NOT PEER-REVIEWED
"PeerJ Preprints" is a venue for early communication or feedback before peer review. Data may be preliminary.

A peer-reviewed article of this Preprint also exists.

View peer-reviewed version

Supplemental Information

CCB-ID prediction probability performance

Per-species secondary performance metrics from the test data. These metrics were calculated using the prediction probability confusion matrix reported in Table S1. Low specificity scores for Pinus palustris, which do not appear in the binary classification results (Fig. 3, main text) reflect how it was frequently predicted at higher probabilities as a minority class.

DOI: 10.7287/peerj.preprints.26972v1/supp-1

Confusion matrix of prediction probability results

Prediction probability results of the CCB-ID model using the competition test data. Each cell contains the sum of prediction probabilities from all observed crowns per species. These data were used to generate Figure S1.

DOI: 10.7287/peerj.preprints.26972v1/supp-2

Additional Information

Competing Interests

The author declares that they have no competing interests.

Author Contributions

Christopher B Anderson conceived and designed the experiments, performed the experiments, analyzed the data, contributed reagents/materials/analysis tools, prepared figures and/or tables, authored or reviewed drafts of the paper, approved the final draft.

Data Deposition

The following information was supplied regarding data availability:

The raw data used in this analysis were provided by the "NIST DSE Plant Identification with NEON Remote Sensing Data" competition. These data are hosted on Zenodo.

http://doi.org/10.5281/zenodo.867646

The code used to processes these data is the CCB-ID package. It is hosted on Github. There is no accession/ID number for this code.

https://github.com/stanford-ccb/ccb-id

Funding

C. B. Anderson was supported by the Bing-Mooney Fellowship in Environmental Science and Conservation at Stanford University's Department of Biology. The ECODSE competition was supported, in part, by a research grant from NIST IAD Data Science Research Program to D.Z. Wang, E.P. White, and S. Bohlman, by the Gordon and Betty Moore Foundation’s Data-Driven Discovery Initiative through grant GBMF4563 to E.P. White, and by an NSF Dimension of Biodiversity program grant (DEB-1442280) to S. Bohlman. The National Ecological Observatory Network is a program sponsored by the National Science Foundation and operated under cooperative agreement by Battelle Memorial Institute. This material is based in part upon work supported by the National Science Foundation through the NEON Program. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.


Add your feedback

Before adding feedback, consider if it can be asked as a question instead, and if so then use the Question tab. Pointing out typos is fine, but authors are encouraged to accept only substantially helpful feedback.

Some Markdown syntax is allowed: _italic_ **bold** ^superscript^ ~subscript~ %%blockquote%% [link text](link URL)
 
By posting this you agree to PeerJ's commenting policies
2 Citations   Views   Downloads