Abstract
Spatio-temporal models can be used to analyze data collected at various spatial locations throughout multiple time points. However, even with a finite number of spatial locations, there may be insufficient resources to collect data from every spatial location at every time point. We develop a spatio-temporal finite-population block kriging (ST-FPBK) method to predict a quantity of interest, such as a mean or total, across a finite number of spatial locations. This ST-FPBK predictor incorporates an appropriate variance reduction for sampling from a finite population. Through an application to moose surveys in the east-central region of Alaska, we show that the predictor has a substantially smaller standard error compared to a predictor from the purely spatial model that is currently used to analyze moose surveys in the region. We also show how the model can be used to forecast a prediction for abundance in a time point for which spatial locations have not yet been surveyed. A separate simulation study shows that the spatio-temporal predictor is unbiased and that prediction intervals from the ST-FPBK predictor attain appropriate coverage. For ecological monitoring surveys completed with some regularity through time, use of ST-FPBK could improve precision. We also give an R package that ecologists and resource managers could use to incorporate data from past surveys in predicting a quantity from a current survey. Supplementary materials accompanying this paper appear on-line.
Similar content being viewed by others
References
Adde A, Darveau M, Barker N, Cumming S (2020) Predicting spatiotemporal abundance of breeding waterfowl across Canada: a Bayesian hierarchical modelling approach. Divers Distrib 26(10):1248–1263
Boertje RD, Keech MA, Young DD, Kellie KA, Tom Seaton C (2009) Managing for elevated yield of moose in interior Alaska. J Wildl Manag 73(3):314–327
Breidt FJ, Opsomer JD (2017) Model-assisted survey estimation with modern prediction techniques
Breivik ON, Aanes F, Søvik G, Aglen A, Mehl S, Johnsen E (2021) Predicting abundance indices in areas without coverage with a latent spatio-temporal Gaussian model. ICES J Mar Sci 78(6):2031–2042
Brus DJ (2021) Statistical approaches for spatial sample survey: persistent misconceptions and new developments. Eur J Soil Sci 72(2):686–703
Chen W, Genton MG, Sun Y (2021) Space-time covariance structures and models. Annu Rev Stat App 8:191–215
Conn PB, Ver Hoef JM, McClintock BT, Moreland EE, London JM, Cameron MF, Dahle SP, Boveng PL (2014) Estimating multispecies abundance using automated detection systems: ice-associated seals in the Bering Sea. Methods Ecol Evol 5(12):1280–1293
Conn PB, Johnson DS, Ver Hoef JM, Hooten MB, London JM, Boveng PL (2015) Using spatiotemporal statistical models to estimate animal abundance and infer ecological dynamics from survey counts. Ecol Monogr 85(2):235–252
Cressie N (2015) Statistics for spatial data—revised edition. Wiley, Hoboken
Cressie N, Lahiri SN (1993) The asymptotic distribution of REML estimators. J Multivar Anal 45(2):217–233
Cressie N, Wikle CK (2015) Statistics for spatio-temporal data. Wiley, Hoboken
Davy CM, Squires K, Ryan Zimmerling J (2021) Estimation of spatiotemporal trends in bat abundance from mortality data collected at wind turbines. Conserv Biol 35(1):227–238
De Cesare L, Myers DE, Posa D (2001) Product-sum covariance for space-time modeling: an environmental application. Environmetrics Off J Int Environmetrics Soc 12(1):11–23
De Iaco S, Myers DE, Posa D (2001) Space-time analysis using a general product-sum model. Stat Probab Lett 52(1):21–28
De Iaco S, Myers DE, Posa D (2002) Nonseparable space-time covariance models: some parametric families. Math Geol 34:23–42
De Iaco S, Palma M, Posa D (2015) Spatio-temporal geostatistical modeling for French fertility predictions. Spatial Stat 14:546–562
DeLong RA (2006) Geospatial population estimator software user’s guide. Alaska Department of Fish; Game, Division of Wildlife Conservation
Dumelle M, Ver Hoef JM, Fuentes C, Gitelman A (2021) A linear mixed model formulation for spatio-temporal random processes with computational advances for the product, sum, and product-sum covariance functions. Spatial Stat 43:100510
Dumelle M, Higham M, Ver Hoef JM, Olsen AR, Madsen L (2022) A comparison of design-based and model-based approaches for finite population spatial sampling and inference. Methods Ecol Evol 13(9):2018–2029
Gasaway WC, DuBois SD, Reed DJ, Harbo SJ (1986) Estimating moose population parameters from aerial surveys. University of Alaska, Institute of Arctic Biology
Gneiting T, Genton MG, Guttorp P (2006) Geostatistical space-time models, stationarity, separability, and full symmetry. Monogr Stat Appl Probab 107:151
Hamilton JD (2020) Time series analysis. Princeton University Press, Princeton
Harville DA (1977) Maximum likelihood approaches to variance component estimation and to related problems. J Am Stat Assoc 72(358):320–338
Heyde CC (1994) A quasi-likelihood approach to the REML estimating equations. Stat Probab Lett 21(5):381–384
Higham M, Ver Hoef J, Frank B, Dumelle M (2021a) Sptotal: predicting totals and weighted sums from spatial data. https://highamm.github.io/sptotal/index.html
