A penalized regression model for spatial functional data with application to the analysis of the production of waste in Venice province

Abstract

We propose a method for the analysis of functional data with complex dependencies, such as spatially dependent curves or time dependent surfaces, over highly textured domains. The models are based on the idea of regression with partial differential regularizations. In particular, we consider here two roughness penalties that account separately for the regularity of the field in space and in time. Among the various modelling features, the proposed method is able to deal with spatial domains featuring peninsulas, islands and other complex geometries. Space-time varying covariate information is included in the model via a semi-parametric framework. The proposed method is compared via simulation studies to other spatio-temporal techniques and it is applied to the analysis of the annual production of waste in the towns of Venice province.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16

Notes

  1. 1.

    http://dati.veneto.it/dataset/produzione-annua-di-rifiuti-urbani-totale-e-pro-capite-1997-2011.

  2. 2.

    http://www.dossier.net/utilities/coordinate-geografiche/.

  3. 3.

    http://www.istat.it/it/archivio/113712.

References

  1. Augustin NH, Trenkel VM, Wood SN, Lorance P (2013) Space-time modelling of blue ling for fisheries stock management. Environmetrics 24(2):109–119

    Article  Google Scholar 

  2. Azzimonti L, Sangalli LM, Secchi P, Domanin M, Nobile F (2015) Blood flow velocity field estimation via spatial regression with PDE penalization. J Am Stat Assoc 110(511):1057–1071

    CAS  Article  Google Scholar 

  3. Caballero W, Giraldo R, Mateu J (2013) A universal kriging approach for spatial functional data. Stochastic Environ Res Risk Assess 27(7):1553–1563

    Article  Google Scholar 

  4. Cressie N, Wikle CK (2011) Statistics for spatio-temporal data. Wiley, New York

    Google Scholar 

  5. Dassi F, Ettinger B, Perotto S, Sangalli LM (2015) A mesh simplification strategy for a spatial regression analysis over the cortical surface of the brain. Appl Num Math 90:111–131

    Article  Google Scholar 

  6. Delicado P, Giraldo R, Comas C, Mateu J (2010) Statistics for spatial functional data: some recent contributions. Environmetrics 21(3–4):224–239

    Google Scholar 

  7. Ettinger B, Perotto S, Sangalli LM (2016) Spatial regression models over two-dimensional manifolds. Biometrika 103(1):71–88

  8. Giraldo R, Delicado P, Mateu J (2011) Ordinary kriging for function-valued spatial data. Environ Ecol Stat 18(3):411–426

    Article  Google Scholar 

  9. Goulard M, Voltz M (1993) Geostatistical interpolation of curves: a case study in soil science. In: Geostatistics Tróia'92, Springer, pp 805–816

  10. Ignaccolo R, Mateu J, Giraldo R (2014) Kriging with external drift for functional data for air quality monitoring. Stochastic Environ Res Risk Assess 28(5):1171–1186

    Article  Google Scholar 

  11. Lila E, Sangalli LM, Ramsay J, Formaggia L (2016) fdaPDE: regression with partial differential regularizations, using the finite element method. URL: https://CRAN.R-project.org/package=fdaPDE, R package version 0.1-1

  12. Marra G, Miller DL, Zanin L (2012) Modelling the spatiotemporal distribution of the incidence of resident foreign population. Stat Neerland 66(2):133–160

    Article  Google Scholar 

  13. Menafoglio A, Secchi P, Dalla Rosa M (2013) A Universal Kriging predictor for spatially dependent functional data of a Hilbert Space. ElectronJ Stat 7:2209–2240

    Google Scholar 

  14. Menafoglio A, Guadagnini A, Secchi P (2014) A kriging approach based on Aitchison geometry for the characterization of particle-size curves in heterogeneous aquifers. Stochastic Environ Res Risk Assess 28(7):1835–1851

