Forum: biomod2 package is now available !
Posted by: damien georges
Content: Dear BIOMOD-users,You were eagerly waiting for it, and we are happy to say that the new version of BIOMOD called biomod2 is now online on R-Forge. Although we kept the same modelling philosophy than the former version (which we will still maintain for a while), we have made crucial changes. biomod2 is now fully object-oriented and made for running on a single species only (see vignette MultiSpeciesModelling for multi-species modelling at once). For advanced BIOMOD users, the new functions might be a bit disturbing at the beginning. Then, you will see that this new version is much more advanced and practical than the former ones. Among the novelties, the addition of MAXENT in the modelling techniques, a large range of evaluation metrics, a more refined definition of ensemble modelling and ensemble forecasting, the possibility to give presence-only data and environmental rasters to biomod2 and let it extract pseudo-absence data directly. We have created several vignettes for you to get use to this new version and a figure explaining the different ways of giving data to BIOMOD. Please bear in mind that R-Forge is a development platform, it means that this new package would experience repeated updating the next couple of weeks (correcting bugs, adding documentation, adding functionalities) so think about updating the package before each new study you will do. Last but not least, all comments are welcome! If you find a bug, if you think some documentation points are unclear, if you think about new functionalities that may be useful, just let us know ASAP. We count on you to help finalizing this new version to a very nice tool. We will then release it to CRAN by the end of July. Please remember to add your code, R-version, OS and BIOMOD-version every time you report a bug or a mistake in the vignette or help files. Hoping you will enjoy this new version of BIOMOD. With our best wishes, Damien & Wilfried |
Latest Newsbiomod2 is now devel on githubdamien georges - 2020-03-02 17:08 -
biomod2 package is now available !damien georges - 2012-07-26 13:56 -
...
|
Monitor Forum | 
Start New Thread
| RE: Binary maps (TSS threshold) [ Reply ] By: Pedro Eisenlohr on 2017-09-27 22:37 | [forum:45424] |
|
Dear Damien, Thank you very much for all support! Best wishes. |
|
| RE: Binary maps (TSS threshold) [ Reply ] By: damien georges on 2017-09-18 09:10 | [forum:45323] |
|
Dear Pedro, The easiest way to handle the binary projection maps is to do it at BIOMOD_Projection() stage. Then you can use the 'binary.meth' argument to specify the model evaluation metric you want to optimize for threshold selection. In your case you should use binary.meth = 'ROC' Hope that helps, Damien |
|
| RE: Binary maps (TSS threshold) [ Reply ] By: Pedro Eisenlohr on 2017-09-13 04:05 | [forum:45322] |
|
Dear Damien, Thank you again! This seems to be a very pretty basic question, but as I am a beginner user of biomod2, I have also the following one: I chose four algorithms to build my ensemble model. To build a binary map from such a model based on BinaryTransformation(), I need the threshold value that maximizes sensitivity + specificity. From your message, I understood that this is returned by ROC evaluation statistics. BinaryTransformation() needs a previously calculated threshold. Thus, considering ROC statistics, should I calculate the mean of all cutoffs that arise from get_evaluations() applied to those four algorithms, and use such mean as threshold in BinaryTransformation()? Thank you for your time! Cheers. |
|
| RE: Binary maps (TSS threshold) [ Reply ] By: damien georges on 2017-09-12 15:38 | [forum:45320] |
|
Dear Pedro, The threshold that maximize sens + spec is the one returned by ROC evaluation statistcs (see best.method ('youden') in pROC::coords() help file which biomod2 is based on). Hope that helps, Danien |
|
| RE: Binary maps (TSS threshold) [ Reply ] By: Pedro Eisenlohr on 2017-09-11 15:39 | [forum:45318] |
|
Dear Damien, Thank you for your interest! Following the code I presented above, the biomod2 returns multiple binary maps, because it apparently does not understand the names, which should be expected by "RF" augment of 'grep' function. It does not happen when I choose Occurrence.grd (continuous maps) instead of TSSbin.grd. I tried to obtain binary maps by the 'BinaryTransformation' function. The consensus binary plot was correctly obtained, but here another question arose: the definition of a threshold. I would like to apply the "Maximum Training Sensitivity plus Specificity" to obtain my binary maps. The 'BinaryTransformation' function requires a value that should be previously calculated. Thus, how can I calculate this threshold for my 10 algorithms processed with biomod2? Thank you again! |
|
| RE: Binary maps (TSS threshold) [ Reply ] By: damien georges on 2017-09-11 08:20 | [forum:45311] |
|
Dear Pedro, Do you have any error message popping-up? Best, Damien |
|
| Binary maps (TSS threshold) [ Reply ] By: Pedro Eisenlohr on 2017-09-08 01:46 | [forum:45307] |
|
Dear All, I would like to build binary maps from my continuous models based on TSS threshold. However, I am having difficulties on this task. My code is: spp.projections <- BIOMOD_Projection( modeling.output = myModelOut.PA, new.env = env.selected, proj.name = "Cur1", selected.models = "all", binary.meth = "TSS", output.format = ".grd") projections <-stack("C:/Users/pedro/Dropbox/Modelos/Occurrence/proj_Cur1/proj_Cur1_Occurrence_TSSbin.grd") names(projections) projections.RF.all <- subset(projections, grep("RF", names(projections))) projections.RF.mean <- mean(projections.RF.all)/1000 windows(w=6, h=6) plot(projections.RF.mean, col = matlab.like(100), main = "RF", las = 1) plot(wrld_simpl, add = TRUE, col="transparent", border="white", lwd = 0.5) Where I am going wrong? Thank you very much! |
|
