Jeo-İstatistik'te Kullanılan Temel Kriging Yöntemleri

Year 2017, Volume: 27 Issue: 1, 10 - 20, 31.03.2017

Pınar Bostan

https://doi.org/10.29133/yyutbd.305093

Cited By: 2

Abstract

Çevresel, hidrolojik, tarımsal
ve benzer çalışmalara ait ölçümler dünya üzerinde yapılmış noktasal gözlemlere
dayanır. Yağış ve sıcaklık değerleri meteorolojik istasyonlarda, toprak
karakteristiği toprak örneklerinden ve göl kirliliği gölden alınan örneklerden
ölçülür. Bunlar noktasal olarak yapılan mekânsal ölçümlere örnektir. Belli
noktalardan örnekler alarak veya belirgin yerlerden ölçüm yaparak sınırlı
sayıda ölçüm yapabiliriz. Ancak ilgilendiğimiz değişkenin dünyanın her
noktasında ya da belli büyüklükteki bir alan üzerinde ölçüm yapmak mantıksal
olarak mümkün değildir. Bunun yerine bilim insanları bir değişkenin tüm alanda
mekânsal olarak nasıl dağıldığını haritalamak için enterpolasyon yöntemini
kullanmayı tercih ederler. Birbirine yakın olan gözlem noktaları benzer
değerlere sahiptirler, ancak birbirinden uzak olan noktalar daha farklı
değerler taşırlar. Bu bilgi tahmin prosedüründe (enterpolasyon)
kullanılır. Burada bahsi geçen kriging yöntemleri de enterpolasyon
yöntemlerindendir. Kriging en uygun tahmin değerleri verir: bir değişkene ait
herhangi bir yerde en olası değeri üretir. Bu derleme çalışmasında
jeo-istatistikte en çok kullanılan kriging metotlarından Sıradan kriging,
Regresyon kriging ve Evrensel kriging yöntemlerine ait yöntemler anlatılmıştır.

Keywords

Jeoistatistik, Enterpolasyon, Sıradan kriging, Regresyon kriging, Evrensel kriging

Basic Kriging Methods in Geostatistics

Abstract

Measurements
of environmental, hydrological, agricultural and similar studies are based on
point observations over the Earth. Precipitation and temperature values are
measured from meteorological stations, soil characteristics are measured from
soil samples, and pollution of a lake is measured by taking samples from lake.
These are some examples from spatial point measurements. These variables can be
measured by taking samples from a limited number of locations or from certain
locations. However, it is logically impossible to measure a variable at all
parts of globe or on a field of certain size. Instead of this it is possible to
make some interpolation to map spatial distributions of that variable.
Observation locations which are close to each other tend to have similar
values, however the ones located farther apart from each other differ more. So
this knowledge is used in prediction procedure (interpolation).  Kriging which will be described here, is an
interpolation method. Kriging makes optimal predictions: it provides the most
likely value at any location of a variable. Methodologies of most commonly used
kriging methods in geostatistics; Ordinary kriging, Regression kriging and
Universal kriging have been described in this review work. 

Keywords

Geostatistics, Interpolation, Ordinary kriging, Regression kriging, Universal kriging

