Maximum Entropy machine learning model output using digitized downed trees (structure) with three variables and regularization multiplier of 1.0
This dataset (multiple outputs files in a compresssed folder) is output from a run of the Maxent ML Model (Phillips et.al., 2006, url: https://biodiversityinformatics.amnh.org/open_source/maxent/) using trees with structure (N=4283) and includes the three environmental variables with most contributi...
| Main Author: | |
|---|---|
| Format: | Dataset |
| Language: | unknown |
| Published: |
Texas Data Repository Dataverse
2020
|
| Subjects: | |
| Online Access: | https://dx.doi.org/10.18738/t8/gmu4xy https://dataverse.tdl.org/citation?persistentId=doi:10.18738/T8/GMU4XY |
| Summary: | This dataset (multiple outputs files in a compresssed folder) is output from a run of the Maxent ML Model (Phillips et.al., 2006, url: https://biodiversityinformatics.amnh.org/open_source/maxent/) using trees with structure (N=4283) and includes the three environmental variables with most contribution according to MaxentVariableSelection (Jueterbock, et.al. 2016) (vegetation community, inundation probability, and soil classification) and implemented as hinge features with a regularization multiplier (beta parameter) of 1.0. The value of 0p150 in the dataset file names refer to the fact that it uses digitized downed trees with structure. Phillips, S.J., Anderson, R.P., Schapire, R.E. (2006). Maximum Entropy modelling of species geographic distribution. Ecological Modelling, 190, 231-259. Jueterbock, A. Smolina, I., Cover, J.A., Hoaru, C. (2016) The fate of arctic seaweed Fucus disticus under climate change: an ecological niche modelling approach. Ecology and Evolution, 6(6), 1712-1724. |
|---|