Skip to main content
SpringerLink
Log in

A scalable Bayesian nonparametric model for large spatio-temporal data

  • Original paper
  • Published:
Computational Statistics Aims and scope Submit manuscript

Abstract

The Bayesian nonparametric (BNP) approach is an effective tool for building flexible spatio-temporal probability models. Despite the flexibility and attractiveness of this approach, the resulting spatio-temporal models become computationally demanding when datasets are large. This paper develops a class of computationally efficient and easy to implement BNP models for large spatio-temporal data. To be more specific, we introduce a random distribution for the spatio-temporal effects based on a stick-breaking construction in which the atoms are modeled in terms of a basis system. In this framework, a low rank basis approximation and a vector autoregressive process are used to model spatial and temporal dependencies, respectively. We demonstrate that the proposed model is an extension of the Gaussian low rank model with similar computational complexity, hence it offers great scalability for large spatio-temporal data. Through a simulation study, we assess the performance of the proposed model. For illustration, we then analyze a set of data comprised of precipitation measurements.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  • Bandyopadhyay S, Rao SS (2017) A test for stationarity for irregularly spaced spatial data. J R Stat Soc Ser B (Stat Method) 79(1):95–123

    MathSciNet  MATH  Google Scholar 

  • Banerjee S, Gelfand AE, Finley AO, Sang H (2008) Gaussian predictive process models for large spatial data sets. J R Stat Soc Ser B (Stat Methodol) 70(4):825–848

    MathSciNet  MATH  Google Scholar 

  • Banerjee S, Finley AO, Waldmann P, Ericsson T (2010) Hierarchical spatial process models for multiple traits in large genetic trials. J Am Stat Assoc 105(490):506–521

    MathSciNet  MATH  Google Scholar 

  • Bradley JR, Cressie N, Shi T (2011) Selection of rank and basis functions in the spatial random effects model. In: Proceedings of the 2011 joint statistical meetings. American Statistical Association, Alexandria, pp 3393–3406

  • Bradley JR, Cressie N, Shi T (2015) Comparing and selecting spatial predictors using local criteria. Test 24(1):1–28

    MathSciNet  MATH  Google Scholar 

  • Bradley JR, Cressie N, Shi T (2016) A comparison of spatial predictors when datasets could be very large. Stat Surv 10:100–131

    MathSciNet  MATH  Google Scholar 

  • Canale A, Scarpa B (2016) Bayesian nonparametric location–scale–shape mixtures. Test 25(1):113–130

    MathSciNet  MATH  Google Scholar 

  • Carter CK, Kohn R (1994) On Gibbs sampling for state space models. Biometrika 81:541–553

    MathSciNet  MATH  Google Scholar 

  • Cavatti Vieira C, Loschi RH, Duarte D (2015) Nonparametric mixtures based on skew-normal distributions: an application to density estimation. Commun Stat Theory Methods 44(8):1552–1570

    MathSciNet  MATH  Google Scholar 

  • Cressie N, Johannesson G (2008) Fixed rank kriging for very large spatial data sets. J R Stat Soc Ser B (Stat Methodol) 70(1):209–226

    MathSciNet  MATH  Google Scholar 

  • Cressie N, Shi T, Kang EL (2010) Fixed rank filtering for spatio-temporal data. J Comput Graph Stat 19(3):724–745

    MathSciNet  Google Scholar 

  • Di Lucca MA, Guglielmi A, Müller P, Quintana FA (2013) A simple class of Bayesian nonparametric autoregression models. Bayesian Anal (Online) 8(1):63

    MathSciNet  MATH  Google Scholar 

  • Duan JA, Guindani M, Gelfand AE (2007) Generalized spatial Dirichlet process models. Biometrika 94(4):809–825

    MathSciNet  MATH  Google Scholar 

  • Escobar MD, West M (1995) Bayesian density estimation and inference using mixtures. J Am Stat Assoc 90(430):577–588

    MathSciNet  MATH  Google Scholar 

  • Finley AO, Banerjee S, Gelfand AE (2012) Bayesian dynamic modeling for large space–time datasets using Gaussian predictive processes, vol 14. Springer, Berlin

    Google Scholar 

  • Frühwirth-Schnatter S (1994) Data augmentation and dynamic linear models. J Time Ser Anal 15(2):183–202

