A general framework for SPDE-based stationary random fields. (English) Zbl 07467712

Carrizo Vergara, Ricardo; Allard, Denis; Desassis, Nicolas

Bernoulli 28, No. 1, 1-32 (2022).

Summary: This paper presents theoretical advances in the application of the Stochastic Partial Differential Equation (SPDE) approach in geostatistics. We show a general approach to construct stationary models related to a wide class of linear SPDEs, with applications to spatio-temporal models having non-trivial properties. Within the framework of Generalized Random Fields, a criterion for existence and uniqueness of stationary solutions for this class of SPDEs is proposed and proven. Their covariance are then obtained through their spectral measure. We present a result relating the covariance of the solution in the case of a White Noise source term with the covariance in a generic case through convolution. Then, we obtain a variety of SPDE-based stationary random fields. In particular, well-known results regarding the Matérn Model and Markovian models are recovered. A new relationship between the Stein model and a particular SPDE is obtained. New spatio-temporal models obtained from evolution SPDEs of arbitrary temporal derivative order are then obtained, for which properties of separability and symmetry can be controlled. We also obtain results concerning stationary solutions for physically inspired models, such as solutions to the heat equation, the advection-diffusion equation, some Langevin’s equations and the wave equation.

MSC:

62Mxx	Inference from stochastic processes
60Gxx	Stochastic processes
86Axx	Geophysics

Keywords:

evolution equation; generalized random fields; Matérn model; space-time geostatistics; SPDE approach; spectral measure; symbol function

Software:

Stem

References:

