7,799 reputation
725
bio website evansmurphy.wix.com/…
location
age
visits member for 2 years, 10 months
seen 13 hours ago

I am a senior landscape ecologist with The Nature Conservancy's, Central Science. I attempt to bring vigor from diverse fields such as landscape ecology, spatial statistics, remote sensing and applied mathematics to answer practical conservation questions. I hold Affiliate Associate Professor status at University of Wyoming and have over 65 publications in peer-reviewed journals.

My research is focused on spatial statistics in ecological applications, species distribution modeling, climate change, landscape genetics, Bayesian statistics, Lidar and spectral remote sensing and gradient modeling. I have ridden horses for 35 years and was a member of the US Equestrian team. I have also played guitar in several swing and bluegrass bands


13h
revised error of randomforest classification with Landsat data
added 73 characters in body
13h
revised error of randomforest classification with Landsat data
added 405 characters in body
15h
answered error of randomforest classification with Landsat data
15h
comment error of randomforest classification with Landsat data
I would highly recommend not using a symbolic model definition and be mindful of your object names (there is a base function called "data"). Where are you getting the error? Is it in the randomForest model or predict? It would be helpful if you could provide some more details. We cannot speculate on the source of the error if we do not know what the data looks like. Use str() on your data object and edit your question to show the results.
22h
comment Different obs. when I extract raster values from polygons in R
Are you accounting for NA's? The default NA behavior for extract is na.rm=TRUE which would change the number of observations.
1d
comment Should i add coords with proj4string when using readOGR in the script if the shp doesn't contain them?
I would say always use readOGR. However, occasionally you get a byte error in the shx file that can be repaired using repair=TRUE in the maptools import functions that is not available in readOGR.
2d
comment Combining continuous raster and point in ArcGIS for Desktop?
possible duplicate of Extract Values to Points between rasters and point shapefiles of the same name
2d
comment Combining continuous raster and point in ArcGIS for Desktop?
This question has been asked numerous times here. Did you take the time to search the forum before posting your question?
2d
comment Should i add coords with proj4string when using readOGR in the script if the shp doesn't contain them?
Can you please edit your post to make this clear? You do not always get data that has a defined projection to begin with. You can check if your data has a defined projection using proj4string. If it is NA, then you would likely want to define the projection.
2d
comment How to read ESRI File Geodatabase (FileGDB) with OGR?
Have you tried accessing an object in the filegeodatabase? You are asking ogrinfo to describe a directory and not a spatial object.
2d
comment Should i add coords with proj4string when using readOGR in the script if the shp doesn't contain them?
Is there a question here? Yes, readOGR imports the projection information whereas shapefile import functions in maptools do not. Same goes for export.
2d
comment How to set raster projection in R
You can define a projection for rasters just like any sp class object, assigning the appropriate projecting string to the object using "proj4string". However, I doubt that that is why your raster object is "tilted" when you plot it. The R plot engine does not perform any on the fly projection or coordinate interpretation and is quite WISWIG.
Apr
17
comment What are LiDAR returns?
One thing to keep in mind here is that discrete return lidar returns multiple measurements from a pulse, but are not tied to the specific pulse. Whereas, waveform lidar represents multiple binned measurements associated with each pulse. The waveform data allows one to derive a continuous distribution of the laser energy for each pulse where discrete return does not.
Apr
17
answered Shapefile One-to-Many Relationship in R
Apr
16
comment How to compute layer by layer after stack?
This is completely different from what you describe as: "I do this day1(2007)+day1(2008)+day1(2009)/3". This is not a 30 day moving average! The paper you cite is actually using the harmonic approach I cited with a +/- 31 day window for the smoothing period. You can accomplish a simplified form of this analysis using movingFun with type="around" and circular=TRUE.
Apr
15
comment How to compute layer by layer after stack?
Yes, you are overwriting the stack each time and not adding to it. If you were to use addLayer or s[[1]] <- r it would throw an error. Were it seems that just overwriting each time would be a tractable solution, you are using up considerable system resources and, without a special garbage collection function, will likely run out of RAM in a real world problem.
Apr
15
revised How to compute layer by layer after stack?
added 1443 characters in body
Apr
15
comment How to compute layer by layer after stack?
You are attempting, unsuccessfully, to apply a rolling average. Using this approach, follow your original attempt with movingFUN. Honestly, you would be better served using something like a polynomial regression to smooth the data. The mean is very sensitive to skewness in the data, which is quite expected. Whereas, an approach like lowess regression is robust to stochasticity in the climate series.
Apr
15
comment How to compute layer by layer after stack?
The way you are defining an empty stack will throw and extent error. You need to define the dimensions of the stack, ideally with a raster used in the analysis, and then populate it. You also do not want to keep "re-stacking" it but rather use "addLayer" to append the existing stack. Alternately, you could also populate the stack with the rasters from the original stack (n - step) and use an index to replace each raster (see my example).
Apr
15
answered How to compute layer by layer after stack?