    MathSciNet  MATH  Google Scholar 

  • Furrer R, Genton MG, Nychka D (2006) Covariance tapering for interpolation of large spatial datasets. J Comput Graph Stat 15(3):502–523

    MathSciNet  Google Scholar 

  • Gelfand AE, Kottas A, MacEachern SN (2005) Bayesian nonparametric spatial modeling with Dirichlet process mixing. J Am Stat Assoc 100(471):1021–1035

    MathSciNet  MATH  Google Scholar 

  • Gelfand AE, Diggle P, Guttorp P, Fuentes M (eds) (2010) Handbook of spatial statistics. CRC Press, Cambridge

    MATH  Google Scholar 

  • Gelfand AE, Banerjee S, Finley A (2012) Spatial design for knot selection in knot-based dimension reduction models. In: Mateu JM, Mueller W (eds) Spatio-temporal design: Advances in efficient data acquisition. Wiley, pp 142–169

  • Ghosal S, Ghosh JK, Ramamoorthi RV (1999) Posterior consistency of Dirichlet mixtures in density estimation. Ann Stat 27(1):143–158

    MathSciNet  MATH  Google Scholar 

  • Griffin JE, Steel MF (2011) Stick-breaking autoregressive processes. J Econom 162(2):383–396

    MathSciNet  MATH  Google Scholar 

  • Gutiérrez L, Mena RH, Ruggiero M (2016) A time dependent bayesian nonparametric model for air quality analysis. Comput Stat Data Anal 95:161–175

    MathSciNet  MATH  Google Scholar 

  • Hanson T, Johnson WO (2002) Modeling regression error with a mixture of Polya trees. J Am Stat Assoc 97(460):1020–1033

    MathSciNet  MATH  Google Scholar 

  • Hastings WK (1970) Monte Carlo sampling methods using Markov chains and their applications. Biometrika 57:97–109

    MathSciNet  MATH  Google Scholar 

  • Heaton MJ, Katzfuss M, Berrett C, Nychka DW (2014) Constructing valid spatial processes on the sphere using kernel convolutions. Environmetrics 25:2–15

    MathSciNet  Google Scholar 

  • Higdon D (1998) A process-convolution approach to modelling temperatures in the North Atlantic Ocean. Environ Ecol Stat 5(2):173–190

    Google Scholar 

  • Hosseinpouri M, Khaledi MJ (2019) An area-specific stick breaking process for spatial data. Stat Pap 60(1):199–221

    MathSciNet  MATH  Google Scholar 

  • Kalli M, Griffin JE (2018) Bayesian nonparametric vector autoregressive models. J Econom 203(2):267–282

    MathSciNet  MATH  Google Scholar 

  • Kalli M, Griffin JE, Walker SG (2011) Slice sampling mixture models. Stat Comput 21(1):93–105

    MathSciNet  MATH  Google Scholar 

  • Kang EL, Cressie N, Shi T (2010) Using temporal variability to improve spatial mapping with application to satellite data. Can J Stat 38(2):271–289

    MathSciNet  MATH  Google Scholar 

  • Katzfuss M (2013) Bayesian nonstationary spatial modeling for very large datasets. Environmetrics 24(3):189–200

    MathSciNet  Google Scholar 

  • Katzfuss M, Cressie N (2011) Bayesian hierarchical spatio-temporal smoothing for very large datasets. Environmetrics 23(1):94–107

    MathSciNet  MATH  Google Scholar 

  • Kaufman L, Rousseeuw P (1990) Finding groups in data, vol 16. Wiley, New York

    MATH  Google Scholar 

  • Lemos RT, Sanso B (2009) A spatio-temporal model for mean, anomaly, and trend fields of North Atlantic sea surface temperature. J Am Stat Assoc 104(485):5–18

    MathSciNet  Google Scholar 

  • Metropolis N, Rosenbluth AW, Rosenbluth MN, Teller AH, Teller E (1953) Equation of state calculations by fast computing machines. J Chem Phys 21(6):1087–1092

    Google Scholar 

  • Nieto-Barajas LE, Contreras-Cristán A (2014) A Bayesian nonparametric approach for time series clustering. Bayesian Anal 9(1):147–170

    MathSciNet  MATH  Google Scholar 

  • Nieto-Barajas L, Müller P, Ji Y, Lu Y, Mills G (2008) Time series dependent Dirichlet process. Preprint