[1]	Åberg, S. and Podgórski, K. (2011). A class of non-Gaussian second order random fields. Extremes 14 187-222. · Zbl 1329.60092 · doi:10.1007/s10687-010-0119-1
[2]	Ailliot, P., Baxevani, A., Cuzol, A., Monbet, V. and Raillard, N. (2011). Space-time models for moving fields with an application to significant wave height fields. Environmetrics 22 354-369. · doi:10.1002/env.1061
[3]	Anh, V.V., Angulo, J.M. and Ruiz-Medina, M.D. (1999). Possible long-range dependence in fractional random fields. J. Statist. Plann. Inference 80 95-110. · Zbl 1039.62090 · doi:10.1016/S0378-3758(98)00244-4
[4]	Benoit, L., Allard, D. and Mariethoz, G. (2018). Stochastic rainfall modelling at sub-kilometer scale. Water Resour. Res. 54 4108-4130.
[5]	Bolin, D. (2014). Spatial Matérn fields driven by non-Gaussian noise. Scand. J. Stat. 41 557-579. · Zbl 1309.62158 · doi:10.1111/sjos.12046
[6]	Bolin, D. and Kirchner, K. (2020). The rational SPDE approach for Gaussian random fields with general smoothness. J. Comput. Graph. Statist. 29 274-285. · Zbl 07499255 · doi:10.1080/10618600.2019.1665537
[7]	Bolin, D. and Lindgren, F. (2011). Spatial models generated by nested stochastic partial differential equations, with an application to global ozone mapping. Ann. Appl. Stat. 5 523-550. · Zbl 1235.60075 · doi:10.1214/10-AOAS383
[8]	Brown, P.E., Kåresen, K.F., Roberts, G.O. and Tonellato, S. (2000). Blur-generated non-separable space-time models. J. R. Stat. Soc. Ser. B. Stat. Methodol. 62 847-860. · Zbl 0957.62081 · doi:10.1111/1467-9868.00269
[9]	Cameletti, M., Lindgren, F., Simpson, D. and Rue, H. (2011). Using the SPDE approach for air quality mapping in Piemonte region. In Spatial2 Conference: Spatial Data Methods for Environmental and Ecological Processes, Foggia (IT), \(1-2 September 2011\).
[10]	Cameletti, M., Lindgren, F., Simpson, D. and Rue, H. (2013). Spatio-temporal modeling of particulate matter concentration through the SPDE approach. AStA Adv. Stat. Anal. 97 109-131. · Zbl 1443.62401 · doi:10.1007/s10182-012-0196-3
[11]	Chilès, J.-P. and Delfiner, P. (2012). Geostatistics: Modeling Spatial Uncertainty, 2nd ed. Wiley Series in Probability and Statistics. Hoboken, NJ: Wiley. · Zbl 1256.86007 · doi:10.1002/9781118136188
[12]	De Iaco, S., Myers, D.E. and Posa, D. (2001). Space-time analysis using a general product-sum model. Statist. Probab. Lett. 52 21-28. · Zbl 1129.62413 · doi:10.1016/S0167-7152(00)00200-5
[13]	De Iaco, S., Myers, D.E. and Posa, D. (2002). Nonseparable space-time covariance models: Some parametric families. Math. Geol. 34 23-42. · Zbl 1033.86003 · doi:10.1023/A:1014075310344
[14]	Demengel, F. and Demengel, G. (2000). Mesures et Distributions. Théorie et Illustrations Par les Exemples. Paris: Ellipses Universités.
[15]	Dierolf, P. and Voigt, J. (1978). Convolution and \[{S^{\prime }}\]-convolution of distributions. Collect. Math. 29 185-196. · Zbl 0439.46029
[16]	Dong, A. (1990). Estimation géostatistique des phénomènes régis par des équations aux dérivées partielles (Doctoral dissertation. Paris, ENMP.
[17]	Donoghue, W.F. Jr. (1969). Distributions and Fourier Transforms. Pure and Applied Mathematics 32. New York: Academic Press. · Zbl 0188.18102
[18]	Fuglstad, G.-A., Lindgren, F., Simpson, D. and Rue, H. (2015). Exploring a new class of non-stationary spatial Gaussian random fields with varying local anisotropy. Statist. Sinica 25 115-133. · Zbl 1480.62194
[19]	Gay, R. and Heyde, C.C. (1990). On a class of random field models which allows long range dependence. Biometrika 77 401-403. · Zbl 0711.62086 · doi:10.1093/biomet/77.2.401
[20]	Gel’fand, I.M. and Vilenkin, N.Ya. (1964). Generalized Functions. Vol. 4: Applications of Harmonic Analysis. New York - London: Academic Press. · Zbl 0136.11201
[21]	Gel’fand, I.M. (1955). Generalized random processes. Dokl. Akad. Nauk SSSR 100 853-856. · Zbl 0068.11201
[22]	Gneiting, T. (2002). Nonseparable, stationary covariance functions for space-time data. J. Amer. Statist. Assoc. 97 590-600. · Zbl 1073.62593 · doi:10.1198/016214502760047113
[23]	Gneiting, T., Genton, M.G. and Guttorp, P. (2006). Geostatistical space-time models, stationarity, separability, and full symmetry. Monogr. Statist. Appl. Probab. 107 151. · Zbl 1282.86019
[24]	Gradshteyn, I.S. and Ryzhik, I.M. (1996). Table of Integrals, Series, and Products, 5th ed. San Diego, CA: Academic Press. · Zbl 0918.65001
[25]	Heine, V. (1955). Models for two-dimensional stationary stochastic processes. Biometrika 42 170-178. · Zbl 0067.36504 · doi:10.1093/biomet/42.1-2.170
[26]	Herrmann, L., Kirchner, K. and Schwab, C. (2020). Multilevel approximation of Gaussian random fields: Fast simulation. Math. Models Methods Appl. Sci. 30 181-223. · Zbl 1448.60110 · doi:10.1142/s0218202520500050
