Harwood's eriastrum - UCSB Species Distribution Model, CA Desert
Dates
Original Data Basin Creation Date
2013-06-20 15:47:50
Original Data Basin Modified Date
2013-06-20 15:47:50
Summary
These data are statistical model outputs for Harwood's eriastrum (Eriastrum harwoodii) species distribution, completed by Frank Davisâ Biogeography Lab at UC Santa Barbara. The UCSB Biogeography Lab used Maxent to generate predictions of habitat occupancy for ~70 species for the CA Energy Commissionâs project âCumulative Biological Impacts Framework for Solar Energy in the CA Desertâ, 500-10-021. Species distribution models were produced at 270 m resolution using a subset of 22 environmental variables. Models were evaluated with 10-foldcross validated AUC scores. Results are preliminary and have notyet been reviewed by expert biologists. Both continuous probability surfaces and binary layers are available for each species [...]
Summary
These data are statistical model outputs for Harwood's eriastrum (
Eriastrum harwoodii) species distribution, completed by Frank Davisâ Biogeography Lab at UC Santa Barbara.
The UCSB Biogeography Lab used Maxent to generate predictions of habitat occupancy for ~70 species for the CA Energy Commissionâs project âCumulative Biological Impacts Framework for Solar Energy in the CA Desertâ, 500-10-021.
Species distribution models were produced at 270 m resolution using a subset of 22 environmental variables. Models were evaluated with 10-foldcross validated AUC scores. Results are preliminary and have notyet been reviewed by expert biologists.
Both continuous probability surfaces and binary layers are available for each species modeled. Binary layers depicting predicted suitable habitat were derived using the equal training sensitivity and specificity threshold.
For
Eriastrum harwoodii (broad extent), Max Sensitivity + Specificity threshold = 0.12; best AUC =0.991; mean AUC =0.99
For
Eriastrum harwoodii (narrow extent), Max Sensitivity + Specificity threshold = 0.22; best AUC =0.986; mean AUC =0.981
For more information on the modeling process and environmental variables used, please refer to the attached PDF file ("DATA DESCRIPTION: UCSB DRECP SPECIES DISTRIBUTION MODELS").
Frank Davis and Oliver Soong<br/>
Bren School of Environmental Science & Management<br/>
University of California<br/>
Santa Barbara, CAÂ 93106-5131
Harvested on Fri May 23 09:35:19 MDT 2014 from Data Basin Service