Lab 5: Interpolation

For this lab, we completed 3 different types of interpolation using Tampa Bay Biochemical Oxygen Demand (BOD) concentration data. First, I conducted the Thiessen interpolation technique which assigns each location the same value as the nearest point and creates a hard polygon boundary around the value. In this case of representing water quality in the bay, I believe the Thiessen technique was the least useful as it ignores the gradual transitions of continuous data, over simplifying spatial processes making it less accurate. The second interpolation method I used was Inverse Distance Weighting (IDW) which estimates values between sample points to create a continuous surface, making it more accurate than the Thiessen polygons. Below is a screenshot of the IDW interpolation surface I created for this lab. 

The third interpolation method I used for the BOD concentration data was Spline interpolation - both Regularized and Tension. Spline interpolation also creates a smooth continuous surface like IDW interpolation.  However, Spline interpolation can spike values beyond their true values creating a peak or depression that is not really there especially when sample points are sparsely distributed. Tension Spline interpolation can help prevent these untrue values in the interpolation surface by forcing estimated values stay closer to the known sample points.