for Conference on Computational Physics Trondheim, Norway, June 23–26, 2010CrossRefGoogle Scholar
  41. Weigel M (2012) Performance potential for simulating spin models on GPU. J Comput Phys 231(8):3064–3082CrossRefGoogle Scholar
  42. Xia YJ, Kuang L, Li XM (2011) Accelerating geospatial analysis on GPUs using CUDA. J Zhejiang Univ Sci C 12(12):990–999CrossRefGoogle Scholar
  43. Zhang W, Li W, Zhang C, Zhao T (2019) Parallel computing solutions for Markov chain spatial sequential simulation of categorical fields. Int J Digit Earth 12(5):566–582CrossRefGoogle Scholar
  44. Zhang Y, Zheng X, Wang Z, Ai G, Huang Q (2018) Implementation of a parallel GPU-based space-time kriging framework. ISPRS Int J Geo-Inf 7(5):193CrossRefGoogle Scholar
  45. Zhong X, Kealy A, Duckham M (2016) Stream kriging: incremental and recursive ordinary kriging over spatiotemporal data streams. Comput Geosci 90:134–143CrossRefGoogle Scholar
  46. Žukovič M, Hristopulos DT (2009a) Classification of missing values in spatial data using spin models. Phys Rev E 80(1):011116CrossRefGoogle Scholar
  47. Žukovič M, Hristopulos DT (2009b) Multilevel discretized random field models with ’spin’ correlations for the simulation of environmental spatial data. J Stat Mech: Theory Exp 02:P02023Google Scholar
  48. Žukovič M, Hristopulos DT (2013a) A directional gradient-curvature method for gap filling of gridded environmental spatial data with potentially anisotropic correlations. Atmos Environ 77:901–909CrossRefGoogle Scholar
  49. Žukovič M, Hristopulos DT (2013b) Reconstruction of missing data in remote sensing images using conditional stochastic optimization with global geometric constraints. Stoch Environ Res Risk Assess 27(4):785–806CrossRefGoogle Scholar

Copyright information

© International Association for Mathematical Geosciences 2019

Authors and Affiliations

  1. 1.Faculty of Science, Institute of PhysicsP. J. Šafárik UniversityKošiceSlovakia
  2. 2.Geostatistics Laboratory, School of Mineral Resources EngineeringTechnical University of CreteChaniaGreece

Personalised recommendations