[27]	Hörmander, L. (2007). The Analysis of Linear Partial Differential Operators. III: Pseudo-Differential Operators. Classics in Mathematics. Berlin: Springer. · Zbl 1115.35005 · doi:10.1007/978-3-540-49938-1
[28]	Hristopulos, D.T. and Tsantili, I.C. (2016). Space-time models based on random fields with local interactions. Internat. J. Modern Phys. B 30 1541007, 26. · Zbl 1397.62610 · doi:10.1142/S0217979215410076
[29]	Huang, J., Malone, B.P., Minasny, B., McBratney, A.B. and Triantafilis, J. (2017). Evaluating a Bayesian modelling approach (INLA-SPDE) for environmental mapping. Sci. Total Environ. 609 621-632.
[30]	Itô, K. (1954). Stationary random distributions. Mem. Coll. Sci., Univ. Kyoto, Ser. A: Math. 28 209-223. · Zbl 0059.11505 · doi:10.1215/kjm/1250777359
[31]	Jones, R.H. and Zhang, Y. (1997). Models for continuous stationary space-time processes. In Modelling Longitudinal and Spatially Correlated Data 289-298. New York, NY: Springer. · Zbl 0897.62103
[32]	Kelbert, M.Ya., Leonenko, N.N. and Ruiz-Medina, M.D. (2005). Fractional random fields associated with stochastic fractional heat equations. Adv. in Appl. Probab. 37 108-133. · Zbl 1102.60049 · doi:10.1239/aap/1113402402
[33]	Lang, A. and Potthoff, J. (2011). Fast simulation of Gaussian random fields. Monte Carlo Methods Appl. 17 195-214. · Zbl 1226.65008 · doi:10.1515/mcma.2011.009
[34]	Lindgren, F., Rue, H. and Lindström, J. (2011). An explicit link between Gaussian fields and Gaussian Markov random fields: The stochastic partial differential equation approach. J. R. Stat. Soc. Ser. B. Stat. Methodol. 73 423-498. · Zbl 1274.62360 · doi:10.1111/j.1467-9868.2011.00777.x
[35]	Lindgren, G. (2013). Stationary Stochastic Processes: Theory and Applications. Chapman & Hall/CRC Texts in Statistical Science Series. Boca Raton, FL: CRC Press. · Zbl 1281.60002
[36]	Liu, X., Guillas, S. and Lai, M.-J. (2016). Efficient spatial modeling using the SPDE approach with bivariate splines. J. Comput. Graph. Statist. 25 1176-1194. · doi:10.1080/10618600.2015.1081597
[37]	Mainardi, F., Luchko, Y. and Pagnini, G. (2001). The fundamental solution of the space-time fractional diffusion equation. Fract. Calc. Appl. Anal. 4 153-192. · Zbl 1054.35156
[38]	Matheron, G. (1965). Les variables régionalisées et leur estimation: Une application de la théorie des fonctions aléatoires aux sciences de la nature. Masson et CIE.
[39]	Mena, H. and Pfurtscheller, L. (2019). An efficient SPDE approach for El Niño. Appl. Math. Comput. 352 146-156. · Zbl 1428.86005 · doi:10.1016/j.amc.2019.01.071
[40]	Opitz, T. (2017). Latent Gaussian modeling and INLA: A review with focus on space-time applications. J. SFdS 158 62-85. · Zbl 1378.62095
[41]	Pereira, M. (2019). Generalized random fields on Riemannian manifolds: Theory and practice Doctoral dissertation, PSL Research University.
[42]	Porcu, E., Mateu, J. and Christakos, G. (2009). Quasi-arithmetic means of covariance functions with potential applications to space-time data. J. Multivariate Anal. 100 1830-1844. · Zbl 1166.62071 · doi:10.1016/j.jmva.2009.02.013
[43]	Reed, M. and Simon, B. (1980). Methods of Modern Mathematical Physics. I. Functional Analysis. London: Academic Press. · Zbl 0459.46001
[44]	Rozanov, Ju.A. (1977). Markovian random fields, and stochastic partial differential equations. Math. USSR, Sb. 32 515-534. · Zbl 0396.60057
[45]	Rozanov, Yu.A. (1982). Markov Random Fields. Applications of Mathematics. New York-Berlin: Springer. · Zbl 0498.60057
[46]	Rudin, W. (1987). Real and Complex Analysis, 3rd ed. New York: McGraw-Hill. · Zbl 0925.00005
[47]	Ruiz-Medina, M.D., Angulo, J.M., Christakos, G. and Fernández-Pascual, R. (2016). New compactly supported spatiotemporal covariance functions from SPDEs. Stat. Methods Appl. 25 125-141. · Zbl 1416.62302 · doi:10.1007/s10260-015-0333-8
[48]	Schwartz, L. (1966). Théorie des Distributions. Paris: Hermann. · Zbl 0149.09501
[49]	Sigrist, F., Künsch, H.R. and Stahel, W.A. (2015). Stochastic partial differential equation based modelling of large space-time data sets. J. R. Stat. Soc. Ser. B. Stat. Methodol. 77 3-33. · Zbl 1414.62405 · doi:10.1111/rssb.12061
[50]	Simpson, D., Lindgren, F. and Rue, H. (2012). In order to make spatial statistics computationally feasible, we need to forget about the covariance function. Environmetrics 23 65-74. · doi:10.1002/env.1137
[51]	Stein, M.L. (2005). Space-time covariance functions. J. Amer. Statist. Assoc. 100 310-321. · Zbl 1117.62431 · doi:10.1198/016214504000000854
[52]	Trèves, F. (1967). Topological Vector Spaces, Distributions and Kernels. New York: Academic Press. · Zbl 0171.10402
[53]	Vecchia, A.V. (1985). A general class of models for stationary two-dimensional random processes. Biometrika 72 281-291. · Zbl 0565.60037 · doi:10.1093/biomet/72.2.281
[54]	Whittle, P. (1963). Stochastic processes in several dimensions. Bull. Int. Stat. Inst. 40 974-994 · Zbl 0129.10603