Editing Geostatistics

{{short description|Branch of statistics focusing on spatial data sets}}
{{Distinguish|statistical geography}}

'''Geostatistics''' is a branch of [[statistics]] focusing on spatial or [[Spacetime|spatiotemporal]] [[dataset]]s. Developed originally to predict [[probability distribution]]s of [[ore grade]]s for [[mining]] operations,<ref>Krige, Danie G. (1951). "A statistical approach to some basic mine valuation problems on the Witwatersrand". J. of the Chem., Metal. and Mining Soc. of South Africa 52 (6): 119–139</ref> it is currently applied in diverse disciplines including [[petroleum geology]], [[hydrogeology]], [[hydrology]], [[meteorology]], [[oceanography]], [[geochemistry]], [[geometallurgy]], [[geography]], [[forestry]], [[environmental control]], [[landscape ecology]], [[soil science]], and [[agriculture]] (esp. in [[precision farming]]). Geostatistics is applied in varied branches of [[geography]], particularly those involving the spread of diseases ([[epidemiology]]), the practice of commerce and military planning ([[logistics]]), and the development of efficient [[spatial network]]s. Geostatistical algorithms are incorporated in many places, including [[geographic information systems]] (GIS).

==Background==
Geostatistics is intimately related to interpolation methods but extends far beyond simple interpolation problems. Geostatistical techniques rely on statistical models based on random function (or [[random variable]]) theory to model the uncertainty associated with spatial estimation and simulation.

A number of simpler interpolation methods/algorithms, such as [[inverse distance weighting]], [[bilinear interpolation]] and [[nearest-neighbor interpolation]], were already well known before geostatistics.<ref name="IandS1989">Isaaks, E. H. and Srivastava, R. M. (1989), ''An Introduction to Applied Geostatistics,'' Oxford University Press, New York, USA.</ref> Geostatistics goes beyond the interpolation problem by considering the studied phenomenon at unknown locations as a set of correlated random variables.

Let {{math|''Z''('''x''')}} be the value of the variable of interest at a certain location {{math|'''x'''}}. This value is unknown (e.g., temperature, rainfall, [[Potentiometric surface|piezometric level]], geological facies, etc.). Although there exists a value at location {{math|'''x'''}} that could be measured, geostatistics considers this value as random since it was not measured or has not been measured yet. However, the randomness of {{math|''Z''('''x''')}} is not complete. Still, it is defined by a [[cumulative distribution function]] (CDF) that depends on certain information that is known about the value {{math|''Z''('''x''')}}:

:<math>F(\mathit{z}, \mathbf{x}) = \operatorname{Prob} \lbrace Z(\mathbf{x}) \leqslant \mathit{z} \mid \text{information} \rbrace . </math>

Typically, if the value of {{math|''Z''}} is known at locations close to {{math|'''x'''}} (or in the [[Neighbourhood (mathematics)|neighborhood]] of {{math|'''x'''}}) one can constrain the CDF of {{math|''Z''('''x''')}} by this neighborhood: if a high spatial continuity is assumed, {{math|''Z''('''x''')}} can only have values similar to the ones found in the neighborhood. Conversely, in the absence of spatial continuity {{math|''Z''('''x''')}} can take any value. The spatial continuity of the random variables is described by a model of spatial continuity that can be either a parametric function in the case of [[variogram]]-based geostatistics, or have a non-parametric form when using other methods  such as [[multiple-point simulation]]<ref>Mariethoz, Gregoire, Caers, Jef (2014). Multiple-point geostatistics: modeling with training images.  Wiley-Blackwell, Chichester, UK, 364 p.</ref> or [[pseudo-genetic]] techniques.

By applying a single spatial model on an entire domain, one makes the assumption that {{math|''Z''}} is a [[stationary process]]. It means that the same statistical properties are applicable on the entire domain. Several geostatistical methods provide ways of relaxing this stationarity assumption.

In this framework, one can distinguish two modeling goals:

# [[Estimation theory|Estimating]] the value for {{math|''Z''('''x''')}}, typically by the [[Expected value|expectation]], the [[median]] or the [[Mode (statistics)|mode]] of the CDF {{math|''f''(''z'','''x''')}}. This is usually denoted as an estimation problem.
# [[Sampling (statistics)|Sampling]] from the entire probability density function {{math|''f''(''z'','''x''')}} by actually considering each possible outcome of it at each location. This is generally done by creating several alternative maps of {{math|''Z''}}, called realizations. Consider a domain discretized in {{math|''N''}} grid nodes (or pixels). Each realization is a sample of the complete {{math|''N''}}-dimensional joint distribution function

:: <math>F(\mathbf{z}, \mathbf{x}) = \operatorname{Prob} \lbrace Z(\mathbf{x}_1) \leqslant z_1, Z(\mathbf{x}_2) \leqslant z_2, ..., Z(\mathbf{x}_N) \leqslant z_N \rbrace .</math>

