|
|
| Line 1: |
Line 1: |
| In [[statistics]], originally in [[geostatistics]], '''kriging''' or '''Gaussian process regression''' is a method of [[interpolation]] for which the interpolated values are modeled by a [[Gaussian process]] governed by prior [[covariance]]s, as opposed say to a piecewise-polynomial [[smoothing spline|spline]] chosen to optimize smoothness of the fitted values. Under suitable assumptions on the priors, kriging gives the [[best linear unbiased prediction]] of the intermediate values. Interpolating methods based on other criteria such as smoothness need not yield the most likely intermediate values. The method is widely used in the domain of [[Spatial_analysis#Sampling|spatial analysis]] and [[computer experiment]]s. The technique is also known as '''Kolmogorov Wiener prediction'''.
| | Elderly video games ought in order to be discarded. They can be worth some money at several video retailers. Means positivity . buy and sell several game titles, you could even get your upcoming title at no cost!<br><br> |
|
| |
|
| [[File:Example_of_kriging_interpolation_in_1D.png|thumb|400px|Example of one-dimensional data interpolation by kriging, with confidence intervals. Squares indicate the location of the data. The kriging interpolation, shown in red, runs along the means of the normally distributed confidence intervals shown in gray. The dashed curve shows a spline that while smooth nevertheless departs significantly from the expected intermediate values given by those means.]]
| | People may possibly play betting games to rest following a extremely long working day and a workplace. Some love socializing by tinkering considering friends and family. If you have pretty much any inquiries about where and how to use Clash Clans Cheat, you can build contact with us at just our web site. Other individuals perform them when they're jobless combined with [http://Www.thefreedictionary.com/require require] something for having their brains away their scenario. If you have any sort of inquiries regarding where and the best ways to utilize [http://circuspartypanama.com astuces clash of clans], you can contact us at our web page. No be importance reasons why you enjoy, this information will guide you to engage in usual way which is much better.<br><br>Temperance is essential in a large amount of things, and enjoying clash of clans cheats is no new and exciting. Playing for hours on finish is not just good-for-you, bodily or on an emotional level. There are some games out there which know this you need to include measures to remind one to take rests. Consider the initiative yourself, although! Place an alarm a person don't play for over an hour right.<br><br>Primarily clash of clans identify tool no survey encourages believe in among a new people. Society may be definitely powered by professional pressure, one of the main most powerful forces about the planet. Considering that long as peer stress and anxiety utilizes its power by good, clash of clans hack tool no stare at will have its put in community.<br><br>Make sure you may not let online games take over your days. Game titles can be quite additive, whenever your have to make sure you moderate the free time that you investing trying to play such games. In case you invest an excessive number of time playing video game, your [http://photobucket.com/images/actual+life actual life] could actually begin to falter.<br><br>It looks like computer games are pretty much everywhere these times. You can do play them on your main telephone, boot a unit in the home and even see them through social media on your personal computer systems. It helps to comprehend this associated with amusement to help they benefit from the numerous offers which are out.<br><br>Pc games or computer games have increased in popularity nowadays, merely with the younger generation, but also with adults as well. There are many games available, ranging from the intellectual to the seven days a week - your options would be limitless. Online element playing games are one of the most popular games anywhere which is. With this popularity, plenty of men and women are exploring and struggling to find ways to go the actual whole game as at once as they can; reasons for using computer How to compromise in clash of clans range from simply wanting to own your own friends stare at you inside awe, or getting additional of game money an individual really can sell later, or simply just that will help rid the game for this fun factor for one other players. |
| | |
| The theoretical basis for the method was developed by the French mathematician [[Georges Matheron]] based on the Master's thesis of [[Danie G. Krige]], the pioneering plotter of distance-weighted average gold grades at the [[Witwatersrand]] reef complex in [[South Africa]]. Krige sought to estimate the most likely distribution of gold based on samples from a few boreholes. The English verb is ''to krige'' and the most common noun is ''kriging''; both are often pronounced with a [[Hard and soft g|hard "g"]], following the pronunciation of the name "Krige".
| |
| | |
| ==Main principles==
| |
| | |
| ===Related terms and techniques===
| |
| The basic idea of kriging is to predict the value of a function at a given point by computing a weighted average of the known values of the function in the neighborhood of the point. The method is mathematically closely related to [[regression analysis]]. Both theories derive a [[best linear unbiased estimator]], based on assumptions on [[covariance]]s, make use of [[Gauss-Markov theorem]] to prove independence of the estimate and error, and make use of very similar formulae. They are nevertheless, useful in different frameworks: kriging is made for estimation of a single realization of a random field, while regression models are based on multiple observations of a multivariate dataset.
