Skip to main content

Kriging in GIS and variogram

Kriging is an advanced spatial interpolation technique used in GIS (Geographic Information System) that estimates values for unknown locations based on the values observed at nearby known locations. It is a geostatistical method that takes into account not only the distances between points but also the spatial correlation or variability in the data.

Unlike simpler interpolation methods like IDW, which assume a constant variation across the study area, kriging incorporates the spatial autocorrelation of the data to produce more accurate and precise estimates. Kriging considers the spatial arrangement and patterns of the data points to generate a surface that honors the underlying spatial structure.

The key principle behind kriging is the variogram, which quantifies the spatial correlation between pairs of points at different distances. The variogram measures how the values of nearby points vary from each other as a function of distance. It provides information about the spatial dependence or variability in the dataset.

The kriging process involves three main steps:

1. Variogram modeling: The first step in kriging is to construct a variogram, which is a plot of the semivariance (a measure of dissimilarity or variability) against distance or lag between pairs of points. The variogram helps to understand the spatial structure of the data and determine the range, sill, and nugget effect. Based on the variogram, a mathematical model is fitted to describe the spatial correlation.

2. Interpolation: Once the variogram is modeled, kriging calculates the weights or coefficients for the known points based on their spatial relationship to the target location. The weights are determined through a process known as kriging equations, which consider the variogram and covariance between points. These equations generate the optimal weights that minimize the prediction error.

   - Ordinary Kriging (OK): Assumes a constant mean value across the study area.
   - Simple Kriging (SK): Accounts for an unknown mean value, estimating it from the data.
   - Universal Kriging (UK): Incorporates additional spatially correlated variables (covariates) in addition to the location coordinates.

3. Prediction: The final step is the estimation of values at the unknown locations using the calculated weights. Kriging provides not only the predicted values but also the estimation error or uncertainty associated with each prediction. This information can be valuable in decision-making processes.

Kriging is particularly useful when dealing with spatial datasets that exhibit spatial autocorrelation, anisotropy (directional dependence), or irregularly spaced points. It provides a more sophisticated approach to spatial interpolation by considering the inherent spatial relationships in the data.

GIS software typically provides various kriging algorithms and tools that allow users to model the variogram, perform the interpolation, and generate kriging predictions and associated error maps.

Comments

Popular posts from this blog

Water cycle. Hydrological cycle.

Water cycle. Hydrological cycle.  Usgs 

Global Water Balance (Water Budget)

Definition The Global Water Balance , also called the Global Water Budget , refers to the balance between the water entering, leaving and stored in different parts of the Earth. Water continuously moves between three major components: Atmosphere – Water vapour, clouds and precipitation. Oceans – The largest storage of water on Earth. Land – Rivers, lakes, glaciers, groundwater and soil moisture. The water balance explains how much water is received, how much is lost and how much remains stored in a particular area. Simple definition: The global water balance is the relationship between precipitation, evaporation, runoff and changes in water storage on Earth. Basic principle: Conservation of Mass Water cannot be created or destroyed during the no...

Quantitative Revolution in Geography

The Quantitative Revolution was a major change in Geography during the 1950s and 1960s. It introduced mathematical, statistical and scientific methods to understand geographical phenomena. Before this revolution, geographers mainly described places, regions, landscapes and differences between areas. After the revolution, they increasingly used numerical data, statistical analysis, mathematical models and theories to explain why geographical patterns occur and how they may change. For example: Traditional approach: Describe the distribution of population in different regions. Quantitative approach: Use statistical methods to identify population patterns, explain the factors influencing population distribution and predict future population growth. The revolution helped establish Geography as a spatial science, focusing on the location, distribution, relati...

IDW and Kriging

Kriging and Inverse Distance Weighting (IDW) are both interpolation techniques commonly used in GIS to estimate values at unmeasured locations based on a set of known data points. Here's an explanation and a comparison of Kriging and IDW: Kriging: Kriging is a geostatistical interpolation method that takes into account the spatial autocorrelation of the data. It provides the best linear unbiased prediction of the unknown values. Kriging assumes that the data follows a spatial pattern and calculates weights based on the spatial relationship between known points. It considers the distance between points, the variability of the data, and the spatial structure to generate the interpolated surface. Kriging provides estimates of the spatial variability and uncertainty through the calculation of a variogram or covariance model. IDW (Inverse Distance Weighting): IDW is a simpler interpolation method that assigns weights to known points based on their distance from the target location. The ...

Spectral Signature vs. Spectral Reflectance Curve

Spectral Signature  A spectral signature is the unique pattern in which an object: absorbs energy reflects energy emits energy across different wavelengths of the electromagnetic spectrum. ✔ Key Points Every natural and man-made object on Earth interacts with sunlight differently. These interactions produce a distinct pattern , just like a "fingerprint". Sensors on satellites record these patterns as digital numbers (DN values) . These patterns help to identify and differentiate objects such as vegetation, soil, water, snow, buildings, minerals, etc. ✔ Examples of Spectral Signatures Healthy vegetation → High reflectance in NIR , strong absorption in red Water → Strong absorption in NIR and SWIR , low reflectance Dry soil → Gradual increase in reflectance from visible to NIR Snow → High reflectance in visible , low in SWIR ✔ Why Spectral Signature Matters It allows: Land cover classification Chan...