: In this approach, the presence of multiple solutions to the interpolation problem is acknowledged. Each realization is considered as a possible scenario of what the real variable could be. All associated workflows are then considering ensemble of realizations, and consequently ensemble of predictions that allow for probabilistic forecasting. Therefore, geostatistics is often used to generate or update spatial models when solving [[inverse problem]]s.<ref>Hansen, T.M., Journel, A.G., Tarantola, A. and Mosegaard, K. (2006). "Linear inverse Gaussian theory and geostatistics", ''Geophysics'' 71</ref><ref>Kitanidis, P.K. and Vomvoris, E.G. (1983). "A geostatistical approach to the inverse problem in groundwater modeling (steady state) and one-dimensional simulations", ''Water Resources Research'' 19(3):677-690</ref>

A number of methods exist for both geostatistical estimation and multiple realizations approaches. Several reference books provide a comprehensive overview of the discipline.<ref name="IandS1989" /><ref>Remy, N., et al. (2009), ''Applied Geostatistics with SGeMS: A User's Guide,'' 284 pp., Cambridge University Press, Cambridge.
</ref><ref>
Deutsch, C.V., Journel, A.G, (1997). ''GSLIB: Geostatistical Software Library and User's Guide (Applied Geostatistics Series), Second Edition,'' Oxford University Press, 369 pp., http://www.gslib.com/
</ref><ref>Chilès, J.-P., and P. Delfiner (1999), ''Geostatistics - Modeling Spatial Uncertainty,'' John Wiley & Sons, Inc., New York, USA.
</ref><ref>Lantuéjoul, C. (2002), ''Geostatistical simulation: Models and algorithms,'' 232 pp., Springer, Berlin.
</ref><ref>Journel, A. G. and Huijbregts, C.J. (1978) ''Mining Geostatistics,'' Academic Press. {{ISBN|0-12-391050-1}}
</ref><ref>Kitanidis, P.K.  (1997) ''Introduction to Geostatistics: Applications in Hydrogeology,'' Cambridge University Press.
</ref><ref>Wackernagel, H. (2003). ''Multivariate geostatistics,'' Third edition, Springer-Verlag, Berlin, 387 pp.
</ref><ref>Pyrcz, M. J. and Deutsch, C.V., (2014). ''Geostatistical Reservoir Modeling, 2nd Edition'', Oxford University Press, 448 pp.
</ref><ref>Tahmasebi, P., Hezarkhani, A., Sahimi, M., 2012, Multiple-point geostatistical modeling based on the cross-correlation functions, Computational Geosciences, 16(3):779-79742,  
</ref><ref>{{cite web|url=http://www.statios.com/WinGslib/index.html|title=Statios - WinGslib|first=Manu|last=Schnetzler|access-date=2005-10-10|archive-date=2015-05-11|archive-url=https://web.archive.org/web/20150511095032/http://www.statios.com/WinGslib/index.html|url-status=dead}}</ref>

==Methods==

===Estimation===

==== Kriging ====
{{Main|Kriging}}
Kriging is a group of geostatistical techniques to interpolate the value of a random field (e.g., the elevation, z, of the landscape as a function of the geographic location) at an unobserved location from observations of its value at nearby locations.

==== Bayesian estimation ====
{{Main|Bayesian inference}}
Bayesian inference is a method of statistical inference in which [[Bayes' theorem]] is used to update a probability model as more evidence or information becomes available. Bayesian inference is playing an increasingly important role in geostatistics.<ref>Banerjee S., Carlin B.P., and Gelfand A.E. (2014). Hierarchical Modeling and Analysis for Spatial Data, Second Edition. Chapman & Hall/CRC Monographs on Statistics & Applied Probability. {{ISBN|9781439819173}}</ref> Bayesian estimation implements kriging through a spatial process, most commonly a [[Gaussian process]], and updates the process using [[Bayes' Theorem]] to calculate its posterior. High-dimensional Bayesian geostatistics.<ref>Banerjee, Sudipto. High-Dimensional Bayesian Geostatistics. Bayesian Anal. 12 (2017), no. 2, 583--614. {{doi|10.1214/17-BA1056R}}. https://projecteuclid.org/euclid.ba/1494921642</ref>

==== Finite difference method ====
Considering the principle of conservation of probability, recurrent difference equations (finite difference equations) were used in conjunction with lattices to compute probabilities quantifying uncertainty about the geological structures. This procedure is a numerical alternative method to Markov chains and Bayesian models.<ref>{{cite journal|last1= Cardenas |first1=IC|title= A two-dimensional approach to quantify stratigraphic uncertainty from borehole data using non-homogeneous random fields|journal=Engineering Geology|date=2023|doi=10.1016/j.enggeo.2023.107001|doi-access=free}}</ref>

===Simulation===
* Aggregation
* Dissagregation
* [[Turning bands]]
* [[Cholesky decomposition]]
* Truncated Gaussian
* Plurigaussian
* Annealing 
* Spectral simulation
* Sequential Indicator
* Sequential Gaussian 
* Dead Leave 
* [[Transition probabilities]]
* [[Markov chain geostatistics]]
* [[Support vector machine]]
* [[Boolean simulation]]
* Genetic models
* Pseudo-genetic models
* [[Cellular automata]]
* Multiple-Point Geostatistics