| |
| | |
| The kriging estimation may also be seen as a [[spline (mathematics)|spline]] in a [[reproducing kernel Hilbert space]], with the reproducing kernel given by the covariance function.<ref>{{cite book|author =Grace Wahba|title = Spline Models for Observational Data| publisher = SIAM| volume = 59| page=162| year=1990}}</ref> The difference with the classical kriging approach is provided by the interpretation: while the spline is motivated by a minimum norm interpolation based on a Hilbert space structure, kriging is motivated by an expected squared prediction error based on a stochastic model.
| |
| | |
| Kriging with ''polynomial trend surfaces'' is mathematically identical to [[generalized least squares]] polynomial [[curve fitting]].
| |
| | |
| Kriging can also be understood as a form of [[Bayesian inference]].<ref>{{cite doi|10.1007/978-94-011-5014-9_23}}</ref> Kriging starts with a [[prior probability distribution|prior]] [[probability distribution|distribution]] over [[Function (mathematics)|function]]s. This prior takes the form of a Gaussian process: <math>N</math> samples from a function will be [[normal distribution|normally distributed]], where the [[covariance]] between any two samples is the covariance function (or [[kernel (set theory)|kernel]]) of the Gaussian process evaluated at the spatial location of two points. A [[Set (mathematics)|set]] of values is then observed, each value associated with a spatial location. Now, a new value can be predicted at any new spatial location, by combining the Gaussian prior with a Gaussian [[likelihood function]] for each of the observed values. The resulting [[Posterior probability|posterior]] distribution is also Gaussian, with a mean and covariance that can be simply computed from the observed values, their variance, and the kernel matrix derived from the prior.
| |
| | |
| ===Geostatistical estimator===
| |
| In geostatistical models, sampled data is interpreted as a result of a random process. The fact that this models incorporate uncertainty in its conceptualization doesn't mean that the phenomenon - the forest, the aquifer, the mineral deposit - has resulted from a random process, but solely allows to build a methodological basis for the spatial inference of quantities in unobserved locations and to the quantification of the uncertainty associated with the estimator.
| |
| | |
| A [[stochastic process]] is simply, in the context of this model, a way to approach the set of data collected from the samples. The first step in geostatistical modulation is the creation of a random process that best describes the set of experimental observed data.<ref>Soares 2006, p.18</ref>
| |
| | |
| A value spatially located at <math>x_1</math> (generic denomination of a set of [[Geographic coordinate system|geographic coordinates]]) is interpreted as a realization <math>z(x_1)</math> of the [[random variable]] <math>Z(x_1)</math>. In the space <math>A</math>, where the set of samples is dispersed, exists <math>N</math> realizations of the random variables <math>Z(x_1), Z(x_2), \cdots, Z(x_N)</math>, correlated between themselves.
| |
| | |
| The set of random variables, constitutes a random function of which only one realization is known <math>z(x_i)</math> - the set of experimental data. With only one realization of each random variable it's theoretically impossible to determine any statistical parameter of the individual variables or the function.
| |
| | |
| :The proposed solution in the geostatistical formalism consists in assuming various degrees of stationarity in the random function, in order to make possible the inference of some statistic values.<ref>Matheron G. 1978</ref>
| |
| | |
| For instance, if a workgroup of scientists assumes appropriate, based on the homogeneity of samples in area <math>A</math> where the variable is distributed, the hypothesis that the [[Moment_(mathematics)#Mean|first moment]] is stationary (i.e. all random variables have the same mean), than, they are implying that the mean can be estimated by the arithmetic mean of sampled values. Judging an hypothesis like this as appropriate is the same as considering that sample values are sufficiently homogeneous to validate that representativity.