  • Nguyen H, Cressie N, Braverman A (2012) Spatial statistical data fusion for remote sensing applications. J Am Stat Assoc 107(499):1004–1018

    MathSciNet  MATH  Google Scholar 

  • Pati D, Dunson DB, Tokdar ST (2013) Posterior consistency in conditional distribution estimation. J Multivar Anal 116:456–472

    MathSciNet  MATH  Google Scholar 

  • Petrone S, Guindani M, Gelfand AE (2009) Hybrid Dirichlet mixture models for functional data. J R Stat Soc Ser B (Stat Methodol) 71(4):755–782

    MathSciNet  MATH  Google Scholar 

  • Reich BJ, Fuentes M (2007) A multivariate semiparametric Bayesian spatial modeling framework for hurricane surface wind fields. Ann Appl Stat 1:249–264

    MathSciNet  MATH  Google Scholar 

  • Reich BJ, Fuentes M (2012) Nonparametric Bayesian models for a spatial covariance. Stat Methodol 9(1–2):265–274

    MathSciNet  MATH  Google Scholar 

  • Rue H, Held L (2005) Gaussian Markov random fields: theory and applications. CRC Press, Cambridge

    MATH  Google Scholar 

  • Rue H, Tjelmeland H (2002) Fitting Gaussian Markov random fields to Gaussian fields. Scand J Stat 29(1):31–49

    MathSciNet  MATH  Google Scholar 

  • Sahr K, White D, Kimerling AJ (2003) Geodesic discrete global grid systems. Cartogr Geogr Inf Sci 30(2):121–134

    Google Scholar 

  • Schörgendorfer A, Branscum AJ, Hanson TE (2013) A Bayesian goodness of fit test and semiparametric generalization of logistic regression with measurement data. Biometrics 69(2):508–519

    MathSciNet  MATH  Google Scholar 

  • Spiegelhalter DJ, Best NG, Carlin BP, van der Linde A (2002) Bayesian measures of model complexity and fit (with Discussion). J Roy Stat Soc B 64:583–639

    MATH  Google Scholar 

  • Stein ML (2014) Limitations on low rank approximations for covariance matrices of spatial data. Spat Stat 8:1–19

    MathSciNet  Google Scholar 

  • Stein ML, Chi Z, Welty LJ (2004) Approximating likelihoods for large spatial data sets. J R Stat Soc Ser B (Stat Methodol) 66(2):275–296

    MathSciNet  MATH  Google Scholar 

  • Vecchia AV (1988) Estimation and model identification for continuous spatial processes. J R Stat Soc Ser B (Methodol) 50(2):297–312

    MathSciNet  Google Scholar 

  • Walker SG (2007) Sampling the Dirichlet mixture model with slices. Commun Stat Simul Comput 36(1):45–54

    MathSciNet  MATH  Google Scholar 

  • Walker SG, Mallick BK (1999) Semiparametric accelerated life time model. Biometrics 55:477–483

    MathSciNet  MATH  Google Scholar 

  • Warren J, Fuentes M, Herring A, Langlois P (2012) Bayesian spatial–temporal model for cardiac congenital anomalies and ambient air pollution risk assessment. Environmetrics 23(8):673–684

    MathSciNet  Google Scholar 

  • West M, Harrison J (1997) Bayesian forecasting and dynamic models, 2nd edn. Springer, New York

    MATH  Google Scholar 

  • Xu K, Wikle CK, Fox NI (2005) A kernel-based spatio-temporal dynamical model for nowcasting weather radar reflectivities. J Am Stat Assoc 100(472):1133–1144

    MathSciNet  MATH  Google Scholar 

Download references

Acknowledgements

The Editor, and two referees are gratefully acknowledged. Their precise comments and constructive suggestions have substantially improved the manuscript.

Author information

Authors and Affiliations

  1. Department of Statistics, Faculty of Mathematical Sciences, Shahid Beheshti University, Tehran, Iran

    Zahra Barzegar & Firoozeh Rivaz

Authors
  1. Zahra Barzegar
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Firoozeh Rivaz
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Firoozeh Rivaz.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 67 KB)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Barzegar, Z., Rivaz, F. A scalable Bayesian nonparametric model for large spatio-temporal data. Comput Stat 35, 153–173 (2020). https://doi.org/10.1007/s00180-019-00905-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00180-019-00905-y

Keywords

Search

Navigation