Kriging and Variogram Models

doi:10.1016/B978-008044910-4.00461-2

International Encyclopedia of Human Geography

2009, Pages 49-55

https://doi.org/10.1016/B978-008044910-4.00461-2 Get rights and content

Geostatistics is a popular class of statistical methods for estimating, or predicting, the value of a continuous spatial process at unobserved locations given the value of the process at a set of known locations. Spatial prediction of this sort is typically performed using the method known as kriging, which provides estimates that are optimized over the class of predictors that are a linear combination of the observed values of the process. Beyond providing point estimates of the process at unobserved locations, the variances of kriging estimates (or kriging standard errors) are readily available as measures of uncertainty in predictions. An underlying assumption in kriging is that the covariance structure of the spatial process is known. Thus, before kriging can be performed, the spatial-dependence structure must be determined using the observed values of the process. Rather than estimating the covariance function of the spatial process directly, an alternative description of the spatial-dependence structure known as the variogram is estimated from the observed data. In this article, we review both kriging and variogram methods. In addition, we illustrate these methods using a rainfall dataset and provide brief introductions to some extensions of standard geostatistical methods.

References (0)

Cited by (28)

RKPCA-based approach for fault detection in large scale systems using variogram method
2022, Chemometrics and Intelligent Laboratory Systems
Principal Component Analysis (PCA)-based approach for fault detection is a simple and accurate data-driven technique for feature extraction and selection. However, PCA performs poorly if the data used has nonlinear characteristics where this type of data is widely present in most industrial processes. To overcome this drawback, Kernel PCA (KPCA) is an alternative technique used to work on this type of data but it requires more computation time and memory storage space for large-sized data sets. Many size reduction techniques have been developed to select the most relevant observations that will be employed by KPCA. This, known as Reduced KPCA (RKPCA), consequently requires less computation time and memory storage space than KPCA. Besides, it possesses the advantages of both KPCA and standard PCA. In this paper, a reduction in the size of a data set based on a multivariate variogram is proposed. According to its conventional formalism, the uncorrelated observations are selected and kept to form a reduced training data set. Afterward, the KPCA model is built through this data set for faults detection purposes. The proposed RKPCA scheme is tested using an actual involuntary process fault and various simulated sensor faults in a cement plant. Compared to other RKPCA techniques, the developed one yields better results.
Mapping the time-varying spatial heterogeneity of temperature processes over the urban landscape of Augsburg, Germany
2022, Urban Climate
Generating high-resolution spatial interpolations of temperature processes is a vital task for studying urban climate anomalies and their various consequences. Such processes often constitute a complex and demanding data environment: Anthropogenic and natural conditions of the urban landscape result in anisotropic spatial dependencies and trend patterns that often vary in diurnal and seasonal cycles. Two-step geostatistical methods such as residual kriging take spatial heterogeneity into account but ignore the temporal dimension, which can result in a significant loss of potentially useful information. In this study, we propose nonparametric spatial detrending to obtain a process that fulfills the assumptions of ordinary kriging. In our application to urban air temperature series from monitoring sites distributed over the urban and suburban area of Augsburg, Germany, we provide an in-depth analysis of time-varying spatial heterogeneity. By using sub-sampling to account for diurnal, seasonal, and spatial trends, we produce interpolation maps with a resolution of 100 m × 100 m. The validation in a narrower sense is based on cross-validation and shows favorable behavior of the proposed method even when sub-samples are neglected. The broader sense validation is based on hold-out monitoring sites and provides further empirical support for our proposal.
Geostatistical analysis of uranium concentrations in North-Western part of Ogun State, Nigeria
2021, Journal of Environmental Radioactivity
Several statistical techniques have been adopted in the analysis and interpretation of radiometric survey data set with little attention to the geostatistical approach. In this study, the geostatistical technique was used to analyse an airborne uranium data set in the North-western part of Ogun state to deduce the autocorrelation level of uranium with the corresponding geological composition through the geostatistical model fitting. Twelve uranium lithological (UL) units were identified and analysed using variogram and kriging. Three variogram models namely; spherical, exponential and gaussian, were utilised. The variogram results showed that the three models fit in the interpretation of uranium data in the order of Spherical < Gaussian < Exponential models for all the UL units except at UL6 which had range (R) values of 4227.3 m, 5318.2 m and 5636.4 m for Gaussian, Spherical and Exponential models, respectively. The Nugget-Sill ratios (NSR) were in the range of 3.57–18.97% for the three models across the 12 UL units. These results indicate strong spatial autocorrelation/dependency of uranium concentration on geological composition. The ordinary kriging estimator revealed that the weathered basement formation has the highest uranium concentration compared to basement and sedimentary formations across the study area. The coefficient of variation results also revealed homogeneity in the uranium source across the UL units. The geostatistics technique is a useful mathematical tool in the analysis and interpretation of uranium concentration in the North-western part of Ogun State.