| |
| | |
| The hypothesis of stationarity related to the [[Moment_(mathematics)#Variance|second moment]] is defined in the following way: the correlation between two random variables solely depends on the spatial distance that separates them and is independent of its location:
| |
| | |
| :<math>C(Z(x_1),Z(x_2)) = C(Z(x_i),Z(x_i+\mathbf{h})) = C(\mathbf{h})</math>
| |
| :
| |
| :<math>\gamma(Z(x_1),Z(x_2)) = \gamma(Z(x_i),Z(x_i+\mathbf{h})) = \gamma(\mathbf{h})</math>
| |
| | |
| where <math>\mathbf{h} = (x_1,x_2) = (x_i,x_i+\mathbf{h})</math>
| |
| | |
| This hypothesis allows to infer those two measures - the [[variogram]] and the [[covariogram]] - based on the <math>N</math> samples:
| |
| | |
| :<math>\gamma(\mathbf{h})=\frac{1}{2N(\mathbf{h})}\sum^{N(\mathbf{h})}_{i=1}\left(Z(x_i)-Z(x_i+\mathbf{h})\right)^2</math>
| |
| :
| |
| :<math>C(\mathbf{h})=\frac{1}{N(\mathbf{h})}\sum^{N(\mathbf{h})}_{i=1}\left(Z(x_i)Z(x_i+\mathbf{h})\right)-m(x_i)m(x_i+\mathbf{h})</math>
| |
| | |
| where <math>m(x_i)=\frac{1}{N(\mathbf{h})}\sum^{N(\mathbf{h})}_{i=1}Z(x_i)</math>
| |
| | |
| ===Linear estimation===
| |
| Spatial inference, or estimation, of a quantity <math>Z: \mathbb{R}^n\rightarrow\mathbb{R}</math>, at an unobserved location <math>x_0</math>, is calculated from a linear combination of the observed values <math>z_i=Z(x_i)</math> and weights <math>w_i(x_0),\;i=1,\ldots,N</math>:
| |
| | |
| <math>\hat{Z}(x_0) = \begin{bmatrix}
| |
| w_1 & w_2 & \cdots & w_N
| |
| \end{bmatrix}
| |
| \cdot
| |
| \begin{bmatrix}
| |
| z_1\\
| |
| z_2\\
| |
| \vdots\\
| |
| z_N
| |
| \end{bmatrix} = \sum_{i=1}^n w_i(x_0) \times Z(x_i)</math>
| |
| | |
| The weights <math>w_i</math> are intended to summarize two extremely important procedures in a spatial inference process:
| |
| | |
| * reflect the structural "proximity" of samples to the estimation location, <math>x_0</math>
| |
| * at the same time, they should have a desegregation effect, in order to avoid bias caused by eventual sample ''clusters''
| |
| | |
| When calculating the weights <math>w_i</math>, there are two objectives in the geostatistical formalism: ''unbias'' and ''minimal variance of estimation''.
| |
| | |
| If the cloud of real values <math>Z(x_0)</math> is plotted against the estimated values <math>\hat{Z}(x_0)</math>, the criterion for global unbias, ''intrinsic stationarity'' or [[stationary process|wide sense stationarity]] of the field, implies that the mean of the estimations must be equal to mean of the real values.
| |
| | |
| The second criterion says that the mean of the squared deviations <math>(\hat{Z}(x)-Z(x))</math> must be minimal, which means that when the cloud of estimated values ''versus'' the cloud real values is more disperse, the estimator is more imprecise.
| |
| | |
| ==Methods==
| |
| Depending on the stochastic properties of the random field and the various degrees of stationarity assumed, different methods for calculating the weights can be deducted, i.e. different types of kriging apply. Classical methods are:
| |
| | |
| * ''Ordinary kriging'' assumes stationarity of the [[Moment_(mathematics)#Mean|first moment]] of all random variables: <math>E\{Z(x_i)\}=E\{Z(x_0)\}=m</math>, where <math>m</math> is unknown.
| |
| * ''Simple kriging'' assumes a known stationary mean: <math>E\{Z(x)\}=m</math>, where <math>m</math> is known.
| |
| * ''Universal kriging'' assumes a general polynomial trend model, such as linear trend model <math>E\{Z(x)\}=\sum_{k=0}^p \beta_k f_k(x)</math>.
| |
| * ''IRFk-kriging'' assumes <math>E\{Z(x)\}</math> to be an unknown [[polynomial]] in <math>x</math>.
| |
| * ''Indicator kriging'' uses [[indicator function]]s instead of the process itself, in order to estimate transition probabilities.
| |
| * ''[[Multiple-indicator kriging]]'' is a version of indicator kriging working with a family of indicators. However, MIK has fallen out of favour as an interpolation technique in recent years. This is due to some inherent difficulties related to operation and model validation. Conditional simulation is fast becoming the accepted replacement technique in this case.