Higham M, Ver Hoef J, Madsen L, Aderman A (2021b) Adjusting a finite population block kriging estimator for imperfect detection. Environmetrics 32(1):e2654
Kellie KA, DeLong RA (2006) Geospatial survey operations manual. Alaska Department of Fish; Game
Kellie KA, Colson KE, Reynolds JH (2019) Challenges to monitoring moose in Alaska. Alaska Department of Fish, Game, Division of Wildlife Conservation Juneau
Lemos RT, Sansó 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
Lohr SL (2021) Sampling: design and analysis. Hall/CRC, Chapman
Martínez-Beneito MA, López-Quilez A, Botella-Rocamora P (2008) An autoregressive approach to spatio-temporal disease mapping. Stat Med 27(15):2874–2889
Montero J-M, Fernández-Avilés G, Mateu J (2015) Spatial and spatio-temporal geostatistical modeling and kriging. Wiley, Hoboken
Patterson HD, Thompson R (1971) Recovery of inter-block information when block sizes are unequal. Biometrika 58(3):545–554
Peters W, Hebblewhite M, Smith KG, Webb SM, Webb N, Russell M, Stambaugh C, Anderson RB (2014) Contrasting aerial moose population estimation methods and evaluating sightability in west-central Alberta, Canada. Wildl Soc Bull 38(3):639–649
Porcu E, Furrer R, Nychka D (2021) 30 years of space-time covariance functions. Wiley Interdiscip Rev Comput Stat 13(2):e1512
Posa D (1993) A simple description of spatial-temporal processes. Comput Stat Data Anal 15(4):425–437
Ross BE, Hooten MB, Koons DN (2012) An accessible method for implementing hierarchical models with spatio-temporal abundance data. PLoS ONE 7(11):e49395
Rouhani S, Hall TJ (1989) Space-time kriging of groundwater data. In: Geostatistics: proceedings of the third international geostatistics congress, September 5–9, 1988, Avignon, France. Springer, pp 639–50
Sahu SK, Böhning D (2022) Bayesian spatio-temporal joint disease mapping of Covid-19 cases and deaths in local authorities of England. Spatial Stat 49:100519
Sauer JR, Link WA (2011) Analysis of the North American breeding bird survey using hierarchical models. Auk 128(1):87–98
Schmidt JH, Cameron MD, Joly K, Pruszenski JM, Reynolds JH, Sorum MS (2022) Bayesian spatial modeling of moose count data: increasing estimator efficiency and exploring ecological hypotheses. J Wildl Manag 86:e22220
Sherman J, Morrison WJ (1950) Adjustment of an inverse matrix corresponding to a change in one element of a given matrix. Ann Math Stat 21(1):124–127
Smith TE (1980) A central limit theorem for spatial samples. Geogr Anal 12(4):299–324
Stegle O, Lippert C, Mooij JM, Lawrence N, Borgwardt K (2011) Efficient inference in matrix-variate Gaussian models with\(\backslash \)iid observation noise. Adv Neural Inf Process Syst 24:630–638
Stein ML (2005) Space-time covariance functions. J Am Stat Assoc 100(469):310–321
Stock BC, Ward EJ, Eguchi T, Jannot JE, Thorson JT, Feist BE, Semmens BX (2020) Comparing predictions of fisheries bycatch using multiple spatiotemporal species distribution model frameworks. Can J Fish Aquat Sci 77(1):146–163
Urquhart NS (2012) The role of monitoring design in detecting trend in long-term ecological monitoring studies. Des Anal Long-Term Ecol Monit Stud 151–173
Ver Hoef JM (2008) Spatial methods for plot-based sampling of wildlife populations. Environ Ecol Stat 15(1):3–13
Ver Hoef JM, Jansen JK (2007) Space–time zero-inflated count models of harbor seals. Environmetrics Off J Int Environmetrics Soc 18(7):697–712
Ver Hoef JM, London JM, Boveng PL (2010) Fast computing of some generalized linear mixed pseudo-models with temporal autocorrelation. Comput Stat 25:39–55
Ver Hoef JM, Johnson D, Angliss R, Higham M (2021) Species density models from opportunistic citizen science data. Methods Ecol Evol 12(10):1911–1925
Wang Z, Zhu Z (2019) Spatiotemporal balanced sampling design for longitudinal area surveys. J Agric Biol Environ Stat 24:245–263
Wickham H (2016) Data analysis. In: Ggplot2. Springer, pp 189–201
Wikle CK, Zammit-Mangion A, Cressie N (2019) Spatio-temporal statistics with r. Hall/CRC, Chapman
Wolf H (1979) The Helmert block method and its origin. In: Proceedings: second international symposium on problems related to the redefinition of North American geodetic networks, held at the Marriott Hotel, Arlington, Virginia, April 24 to 28, 1978, 55:319. Department of Commerce, National Oceanic; Atmospheric Administration
Woodbury MA (1950) Inverting modified matrices. Department of Statistics, Princeton University
Xu J, Shu H (2015) Spatio-temporal kriging based on the product-sum model: some computational aspects. Earth Sci Inform 8(3):639–648
Acknowledgements
The views expressed in this manuscript are those of the authors and do not necessarily represent the views or policies of the U.S. Environmental Protection Agency or the National Oceanic and Atmospheric Administration. Any mention of trade names, products, or services does not imply an endorsement by the U.S. government, the U.S. Environmental Protection Agency, or the National Oceanic and Atmospheric Administration. The U.S. Environmental Protection Agency and National Oceanic and Atmospheric Administration do not endorse any commercial products, services, or enterprises.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest.