Assessing population vulnerability towards summer energy poverty: Case studies of Madrid and London
2019, Energy and Buildings
Citation Excerpt :
For Madrid, the kriging geostatistical analysis method from ArcGIS 10.5 software was used to interpolate between the computed CDHs at each sensor location. The variogram was set to be exponential, as it has been widely used in meteorology and contamination prediction and it gave a smaller mean-squared error than the spherical and the Gaussian variograms [61–63]. To make data comparable between cities, values were classified into deciles, with the first decile representing the highest temperature values and hence the most severe weather conditions.
Climate change is expected to increase the frequency and duration of hot weather and its associated adverse health effects. In dense urban areas, these phenomena will be exacerbated by the Urban Heat Island (UHI) effect and indoor overheating.
This paper assesses population exposure and vulnerability to high summer temperatures by exploring the geospatial connection between the UHI, housing energy efficiency and overheating risk, and social vulnerability indicators, such as income and the elderly population. Focusing on Madrid and London, two European cities with strong UHIs but contrasting drivers of indoor heat risk, the spatial distribution of selected indicators were analysed by means of Geographical Information Systems, and areas with the highest vulnerability towards summer energy poverty were identified.
It was found that while ‘hot and vulnerable’ areas are present in both Madrid and London, there are significant differences in climate, socioeconomic distribution and housing between the two cities. In warmer climates such as Madrid, energy poverty—traditionally defined by wintertime heating—requires its definition to be broadened to include summertime cooling needs; in the context of climate change and urban warming trends, this may soon also be the case in northern cities such as London.
Correlation between Mo mineralization and faults using geostatistical and fractal modeling in porphyry deposits of Kerman Magmatic Belt, SE Iran
2017, Journal of Geochemical Exploration
Citation Excerpt :
The variograms and anisotropic ellipsoid are important tools for spatial analysis in the geostatistical methods (David, 1970; Journel and Huijbregts, 1978; Deutsch and Journel, 1998; Davis, 2002; Pyrcz and Deutsch, 2014). These are fundamental in geostatistical interpretation because directions of different ranges for a regional variables (e.g., ore grades) are determined, and also the main trends of geological particulars can be delineated (VerHoef and Cressie, 1993; Calder and Cressie, 2009). In this study, variography and creation of anisotropic ellipsoid were carried out for Mo, Cu and FD by RockWorks 15 software package.
Kerman Magmatic Belt (KMB) is located in the southern part of Urumieh-Dokhtar Magmatic Belt (UDMB), SE Iran. There are many Cu-Mo porphyry deposits which may have correlation with existing faults. The aim of this study is determination of correlation between Mo mineralization in the porphyry deposits of the KMB and faults based on fractal and geostatistical modeling. Fault density (FD) was calculated and classified by Concentration-Area (C-A) fractal model. Moreover, the Mo values in the porphyry deposits were classified by Concentration-Number (C-N) fractal model. However, the variograms and anisotropic ellipsoids for Mo, Cu and FD show that there is a proper relationship between Mo mineralization and FD trends. Consequently, the correlation between Mo mineralization and faults was calculated by logratio matrix. Based on the results derived via the fractal and geostatistical modeling, the Mo mineralization in Cu-Mo porphyry deposit have good correlation with faults in the KMB especially in the central part of the region including Sarcheshmeh mine and Nowchun deposit. Areas with extremely FD may be prospects for exploration of new porphyry deposits.
Estimating gasoline performance in internal combustion engines with simulation metamodels
2017, Fuel
Citation Excerpt :
Kriging allows unbiased spatial predictions at any position in a domain by linear interpolation of observed points with minimum variance. It is usually designated as Best Linear Unbiased Estimators (BLUE) [49–53]. The fundamental concept of kriging is the spatial dependence.
The accurate simulation of fuel properties’ influence in the performance of internal combustion engines is a very complex subject and combines many physical and chemical concepts such as combustion phenomena, chemical kinetics, fluid dynamics, turbulence and thermodynamics. In order to circumvent the complexity of these concepts, many of simulations packages for engine performance usually consider standard or surrogate fuels, which might not be enough for new fuel developments in some cases. This study aims to evaluate the influence of different formulations of gasoline on the behavior of a flexible fuel engine, relating the physicochemical properties of fuels with performance, efficiency and gaseous emissions. Based on an experimental dataset, metamodels were generated using different radial basis functions and kriging techniques in order to accurately predict torque, fuel consumption, specific fuel consumption, global efficiency and CO₂ emission with twelve blends of iso-octane, n-heptane, toluene and ethanol at different engine speeds and load conditions. The “leave-one-out” cross-validation procedure was applied to automatically select the best metamodel for each case. Metamodels were able to estimate the experimental results of five fuels within the 95% confidence intervals and most of the prediction residuals were lower than 3%.

View all citing articles on Scopus

View full text