| |
| * ''Disjunctive kriging'' is a nonlinear generalisation of kriging.
| |
| * ''[[Log-normal distribution|Lognormal]] kriging'' interpolates positive data by means of [[logarithm]]s.
| |
| | |
| ===Ordinary kriging===
| |
| The unknown value <math>Z(x_0)</math> is interpreted as a random variable located in <math>x_0</math>, as well as the values of neighbors samples <math>Z(x_i), i=1,\cdots ,N</math>. The estimator <math>\hat{Z}(x_0)</math> is also interpreted as a random variable located in <math>x_0</math>, a result of the linear combination of variables.
| |
| | |
| In order to deduce the kriging system for the assumptions of the model, the following error committed while estimating <math>Z(x)</math> in <math>x_0</math> is declared:
| |
| | |
| :<math>\epsilon(x_0) = \hat{Z}(x_0) - Z(x_0) =
| |
| \begin{bmatrix}W^T&-1\end{bmatrix} \cdot \begin{bmatrix}Z(x_i)&\cdots&Z(x_N)&Z(x_0)\end{bmatrix}^T =
| |
| \sum^{N}_{i=1}w_i(x_0) \times Z(x_i) - Z(x_0)</math>
| |
| | |
| The two quality criteria referred previously can now be expressed in terms of the mean and variance of the new random variable <math>\epsilon(x_0)</math>:
| |
| | |
| '''Unbias'''
| |
| | |
| Since the random function is stationary, <math>E(Z(x_i))=E(Z(x_0))=m</math>, the following constraint is observed:
| |
| | |
| :<math>E\left(\epsilon(x_0)\right)=0 \Leftrightarrow \sum^{N}_{i=1}w_i(x_0) \times E(Z(x_i)) - E(Z(x_0))=0 \Leftrightarrow</math>
| |
| :
| |
| :<math>\Leftrightarrow m\sum^{N}_{i=1}w_i(x_0) - m=0 \Leftrightarrow \sum^{N}_{i=1}w_i(x_0) = 1 \Leftrightarrow \mathbf{1}^T \cdot W = 1</math>
| |
| | |
| In order to ensure that the model is unbiased, the sum of weights needs to be one.
| |
| | |
| '''Minimal Variance''': minimize <math>E\left(\epsilon(x_0)^2\right)</math>
| |
| | |
| Two estimators can have <math>\epsilon(x_0)=0</math>, but the dispersion around their mean determines the difference between the quality of estimators.
| |
| | |
| :<math>\begin{array}{rl}
| |
| Var(\epsilon(x_0)) &= Var\left(\begin{bmatrix}W^T&-1\end{bmatrix} \cdot
| |
| \begin{bmatrix}Z(x_i)&\cdots&Z(x_N)&Z(x_0)\end{bmatrix}^T\right) =\\
| |
| &\overset{*}{=} \begin{bmatrix}W^T&-1\end{bmatrix} \cdot
| |
| Var\left(\begin{bmatrix}Z(x_i)&\cdots&Z(x_N)&Z(x_0)\end{bmatrix}^T\right) \cdot
| |
| \begin{bmatrix}W\\-1\end{bmatrix}
| |
| \end{array}</math>
| |
| | |
| '''*''' see [[Covariance_matrix#As_a_linear_operator|covariance matrix]] for a detailed explanation
| |
| | |
| :<math>Var(\epsilon(x_0)) \overset{*}{=} \begin{bmatrix}W^T&-1\end{bmatrix} \cdot
| |
| \begin{bmatrix}Var_{x_i}& Cov_{x_ix_0}\\Cov_{x_ix_0}^T & Var_{x_0}\end{bmatrix} \cdot
| |
| \begin{bmatrix}W\\-1\end{bmatrix}</math>
| |
| | |
| '''*''' where the literals <math>\left\{Var_{x_i}, Var_{x_0}, Cov_{x_ix_0}\right\}</math> stand for <math> | |
| \left\{Var\left(\begin{bmatrix}Z(x_1)&\cdots&Z(x_N)\end{bmatrix}^T\right),
| |
| Var\left(Z(x_0)\right),
| |
| Cov\left(\begin{bmatrix}Z(x_1)&\cdots&Z(x_N)\end{bmatrix}^T,Z(x_0)\right)\right\}</math>.
