Abstract
With rapid advances of geospatial technologies, the amount of spatial data has been increasing exponentially over the past few decades. Usually collected by diverse source providers, the available spatial data tend to be fragmented by a large variety of data heterogeneities, which highlights the need of sound methods capable of efficiently fusing the diverse and incompatible spatial information. Within the context of spatial prediction of categorical variables, this paper describes a statistical framework for integrating and drawing inferences from a collection of spatially correlated variables while accounting for data heterogeneities and complex spatial dependencies. In this framework, we discuss the spatial prediction of categorical variables in the paradigm of latent random fields, and represent each spatial variable via spatial covariance functions, which define two-point similarities or dependencies of spatially correlated variables. The representation of spatial covariance functions derived from different spatial variables is independent of heterogeneous characteristics and can be combined in a straightforward fashion. Therefore it provides a unified and flexible representation of heterogeneous spatial variables in spatial analysis while accounting for complex spatial dependencies. We show that in the spatial prediction of categorical variables, the sought-after class occurrence probability at a target location can be formulated as a multinomial logistic function of spatial covariances of spatial variables between the target and sampled locations. Group least absolute shrinkage and selection operator is adopted for parameter estimation, which prevents the model from over-fitting, and simultaneously selects an optimal subset of important information (variables). Synthetic and real case studies are provided to illustrate the introduced concepts, and showcase the advantages of the proposed statistical framework.
Similar content being viewed by others
References
Atkinson P, Lewis P (2000) Geostatistical classification for remote sensing: an introduction. Comput Geosci 26(4):361–371
Atkinson PM (2012) Downscaling in remote sensing. Int J Appl Earth Obs Geoinf
Barzilai J, Borwein JM (1988) Two-point step size gradient methods. IMA J Numer Anal 8(1):141–148
Birgin E, Marttinez J, Raydan M (2000) Nonmonotone spectral projected gradient methods on convex sets. SISM SISM J Optim 10:1196–1211
Bogaert P (2002) Spatial prediction of categorical variables: the Bayesian maximum entropy approach. Stoch Environ Res Risk Assess 16(6):425–448
Bogaert P, Fasbender D (2007) Bayesian data fusion in a spatial prediction context: a general formulation. Stoch Environ Res Risk Assess 21:695–709
Bogard V (1973) Soil survey of Pontotoc County, Oklahoma, U.S. Soil Conservation Service
Breslow N, Clayton D (1993) Approximate inference in generalized linear mixed models. J Am Stat Assoc 88(421):9–25
Burgess D (1977) Soil survey of Johnston County, Oklahoma, National Cooperative Soil Survey
Cao G, Kyriakidis P, Goodchild M (2011) A multinomial logistic mixed model for the prediction of categorical spatial data. Int J Geogr Inf Sci 25(12):2071–2086
Chiles J, Delfiner P (1999) Geostatistics: modeling spatial uncertainty. Wiley, New York
Christakos G (1990) A Bayesian/maximum-entropy view to the spatial estimation problem. Math Geol 22(7):763–777
Christensen O (2004) Monte Carlo maximum likelihood in model-based geostatistics. J Comput Graph Stat 13(3):702–718
Diggle P, Tawn J, Moyeed R (1998) Model-based geostatistics. Appl Stat 47(3):299–350
Fagin T, Hoagland B (2011) Patterns from the past: modeling Public Land Survey witness tree distributions with weights-of-evidence. Plant Ecol 212:207–217
Foody GM (2002) Status of land cover classification accuracy assessment. Remote Sens Environ 80:185–201
Goodchild M, Zhang J, Kyriakidis P (2009) Discriminant models of uncertainty in nominal fields. Trans GIS 13(1):7–23
Goovaerts P (1997) Geostatistics for natural resources evaluation. Oxford University Press, New York
Goovaerts P (1998) Accounting for estimation optimality criteria in simulated annealing. Math Geol 30(5):511–534
Gotway CA, Stroup WW (1997) A generalized linear model approach to spatial data analysis and prediction. J Agric Biol Environ Stat 2(2):157
Goulard M, Voltz M (1992) Linear coregionalization model: tools for estimation and choice of cross-variogram matrix. Math Geol 24(3):269–286
He H, Dey D, Fan X, Hooten M, Kabrick J, Wikle C, Fan Z (2007) Mapping pre-European settlement vegetation at fine resolutions using a hierarchical Bayesian model and GIS. Plant Ecol 11:85–94
He H, Mladenoff D, Sickley T, Guntenspergen G (2000) GIS interpolations of witness tree records (1839–1866) for Northern Wisconsin at multiple scales. J Biogeogr 27:1131–1042
Hengl T, Heuvelink G, Rossiter D (2007) About regression-kriging: from equations to case studies. Comput Geosci 33(10):1301–1315