==Definitions and tools==
* [[Regionalized variable theory]]
* [[Covariance function]]
* [[Semi-variance]]
* [[Variogram]]
* [[Kriging]]
* [[Range (geostatistics)]]
* [[Sill (geostatistics)]]
* [[Nugget effect]]
* [[Training image]]
* [[Finite difference method]]

== See also ==
{{div col|colwidth=30em}}
* [[Arbia's law of geography]]
* [[Concepts and Techniques in Modern Geography]]
* [[Multivariate interpolation]]
* [[Spline interpolation]]
* [[Geodemographic segmentation]]
* [[Geodesy]]
* [[Geographic Information Science]]
* [[Geographic Information Systems]]
* [[Geomatics]]
* [[SaTScan]]
* [[Remote sensing]]
* [[Pedometrics]]
* [[Time geography]]
* [[Tobler's first law of geography]]
* [[Tobler's second law of geography]]
* [[Uncertain geographic context problem]]
{{div col end}}

== Notes ==
{{reflist}}

== References ==
# Armstrong, M and Champigny, N, 1988, A Study on Kriging Small Blocks, CIM Bulletin, Vol 82, No 923
# Armstrong, M, 1992, [https://web.archive.org/web/20061221032347/http://geostatscam.com/Adobe/DeGeo199207.pdf Freedom of Speech?] De Geeostatisticis, July, No 14
# Champigny, N, 1992, [https://web.archive.org/web/20110711085650/http://www.geostatscam.com/Adobe/TNM19920518.pdf Geostatistics: A tool that works], [[The Northern Miner (Canada)|The Northern Miner]], May 18
# Clark I, 1979, [http://www.kriging.com/pg1979_download.html Practical Geostatistics], Applied Science Publishers, London
# David, M, 1977, Geostatistical Ore Reserve Estimation, Elsevier Scientific Publishing Company, Amsterdam
# Hald, A, 1952, Statistical Theory with Engineering Applications, John Wiley & Sons, New York
# {{cite journal|doi=10.1007/s11004-010-9276-7|title=Stochastic Simulation of Patterns Using Distance-Based Pattern Modeling|journal=Mathematical Geosciences|volume=42|issue=5|pages=487–517|year=2010|last1=Honarkhah|first1=Mehrdad|last2=Caers|first2=Jef|s2cid=73657847 }} (best paper award IAMG 09)
# ISO/DIS 11648-1 Statistical aspects of sampling from bulk materials-Part1: General principles
# Lipschutz, S, 1968, Theory and Problems of Probability, McCraw-Hill Book Company, New York.
# Matheron, G. 1962. Traité de géostatistique appliquée. Tome 1, Editions Technip, Paris, 334 pp.
# Matheron, G. 1989. Estimating and choosing, Springer-Verlag, Berlin.
# McGrew, J. Chapman, & Monroe, Charles B., 2000. An introduction to statistical problem solving in geography, second edition, McGraw-Hill, New York.
# Merks, J W, 1992, [https://web.archive.org/web/20060901132329/http://geostatscam.com/Adobe/TNM19920420.pdf Geostatistics or voodoo science], The Northern Miner, May 18
# <cite id=merks93>Merks, J W, [https://web.archive.org/web/20060629194347/http://www.geostatscam.com/Adobe/Abuse_stats.pdf Abuse of statistics], CIM Bulletin, January 1993, Vol 86, No 966</cite>
# Myers, Donald E.; [http://www.u.arizona.edu/~donaldm/homepage/whatis.html "What Is Geostatistics?]
# <cite id=philip86>Philip, G M and Watson, D F, 1986, Matheronian Geostatistics; Quo Vadis?, Mathematical Geology, Vol 18, No 1 </cite>
# Pyrcz, M.J. and Deutsch, C.V., 2014, Geostatistical Reservoir Modeling, 2nd Edition, Oxford University Press, New York, p.&nbsp;448 
# Sharov, A: Quantitative Population Ecology, 1996, https://web.archive.org/web/20020605050231/http://www.ento.vt.edu/~sharov/PopEcol/popecol.html
# Shine, J.A., Wakefield, G.I.: A comparison of supervised imagery classification using analyst-chosen and geostatistically-chosen training sets, 1999, https://web.archive.org/web/20020424165227/http://www.geovista.psu.edu/sites/geocomp99/Gc99/044/gc_044.htm
# Strahler, A. H., and Strahler A., 2006, Introducing Physical Geography, 4th Ed., Wiley.
# Tahmasebi, P., Hezarkhani, A., Sahimi, M., 2012, [https://doi.org/10.1007%2Fs10596-012-9287-1 Multiple-point geostatistical modeling based on the cross-correlation functions], Computational Geosciences, 16(3):779-79742.
# Volk, W, 1980, Applied Statistics for Engineers, Krieger Publishing Company, Huntington, New York.

== External links==
{{Commons category}}
* [http://www.cg.ensmp.fr/bibliotheque On-Line Library that chronicles Matheron's journey from classical statistics to the new science of geostatistics]
* [http://www.u.arizona.edu/~donaldm/homepage/whatis.html]

{{Statistics}}

{{Authority control}}

[[Category:Geostatistics| ]]