| |
| | |
| Once defined the covariance model or [[variogram]], <math>C(\mathbf{h})</math> or <math>\gamma(\mathbf{h})</math>, valid in all field of analysis of <math>Z(x)</math>, than we can write an expression for the estimation variance of any estimator in function of the covariance between the samples and the covariances between the samples and the point to estimate:
| |
| | |
| :<math>\left\{\begin{array}{l}
| |
| Var(\epsilon(x_0)) = W^T \cdot Var_{x_i} \cdot W - Cov_{x_ix_0}^T \cdot W - W^T \cdot Cov_{x_ix_0} + Var_{x_0}\\
| |
| Var(\epsilon(x_0)) = Cov(0) + \sum_{i}\sum_{j}w_iw_jCov(x_i,x_j) - 2 \sum_iw_iC(x_i,x_0)\end{array} \right.</math>
| |
| | |
| Some conclusions can be asserted from this expressions. The variance of estimation:
| |
| | |
| * is not quantifiable to any linear estimator, once the stationarity of the mean and of the spatial covariances, or variograms, are assumed.
| |
| | |
| * grows with the covariance between samples <math>C(x_i,x_j)</math>, i.e. to the same distance to the estimating point, if the samples are proximal to each other, than the ''clustering effect'', or informational redundancy, is bigger, so the estimation is worst. This conclusion is valid to any value of the weights: a preferential grouping of samples is always worst, which means that for the same number of samples the estimation variance grows with the relative weight of the sample ''clusters''.
| |
| | |
| * grows when the covariance between the samples and the point to estimate decreases. This means that, when the samples are more far away from <math>x_0</math>, the worst is the estimation.
| |
| | |
| * grows with the ''a priori'' variance <math>C(0)</math> of the variable <math>Z(x)</math>. When the variable is less disperse, the variance is lower in any point of the area <math>A</math>.
| |
| | |
| * does not depend on the values of the samples. This means that the same spatial configuration (with the same geometrical relations between samples and the point to estimate) always reproduces the same estimation variance in any part of the area <math>A</math>. This way, the variance does not measures the uncertainty of estimation produced by the local variable.
| |
| | |
| ====Kriging system====
| |
| :<math>\begin{align}
| |
| &\underset{W}{\operatorname{minimize}}& & W^T \cdot Var_{x_i} \cdot W - Cov_{x_ix_0}^T \cdot W - W^T \cdot Cov_{x_ix_0} + Var_{x_0} \\
| |
| &\operatorname{subject\;to}
| |
| & &\mathbf{1}^T \cdot W = 1
| |
| \end{align}</math>
| |
| | |
| Solving this optimization problem (see [[Lagrange multipliers]]) results in the ''kriging system'':
| |
| | |
| :<math>\begin{bmatrix}\hat{W}\\\mu\end{bmatrix} = \begin{bmatrix}
| |
| Var_{x_i}& \mathbf{1}\\
| |
| \mathbf{1}^T& 0
| |
| \end{bmatrix}^{-1}\cdot \begin{bmatrix}Cov_{x_ix_0}\\ 1\end{bmatrix} = \begin{bmatrix}
| |
| \gamma(x_1,x_1) & \cdots & \gamma(x_1,x_n) &1 \\
| |
| \vdots & \ddots & \vdots & \vdots \\
| |
| \gamma(x_n,x_1) & \cdots & \gamma(x_n,x_n) & 1 \\
| |
| 1 &\cdots& 1 & 0
| |
| \end{bmatrix}^{-1}
| |
| \begin{bmatrix}\gamma(x_1,x^*) \\ \vdots \\ \gamma(x_n,x^*) \\ 1\end{bmatrix}
| |
| </math>
| |
| | |
| the additional parameter <math>\mu</math> is a [[Lagrange multiplier]] used in the minimization of the kriging error <math>\sigma_k^2(x)</math> to honor the unbiasedness condition.
| |
| | |
| ===Simple kriging===
| |
| {{notice|this section is very poor and needs to be improved}}
| |
| Simple kriging is mathematically the simplest, but the least general. It assumes the [[expected value|expectation]] of the [[random field]] to be known, and relies on a [[covariance function]]. However, in most applications neither the expectation nor the covariance are known beforehand.
| |
| | |
| The practical assumptions for the application of ''simple kriging'' are:
| |
| * [[stationary process|wide sense stationarity]] of the field.
