It seems to have no effect on the final tif expression effect and the number of statistical rasters (just ignore the number of nodata rasters). The only uncertainty now is whether it will affect the subsequent prediction function of plus
thank u
Welcome to the community @uuuu ,
In general, it is not necessary to remove nodata values from raster datasets. The best thing to do is make sure that your rasters have a nodata value defined in their metadata. That way InVEST will be able to correctly identify the nodata pixels, and deal with them appropriately. We are always checking for nodata.
1 Like
Thank you very much for your reply!
I don’t know if it’s because of the version update. In fact, some tutorials I collected on other platforms one or two years ago said that the nodata value in the study area should be reclassified to 0 in advance to avoid affecting the correctness of the results, so I am not sure whether the data I made without reclassification is accurate. Now I am confident in my results 
This topic was automatically closed 7 days after the last reply. New replies are no longer allowed.