Data and Code Availability
The Alaska Department of Fish and Game collected and provided the moose survey data used in this study. This manuscript has a supplementary R package that contains all of the data and code used in its creation, with the exception of the shapefile used to make the maps in some of the figures (which cannot be released due to Alaska Department of Fish and Game policy). The supplementary R package, along with the data used in the application, is hosted on GitHub and can be found at https://github.com/highamm/FPSpatioTemp. The data set is also available on Zenodo at https://doi.org/10.5281/zenodo.7636130.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
1.1 A.1: Simulation Tables
1.2 A.2: Supplementary Analysis
As mentioned in Sect. 3, moose surveys in Alaska are often stratified into “High” and “Low” sites. When using stratum as a covariate in a spatio-temporal (or spatial, if performing a purely spatial analysis) model, we assume that all errors in the model are generated from the same underlying spatio-temporal (or spatial) parameters. However, for many moose surveys, it is more reasonable to allow the sites in the High stratum to have a different set of spatio-temporal (or spatial) parameters than the sites in the Low stratum.
If we allow the strata to have different covariance parameters, then, to construct the ST-FPBK predictor, we simply fit the model once for each stratum. If we assume that there is no cross-covariance (i.e. errors from sites in different strata are not correlated), then the BLUP for \(\textbf{b}'_a \textbf{y}_a\) is
where \(\varvec{\lambda }_{o, l}\) and \(\varvec{\lambda }_{o, h}'\) are the kriging weights for the Low and High strata, respectively (Eq. 13), and \(\textbf{y}_{o, l}\) and \(\textbf{y}_{o, h}\) are the vectors of observed responses for the Low and High strata, respectively.
Again assuming that there is no cross-covariance, the prediction variance is simply the sum of the prediction variances of \(\varvec{\lambda }_{o, l}' \textbf{y}_{o, l}\) and \(\varvec{\lambda }_{o, h}' \textbf{y}_{o, h}\) using Eq. 14.
We can use the purely spatial model and FPBK as well as the spatio-temporal model and ST-FPBK to predict the total moose abundance in 2020, using separate covariance models for the strata in the moose data set in Sect. 3. Table 6 shows the results.
The spatio-temporal predictors still have a smaller standard error than their purely spatial model counterparts. Interestingly, the purely spatial FPBK predictor has a slightly lower standard error when fitting strata separately, while the ST-FPBK predictor has a slightly lower standard error when using stratum as a covariate. Whether it makes more sense for stratum to be a covariate or for the strata to be fit separately is application dependent.
For the moose application data, fitting separate covariance models to each stratum is probably the better choice, as the errors for sites in the high stratum have much more overall variability than the errors in the low stratum. However, we chose to have the separate-strata model in the supplementary materials for two reasons. First, the method can be applied to any data set with spatio-temporal covariance and a finite number of sites, and applications in other domains may not have stratification at all. Second, the syntax in the development of the ST-FPBK predictor is much cleaner when stratum is treated as a covariate than when the strata are fit separately. Using the model with stratum as a covariate allows for a better focus on the proposed method itself.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Higham, M., Dumelle, M., Hammond, C. et al. An Application of Spatio-Temporal Modeling to Finite Population Abundance Prediction. JABES (2023). https://doi.org/10.1007/s13253-023-00565-y
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s13253-023-00565-y