Maximilian Pichler

The zero, because we do not want a reference level for year, actually also not for the env*year interactions, so it should rather be: ~year*(env1+env2+...) - 0 - env1 -...

Hi, no: ~0+year+year:env1+year:env2, will create an interaction between year and your env variables, so that you get different env effects for each year.

Hi @fetafretka, Have you scaled your coordinates, or the other variables? Optimization can go wrong if variables are on large scales, thus I would suggest to scale all of them.

hi @fetafretka, Sorry, it is hard to say if it is because of the data or because of convergence problems in the model. If this is ok for you, could...

Hi @fetafretka , Sorry I somehow missed your post. I will look at your data asap.

Could you please send me the factors.csv via email? The link above doesn't work [email protected]

Hi @Sarahbouclette, Could you also share a histogram of your response? It may also be difficult for the optimizer if your response is strongly overdispersed. In this case, you may...

Hi @Sarahbouclette, Sorry, it is hard to say if it is because of the data or because of convergence problems in the model. If this is ok for you, could...

Hi @YJ781, If you set n_gpu = 1L , sjSDM_cv is expecting a CPU parallelization which you didn't specify, so either you turn on CPU parallelization by using n_cores =...

Hi @YJ781, This is a bug, I forgot to move a tensor to the right device. I pushed a fix to the development branch (master branch of the github repository),...