Module 5 - Surface Interpolation

 In this week's lab, we were tasked with carrying out different surface interpolation techniques in GIS, critically interpreting the results from the interpolation techniques, and then comparing and contrasting the different interpolation techniques. Those surface interpolation techniques we explored are Theissen interpolation, Inverse Distance Weighting (IDW) interpolation, and Spline interpolation (Regularized and Tension). The area we created the surface interpolation for was Tampa Bay water quality, specifically, Biological Oxygen Demand (BOD). Each method of interpolation conducted resulted in a different output for the same data. 

IDW is a method of surface interpolation that estimates cell values by averaging out all of the data from the sample points, resulting in this output:

Spline is a method of interpolation that estimates values using a mathematical function to minimize surface curvature, resulting in a smooth surface that directly passes and connects points together. However, there are two methods of spline, regularized and tension. Regularized creates the smooth surface common with splines by changing surface values that may lie outside the set data range set by the collected points. Here is what a regularized output may look like:

A tension spline primarily controls the stiffness of a surface. This results in a less smooth surface that is constrained to the set data range, resulting in this output:

The last method is the Theissen Method, which is the simplest form of interpolation. It assigns each cell location the same value as the nearest point, resulting in precise measurements for the cells. It is done by first converting the points to Thiessen polygons, then converting those polygons to a raster by utilizing the feature to raster tool, resulting in this output:

Overall, this lab definitely opened my eyes to how complex GIS can be, and I learned a lot about different methods of interpolation I can now use at my place of employment.