| |
| * The expectation is zero everywhere: <math>\mu(x)=0</math>.
| |
| * Known [[covariance function]] <math>c(x,y)=\mathrm{Cov}(Z(x),Z(y))</math>
| |
| | |
| ====Kriging system====
| |
| The ''kriging weights'' of ''simple kriging'' have no unbiasedness condition
| |
| and are given by the ''simple kriging equation system'':
| |
| :<math>\begin{pmatrix}w_1 \\ \vdots \\ w_n \end{pmatrix}=
| |
| \begin{pmatrix}c(x_1,x_1) & \cdots & c(x_1,x_n) \\
| |
| \vdots & \ddots & \vdots \\
| |
| c(x_n,x_1) & \cdots & c(x_n,x_n)
| |
| \end{pmatrix}^{-1}
| |
| \begin{pmatrix}c(x_1,x_0) \\ \vdots \\ c(x_n,x_0) \end{pmatrix}
| |
| </math>
| |
| | |
| This is analogous to a linear regression of <math>Z(x_0)</math> on the other <math>z_1 , \ldots, z_n</math>.
| |
| | |
| ====Estimation====
| |
| The interpolation by simple kriging is given by:
| |
| :<math>\hat{Z}(x_0)=\begin{pmatrix}z_1 \\ \vdots \\ z_n \end{pmatrix}'
| |
| \begin{pmatrix}c(x_1,x_1) & \cdots & c(x_1,x_n) \\
| |
| \vdots & \ddots & \vdots \\
| |
| c(x_n,x_1) & \cdots & c(x_n,x_n)
| |
| \end{pmatrix}^{-1}
| |
| \begin{pmatrix}c(x_1,x_0) \\ \vdots \\ c(x_n,x_0)\end{pmatrix}
| |
| </math>
| |
| | |
| The kriging error is given by:
| |
| :<math>\mathrm{Var}\left(\hat{Z}(x_0)-Z(x_0)\right)=\underbrace{c(x_0,x_0)}_{\mathrm{Var}(Z(x_0))}-
| |
| \underbrace{\begin{pmatrix}c(x_1,x_0) \\ \vdots \\ c(x_n,x_0)\end{pmatrix}'
| |
| \begin{pmatrix}
| |
| c(x_1,x_1) & \cdots & c(x_1,x_n) \\
| |
| \vdots & \ddots & \vdots \\
| |
| c(x_n,x_1) & \cdots & c(x_n,x_n)
| |
| \end{pmatrix}^{-1}
| |
| \begin{pmatrix}c(x_1,x_0) \\ \vdots \\ c(x_n,x_0) \end{pmatrix}}_{\mathrm{Var}(\hat{Z}(x_0))}
| |
| </math>
| |
| which leads to the generalised least squares version of the [[Gauss-Markov theorem]] (Chiles & Delfiner 1999, p. 159):
| |
| :<math>\mathrm{Var}(Z(x_0))=\mathrm{Var}(\hat{Z}(x_0))+\mathrm{Var}\left(\hat{Z}(x_0)-Z(x_0)\right).</math>
| |
| | |
| === Properties ===
| |
| {{notice|this section needs revision. Incorrect or confusing text should be removed.}}
| |
| (Cressie 1993, Chiles&Delfiner 1999, Wackernagel 1995)
| |
| * The kriging estimation is unbiased: <math>E[\hat{Z}(x_i)]=E[Z(x_i)]</math>
| |
| * The kriging estimation honors the actually observed value: <math>\hat{Z}(x_i)=Z(x_i)</math> (assuming no measurement error is incurred)
| |
| * The kriging estimation <math>\hat{Z}(x)</math> is the [[best linear unbiased estimator]] of <math>Z(x)</math> if the assumptions hold. However (e.g. Cressie 1993):
| |
| ** As with any method: If the assumptions do not hold, kriging might be bad.
| |
| ** There might be better nonlinear and/or biased methods.
| |
| ** No properties are guaranteed, when the wrong variogram is used. However typically still a 'good' interpolation is achieved.
| |
| ** Best is not necessarily good: e.g. In case of no spatial dependence the kriging interpolation is only as good as the arithmetic mean.
| |
| * Kriging provides <math>\sigma_k^2</math> as a measure of precision. However this measure relies on the correctness of the variogram.