    Article  Google Scholar 

  15. Nerini D, Monestiez P, Manté C (2010) Cokriging for spatial functional data. J Multivar Anal 101(2):409–418

    Article  Google Scholar 

  16. Pebesma EJ (2004) Multivariable geostatistics in S: the gstat package. Comput Geosci 30:683–691

    Article  Google Scholar 

  17. R Core Team (2014) R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, URL: http://www.R-project.org/

  18. Ramsay T (2002) Spline smoothing over difficult regions. J R Stat Soc 64(2):307–319

    Article  Google Scholar 

  19. Ramsay JO, Silverman BW (2005) Functional data analysis. Springer, New York

    Google Scholar 

  20. Sangalli LM, Ramsay JO, Ramsay TO (2013) Spatial spline regression models. J R Stat Soc 75(4):681–703

    Article  Google Scholar 

  21. Schlather M, Malinowski A, Menck PJ, Oesting M, Strokorb K (2015) Analysis, simulation and prediction of multivariate random fields with package RandomFields. J Stat Softw 63(8):1–25

    Article  Google Scholar 

  22. Wilhelm M, Dedè L, Sangalli LM, Wilhelm P (2016) IGS: an IsoGeometric approach for Smoothing on surfaces. Comput Methods Appl Mechan Eng DOI 10.1016/j.cma.2015.12.028

  23. Wood S (2006) Generalized additive models: an introduction with R. CRC Press, Boca Raton

    Google Scholar 

  24. Wood SN, Bravington MV, Hedley SL (2008) Soap film smoothing. J R Stat Soc 70(5):931–955

    Article  Google Scholar 

Download references

Acknowledgments

We thank Alessandra Menafoglio for comments on this work. We are also grateful to the Associate Editor and three anonymous referees, whose suggestions greatly improved the presentation of this work. L.M. Sangalli acknowledges funding by MIUR Ministero dell’Istruzione dell’Università e della Ricerca, FIRB Futuro in Ricerca Starting Grant project “Advanced statistical and numerical methods for the analysis of high dimensional functional data in life sciences and engineering” http://mox.polimi.it/users/sangalli/firbSNAPLE.html.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Laura M. Sangalli.

Spatio-temporal test function

Spatio-temporal test function

The spatio-temporal test function f(xyt), defined over the C-shaped domain, used in the simulation studies, is constructed as:

$$\begin{aligned} \begin{array}{lr} \cos (t)(q+x)+(y-r)^2 &{}\text {if}\ \ \ x\ge 0 \ \ \& \ \ y>0 \\ \cos (2t)(-q-x)+(-y-r)^2 &{}\text {if}\ \ \ x\ge 0 \ \ \& \ \ y\le 0 \\ \cos (t)(-\arctan \left(\frac{y}{x}\right)r)+(\sqrt{x^2+y^2}-r)^2 K(x,y) &{}\text {if}\ \ \ x< 0 \ \ \& \ \ y>0 \\ \cos (2t)(-\arctan \left(\frac{y}{x}\right)r)+(\sqrt{x^2+y^2}-r)^2 K(x,y) &{}\text {if}\ \ \ x< 0 \ \ \& \ \ y\le 0 \end{array}, \end{aligned}$$

where \(K(x,y)=\left(\frac{y}{r_0}{\mathbbm{1}}_{|y|\le r_0 \& x>-r}+{\mathbbm{1}}_{|y|> r_0 || x\le -r}\right)^2\)\({\mathbbm{1}}_A\) denotes the indicator function of the subset A, \(r_0 = 0.1\), \(r = 0.5\) and \(q=\frac{\pi r}{2}\).

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Bernardi, M.S., Sangalli, L.M., Mazza, G. et al. A penalized regression model for spatial functional data with application to the analysis of the production of waste in Venice province. Stoch Environ Res Risk Assess 31, 23–38 (2017). https://doi.org/10.1007/s00477-016-1237-3

Download citation

Keywords

  • Space-time model
  • Differential regularization
  • Finite elements