CAFRI Labs: GNN-SPP Rank Correlation

Sam Gordon

To choose how many species to rank, consider the distribution of species basal area totals across all sites.

Given this distribution, we could focus on the ranking of the top ten species.

x
SP_red.maple
SP_sugar.maple
SP_eastern.hemlock
SP_American.beech
SP_eastern.white.pine
SP_yellow.birch
SP_white.ash
SP_northern.red.oak
SP_black.cherry
SP_red.spruce

Predictor Variables

Environmental

tcb, tcg, tcw, delta_nbr, delta_tcb, delta_tcg, delta_tcw, twi, slope, chm, mag, dem, yod

precip, tmax, tmin, aspect, lcpri, lcsec, ecozones, tax_2019

Species Matrix

130 tree species, total basal area (in^2) per species per plot

70/30 Train/Test Set Comparison

Bray Curtis Dissimilarity against Test Set (Basal Area per Species)

Histogram of Spearman Rank Correlation Coefficients Against Test Set

Corrections

If you see mistakes or want to suggest changes, please create an issue on the source repository.

Citation

For attribution, please cite this work as

Gordon (2023, June 1). CAFRI Labs: GNN-SPP Rank Correlation. Retrieved from https://cafri-labs.github.io/acceptable-growing-stock/posts/gnn-spp-rank-correlation/

BibTeX citation

@misc{gordon2023gnn-spp,
  author = {Gordon, Sam},
  title = {CAFRI Labs: GNN-SPP Rank Correlation},
  url = {https://cafri-labs.github.io/acceptable-growing-stock/posts/gnn-spp-rank-correlation/},
  year = {2023}
}