topic Re: How to find the best kernel size statistically (in Focal statistics) in ArcGIS Spatial Analyst Questions https://community.esri.com/t5/arcgis-spatial-analyst-questions/how-to-find-the-best-kernel-size-statistically-in/m-p/459623#M6623 <HTML><HEAD></HEAD><BODY><P>That will vary with the input raster, the nature of the kernel and other factors...All I can tell you with any certainty as the kernel size increases, any value being calculated approaches that of the overall value for the raster as a whole.&nbsp; As an example, you can verify this by setting kernel size so that it equal raster size and calculating the mean.&nbsp; As you decrease kernel size, you begin...potentially... to introduce variation in the calculated values and they may become more diverse until each cell is unique at that location</P></BODY></HTML> Wed, 09 Dec 2015 16:01:59 GMT DanPatterson_Retired 2015-12-09T16:01:59Z How to find the best kernel size statistically (in Focal statistics) https://community.esri.com/t5/arcgis-spatial-analyst-questions/how-to-find-the-best-kernel-size-statistically-in/m-p/459620#M6620 <HTML><HEAD></HEAD><BODY><P>I would like to find an appropriate kernel size for evaluation of mean for my raster DEM in <A href="http://resources.arcgis.com/EN/HELP/MAIN/10.1/index.html#//009z000000qs000000">Focal Statistics</A>. Is there a way to select the best kernel size statistically without looking into the data?</P></BODY></HTML> Wed, 09 Dec 2015 14:11:22 GMT https://community.esri.com/t5/arcgis-spatial-analyst-questions/how-to-find-the-best-kernel-size-statistically-in/m-p/459620#M6620 KarolinaKorzeniowska 2015-12-09T14:11:22Z Re: How to find the best kernel size statistically (in Focal statistics) https://community.esri.com/t5/arcgis-spatial-analyst-questions/how-to-find-the-best-kernel-size-statistically-in/m-p/459621#M6621 <HTML><HEAD></HEAD><BODY><P>In short... No ... It is not only the size of the kernel, but its shape. If you happen to be analysing a raster with a directional pattern, then you would want to use one whose shape best reflects the directionality.&nbsp; Focal statistics are often used to analyse the nature of the raster by varying the size and shape of the kernel</P><P><A href="http://desktop.arcgis.com/en/desktop/latest/tools/spatial-analyst-toolbox/focal-statistics.htm" title="http://desktop.arcgis.com/en/desktop/latest/tools/spatial-analyst-toolbox/focal-statistics.htm">Focal Statistics—Help | ArcGIS for Desktop</A> </P><P>other options entail converting your raster to numpy arrays and use numpy or scipy to look for other patterns</P></BODY></HTML> Wed, 09 Dec 2015 14:17:15 GMT https://community.esri.com/t5/arcgis-spatial-analyst-questions/how-to-find-the-best-kernel-size-statistically-in/m-p/459621#M6621 DanPatterson_Retired 2015-12-09T14:17:15Z Re: How to find the best kernel size statistically (in Focal statistics) https://community.esri.com/t5/arcgis-spatial-analyst-questions/how-to-find-the-best-kernel-size-statistically-in/m-p/459622#M6622 <HTML><HEAD></HEAD><BODY><P>Thank you for your answer. I thought that it might be possible to find a kernel size (as a threshold) which tells me that e.g. smoothing above this kernel size will not change the the results significantly more than smoothing using this kernel.</P></BODY></HTML> Wed, 09 Dec 2015 15:01:01 GMT https://community.esri.com/t5/arcgis-spatial-analyst-questions/how-to-find-the-best-kernel-size-statistically-in/m-p/459622#M6622 KarolinaKorzeniowska 2015-12-09T15:01:01Z Re: How to find the best kernel size statistically (in Focal statistics) https://community.esri.com/t5/arcgis-spatial-analyst-questions/how-to-find-the-best-kernel-size-statistically-in/m-p/459623#M6623 <HTML><HEAD></HEAD><BODY><P>That will vary with the input raster, the nature of the kernel and other factors...All I can tell you with any certainty as the kernel size increases, any value being calculated approaches that of the overall value for the raster as a whole.&nbsp; As an example, you can verify this by setting kernel size so that it equal raster size and calculating the mean.&nbsp; As you decrease kernel size, you begin...potentially... to introduce variation in the calculated values and they may become more diverse until each cell is unique at that location</P></BODY></HTML> Wed, 09 Dec 2015 16:01:59 GMT https://community.esri.com/t5/arcgis-spatial-analyst-questions/how-to-find-the-best-kernel-size-statistically-in/m-p/459623#M6623 DanPatterson_Retired 2015-12-09T16:01:59Z