| |
| | |
| ==Applications==
| |
| {{notice|this section is very poor and needs to be improved}}
| |
| <!-- [[File:Syncline and anticline.jpg|thumb|300px|An illustrated depiction of a [[syncline]] and [[anticline]] commonly studied in [[Structural geology]] and [[Geomorphology]].]] -->
| |
| Although kriging was developed originally for applications in geostatistics, it is a general method of statistical interpolation that can be applied within any discipline to sampled data from random fields that satisfy the appropriate mathematical assumptions.
| |
| | |
| To date kriging has been used in a variety of disciplines, including the following:
| |
| * [[Environmental science]]<ref>Hanefi Bayraktar and F. Sezer. Turalioglu (2005) "A Kriging-based approach for locating a sampling site—in the assessment of air quality'', ''SERRA'', 19 (4), 301-305 {{DOI|10.1007/s00477-005-0234-8}}</ref>
| |
| * [[Hydrogeology]]<ref name="Chiles">Chiles, J.-P. and P. Delfiner (1999) ''Geostatistics, Modeling Spatial Uncertainty'', Wiley Series in Probability and statistics.</ref><ref>{{cite doi|10.1029/98WR00003}}</ref><ref>{{cite doi|10.1111/j.1745-6584.2002.tb02503.x}}</ref>
| |
| * [[Mining]]<ref name="Journel">Journel, A.G. and C.J. Huijbregts (1978) ''Mining Geostatistics'', Academic Press London</ref><ref>{{cite doi|10.1023/A:1023239606028}}</ref>
| |
| * [[Natural resource]]s<ref name="multiple">Goovaerts (1997) ''Geostatistics for natural resource evaluation'', OUP. ISBN 0-19-511538-4</ref><ref>{{cite doi|10.1007/s11004-005-1560-6}}</ref>
| |
| * [[Remote sensing]]<ref>{{cite doi|10.1007/0-306-47647-9_6}}</ref>
| |
| * [[Real estate appraisal]]<ref>Barris, J. (2008) ''An expert system for appraisal by the method of comparison''. PhD Thesis, UPC, Barcelona</ref><ref>Barris, J. and Garcia Almirall,P.(2010) ''A density function of the appraisal value''., UPC, Barcelona</ref>
| |
| | |
| and many others.
| |
| | |
| ===Design and analysis of computer experiments===
| |
| Another very important and rapidly growing field of application, in [[engineering]], is the interpolation of data coming out as response variables of deterministic computer simulations,<ref>{{cite book|author = Sacks, J. and Welch, W.J. and Mitchell, T.J. and Wynn, H.P.| title = Design and Analysis of Computer Experiments| publisher = Statistical Science| volume = 4| number = 4| pages=409–435| year=1989}}</ref> e.g. [[finite element method]] (FEM) simulations. In this case, kriging is used as a [[metamodeling]] tool, i.e. a black box model built over a designed set of [[computer experiment]]s. In many practical engineering problems, such as the design of a [[metal forming]] process, a single FEM simulation might be several hours or even a few days long. It is therefore more efficient to design and run a limited number of computer simulations, and then use a kriging interpolator to rapidly predict the response in any other design point. Kriging is therefore used very often as a so-called [[surrogate model]], implemented inside [[optimization]] routines.<ref name=sheetforming>{{Cite doi|10.1007/s12289-008-0001-8}}</ref>
| |
| | |
| ==See also==
| |
| {{Commons category|Kriging}}
| |
| * [[Bayes linear statistics]]
| |
| * [[Gaussian process]]
| |
| * [[Multiple-indicator kriging]]
| |
| * [[Spatial dependence]]
| |
| * [[Variogram]]
| |
| * [[Multivariate interpolation]]
| |
| | |
| ==References==
| |
| <references />
| |
| | |
| ===Books===
| |
| * Abramowitz, M., and Stegun, I. (1972), Handbook of Mathematical Functions, Dover Publications, New York.
| |
| * Banerjee, S., Carlin, B.P. and Gelfand, A.E. (2004). Hierarchical Modeling and Analysis for Spatial Data. Chapman and Hall/CRC Press, Taylor and Francis Group.
| |
| * Chiles, J.-P. and P. Delfiner (1999) ''Geostatistics, Modeling Spatial uncertainty'', Wiley Series in Probability and statistics.
