heat mapqgis
I am using QGIS and heatmap plugin and I need help with finding the meaning of the resulting raster values. I know there have been some questions, but none of them helped. This is my point layer input
This is a print screen of the settings of the heatmap plugin
And finally this is the resulting raster with minimum and maximum values. I need to convert these values to some meaningful values to get a reasonable legend. Do you know how the raster values are calculated?
The answer is a little bit technical... What actually happens is that the value from each point (usually 1, unless you're using a weight column) is "spread out" over the chosen heatmap radius. Imagine a spike of height 1 at each of your points which has been squashed down to make a bump shape. Each of these is then added to get the resultant raster.
To summarise:
the maximum value that each feature contributes to your raster will be less than the attribute's value, since this value is "spread out" over a circular area.
the smoothed value from each feature is added for every pixel in the raster, so the maximum value in the raster will also be affected by the density and number of points in your table. Thus the maximum value in your output raster will depend on both the radius/smoothing type applied, and the spatial distribution of these points.
pixels in your output raster which are further then the search radius from the nearest point will have a zero value.
Google "kernel density estimation" if you're after more details... that's what the mathematical process behind heatmap creation is called.
the units in a "normal" heatmap represent a probability estimate of there being a point at that location.
Imagine taking a bell curve, and rotating around its vertical axis. Now, put one of these centered on each point. Then, for each pixel, sum up the heights all these curves, sampled at that point. That gives the heatmap surface.
The height of this surface gives a good estimate of how likely you are to find a point there. But this surface is continuous (smooth)
The kernel option you choose determines the shape of these curves, and how they "fall-off" (or decay) from the point outwards. The radius specifies how large the curve is.
Here's an example with the default, "quartic". I have a series of random points, and a 400 meter radius.
If you want a count of the number of points within a given radius from each cell, you can use the Uniform kernel. This sweeps out a cylinder of fixed height around each point, and sums their heights for each pixel in the raster. The curve in this case is flat, and doesn't reduce in height away from the point.
Assuming that you :-
each cell will give the number of points within the kernel radius... again, using a 400 meter radius with the same data
useful sources:
Best Answer
I don't think it makes any sense to try use the raw values from a heatmap in the legend, as they will have practically no meaning to anyone who reads your map. You're much better using descriptive terms in your legend like "higher density" and "lower density". If you REALLY need to use raw values, then it would be something like "0.039 sum of point values weighted by inverse distance from cell and scaled by total volume of 20km radius kernel function".
My recommendation - stick with the descriptive terms and treat the output as just a relative indicator of density...