Hengl T, Heuvelink G, Stein A (2004) A generic framework for spatial prediction of soil variables based on regression-kriging. Geoderma 120(1):75–93
Hengl T, Toomanian N, Reuter H, Malakouti M (2007) Methods to interpolate soil categorical variables from profile observations: lessons from Iran. Geoderma 140:417–427
Journel AG (1983) Nonparametric estimation of spatial distributions. Math Geol 15(3):445–468
Journel AG, Alabert F (1989) No-Gaussian data expansion in the Earth Sciences. Terra Nova 1(1):123–134
Kimeldorf G, Wahba G (1970) A correspondence between Bayesian estimation on stochastic processes and smoothing by splines. Ann Math Stat 41(2):495–502
Lanckriet GRG, De Bie T, Cristianini N, Jordan MI, Noble WS (2004) A statistical framework for genomic data fusion. Bioinformatics 20(16):2626–2635
Li D, Zhang J, Wu H (2012) Spatial data quality and beyond. Int J Geogr Inf Sci 26(12):2277–2290
Liang K, Zeger S (1986) Longitudinal data analysis using generalized linear models. Biometrika 73(1):13
Meier L, Geer SVD, Bühlmann P (2008) The group lasso for logistic regression. J R Stat Soc B 70:53–71
Miller HJ, Han J (2003) Geographic data mining and knowledge discovery. CRC Press, Boca Raton
Nocedal J (1980) Updating quasi-newton matrices with limited storage. Math Comput 35(151):773–782
Obozinski G, Taskar B, Jordan M (2007) Joint covariate selection for grouped classification, technical report, University of California, Berkeley
Pardo-Igúzquiza E, Dowd P, Pardoiguzquiza E (2005) Multiple indicator cokriging with application to optimal sampling for environmental monitoring. Comput Geosci 31(1):1–13
Rue H, Martino S, Chopin N (2009) Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations. J R Stat Soc B 71(2):319–392
Schmidt M (2010) Graphical model structure learning with l1-regularization. PhD thesis, University of British Columbia
Schmidt M, Berg EVD, Friedlander M, Murphy K (2009) Optimizing costly functions with simple constraints: a limited-memory projected quasi-newton algorithm. In: Proceedings of the 12th international conference on artificial intelligence and statistics (AISTATS), pp. 456–463
Schölkopf B, Herbrich R, Smola A (2001) A generalized representer theorem. In: Proceedings of the annual conference on computational learning theory, pp. 416–426
Schölkopf B, Smola A (2002) Learning with kernels: support vector machines, regularization, optimization, and beyond. MIT Press, Cambridge
Schoölkopf B, Tsuda K, Vert J-P (2004) Kernel methods in computational biology. MIT Press, Cambridge
Tibshirani R (1996) Regression shrinkage and selection via the lasso. J R Stat Soc 58:267–288
Tso B, Mather P (2009) Classification methods for remotely sensed data. CRC Press, Boca Raton
Wackernagel H (1998) Multivariate geostatistics—an Introduction with applications, 2nd edn. Springer, New York
Wahba G (1990) Spline models for observational data, vol. 59. Society for Industrial and Applied Mathematics, Philadelphia
West M (2003) Bayesian factor regression models in the large p, small n paradigm. Bayesian Stat 7(2003):723–732
Wibrin M, Bogaert P, Fasbender D (2006) Combining categorical and continuous spatial information within the Bayesian Maximum Entropy paradigm. Stoch Environ Res Risk Assess 20:423–433
Williams C, Barber D (2002) Bayesian classification with Gaussian processes. Pattern Anal Mach Intell IEEE Trans 20(12):1342–1351
Yoo E-H, Hoagland BW, Cao G, Fagin T (2013) Spatial distribution of trees and landscapes of the past: a mixed spatially correlated multinomial logit model approach for the analysis of the public land survey data. Geogr Anal 45(4):419–440
Yoo E-H, Trgovac A (2011) Scale effects in uncertainty modeling of presettlement vegetation distribution. Int J Geogr Inf Sci 25(3):405–421
Yuan M, Lin Y (2006) Model selection and estimation in regression with grouped variables. J R Stat Soc B 68:49–67
Zhang H (2002) On estimation and prediction for spatial generalized linear mixed models. Biometrics 58(1):129–136
Zhang J, Goodchild M (2002) Uncertainty in geographic information. Taylor & Francis, London
Acknowledgments
We gratefully acknowledge the funding provided by the National Science Foundation under grant number OCI-1047916 to support this research. We would like to thank Professors Bruce W. Hoagland and Todd D. Fagin from the University of Oklahoma for valuable discussions and the datasets they kindly provided. We would also thank the anonymous reviewers for the constructive comments and suggestions, and thank Professor Jeff Lee from Texas Tech University for his proofreading which has profoundly improved the composition of this manuscript.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Cao, G., Yoo, Eh. & Wang, S. A statistical framework of data fusion for spatial prediction of categorical variables. Stoch Environ Res Risk Assess 28, 1785–1799 (2014). https://doi.org/10.1007/s00477-013-0842-7
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00477-013-0842-7