<div>Hi,</div><div><br></div><div>I've produced an ensemble forecast prediction that have a noisy</div><div>pattern of dispersion of binary presence points. There are some</div><div>continuous areas of predicted presence but most of the prediction</div>
<div>comes on scattered present points dispersed on systematic patterns</div><div>like waves (see attached pic). Is this normal? Is this related to the</div><div>method to create pseudo-absences? If not what may be causing it?</div>
<div><br></div><div>Thanks for the help!</div><div><br></div><div>Alexandre Sampaio</div><div><br></div><div>Code:</div><div> Initial.State(Response = back[,7], Explanatory = back[,1:3],</div><div> IndependentResponse = NULL, IndependentExplanatory = NULL,</div>
<div> <a href="http://sp.name">sp.name</a>="melinis")</div><div><br></div><div> Models(GLM = T, TypeGLM = "poly", Test = "AIC", GBM = T, No.trees =</div><div> 2000, GAM = T,</div><div> Spline = 3, CTA = T, CV.tree = 50, ANN = T, CV.ann = 2, SRE = T,</div>
<div> Perc025=T, Perc05=F, MDA = T,</div><div> MARS = T, RF = T, NbRunEval = 3, DataSplit = 80, Yweights=NULL, Roc =</div><div> T, Optimized.Threshold.Roc = T,</div><div> Kappa = T, TSS=T, KeepPredIndependent = F, VarImport=F, NbRepPA=1,</div>
<div> strategy="circles",</div><div> coor=CoorXY, distance=2, nb.absences=1000)</div><div><br></div><div> Projection(Proj = back[,1:3], Proj.name='melinis', GLM = T, GBM = T, GAM = T,</div><div> CTA = F, ANN = T, SRE = T, MDA =T, MARS = T, RF = T,</div>
<div> BinRoc = T, BinKappa = T, BinTSS = T, FiltRoc = F, FiltKappa = F, FiltTSS = F,</div><div> repetition.models=T)</div><div><br></div><div> Ensemble.Forecasting(Proj.name= "melinis", weight.method='Roc', PCA.median=T,</div>
<div> binary=T, bin.method='Roc', Test=F, decay=1.6, repetition.models=T)</div><div><br></div><div> level.plot(consensus_melinis_melinis_full_bin[,2], back[,1:3])</div><br>