References

• Anonymous (2016). http://maps.unomaha.edu/Peterson/gisII/ESRImanuals/Ch3_Principles.pdf (access on 29.11.2016).
• Bailey TC, Gatrell AC (1995). Interactive Spatial Data Analysis. ISBN: 0-582-24493-5.
• Boer EPJ, Beurs KM, Hartkamp AD (2001). Kriging and thin plate splines for mapping climate variables JAG l 3(2): 146-154.
• Bostan PA, Heuvelink GBM, Akyürek SZ (2012). Comparison of Regression and Kriging Techniques for Mapping the Average Annual Precipitation of Turkey, International Journal of Applied Earth Observation and Geoinformation 19: 115-126. Bostan PA (2013). Analysis and Modelling of Spatially and Temporally Varying Meteorological Parameter: Precipitation over Turkey, A thesis submitted to the Graduate School of Natural and Applied Sciences of Middle East Technical University, Ankara. Brus DJ, Heuvelink GBM (2007). Optimization of sample patterns for universal kriging of environmental variables, Goederma 138: 86-95 . Carrera-Hernández JJ, Gaskin SJ (2007). Spatio temporal analysis of daily precipitation and temperature in the Basin of Mexico, Journal of Hydrology 336: 231-249.
• Düzgün Ş (2008), GGIT 538 Lecture Notes, METU-Ankara. Gething PW, Atkinson PM, Noor AM, Gikandi PW, Hay SI, Nixon MS (2007). A local space-time kriging approach applied to a national outpatient malaria data set, Computers & Geosicences 33: 1337-1350.
• Grimes IFD, Pardo-Iguzquiza E (2010). Geo-statistical Analysis of Rainfall, Geographical Analysis 42: 136-160.
• Hengl T, Heuvelink GBM, Stein A (2004). A generic framework for spatial prediction of soil variables based on regression kriging, Geoderma 120: 75-93.
• Hengl T (2009). A Practical Guide to Geostatistical Mapping. ISBN 978-90-9024981-0.
• Heuvelink GBM (2006). Incorporating process knowledge in spatial interpolation of environmental variables, In: Proceedings of Accuracy 2006 (Eds. M. Caetano and M. Painho), Lisbon: Instituto Geográfico Portugués, pp. 32-47. Heuvelink GBM, Griffith DA (2010). Space–Time Geostatistics for Geography: A Case Study of Radiation Monitoring Across Parts of Germany, Geographical Analysis, ISSN 0016-7363., Wageningen University, Netherlands.
• Isaaks EH and Srivastava RH (1989). Applied Geostatistics, Oxford University Press, New York, ISBN: 0195050134.
• Journel and Rossi (1989). When do we need a trend model in kriging, Mathematical Geo., 21(7): 715-739.
• Knotters M, Brus DJ, Voshaar JHO (1995). A comparison of kriging, co-kriging, and kriging combined with regression for spatial interpolation of horizon depth with censored observations, Geoderma 67: 227-246.
• Knotters M, Heuvelink GBM, Hoogland T, Walvoort DJJ (2010). A disposition of interpolation techniques, Wageningen Statutory Research Tasks Unit for Nature and the Env., WOT-werkdocument 190.
• Lloyd CD (2005). Assessing the Effect of Integrating Elevation Data into the Estimation of Monthly Precipitation in Great Britain, Journal of Hydrology 308: 128-150.
• Lloyd CD (2006). Local Modals for Spatial Analysis, 244 p., ISBN: 0-4153-1681-2.
• Müller W, Zimmerman DL (1997). Optimal Design for Variogram Estimation. Forschungsberichte / Institut für Statistik, 51. Department of Statistics and Mathematics, WU Vienna University of Economics and Business, Vienna.
• Phillips DL, Lee EH, Herstrom AA, Hogsett WE, Tingey DT (1997). Use of auxiliary data for spatial interpolation of ozone exposure in south-eastern forests, Environmetrics 8: 43-61.
• Snepvangers JJJC, Heuvelink GBM, Huisman JA (2003). Soil water content interpolation using spatio-temporal kriging with external drift, Geoderma 112: 253- 271.
• Wang J, He T, Lv CY, Chen YQ, Jian W (2010). Mapping soil organic matter based on land degradation spectral response units using Hyperion images, International Journal of Applied Earth Observation and Geoinformation 12: 171-180.
• Webster R, Oliver MA (2007). Geostatistics for Environmental Scientists. ISBN: 978-0-470-02858-2.
• Zimmerman DL, Zimmerman MB (1991). A Comparison of Spatial Semivariogram Estimators and Corresponding Ordinary Kriging Predictors, Technometrics, 33(1): 77-91.