| |
| * Cressie, N (1993) ''Statistics for spatial data'', Wiley, New York
| |
| * David, M (1988) ''Handbook of Applied Advanced Geostatistical Ore Reserve Estimation'', Elsevier Scientific Publishing
| |
| * Deutsch, C.V., and Journel, A. G. (1992), GSLIB - Geostatistical Software Library and User's Guide, Oxford University Press, New York, 338 pp.
| |
| * Goovaerts, P. (1997) ''Geostatistics for Natural Resources Evaluation'', Oxford University Press, New York ISBN 0-19-511538-4
| |
| * Isaaks, E. H., and Srivastava, R. M. (1989), An Introduction to Applied Geostatistics, Oxford University Press, New York, 561 pp.
| |
| * Journel, A. G. and C. J. Huijbregts (1978) ''Mining Geostatistics'', Academic Press London
| |
| * Journel, A. G. (1989), Fundamentals of Geostatistics in Five Lessons, American Geophysical Union, Washington D.C.
| |
| * {{Citation |last1=Press|first1=WH|last2=Teukolsky|first2=SA|last3=Vetterling|first3=WT|last4=Flannery|first4=BP|year=2007|title=Numerical Recipes: The Art of Scientific Computing|edition=3rd|publisher=Cambridge University Press| publication-place=New York|isbn=978-0-521-88068-8|chapter=Section 3.7.4. Interpolation by Kriging|chapter-url=http://apps.nrbook.com/empanel/index.html?pg=144}}. Also, [http://apps.nrbook.com/empanel/index.html?pg=836 "Section 15.9. Gaussian Process Regression"].
| |
| * Soares, A. (2000), ''Geoestatística para as Ciências da Terra e do Ambiente'', IST Press, Lisbon, ISBN 972-8469-46-2
| |
| * Stein, M. L. (1999), ''Statistical Interpolation of Spatial Data: Some Theory for Kriging'', Springer, New York.
| |
| * Wackernagel, H. (1995) ''Multivariate Geostatistics - An Introduction with Applications'', Springer Berlin
| |
| | |
| ===Historical references===
| |
| # Agterberg, F P, ''Geomathematics, Mathematical Background and Geo-Science Applications'', Elsevier Scientific Publishing Company, Amsterdam, 1974
| |
| # Cressie, N. A. C., ''The Origins of Kriging, Mathematical Geology'', v. 22, pp 239–252, 1990
| |
| # Krige, D.G, ''A statistical approach to some mine valuations and allied problems at the Witwatersrand'', Master's thesis of the University of Witwatersrand, 1951
| |
| # Link, R F and Koch, G S, ''Experimental Designs and Trend-Surface Analsysis, Geostatistics'', A colloquium, Plenum Press, New York, 1970
| |
| # Matheron, G., "Principles of geostatistics", ''Economic Geology'', 58, pp 1246–1266, 1963
| |
| # Matheron, G., "The intrinsic random functions, and their applications", ''Adv. Appl. Prob''., 5, pp 439–468, 1973
| |
| # Merriam, D F, Editor, ''Geostatistics'', a colloquium, Plenum Press, New York, 1970
| |
| | |
| ===Software related to kriging===
| |
| | |
| * R packages
| |
| # BACCO - Bayesian analysis of computer code software
| |
| # tgp - Treed Gaussian processes
| |
| # DiceDesign, DiceEval, DiceKriging, DiceOptim - metamodeling packages of the Dice Consortium.
| |
| | |
| * Matlab/GNU Octave
| |
| # [http://mgstat.sourceforge.net/ mGstat] - Geostistics toolbox for Matlab.
| |
| # [http://www2.imm.dtu.dk/~hbn/dace/ DACE] - Design and Analysis of Computer Experiments. A matlab kriging toolbox.
| |
| # GPML - Gaussian Processes for Machine Learning.
| |
| # [http://sourceforge.net/projects/kriging STK] - Small (Matlab/GNU Octave) Toolbox for Kriging for design and analysis of computer experiments.
| |
| # scalaGAUSS - Matlab kriging toolbox with a focus on large datasets
| |
| | |
| * Scilab
| |
| # DACE-Scilab - Scilab port of the DACE kriging matlab toolbox
| |
| # krigeage - Kriging toolbox for Scilab
| |
| # KRISP - Kriging based regression and optimization package for Scilab
| |
|
| |
| * Python
| |
| # scikit-learn - machine learning in Python
| |
| | |
| [[Category:Geostatistics]]
| |
| [[Category:Interpolation]]
| |
| [[Category:Multivariate interpolation]]
| |