In this tutorial, you will learn how to make use of a discrete point dataset to generate a seamless continuous raster using a number of different geostatistical interpolation methods.

Geostatistical interpolation methods are a set of powerful techniques used in Geographic Information Systems (GIS) and spatial analysis, including within the QGIS environment, to estimate and predict values at unsampled locations based on observed data. These methods are particularly valuable when dealing with spatially distributed data and can be applied to various applications. Popular geostatistical interpolation methods include Kriging, Inverse Distance Weighting (IDW), and Spline.

In the first part of this tutorial, we will see how to make use of Voronoi Polygons (which is also known as Thiessen polygons) to define an area of influence based on the proximity of each point to one another, and create a rainfall distribution map based on a point dataset. We will make use of a color ramp in order to visualise the polygons which shows the gradient of the variable with a clear distinction of the high and low values.

Following that, we will use a very commonly used geostatistical interpolation method called IDW, which stands for Inverse Distance Weighting in order to generate a seamless continuous raster, by predicting values for unknown areas based on the available point values in the same dataset.

Finally, we will also make use of another interpolation method which is called Thin Plate Spline (which you can find under SAGA tools in QGIS) to perform a similar task, and then we will compare the results and see how each interpolation method differ from one another, with some thoughts on how to select a specific interpolation method for a given task at hand.

Download the average annual rainfall sample dataset - https://drive.google.com/drive/folder...